A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy

Energy Technology Data Exchange (ETDEWEB)

Boucher, Thomas F., E-mail: boucher@cs.umass.edu [School of Computer Science, University of Massachusetts Amherst, 140 Governor' s Drive, Amherst, MA 01003, United States. (United States); Ozanne, Marie V. [Department of Astronomy, Mount Holyoke College, South Hadley, MA 01075 (United States); Carmosino, Marco L. [School of Computer Science, University of Massachusetts Amherst, 140 Governor' s Drive, Amherst, MA 01003, United States. (United States); Dyar, M. Darby [Department of Astronomy, Mount Holyoke College, South Hadley, MA 01075 (United States); Mahadevan, Sridhar [School of Computer Science, University of Massachusetts Amherst, 140 Governor' s Drive, Amherst, MA 01003, United States. (United States); Breves, Elly A.; Lepore, Kate H. [Department of Astronomy, Mount Holyoke College, South Hadley, MA 01075 (United States); Clegg, Samuel M. [Los Alamos National Laboratory, P.O. Box 1663, MS J565, Los Alamos, NM 87545 (United States)

2015-05-01

dimensionality of the data (6144 channels) relative to the small number of samples studied. The best-performing models were SVR-Lin for SiO{sub 2}, MgO, Fe{sub 2}O{sub 3}, and Na{sub 2}O, lasso for Al{sub 2}O{sub 3}, elastic net for MnO, and PLS-1 for CaO, TiO{sub 2}, and K{sub 2}O. Although these differences in model performance between methods were identified, most of the models produce comparable results when p ≤ 0.05 and all techniques except kNN produced statistically-indistinguishable results. It is likely that a combination of models could be used together to yield a lower total error of prediction, depending on the requirements of the user. - Highlights: • We compared 9 machine learning regression models for predicting mineral composition from LIBS. • These models vary over factors: linear/nonlinear, sparse/dense, univariate/multivariate. • The linear models evaluated generalized well for out-of-sample predictions. • The nonlinear models evaluated tended to overfit the training data and generalize poorly. • Sparse models best predicted the elements with a small number of high transition probability emission lines.

PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors

Science.gov (United States)

Zhu, Suling; Lian, Xiuyuan; Wei, Lin; Che, Jinxing; Shen, Xiping; Yang, Ling; Qiu, Xuanlin; Liu, Xiaoning; Gao, Wenlong; Ren, Xiaowei; Li, Juansheng

2018-06-01

The PM2.5 is the culprit of air pollution, and it leads to respiratory system disease when the fine particles are inhaled. Therefore, it is increasingly significant to develop an effective model for PM2.5 forecasting and warnings that informs people to foresee the air quality. People can reduce outdoor activities and take preventive measures if they know the air quality is bad ahead of time. In addition, reliable forecasting results can remind the relevant departments to control and reduce pollutants discharge. According to our knowledge, the current hybrid forecasting techniques of PM2.5 do not take the meteorological factors into consideration. Actually, meteorological factors affect the concentrations of air pollution, but it is unclear whether meteorological factors are helpful for improving the PM2.5 forecasting results or not. This paper proposes a hybrid model called CEEMD-PSOGSA-SVR-GRNN, based on complementary ensemble empirical mode decomposition (CEEMD), particle swarm optimization and gravitational search algorithm (PSOGSA), support vector regression (SVR), generalized regression neural network (GRNN) and grey correlation analysis (GCA), for the daily PM2.5 concentrations forecasting. The main steps of proposed model are described as follows: the original PM2.5 data decomposition with CEEMD, optimal SVR selection with PSOGCA, meteorological factors selection with GCA, residual revision by GRNN and forecasting results analysis. Three cities (Chongqing, Harbin and Jinan) in China with different characteristics of climate, terrain and pollution sources are selected to verify the effectiveness of proposed model, and CEEMD-PSOGSA-SVR*, EEMD-PSOGSA-SVR, PSOGSA-SVR, CEEMD-PSO-SVR, CEEMD-GSA-SVR, CEEMD-GWO-SVR are considered to be compared models. The experimental results show that the hybrid CEEMD-PSOGSA-SVR-GRNN model outperforms other six compared models. Therefore, the proposed CEEMD-PSOGSA-SVR-GRNN model can be used to develop air quality forecasting and

Soft sensor development and optimization of the commercial petrochemical plant integrating support vector regression and genetic algorithm

Directory of Open Access Journals (Sweden)

S.K. Lahiri

2009-09-01

Full Text Available Soft sensors have been widely used in the industrial process control to improve the quality of the product and assure safety in the production. The core of a soft sensor is to construct a soft sensing model. This paper introduces support vector regression (SVR, a new powerful machine learning methodbased on a statistical learning theory (SLT into soft sensor modeling and proposes a new soft sensing modeling method based on SVR. This paper presents an artificial intelligence based hybrid soft sensormodeling and optimization strategies, namely support vector regression – genetic algorithm (SVR-GA for modeling and optimization of mono ethylene glycol (MEG quality variable in a commercial glycol plant. In the SVR-GA approach, a support vector regression model is constructed for correlating the process data comprising values of operating and performance variables. Next, model inputs describing the process operating variables are optimized using genetic algorithm with a view to maximize the process performance. The SVR-GA is a new strategy for soft sensor modeling and optimization. The major advantage of the strategies is that modeling and optimization can be conducted exclusively from the historic process data wherein the detailed knowledge of process phenomenology (reaction mechanism, kinetics etc. is not required. Using SVR-GA strategy, a number of sets of optimized operating conditions were found. The optimized solutions, when verified in an actual plant, resulted in a significant improvement in the quality.

Developing a dengue forecast model using machine learning: A case study in China.

Science.gov (United States)

Guo, Pi; Liu, Tao; Zhang, Qin; Wang, Li; Xiao, Jianpeng; Zhang, Qingying; Luo, Ganfeng; Li, Zhihao; He, Jianfeng; Zhang, Yonghui; Ma, Wenjun

2017-10-01

In China, dengue remains an important public health issue with expanded areas and increased incidence recently. Accurate and timely forecasts of dengue incidence in China are still lacking. We aimed to use the state-of-the-art machine learning algorithms to develop an accurate predictive model of dengue. Weekly dengue cases, Baidu search queries and climate factors (mean temperature, relative humidity and rainfall) during 2011-2014 in Guangdong were gathered. A dengue search index was constructed for developing the predictive models in combination with climate factors. The observed year and week were also included in the models to control for the long-term trend and seasonality. Several machine learning algorithms, including the support vector regression (SVR) algorithm, step-down linear regression model, gradient boosted regression tree algorithm (GBM), negative binomial regression model (NBM), least absolute shrinkage and selection operator (LASSO) linear regression model and generalized additive model (GAM), were used as candidate models to predict dengue incidence. Performance and goodness of fit of the models were assessed using the root-mean-square error (RMSE) and R-squared measures. The residuals of the models were examined using the autocorrelation and partial autocorrelation function analyses to check the validity of the models. The models were further validated using dengue surveillance data from five other provinces. The epidemics during the last 12 weeks and the peak of the 2014 large outbreak were accurately forecasted by the SVR model selected by a cross-validation technique. Moreover, the SVR model had the consistently smallest prediction error rates for tracking the dynamics of dengue and forecasting the outbreaks in other areas in China. The proposed SVR model achieved a superior performance in comparison with other forecasting techniques assessed in this study. The findings can help the government and community respond early to dengue epidemics.

Support vector regression scoring of receptor-ligand complexes for rank-ordering and virtual screening of chemical libraries.

Science.gov (United States)

Li, Liwei; Wang, Bo; Meroueh, Samy O

2011-09-26

The community structure-activity resource (CSAR) data sets are used to develop and test a support vector machine-based scoring function in regression mode (SVR). Two scoring functions (SVR-KB and SVR-EP) are derived with the objective of reproducing the trend of the experimental binding affinities provided within the two CSAR data sets. The features used to train SVR-KB are knowledge-based pairwise potentials, while SVR-EP is based on physicochemical properties. SVR-KB and SVR-EP were compared to seven other widely used scoring functions, including Glide, X-score, GoldScore, ChemScore, Vina, Dock, and PMF. Results showed that SVR-KB trained with features obtained from three-dimensional complexes of the PDBbind data set outperformed all other scoring functions, including best performing X-score, by nearly 0.1 using three correlation coefficients, namely Pearson, Spearman, and Kendall. It was interesting that higher performance in rank ordering did not translate into greater enrichment in virtual screening assessed using the 40 targets of the Directory of Useful Decoys (DUD). To remedy this situation, a variant of SVR-KB (SVR-KBD) was developed by following a target-specific tailoring strategy that we had previously employed to derive SVM-SP. SVR-KBD showed a much higher enrichment, outperforming all other scoring functions tested, and was comparable in performance to our previously derived scoring function SVM-SP.

The application of SVR model in the improvement of QbD: a case study of the extraction of podophyllotoxin.

Science.gov (United States)

Zhai, Chun-Hui; Xuan, Jian-Bang; Fan, Hai-Liu; Zhao, Teng-Fei; Jiang, Jian-Lan

2018-05-03

In order to make a further optimization of process design via increasing the stability of design space, we brought in the model of Support Vector Regression (SVR). In this work, the extraction of podophyllotoxin was researched as a case study based on Quality by Design (QbD). We compared the fitting effect of SVR and the most used quadratic polynomial model (QPM) in QbD, and an analysis was made between the two design spaces obtained by SVR and QPM. As a result, the SVR stayed ahead of QPM in prediction accuracy, the stability of model and the generalization ability. The introduction of SVR into QbD made the extraction process of podophyllotoxin well designed and easier to control. The better fitting effect of SVR improved the application effect of QbD and the universal applicability of SVR, especially for non-linear, complicated and weak-regularity problems, widened the application field of QbD.

Generation of daily global solar irradiation with support vector machines for regression

International Nuclear Information System (INIS)

Antonanzas-Torres, F.; Urraca, R.; Antonanzas, J.; Fernandez-Ceniceros, J.; Martinez-de-Pison, F.J.

2015-01-01

Highlights: • New methodology for estimation of daily solar irradiation with SVR. • Automatic procedure for training models and selecting meteorological features. • This methodology outperforms other well-known parametric and numeric techniques. - Abstract: Solar global irradiation is barely recorded in isolated rural areas around the world. Traditionally, solar resource estimation has been performed using parametric-empirical models based on the relationship of solar irradiation with other atmospheric and commonly measured variables, such as temperatures, rainfall, and sunshine duration, achieving a relatively high level of certainty. Considerable improvement in soft-computing techniques, which have been applied extensively in many research fields, has lead to improvements in solar global irradiation modeling, although most of these techniques lack spatial generalization. This new methodology proposes support vector machines for regression with optimized variable selection via genetic algorithms to generate non-locally dependent and accurate models. A case of study in Spain has demonstrated the value of this methodology. It achieved a striking reduction in the mean absolute error (MAE) – 41.4% and 19.9% – as compared to classic parametric models; Bristow & Campbell and Antonanzas-Torres et al., respectively

Prediction of Mind-Wandering with Electroencephalogram and Non-linear Regression Modeling.

Science.gov (United States)

Kawashima, Issaku; Kumano, Hiroaki

2017-01-01

Mind-wandering (MW), task-unrelated thought, has been examined by researchers in an increasing number of articles using models to predict whether subjects are in MW, using numerous physiological variables. However, these models are not applicable in general situations. Moreover, they output only binary classification. The current study suggests that the combination of electroencephalogram (EEG) variables and non-linear regression modeling can be a good indicator of MW intensity. We recorded EEGs of 50 subjects during the performance of a Sustained Attention to Response Task, including a thought sampling probe that inquired the focus of attention. We calculated the power and coherence value and prepared 35 patterns of variable combinations and applied Support Vector machine Regression (SVR) to them. Finally, we chose four SVR models: two of them non-linear models and the others linear models; two of the four models are composed of a limited number of electrodes to satisfy model usefulness. Examination using the held-out data indicated that all models had robust predictive precision and provided significantly better estimations than a linear regression model using single electrode EEG variables. Furthermore, in limited electrode condition, non-linear SVR model showed significantly better precision than linear SVR model. The method proposed in this study helps investigations into MW in various little-examined situations. Further, by measuring MW with a high temporal resolution EEG, unclear aspects of MW, such as time series variation, are expected to be revealed. Furthermore, our suggestion that a few electrodes can also predict MW contributes to the development of neuro-feedback studies.

Prediction of Mind-Wandering with Electroencephalogram and Non-linear Regression Modeling

Directory of Open Access Journals (Sweden)

Issaku Kawashima

2017-07-01

Full Text Available Mind-wandering (MW, task-unrelated thought, has been examined by researchers in an increasing number of articles using models to predict whether subjects are in MW, using numerous physiological variables. However, these models are not applicable in general situations. Moreover, they output only binary classification. The current study suggests that the combination of electroencephalogram (EEG variables and non-linear regression modeling can be a good indicator of MW intensity. We recorded EEGs of 50 subjects during the performance of a Sustained Attention to Response Task, including a thought sampling probe that inquired the focus of attention. We calculated the power and coherence value and prepared 35 patterns of variable combinations and applied Support Vector machine Regression (SVR to them. Finally, we chose four SVR models: two of them non-linear models and the others linear models; two of the four models are composed of a limited number of electrodes to satisfy model usefulness. Examination using the held-out data indicated that all models had robust predictive precision and provided significantly better estimations than a linear regression model using single electrode EEG variables. Furthermore, in limited electrode condition, non-linear SVR model showed significantly better precision than linear SVR model. The method proposed in this study helps investigations into MW in various little-examined situations. Further, by measuring MW with a high temporal resolution EEG, unclear aspects of MW, such as time series variation, are expected to be revealed. Furthermore, our suggestion that a few electrodes can also predict MW contributes to the development of neuro-feedback studies.

Support vector regression for porosity prediction in a heterogeneous reservoir: A comparative study

Science.gov (United States)

Al-Anazi, A. F.; Gates, I. D.

2010-12-01

In wells with limited log and core data, porosity, a fundamental and essential property to characterize reservoirs, is challenging to estimate by conventional statistical methods from offset well log and core data in heterogeneous formations. Beyond simple regression, neural networks have been used to develop more accurate porosity correlations. Unfortunately, neural network-based correlations have limited generalization ability and global correlations for a field are usually less accurate compared to local correlations for a sub-region of the reservoir. In this paper, support vector machines are explored as an intelligent technique to correlate porosity to well log data. Recently, support vector regression (SVR), based on the statistical learning theory, have been proposed as a new intelligence technique for both prediction and classification tasks. The underlying formulation of support vector machines embodies the structural risk minimization (SRM) principle which has been shown to be superior to the traditional empirical risk minimization (ERM) principle employed by conventional neural networks and classical statistical methods. This new formulation uses margin-based loss functions to control model complexity independently of the dimensionality of the input space, and kernel functions to project the estimation problem to a higher dimensional space, which enables the solution of more complex nonlinear problem optimization methods to exist for a globally optimal solution. SRM minimizes an upper bound on the expected risk using a margin-based loss function ( ɛ-insensitivity loss function for regression) in contrast to ERM which minimizes the error on the training data. Unlike classical learning methods, SRM, indexed by margin-based loss function, can also control model complexity independent of dimensionality. The SRM inductive principle is designed for statistical estimation with finite data where the ERM inductive principle provides the optimal solution (the

Image superresolution using support vector regression.

Science.gov (United States)

Ni, Karl S; Nguyen, Truong Q

2007-06-01

A thorough investigation of the application of support vector regression (SVR) to the superresolution problem is conducted through various frameworks. Prior to the study, the SVR problem is enhanced by finding the optimal kernel. This is done by formulating the kernel learning problem in SVR form as a convex optimization problem, specifically a semi-definite programming (SDP) problem. An additional constraint is added to reduce the SDP to a quadratically constrained quadratic programming (QCQP) problem. After this optimization, investigation of the relevancy of SVR to superresolution proceeds with the possibility of using a single and general support vector regression for all image content, and the results are impressive for small training sets. This idea is improved upon by observing structural properties in the discrete cosine transform (DCT) domain to aid in learning the regression. Further improvement involves a combination of classification and SVR-based techniques, extending works in resolution synthesis. This method, termed kernel resolution synthesis, uses specific regressors for isolated image content to describe the domain through a partitioned look of the vector space, thereby yielding good results.

Improved SVR Model for Multi-Layer Buildup Factor Calculation

International Nuclear Information System (INIS)

Trontl, K.; Pevec, D.; Smuc, T.

2006-01-01

The accuracy of point kernel method applied in gamma ray dose rate calculations in shielding design and radiation safety analysis is limited by the accuracy of buildup factors used in calculations. Although buildup factors for single-layer shields are well defined and understood, buildup factors for stratified shields represent a complex physical problem that is hard to express in mathematical terms. The traditional approach for expressing buildup factors of multi-layer shields is through semi-empirical formulas obtained by fitting the results of transport theory or Monte Carlo calculations. Such an approach requires an ad-hoc definition of the fitting function and often results with numerous and usually inadequately explained and defined correction factors added to the final empirical formula. Even more, finally obtained formulas are generally limited to a small number of predefined combinations of materials within relatively small range of gamma ray energies and shield thicknesses. Recently, a new approach has been suggested by the authors involving one of machine learning techniques called Support Vector Machines, i.e., Support Vector Regression (SVR). Preliminary investigations performed for double-layer shields revealed great potential of the method, but also pointed out some drawbacks of the developed model, mostly related to the selection of one of the parameters describing the problem (material atomic number), and the method in which the model was designed to evolve during the learning process. It is the aim of this paper to introduce a new parameter (single material buildup factor) that is to replace the existing material atomic number as an input parameter. The comparison of two models generated by different input parameters has been performed. The second goal is to improve the evolution process of learning, i.e., the experimental computational procedure that provides a framework for automated construction of complex regression models of predefined

Application of SVR with chaotic GASA algorithm in cyclic electric load forecasting

International Nuclear Information System (INIS)

Zhang, Wen Yu; Hong, Wei-Chiang; Dong, Yucheng; Tsai, Gary; Sung, Jing-Tian; Fan, Guo-feng

2012-01-01

The electric load forecasting is complicated, and it sometimes reveals cyclic changes due to cyclic economic activities or climate seasonal nature, such as hourly peak in a working day, weekly peak in a business week, and monthly peak in a demand planned year. Hybridization of support vector regression (SVR) with chaotic sequence and evolutionary algorithms has successfully been applied to improve forecasting accuracy, and to effectively avoid trapping in a local optimum. However, it has not been widely explored to employ SVR-based model to deal with cyclic electric load forecasting. This paper will firstly investigate the potentiality of a novel hybrid algorithm, namely chaotic genetic algorithm-simulated annealing algorithm (CGASA), with an SVR model to improve load forecasting accurate performance. In which, the proposed CGASA employs internal randomness of chaotic iterations to overcome premature local optimum. Secondly, the seasonal mechanism will then be applied to well adjust the cyclic load tendency. Finally, a numerical example from an existed reference is employed to compare the forecasting performance of the proposed SSVRCGASA model. The forecasting results show that the SSVRCGASA model yields more accurate forecasting results than ARIMA and TF-ε-SVR-SA models. -- Highlights: ► Hybridizing the seasonal adjustment mechanism into an SVR model. ► Employing chaotic sequence to improve the premature convergence of genetic algorithm and simulated annealing algorithm. ► Successfully providing significant accurate monthly load demand forecasting.

Hybridizing DEMD and Quantum PSO with SVR in Electric Load Forecasting

Directory of Open Access Journals (Sweden)

Li-Ling Peng

2016-03-01

Full Text Available Electric load forecasting is an important issue for a power utility, associated with the management of daily operations such as energy transfer scheduling, unit commitment, and load dispatch. Inspired by strong non-linear learning capability of support vector regression (SVR, this paper presents an SVR model hybridized with the differential empirical mode decomposition (DEMD method and quantum particle swarm optimization algorithm (QPSO for electric load forecasting. The DEMD method is employed to decompose the electric load to several detail parts associated with high frequencies (intrinsic mode function—IMF and an approximate part associated with low frequencies. Hybridized with quantum theory to enhance particle searching performance, the so-called QPSO is used to optimize the parameters of SVR. The electric load data of the New South Wales (Sydney, Australia market and the New York Independent System Operator (NYISO, New York, USA are used for comparing the forecasting performances of different forecasting models. The results illustrate the validity of the idea that the proposed model can simultaneously provide forecasting with good accuracy and interpretability.

Study on the medical meteorological forecast of the number of hypertension inpatient based on SVR

Science.gov (United States)

Zhai, Guangyu; Chai, Guorong; Zhang, Haifeng

2017-06-01

The purpose of this study is to build a hypertension prediction model by discussing the meteorological factors for hypertension incidence. The research method is selecting the standard data of relative humidity, air temperature, visibility, wind speed and air pressure of Lanzhou from 2010 to 2012(calculating the maximum, minimum and average value with 5 days as a unit ) as the input variables of Support Vector Regression(SVR) and the standard data of hypertension incidence of the same period as the output dependent variables to obtain the optimal prediction parameters by cross validation algorithm, then by SVR algorithm learning and training, a SVR forecast model for hypertension incidence is built. The result shows that the hypertension prediction model is composed of 15 input independent variables, the training accuracy is 0.005, the final error is 0.0026389. The forecast accuracy based on SVR model is 97.1429%, which is higher than statistical forecast equation and neural network prediction method. It is concluded that SVR model provides a new method for hypertension prediction with its simple calculation, small error as well as higher historical sample fitting and Independent sample forecast capability.

Machine Learning of the Reactor Core Loading Pattern Critical Parameters

Directory of Open Access Journals (Sweden)

Krešimir Trontl

2008-01-01

Full Text Available The usual approach to loading pattern optimization involves high degree of engineering judgment, a set of heuristic rules, an optimization algorithm, and a computer code used for evaluating proposed loading patterns. The speed of the optimization process is highly dependent on the computer code used for the evaluation. In this paper, we investigate the applicability of a machine learning model which could be used for fast loading pattern evaluation. We employ a recently introduced machine learning technique, support vector regression (SVR, which is a data driven, kernel based, nonlinear modeling paradigm, in which model parameters are automatically determined by solving a quadratic optimization problem. The main objective of the work reported in this paper was to evaluate the possibility of applying SVR method for reactor core loading pattern modeling. We illustrate the performance of the solution and discuss its applicability, that is, complexity, speed, and accuracy.

Machine Learning of the Reactor Core Loading Pattern Critical Parameters

International Nuclear Information System (INIS)

Trontl, K.; Pevec, D.; Smuc, T.

2008-01-01

The usual approach to loading pattern optimization involves high degree of engineering judgment, a set of heuristic rules, an optimization algorithm, and a computer code used for evaluating proposed loading patterns. The speed of the optimization process is highly dependent on the computer code used for the evaluation. In this paper, we investigate the applicability of a machine learning model which could be used for fast loading pattern evaluation. We employ a recently introduced machine learning technique, support vector regression (SVR), which is a data driven, kernel based, nonlinear modeling paradigm, in which model parameters are automatically determined by solving a quadratic optimization problem. The main objective of the work reported in this paper was to evaluate the possibility of applying SVR method for reactor core loading pattern modeling. We illustrate the performance of the solution and discuss its applicability, that is, complexity, speed, and accuracy

A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy

Science.gov (United States)

Boucher, Thomas F.; Ozanne, Marie V.; Carmosino, Marco L.; Dyar, M. Darby; Mahadevan, Sridhar; Breves, Elly A.; Lepore, Kate H.; Clegg, Samuel M.

2015-05-01

The ChemCam instrument on the Mars Curiosity rover is generating thousands of LIBS spectra and bringing interest in this technique to public attention. The key to interpreting Mars or any other types of LIBS data are calibrations that relate laboratory standards to unknowns examined in other settings and enable predictions of chemical composition. Here, LIBS spectral data are analyzed using linear regression methods including partial least squares (PLS-1 and PLS-2), principal component regression (PCR), least absolute shrinkage and selection operator (lasso), elastic net, and linear support vector regression (SVR-Lin). These were compared against results from nonlinear regression methods including kernel principal component regression (K-PCR), polynomial kernel support vector regression (SVR-Py) and k-nearest neighbor (kNN) regression to discern the most effective models for interpreting chemical abundances from LIBS spectra of geological samples. The results were evaluated for 100 samples analyzed with 50 laser pulses at each of five locations averaged together. Wilcoxon signed-rank tests were employed to evaluate the statistical significance of differences among the nine models using their predicted residual sum of squares (PRESS) to make comparisons. For MgO, SiO2, Fe2O3, CaO, and MnO, the sparse models outperform all the others except for linear SVR, while for Na2O, K2O, TiO2, and P2O5, the sparse methods produce inferior results, likely because their emission lines in this energy range have lower transition probabilities. The strong performance of the sparse methods in this study suggests that use of dimensionality-reduction techniques as a preprocessing step may improve the performance of the linear models. Nonlinear methods tend to overfit the data and predict less accurately, while the linear methods proved to be more generalizable with better predictive performance. These results are attributed to the high dimensionality of the data (6144 channels

Linear and support vector regressions based on geometrical correlation of data

Directory of Open Access Journals (Sweden)

Kaijun Wang

2007-10-01

Full Text Available Linear regression (LR and support vector regression (SVR are widely used in data analysis. Geometrical correlation learning (GcLearn was proposed recently to improve the predictive ability of LR and SVR through mining and using correlations between data of a variable (inner correlation. This paper theoretically analyzes prediction performance of the GcLearn method and proves that GcLearn LR and SVR will have better prediction performance than traditional LR and SVR for prediction tasks when good inner correlations are obtained and predictions by traditional LR and SVR are far away from their neighbor training data under inner correlation. This gives the applicable condition of GcLearn method.

Short-term electricity prices forecasting based on support vector regression and Auto-regressive integrated moving average modeling

International Nuclear Information System (INIS)

Che Jinxing; Wang Jianzhou

2010-01-01

In this paper, we present the use of different mathematical models to forecast electricity price under deregulated power. A successful prediction tool of electricity price can help both power producers and consumers plan their bidding strategies. Inspired by that the support vector regression (SVR) model, with the ε-insensitive loss function, admits of the residual within the boundary values of ε-tube, we propose a hybrid model that combines both SVR and Auto-regressive integrated moving average (ARIMA) models to take advantage of the unique strength of SVR and ARIMA models in nonlinear and linear modeling, which is called SVRARIMA. A nonlinear analysis of the time-series indicates the convenience of nonlinear modeling, the SVR is applied to capture the nonlinear patterns. ARIMA models have been successfully applied in solving the residuals regression estimation problems. The experimental results demonstrate that the model proposed outperforms the existing neural-network approaches, the traditional ARIMA models and other hybrid models based on the root mean square error and mean absolute percentage error.

The Amalgamation of SVR and ANFIS Models with Synchronized Phasor Measurements for On-Line Voltage Stability Assessment

Directory of Open Access Journals (Sweden)

Mohammed Amroune

2017-10-01

Full Text Available This paper presents the application of support vector regression (SVR and adaptive neuro-fuzzy inference system (ANFIS models that are amalgamated with synchronized phasor measurements for on-line voltage stability assessment. As the performance of SVR model extremely depends on the good selection of its parameters, the recently developed ant lion optimizer (ALO is adapted to seek for the SVR’s optimal parameters. In particular, the input vector of ALO-SVR and ANFIS soft computing models is provided in the form of voltage magnitudes provided by the phasor measurement units (PMUs. In order to investigate the effectiveness of ALO-SVR and ANFIS models towards performing the on-line voltage stability assessment, in-depth analyses on the results have been carried out on the IEEE 30-bus and IEEE 118-bus test systems considering different topologies and operating conditions. Two statistical performance criteria of root mean square error (RMSE and correlation coefficient (R were considered as metrics to further assess both of the modeling performances in contrast with the power flow equations. The results have demonstrated that the ALO-SVR model is able to predict the voltage stability margin with greater accuracy compared to the ANFIS model.

Real time flaw detection and characterization in tube through partial least squares and SVR: Application to eddy current testing

Science.gov (United States)

Ahmed, Shamim; Miorelli, Roberto; Calmon, Pierre; Anselmi, Nicola; Salucci, Marco

2018-04-01

This paper describes Learning-By-Examples (LBE) technique for performing quasi real time flaw localization and characterization within a conductive tube based on Eddy Current Testing (ECT) signals. Within the framework of LBE, the combination of full-factorial (i.e., GRID) sampling and Partial Least Squares (PLS) feature extraction (i.e., GRID-PLS) techniques are applied for generating a suitable training set in offine phase. Support Vector Regression (SVR) is utilized for model development and inversion during offine and online phases, respectively. The performance and robustness of the proposed GIRD-PLS/SVR strategy on noisy test set is evaluated and compared with standard GRID/SVR approach.

Upport vector machines for nonlinear kernel ARMA system identification.

Science.gov (United States)

Martínez-Ramón, Manel; Rojo-Alvarez, José Luis; Camps-Valls, Gustavo; Muñioz-Marí, Jordi; Navia-Vázquez, Angel; Soria-Olivas, Emilio; Figueiras-Vidal, Aníbal R

2006-11-01

Nonlinear system identification based on support vector machines (SVM) has been usually addressed by means of the standard SVM regression (SVR), which can be seen as an implicit nonlinear autoregressive and moving average (ARMA) model in some reproducing kernel Hilbert space (RKHS). The proposal of this letter is twofold. First, the explicit consideration of an ARMA model in an RKHS (SVM-ARMA2K) is proposed. We show that stating the ARMA equations in an RKHS leads to solving the regularized normal equations in that RKHS, in terms of the autocorrelation and cross correlation of the (nonlinearly) transformed input and output discrete time processes. Second, a general class of SVM-based system identification nonlinear models is presented, based on the use of composite Mercer's kernels. This general class can improve model flexibility by emphasizing the input-output cross information (SVM-ARMA4K), which leads to straightforward and natural combinations of implicit and explicit ARMA models (SVR-ARMA2K and SVR-ARMA4K). Capabilities of these different SVM-based system identification schemes are illustrated with two benchmark problems.

On Weighted Support Vector Regression

DEFF Research Database (Denmark)

Han, Xixuan; Clemmensen, Line Katrine Harder

2014-01-01

We propose a new type of weighted support vector regression (SVR), motivated by modeling local dependencies in time and space in prediction of house prices. The classic weights of the weighted SVR are added to the slack variables in the objective function (OF‐weights). This procedure directly...... shrinks the coefficient of each observation in the estimated functions; thus, it is widely used for minimizing influence of outliers. We propose to additionally add weights to the slack variables in the constraints (CF‐weights) and call the combination of weights the doubly weighted SVR. We illustrate...... the differences and similarities of the two types of weights by demonstrating the connection between the Least Absolute Shrinkage and Selection Operator (LASSO) and the SVR. We show that an SVR problem can be transformed to a LASSO problem plus a linear constraint and a box constraint. We demonstrate...

River flow prediction using hybrid models of support vector regression with the wavelet transform, singular spectrum analysis and chaotic approach

Science.gov (United States)

Baydaroğlu, Özlem; Koçak, Kasım; Duran, Kemal

2018-06-01

Prediction of water amount that will enter the reservoirs in the following month is of vital importance especially for semi-arid countries like Turkey. Climate projections emphasize that water scarcity will be one of the serious problems in the future. This study presents a methodology for predicting river flow for the subsequent month based on the time series of observed monthly river flow with hybrid models of support vector regression (SVR). Monthly river flow over the period 1940-2012 observed for the Kızılırmak River in Turkey has been used for training the method, which then has been applied for predictions over a period of 3 years. SVR is a specific implementation of support vector machines (SVMs), which transforms the observed input data time series into a high-dimensional feature space (input matrix) by way of a kernel function and performs a linear regression in this space. SVR requires a special input matrix. The input matrix was produced by wavelet transforms (WT), singular spectrum analysis (SSA), and a chaotic approach (CA) applied to the input time series. WT convolutes the original time series into a series of wavelets, and SSA decomposes the time series into a trend, an oscillatory and a noise component by singular value decomposition. CA uses a phase space formed by trajectories, which represent the dynamics producing the time series. These three methods for producing the input matrix for the SVR proved successful, while the SVR-WT combination resulted in the highest coefficient of determination and the lowest mean absolute error.

Application of Machine-Learning Models to Predict Tacrolimus Stable Dose in Renal Transplant Recipients

Science.gov (United States)

Tang, Jie; Liu, Rong; Zhang, Yue-Li; Liu, Mou-Ze; Hu, Yong-Fang; Shao, Ming-Jie; Zhu, Li-Jun; Xin, Hua-Wen; Feng, Gui-Wen; Shang, Wen-Jun; Meng, Xiang-Guang; Zhang, Li-Rong; Ming, Ying-Zi; Zhang, Wei

2017-02-01

Tacrolimus has a narrow therapeutic window and considerable variability in clinical use. Our goal was to compare the performance of multiple linear regression (MLR) and eight machine learning techniques in pharmacogenetic algorithm-based prediction of tacrolimus stable dose (TSD) in a large Chinese cohort. A total of 1,045 renal transplant patients were recruited, 80% of which were randomly selected as the “derivation cohort” to develop dose-prediction algorithm, while the remaining 20% constituted the “validation cohort” to test the final selected algorithm. MLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied and their performances were compared in this work. Among all the machine learning models, RT performed best in both derivation [0.71 (0.67-0.76)] and validation cohorts [0.73 (0.63-0.82)]. In addition, the ideal rate of RT was 4% higher than that of MLR. To our knowledge, this is the first study to use machine learning models to predict TSD, which will further facilitate personalized medicine in tacrolimus administration in the future.

Fault trend prediction of device based on support vector regression

International Nuclear Information System (INIS)

Song Meicun; Cai Qi

2011-01-01

The research condition of fault trend prediction and the basic theory of support vector regression (SVR) were introduced. SVR was applied to the fault trend prediction of roller bearing, and compared with other methods (BP neural network, gray model, and gray-AR model). The results show that BP network tends to overlearn and gets into local minimum so that the predictive result is unstable. It also shows that the predictive result of SVR is stabilization, and SVR is superior to BP neural network, gray model and gray-AR model in predictive precision. SVR is a kind of effective method of fault trend prediction. (authors)

Forecasting systems reliability based on support vector regression with genetic algorithms

International Nuclear Information System (INIS)

Chen, K.-Y.

2007-01-01

This study applies a novel neural-network technique, support vector regression (SVR), to forecast reliability in engine systems. The aim of this study is to examine the feasibility of SVR in systems reliability prediction by comparing it with the existing neural-network approaches and the autoregressive integrated moving average (ARIMA) model. To build an effective SVR model, SVR's parameters must be set carefully. This study proposes a novel approach, known as GA-SVR, which searches for SVR's optimal parameters using real-value genetic algorithms, and then adopts the optimal parameters to construct the SVR models. A real reliability data for 40 suits of turbochargers were employed as the data set. The experimental results demonstrate that SVR outperforms the existing neural-network approaches and the traditional ARIMA models based on the normalized root mean square error and mean absolute percentage error

A Comparison of Advanced Regression Algorithms for Quantifying Urban Land Cover

Directory of Open Access Journals (Sweden)

Akpona Okujeni

2014-07-01

Full Text Available Quantitative methods for mapping sub-pixel land cover fractions are gaining increasing attention, particularly with regard to upcoming hyperspectral satellite missions. We evaluated five advanced regression algorithms combined with synthetically mixed training data for quantifying urban land cover from HyMap data at 3.6 and 9 m spatial resolution. Methods included support vector regression (SVR, kernel ridge regression (KRR, artificial neural networks (NN, random forest regression (RFR and partial least squares regression (PLSR. Our experiments demonstrate that both kernel methods SVR and KRR yield high accuracies for mapping complex urban surface types, i.e., rooftops, pavements, grass- and tree-covered areas. SVR and KRR models proved to be stable with regard to the spatial and spectral differences between both images and effectively utilized the higher complexity of the synthetic training mixtures for improving estimates for coarser resolution data. Observed deficiencies mainly relate to known problems arising from spectral similarities or shadowing. The remaining regressors either revealed erratic (NN or limited (RFR and PLSR performances when comprehensively mapping urban land cover. Our findings suggest that the combination of kernel-based regression methods, such as SVR and KRR, with synthetically mixed training data is well suited for quantifying urban land cover from imaging spectrometer data at multiple scales.

Modeling and prediction of Turkey's electricity consumption using Support Vector Regression

International Nuclear Information System (INIS)

Kavaklioglu, Kadir

2011-01-01

Support Vector Regression (SVR) methodology is used to model and predict Turkey's electricity consumption. Among various SVR formalisms, ε-SVR method was used since the training pattern set was relatively small. Electricity consumption is modeled as a function of socio-economic indicators such as population, Gross National Product, imports and exports. In order to facilitate future predictions of electricity consumption, a separate SVR model was created for each of the input variables using their current and past values; and these models were combined to yield consumption prediction values. A grid search for the model parameters was performed to find the best ε-SVR model for each variable based on Root Mean Square Error. Electricity consumption of Turkey is predicted until 2026 using data from 1975 to 2006. The results show that electricity consumption can be modeled using Support Vector Regression and the models can be used to predict future electricity consumption. (author)

A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting

OpenAIRE

Zhaoxuan Li; SM Mahbobur Rahman; Rolando Vega; Bing Dong

2016-01-01

We evaluate and compare two common methods, artificial neural networks (ANN) and support vector regression (SVR), for predicting energy productions from a solar photovoltaic (PV) system in Florida 15 min, 1 h and 24 h ahead of time. A hierarchical approach is proposed based on the machine learning algorithms tested. The production data used in this work corresponds to 15 min averaged power measurements collected from 2014. The accuracy of the model is determined using computing error statisti...

Support Vector Regression Model Based on Empirical Mode Decomposition and Auto Regression for Electric Load Forecasting

Directory of Open Access Journals (Sweden)

Hong-Juan Li

2013-04-01

Full Text Available Electric load forecasting is an important issue for a power utility, associated with the management of daily operations such as energy transfer scheduling, unit commitment, and load dispatch. Inspired by strong non-linear learning capability of support vector regression (SVR, this paper presents a SVR model hybridized with the empirical mode decomposition (EMD method and auto regression (AR for electric load forecasting. The electric load data of the New South Wales (Australia market are employed for comparing the forecasting performances of different forecasting models. The results confirm the validity of the idea that the proposed model can simultaneously provide forecasting with good accuracy and interpretability.

Phase Space Prediction of Chaotic Time Series with Nu-Support Vector Machine Regression

International Nuclear Information System (INIS)

Ye Meiying; Wang Xiaodong

2005-01-01

A new class of support vector machine, nu-support vector machine, is discussed which can handle both classification and regression. We focus on nu-support vector machine regression and use it for phase space prediction of chaotic time series. The effectiveness of the method is demonstrated by applying it to the Henon map. This study also compares nu-support vector machine with back propagation (BP) networks in order to better evaluate the performance of the proposed methods. The experimental results show that the nu-support vector machine regression obtains lower root mean squared error than the BP networks and provides an accurate chaotic time series prediction. These results can be attributable to the fact that nu-support vector machine implements the structural risk minimization principle and this leads to better generalization than the BP networks.

SVR-based prediction of carbon emissions from energy consumption in Henan Province

Science.gov (United States)

Gou, Guohua

2018-02-01

This paper analyzes the advantage of support vector regression (SVR) in the prediction of carbon emission and establishes the SVR-based carbon emission prediction model. The model is established using the data of Henan’s carbon emissions and influence factors from the 1991 to 2016 to train and test and then predict the carbon emissions from 2017 to 2021. The results show that: from the perspective of carbon emission from energy consumption, it raised 224.876 million tons of carbon dioxide from 1991 to 2016, and the predicted increment from 2017 to 2021 is 30.5563million tons with an average annual growth rate at 3%. From the perspective of growth rate among the six factors related to carbon emissions it is proved that population urbanization rate per capital GDP and energy consumption per unit of GDP influences the growth rate of carbon emissions less than the proportion of secondary industry and coal consumption ratio of carbon. Finally some suggestions are proposed for the carbon emission reduction of Henan Province.

Comparison between Two Linear Supervised Learning Machines' Methods with Principle Component Based Methods for the Spectrofluorimetric Determination of Agomelatine and Its Degradants.

Science.gov (United States)

Elkhoudary, Mahmoud M; Naguib, Ibrahim A; Abdel Salam, Randa A; Hadad, Ghada M

2017-05-01

Four accurate, sensitive and reliable stability indicating chemometric methods were developed for the quantitative determination of Agomelatine (AGM) whether in pure form or in pharmaceutical formulations. Two supervised learning machines' methods; linear artificial neural networks (PC-linANN) preceded by principle component analysis and linear support vector regression (linSVR), were compared with two principle component based methods; principle component regression (PCR) as well as partial least squares (PLS) for the spectrofluorimetric determination of AGM and its degradants. The results showed the benefits behind using linear learning machines' methods and the inherent merits of their algorithms in handling overlapped noisy spectral data especially during the challenging determination of AGM alkaline and acidic degradants (DG1 and DG2). Relative mean squared error of prediction (RMSEP) for the proposed models in the determination of AGM were 1.68, 1.72, 0.68 and 0.22 for PCR, PLS, SVR and PC-linANN; respectively. The results showed the superiority of supervised learning machines' methods over principle component based methods. Besides, the results suggested that linANN is the method of choice for determination of components in low amounts with similar overlapped spectra and narrow linearity range. Comparison between the proposed chemometric models and a reported HPLC method revealed the comparable performance and quantification power of the proposed models.

A dynamic particle filter-support vector regression method for reliability prediction

International Nuclear Information System (INIS)

Wei, Zhao; Tao, Tao; ZhuoShu, Ding; Zio, Enrico

2013-01-01

Support vector regression (SVR) has been applied to time series prediction and some works have demonstrated the feasibility of its use to forecast system reliability. For accuracy of reliability forecasting, the selection of SVR's parameters is important. The existing research works on SVR's parameters selection divide the example dataset into training and test subsets, and tune the parameters on the training data. However, these fixed parameters can lead to poor prediction capabilities if the data of the test subset differ significantly from those of training. Differently, the novel method proposed in this paper uses particle filtering to estimate the SVR model parameters according to the whole measurement sequence up to the last observation instance. By treating the SVR training model as the observation equation of a particle filter, our method allows updating the SVR model parameters dynamically when a new observation comes. Because of the adaptability of the parameters to dynamic data pattern, the new PF–SVR method has superior prediction performance over that of standard SVR. Four application results show that PF–SVR is more robust than SVR to the decrease of the number of training data and the change of initial SVR parameter values. Also, even if there are trends in the test data different from those in the training data, the method can capture the changes, correct the SVR parameters and obtain good predictions. -- Highlights: •A dynamic PF–SVR method is proposed to predict the system reliability. •The method can adjust the SVR parameters according to the change of data. •The method is robust to the size of training data and initial parameter values. •Some cases based on both artificial and real data are studied. •PF–SVR shows superior prediction performance over standard SVR

Forecasting monthly groundwater level fluctuations in coastal aquifers using hybrid Wavelet packet–Support vector regression

Directory of Open Access Journals (Sweden)

N. Sujay Raghavendra

2015-12-01

Full Text Available This research demonstrates the state-of-the-art capability of Wavelet packet analysis in improving the forecasting efficiency of Support vector regression (SVR through the development of a novel hybrid Wavelet packet–Support vector regression (WP–SVR model for forecasting monthly groundwater level fluctuations observed in three shallow unconfined coastal aquifers. The Sequential Minimal Optimization Algorithm-based SVR model is also employed for comparative study with WP–SVR model. The input variables used for modeling were monthly time series of total rainfall, average temperature, mean tide level, and past groundwater level observations recorded during the period 1996–2006 at three observation wells located near Mangalore, India. The Radial Basis function is employed as a kernel function during SVR modeling. Model parameters are calibrated using the first seven years of data, and the remaining three years data are used for model validation using various input combinations. The performance of both the SVR and WP–SVR models is assessed using different statistical indices. From the comparative result analysis of the developed models, it can be seen that WP–SVR model outperforms the classic SVR model in predicting groundwater levels at all the three well locations (e.g. NRMSE(WP–SVR = 7.14, NRMSE(SVR = 12.27; NSE(WP–SVR = 0.91, NSE(SVR = 0.8 during the test phase with respect to well location at Surathkal. Therefore, using the WP–SVR model is highly acceptable for modeling and forecasting of groundwater level fluctuations.

Analysis of process parameters in the laser deposition of YBa{sub 2}Cu{sub 3}O{sub 7} superconducting films by using SVR

Energy Technology Data Exchange (ETDEWEB)

Cai, C.Z., E-mail: caiczh@gmail.com [Department of Applied Physics, Chongqing University, Chongqing 401331 (China); Xiao, T.T. [Department of Applied Physics, Chongqing University, Chongqing 401331 (China); Science and Technology on Plasma Physics Laboratory, Research Center of Laser Fusion, CAEP, P.O. Box 919-988, Mianyang 621900 (China); Tang, J.L.; Huang, S.J. [Department of Applied Physics, Chongqing University, Chongqing 401331 (China)

2013-10-15

Highlights: • Proposed new ideas and strategies to improve energy storage density for SMES system. • One is to increase the effective current density in the superconducting coils. • Another is to optimize the configuration of the SMES coil. • A new conceive of energy compression is also proposed. -- Abstract: There are several process parameters in the growth of YBa{sub 2}Cu{sub 3}O{sub 7} superconducting films by using pulsed laser deposition (PLD). The relationship between the response and process parameters is highly nonlinear and quite complicated. It is very valuable to quantitatively estimate the response under different deposition parameters. In this study, according to an experimental data set on the superconducting transition temperature (T{sub c}) and relative resistance ratio (r{sub R}) of 17 samples of YBa{sub 2}Cu{sub 3}O{sub 7} films deposited under various parameters, the support vector regression (SVR) combined with particle swarm optimization (PSO), was proposed to predict the T{sub c} and r{sub R} for YBa{sub 2}Cu{sub 3}O{sub 7} films. The prediction performance of SVR was compared with that of multiple regression analysis (MRA) models. The results strongly support that the generalization ability of SVR model consistently surpasses that of MRA via leave-one-out cross validation (LOOCV). The mean absolute percentage errors for T{sub c} and r{sub R} are 0.37% and 1.51% respectively via LOOCV test of SVR. Sensitivity analysis discovered the most sensitive parameters affecting the T{sub c} and r{sub R}. This study suggests that the established SVR model can be used to accurately foresee the T{sub c} and r{sub R}. And it can be used to optimizing the deposition parameters in the development of YBa{sub 2}Cu{sub 3}O{sub 7} films via PLD.

Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches.

Science.gov (United States)

Stylianou, Neophytos; Akbarov, Artur; Kontopantelis, Evangelos; Buchan, Iain; Dunn, Ken W

2015-08-01

Predicting mortality from burn injury has traditionally employed logistic regression models. Alternative machine learning methods have been introduced in some areas of clinical prediction as the necessary software and computational facilities have become accessible. Here we compare logistic regression and machine learning predictions of mortality from burn. An established logistic mortality model was compared to machine learning methods (artificial neural network, support vector machine, random forests and naïve Bayes) using a population-based (England & Wales) case-cohort registry. Predictive evaluation used: area under the receiver operating characteristic curve; sensitivity; specificity; positive predictive value and Youden's index. All methods had comparable discriminatory abilities, similar sensitivities, specificities and positive predictive values. Although some machine learning methods performed marginally better than logistic regression the differences were seldom statistically significant and clinically insubstantial. Random forests were marginally better for high positive predictive value and reasonable sensitivity. Neural networks yielded slightly better prediction overall. Logistic regression gives an optimal mix of performance and interpretability. The established logistic regression model of burn mortality performs well against more complex alternatives. Clinical prediction with a small set of strong, stable, independent predictors is unlikely to gain much from machine learning outside specialist research contexts. Copyright © 2015 Elsevier Ltd and ISBI. All rights reserved.

Modeling daily soil temperature over diverse climate conditions in Iran—a comparison of multiple linear regression and support vector regression techniques

Science.gov (United States)

Delbari, Masoomeh; Sharifazari, Salman; Mohammadi, Ehsan

2018-02-01

The knowledge of soil temperature at different depths is important for agricultural industry and for understanding climate change. The aim of this study is to evaluate the performance of a support vector regression (SVR)-based model in estimating daily soil temperature at 10, 30 and 100 cm depth at different climate conditions over Iran. The obtained results were compared to those obtained from a more classical multiple linear regression (MLR) model. The correlation sensitivity for the input combinations and periodicity effect were also investigated. Climatic data used as inputs to the models were minimum and maximum air temperature, solar radiation, relative humidity, dew point, and the atmospheric pressure (reduced to see level), collected from five synoptic stations Kerman, Ahvaz, Tabriz, Saghez, and Rasht located respectively in the hyper-arid, arid, semi-arid, Mediterranean, and hyper-humid climate conditions. According to the results, the performance of both MLR and SVR models was quite well at surface layer, i.e., 10-cm depth. However, SVR performed better than MLR in estimating soil temperature at deeper layers especially 100 cm depth. Moreover, both models performed better in humid climate condition than arid and hyper-arid areas. Further, adding a periodicity component into the modeling process considerably improved the models' performance especially in the case of SVR.

Estimation of the wind turbine yaw error by support vector machines

DEFF Research Database (Denmark)

Sheibat-Othman, Nida; Othman, Sami; Tayari, Raoaa

2015-01-01

Wind turbine yaw error information is of high importance in controlling wind turbine power and structural load. Normally used wind vanes are imprecise. In this work, the estimation of yaw error in wind turbines is studied using support vector machines for regression (SVR). As the methodology...... is data-based, simulated data from a high fidelity aero-elastic model is used for learning. The model simulates a variable speed horizontal-axis wind turbine composed of three blades and a full converter. Both partial load (blade angles fixed at 0 deg) and full load zones (active pitch actuators...

Electricity Load Forecasting Using Support Vector Regression with Memetic Algorithms

Directory of Open Access Journals (Sweden)

Zhongyi Hu

2013-01-01

Full Text Available Electricity load forecasting is an important issue that is widely explored and examined in power systems operation literature and commercial transactions in electricity markets literature as well. Among the existing forecasting models, support vector regression (SVR has gained much attention. Considering the performance of SVR highly depends on its parameters; this study proposed a firefly algorithm (FA based memetic algorithm (FA-MA to appropriately determine the parameters of SVR forecasting model. In the proposed FA-MA algorithm, the FA algorithm is applied to explore the solution space, and the pattern search is used to conduct individual learning and thus enhance the exploitation of FA. Experimental results confirm that the proposed FA-MA based SVR model can not only yield more accurate forecasting results than the other four evolutionary algorithms based SVR models and three well-known forecasting models but also outperform the hybrid algorithms in the related existing literature.

Image Jacobian Matrix Estimation Based on Online Support Vector Regression

Directory of Open Access Journals (Sweden)

Shangqin Mao

2012-10-01

Full Text Available Research into robotics visual servoing is an important area in the field of robotics. It has proven difficult to achieve successful results for machine vision and robotics in unstructured environments without using any a priori camera or kinematic models. In uncalibrated visual servoing, image Jacobian matrix estimation methods can be divided into two groups: the online method and the offline method. The offline method is not appropriate for most natural environments. The online method is robust but rough. Moreover, if the images feature configuration changes, it needs to restart the approximating procedure. A novel approach based on an online support vector regression (OL-SVR algorithm is proposed which overcomes the drawbacks and combines the virtues just mentioned.

Future Projection with an Extreme-Learning Machine and Support Vector Regression of Reference Evapotranspiration in a Mountainous Inland Watershed in North-West China

Directory of Open Access Journals (Sweden)

Zhenliang Yin

2017-11-01

Full Text Available This study aims to project future variability of reference evapotranspiration (ET0 using artificial intelligence methods, constructed with an extreme-learning machine (ELM and support vector regression (SVR in a mountainous inland watershed in north-west China. Eight global climate model (GCM outputs retrieved from the Coupled Model Inter-comparison Project Phase 5 (CMIP5 were employed to downscale monthly ET0 for the historical period 1960–2005 as a validation approach and for the future period 2010–2099 as a projection of ET0 under the Representative Concentration Pathway (RCP 4.5 and 8.5 scenarios. The following conclusions can be drawn: the ELM and SVR methods demonstrate a very good performance in estimating Food and Agriculture Organization (FAO-56 Penman–Monteith ET0. Variation in future ET0 mainly occurs in the spring and autumn seasons, while the summer and winter ET0 changes are moderately small. Annually, the ET0 values were shown to increase at a rate of approximately 7.5 mm, 7.5 mm, 0.0 mm (8.2 mm, 15.0 mm, 15.0 mm decade−1, respectively, for the near-term projection (2010–2039, mid-term projection (2040–2069, and long-term projection (2070–2099 under the RCP4.5 (RCP8.5 scenario. Compared to the historical period, the relative changes in ET0 were found to be approximately 2%, 5% and 6% (2%, 7% and 13%, during the near, mid- and long-term periods, respectively, under the RCP4.5 (RCP8.5 warming scenarios. In accordance with the analyses, we aver that the opportunity to downscale monthly ET0 with artificial intelligence is useful in practice for water-management policies.

Short-Term Wind Speed Forecasting Using Support Vector Regression Optimized by Cuckoo Optimization Algorithm

Directory of Open Access Journals (Sweden)

Jianzhou Wang

2015-01-01

Full Text Available This paper develops an effectively intelligent model to forecast short-term wind speed series. A hybrid forecasting technique is proposed based on recurrence plot (RP and optimized support vector regression (SVR. Wind caused by the interaction of meteorological systems makes itself extremely unsteady and difficult to forecast. To understand the wind system, the wind speed series is analyzed using RP. Then, the SVR model is employed to forecast wind speed, in which the input variables are selected by RP, and two crucial parameters, including the penalties factor and gamma of the kernel function RBF, are optimized by various optimization algorithms. Those optimized algorithms are genetic algorithm (GA, particle swarm optimization algorithm (PSO, and cuckoo optimization algorithm (COA. Finally, the optimized SVR models, including COA-SVR, PSO-SVR, and GA-SVR, are evaluated based on some criteria and a hypothesis test. The experimental results show that (1 analysis of RP reveals that wind speed has short-term predictability on a short-term time scale, (2 the performance of the COA-SVR model is superior to that of the PSO-SVR and GA-SVR methods, especially for the jumping samplings, and (3 the COA-SVR method is statistically robust in multi-step-ahead prediction and can be applied to practical wind farm applications.

Video Quality Assessment and Machine Learning: Performance and Interpretability

DEFF Research Database (Denmark)

Søgaard, Jacob; Forchhammer, Søren; Korhonen, Jari

2015-01-01

In this work we compare a simple and a complex Machine Learning (ML) method used for the purpose of Video Quality Assessment (VQA). The simple ML method chosen is the Elastic Net (EN), which is a regularized linear regression model and easier to interpret. The more complex method chosen is Support...... Vector Regression (SVR), which has gained popularity in VQA research. Additionally, we present an ML-based feature selection method. Also, it is investigated how well the methods perform when tested on videos from other datasets. Our results show that content-independent cross-validation performance...... on a single dataset can be misleading and that in the case of very limited training and test data, especially in regards to different content as is the case for many video datasets, a simple ML approach is the better choice....

Hybrid Forecasting Approach Based on GRNN Neural Network and SVR Machine for Electricity Demand Forecasting

Directory of Open Access Journals (Sweden)

Weide Li

2017-01-01

Full Text Available Accurate electric power demand forecasting plays a key role in electricity markets and power systems. The electric power demand is usually a non-linear problem due to various unknown reasons, which make it difficult to get accurate prediction by traditional methods. The purpose of this paper is to propose a novel hybrid forecasting method for managing and scheduling the electricity power. EEMD-SCGRNN-PSVR, the proposed new method, combines ensemble empirical mode decomposition (EEMD, seasonal adjustment (S, cross validation (C, general regression neural network (GRNN and support vector regression machine optimized by the particle swarm optimization algorithm (PSVR. The main idea of EEMD-SCGRNN-PSVR is respectively to forecast waveform and trend component that hidden in demand series to substitute directly forecasting original electric demand. EEMD-SCGRNN-PSVR is used to predict the one week ahead half-hour’s electricity demand in two data sets (New South Wales (NSW and Victorian State (VIC in Australia. Experimental results show that the new hybrid model outperforms the other three models in terms of forecasting accuracy and model robustness.

Survival Prediction and Feature Selection in Patients with Breast Cancer Using Support Vector Regression

Directory of Open Access Journals (Sweden)

Shahrbanoo Goli

2016-01-01

Full Text Available The Support Vector Regression (SVR model has been broadly used for response prediction. However, few researchers have used SVR for survival analysis. In this study, a new SVR model is proposed and SVR with different kernels and the traditional Cox model are trained. The models are compared based on different performance measures. We also select the best subset of features using three feature selection methods: combination of SVR and statistical tests, univariate feature selection based on concordance index, and recursive feature elimination. The evaluations are performed using available medical datasets and also a Breast Cancer (BC dataset consisting of 573 patients who visited the Oncology Clinic of Hamadan province in Iran. Results show that, for the BC dataset, survival time can be predicted more accurately by linear SVR than nonlinear SVR. Based on the three feature selection methods, metastasis status, progesterone receptor status, and human epidermal growth factor receptor 2 status are the best features associated to survival. Also, according to the obtained results, performance of linear and nonlinear kernels is comparable. The proposed SVR model performs similar to or slightly better than other models. Also, SVR performs similar to or better than Cox when all features are included in model.

Seasonal prediction of winter extreme precipitation over Canada by support vector regression

Directory of Open Access Journals (Sweden)

Z. Zeng

2011-01-01

Full Text Available For forecasting the maximum 5-day accumulated precipitation over the winter season at lead times of 3, 6, 9 and 12 months over Canada from 1950 to 2007, two nonlinear and two linear regression models were used, where the models were support vector regression (SVR (nonlinear and linear versions, nonlinear Bayesian neural network (BNN and multiple linear regression (MLR. The 118 stations were grouped into six geographic regions by K-means clustering. For each region, the leading principal components of the winter maximum 5-d accumulated precipitation anomalies were the predictands. Potential predictors included quasi-global sea surface temperature anomalies and 500 hPa geopotential height anomalies over the Northern Hemisphere, as well as six climate indices (the Niño-3.4 region sea surface temperature, the North Atlantic Oscillation, the Pacific-North American teleconnection, the Pacific Decadal Oscillation, the Scandinavia pattern, and the East Atlantic pattern. The results showed that in general the two robust SVR models tended to have better forecast skills than the two non-robust models (MLR and BNN, and the nonlinear SVR model tended to forecast slightly better than the linear SVR model. Among the six regions, the Prairies region displayed the highest forecast skills, and the Arctic region the second highest. The strongest nonlinearity was manifested over the Prairies and the weakest nonlinearity over the Arctic.

Short-Term Distribution System State Forecast Based on Optimal Synchrophasor Sensor Placement and Extreme Learning Machine

Energy Technology Data Exchange (ETDEWEB)

Jiang, Huaiguang; Zhang, Yingchen

2016-11-14

This paper proposes an approach for distribution system state forecasting, which aims to provide an accurate and high speed state forecasting with an optimal synchrophasor sensor placement (OSSP) based state estimator and an extreme learning machine (ELM) based forecaster. Specifically, considering the sensor installation cost and measurement error, an OSSP algorithm is proposed to reduce the number of synchrophasor sensor and keep the whole distribution system numerically and topologically observable. Then, the weighted least square (WLS) based system state estimator is used to produce the training data for the proposed forecaster. Traditionally, the artificial neural network (ANN) and support vector regression (SVR) are widely used in forecasting due to their nonlinear modeling capabilities. However, the ANN contains heavy computation load and the best parameters for SVR are difficult to obtain. In this paper, the ELM, which overcomes these drawbacks, is used to forecast the future system states with the historical system states. The proposed approach is effective and accurate based on the testing results.

Noise model based ν-support vector regression with its application to short-term wind speed forecasting.

Science.gov (United States)

Hu, Qinghua; Zhang, Shiguang; Xie, Zongxia; Mi, Jusheng; Wan, Jie

2014-09-01

Support vector regression (SVR) techniques are aimed at discovering a linear or nonlinear structure hidden in sample data. Most existing regression techniques take the assumption that the error distribution is Gaussian. However, it was observed that the noise in some real-world applications, such as wind power forecasting and direction of the arrival estimation problem, does not satisfy Gaussian distribution, but a beta distribution, Laplacian distribution, or other models. In these cases the current regression techniques are not optimal. According to the Bayesian approach, we derive a general loss function and develop a technique of the uniform model of ν-support vector regression for the general noise model (N-SVR). The Augmented Lagrange Multiplier method is introduced to solve N-SVR. Numerical experiments on artificial data sets, UCI data and short-term wind speed prediction are conducted. The results show the effectiveness of the proposed technique. Copyright © 2014 Elsevier Ltd. All rights reserved.

Chaotic particle swarm optimization algorithm in a support vector regression electric load forecasting model

International Nuclear Information System (INIS)

Hong, W.-C.

2009-01-01

Accurate forecasting of electric load has always been the most important issues in the electricity industry, particularly for developing countries. Due to the various influences, electric load forecasting reveals highly nonlinear characteristics. Recently, support vector regression (SVR), with nonlinear mapping capabilities of forecasting, has been successfully employed to solve nonlinear regression and time series problems. However, it is still lack of systematic approaches to determine appropriate parameter combination for a SVR model. This investigation elucidates the feasibility of applying chaotic particle swarm optimization (CPSO) algorithm to choose the suitable parameter combination for a SVR model. The empirical results reveal that the proposed model outperforms the other two models applying other algorithms, genetic algorithm (GA) and simulated annealing algorithm (SA). Finally, it also provides the theoretical exploration of the electric load forecasting support system (ELFSS)

DNBR Prediction Using a Support Vector Regression

International Nuclear Information System (INIS)

Yang, Heon Young; Na, Man Gyun

2008-01-01

PWRs (Pressurized Water Reactors) generally operate in the nucleate boiling state. However, the conversion of nucleate boiling into film boiling with conspicuously reduced heat transfer induces a boiling crisis that may cause the fuel clad melting in the long run. This type of boiling crisis is called Departure from Nucleate Boiling (DNB) phenomena. Because the prediction of minimum DNBR in a reactor core is very important to prevent the boiling crisis such as clad melting, a lot of research has been conducted to predict DNBR values. The object of this research is to predict minimum DNBR applying support vector regression (SVR) by using the measured signals of a reactor coolant system (RCS). The SVR has extensively and successfully been applied to nonlinear function approximation like the proposed problem for estimating DNBR values that will be a function of various input variables such as reactor power, reactor pressure, core mass flowrate, control rod positions and so on. The minimum DNBR in a reactor core is predicted using these various operating condition data as the inputs to the SVR. The minimum DBNR values predicted by the SVR confirm its correctness compared with COLSS values

Advanced Machine Learning for Classification, Regression, and Generation in Jet Physics

CERN Multimedia

CERN. Geneva

2017-01-01

There is a deep connection between machine learning and jet physics - after all, jets are defined by unsupervised learning algorithms. Jet physics has been a driving force for studying modern machine learning in high energy physics. Domain specific challenges require new techniques to make full use of the algorithms. A key focus is on understanding how and what the algorithms learn. Modern machine learning techniques for jet physics are demonstrated for classification, regression, and generation. In addition to providing powerful baseline performance, we show how to train complex models directly on data and to generate sparse stacked images with non-uniform granularity.

Dynamic Heat Supply Prediction Using Support Vector Regression Optimized by Particle Swarm Optimization Algorithm

Directory of Open Access Journals (Sweden)

Meiping Wang

2016-01-01

Full Text Available We developed an effective intelligent model to predict the dynamic heat supply of heat source. A hybrid forecasting method was proposed based on support vector regression (SVR model-optimized particle swarm optimization (PSO algorithms. Due to the interaction of meteorological conditions and the heating parameters of heating system, it is extremely difficult to forecast dynamic heat supply. Firstly, the correlations among heat supply and related influencing factors in the heating system were analyzed through the correlation analysis of statistical theory. Then, the SVR model was employed to forecast dynamic heat supply. In the model, the input variables were selected based on the correlation analysis and three crucial parameters, including the penalties factor, gamma of the kernel RBF, and insensitive loss function, were optimized by PSO algorithms. The optimized SVR model was compared with the basic SVR, optimized genetic algorithm-SVR (GA-SVR, and artificial neural network (ANN through six groups of experiment data from two heat sources. The results of the correlation coefficient analysis revealed the relationship between the influencing factors and the forecasted heat supply and determined the input variables. The performance of the PSO-SVR model is superior to those of the other three models. The PSO-SVR method is statistically robust and can be applied to practical heating system.

Neutron Buildup Factors Calculation for Support Vector Regression Application in Shielding Analysis

International Nuclear Information System (INIS)

Duckic, P.; Matijevic, M.; Grgic, D.

2016-01-01

In this paper initial set of data for neutron buildup factors determination using Support Vector Regression (SVR) method is prepared. The performance of SVR technique strongly depends on the quality of information used for model training. Thus it is very important to provide representable data to the SVR. SVR is a supervised type of learning so it demands data in the input/output form. In the case of neutron buildup factors estimation, the input parameters are the incident neutron energy, shielding thickness and shielding material and the output parameter is the neutron buildup factor value. So far the initial sets of data for different shielding configurations have been obtained using SCALE4.4 sequence SAS3. However, this results were obtained using group constants, thus the incident neutron energy was determined as the average value for each energy group. Obtained this way, the data provided to the SVR are fewer and therefore insufficient. More valuable information is obtained using SCALE6.2beta5 sequence MAVRIC which can perform calculations for the explicit incident neutron energy, which leads to greater maneuvering possibilities when active learning measures are employed, and consequently improves the quality of the developed SVR model.(author).

Estimating Frequency by Interpolation Using Least Squares Support Vector Regression

Directory of Open Access Journals (Sweden)

Changwei Ma

2015-01-01

Full Text Available Discrete Fourier transform- (DFT- based maximum likelihood (ML algorithm is an important part of single sinusoid frequency estimation. As signal to noise ratio (SNR increases and is above the threshold value, it will lie very close to Cramer-Rao lower bound (CRLB, which is dependent on the number of DFT points. However, its mean square error (MSE performance is directly proportional to its calculation cost. As a modified version of support vector regression (SVR, least squares SVR (LS-SVR can not only still keep excellent capabilities for generalizing and fitting but also exhibit lower computational complexity. In this paper, therefore, LS-SVR is employed to interpolate on Fourier coefficients of received signals and attain high frequency estimation accuracy. Our results show that the proposed algorithm can make a good compromise between calculation cost and MSE performance under the assumption that the sample size, number of DFT points, and resampling points are already known.

Prediction of the distillation temperatures of crude oils using ¹H NMR and support vector regression with estimated confidence intervals.

Science.gov (United States)

Filgueiras, Paulo R; Terra, Luciana A; Castro, Eustáquio V R; Oliveira, Lize M S L; Dias, Júlio C M; Poppi, Ronei J

2015-09-01

This paper aims to estimate the temperature equivalent to 10% (T10%), 50% (T50%) and 90% (T90%) of distilled volume in crude oils using (1)H NMR and support vector regression (SVR). Confidence intervals for the predicted values were calculated using a boosting-type ensemble method in a procedure called ensemble support vector regression (eSVR). The estimated confidence intervals obtained by eSVR were compared with previously accepted calculations from partial least squares (PLS) models and a boosting-type ensemble applied in the PLS method (ePLS). By using the proposed boosting strategy, it was possible to identify outliers in the T10% property dataset. The eSVR procedure improved the accuracy of the distillation temperature predictions in relation to standard PLS, ePLS and SVR. For T10%, a root mean square error of prediction (RMSEP) of 11.6°C was obtained in comparison with 15.6°C for PLS, 15.1°C for ePLS and 28.4°C for SVR. The RMSEPs for T50% were 24.2°C, 23.4°C, 22.8°C and 14.4°C for PLS, ePLS, SVR and eSVR, respectively. For T90%, the values of RMSEP were 39.0°C, 39.9°C and 39.9°C for PLS, ePLS, SVR and eSVR, respectively. The confidence intervals calculated by the proposed boosting methodology presented acceptable values for the three properties analyzed; however, they were lower than those calculated by the standard methodology for PLS. Copyright © 2015 Elsevier B.V. All rights reserved.

A Novel Empirical Mode Decomposition With Support Vector Regression for Wind Speed Forecasting.

Science.gov (United States)

Ren, Ye; Suganthan, Ponnuthurai Nagaratnam; Srikanth, Narasimalu

2016-08-01

Wind energy is a clean and an abundant renewable energy source. Accurate wind speed forecasting is essential for power dispatch planning, unit commitment decision, maintenance scheduling, and regulation. However, wind is intermittent and wind speed is difficult to predict. This brief proposes a novel wind speed forecasting method by integrating empirical mode decomposition (EMD) and support vector regression (SVR) methods. The EMD is used to decompose the wind speed time series into several intrinsic mode functions (IMFs) and a residue. Subsequently, a vector combining one historical data from each IMF and the residue is generated to train the SVR. The proposed EMD-SVR model is evaluated with a wind speed data set. The proposed EMD-SVR model outperforms several recently reported methods with respect to accuracy or computational complexity.

Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma

Science.gov (United States)

Singal, Amit G.; Mukherjee, Ashin; Elmunzer, B. Joseph; Higgins, Peter DR; Lok, Anna S.; Zhu, Ji; Marrero, Jorge A; Waljee, Akbar K

2015-01-01

Background Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine learning algorithms. Methods We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared to the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. Results After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95%CI 0.56-0.67), whereas the machine learning algorithm had a c-statistic of 0.64 (95%CI 0.60–0.69) in the validation cohort. The machine learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (pmachine learning algorithm (p=0.047). Conclusion Machine learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC. PMID:24169273

Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression

Science.gov (United States)

Cornejo-Bueno, L.; Casanova-Mateo, C.; Sanz-Justo, J.; Cerro-Prada, E.; Salcedo-Sanz, S.

2017-11-01

We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is {>}1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions ({algorithm performance in daytime and nighttime conditions, and for different prediction time horizons.

Integrating principal component analysis and vector quantization with support vector regression for sulfur content prediction in HDS process

Directory of Open Access Journals (Sweden)

Shokri Saeid

2015-01-01

Full Text Available An accurate prediction of sulfur content is very important for the proper operation and product quality control in hydrodesulfurization (HDS process. For this purpose, a reliable data- driven soft sensors utilizing Support Vector Regression (SVR was developed and the effects of integrating Vector Quantization (VQ with Principle Component Analysis (PCA were studied on the assessment of this soft sensor. First, in pre-processing step the PCA and VQ techniques were used to reduce dimensions of the original input datasets. Then, the compressed datasets were used as input variables for the SVR model. Experimental data from the HDS setup were employed to validate the proposed integrated model. The integration of VQ/PCA techniques with SVR model was able to increase the prediction accuracy of SVR. The obtained results show that integrated technique (VQ-SVR was better than (PCA-SVR in prediction accuracy. Also, VQ decreased the sum of the training and test time of SVR model in comparison with PCA. For further evaluation, the performance of VQ-SVR model was also compared to that of SVR. The obtained results indicated that VQ-SVR model delivered the best satisfactory predicting performance (AARE= 0.0668 and R2= 0.995 in comparison with investigated models.

A machine learning approach for real-time modelling of tissue deformation in image-guided neurosurgery.

Science.gov (United States)

Tonutti, Michele; Gras, Gauthier; Yang, Guang-Zhong

2017-07-01

Accurate reconstruction and visualisation of soft tissue deformation in real time is crucial in image-guided surgery, particularly in augmented reality (AR) applications. Current deformation models are characterised by a trade-off between accuracy and computational speed. We propose an approach to derive a patient-specific deformation model for brain pathologies by combining the results of pre-computed finite element method (FEM) simulations with machine learning algorithms. The models can be computed instantaneously and offer an accuracy comparable to FEM models. A brain tumour is used as the subject of the deformation model. Load-driven FEM simulations are performed on a tetrahedral brain mesh afflicted by a tumour. Forces of varying magnitudes, positions, and inclination angles are applied onto the brain's surface. Two machine learning algorithms-artificial neural networks (ANNs) and support vector regression (SVR)-are employed to derive a model that can predict the resulting deformation for each node in the tumour's mesh. The tumour deformation can be predicted in real time given relevant information about the geometry of the anatomy and the load, all of which can be measured instantly during a surgical operation. The models can predict the position of the nodes with errors below 0.3mm, beyond the general threshold of surgical accuracy and suitable for high fidelity AR systems. The SVR models perform better than the ANN's, with positional errors for SVR models reaching under 0.2mm. The results represent an improvement over existing deformation models for real time applications, providing smaller errors and high patient-specificity. The proposed approach addresses the current needs of image-guided surgical systems and has the potential to be employed to model the deformation of any type of soft tissue. Copyright © 2017 Elsevier B.V. All rights reserved.

Regression Methods for Virtual Metrology of Layer Thickness in Chemical Vapor Deposition

DEFF Research Database (Denmark)

Purwins, Hendrik; Barak, Bernd; Nagi, Ahmed

2014-01-01

The quality of wafer production in semiconductor manufacturing cannot always be monitored by a costly physical measurement. Instead of measuring a quantity directly, it can be predicted by a regression method (Virtual Metrology). In this paper, a survey on regression methods is given to predict...... average Silicon Nitride cap layer thickness for the Plasma Enhanced Chemical Vapor Deposition (PECVD) dual-layer metal passivation stack process. Process and production equipment Fault Detection and Classification (FDC) data are used as predictor variables. Various variable sets are compared: one most...... algorithm, and Support Vector Regression (SVR). On a test set, SVR outperforms the other methods by a large margin, being more robust towards changes in the production conditions. The method performs better on high-dimensional multivariate input data than on the most predictive variables alone. Process...

Optimized support vector regression for drilling rate of penetration estimation

Science.gov (United States)

Bodaghi, Asadollah; Ansari, Hamid Reza; Gholami, Mahsa

2015-12-01

In the petroleum industry, drilling optimization involves the selection of operating conditions for achieving the desired depth with the minimum expenditure while requirements of personal safety, environment protection, adequate information of penetrated formations and productivity are fulfilled. Since drilling optimization is highly dependent on the rate of penetration (ROP), estimation of this parameter is of great importance during well planning. In this research, a novel approach called `optimized support vector regression' is employed for making a formulation between input variables and ROP. Algorithms used for optimizing the support vector regression are the genetic algorithm (GA) and the cuckoo search algorithm (CS). Optimization implementation improved the support vector regression performance by virtue of selecting proper values for its parameters. In order to evaluate the ability of optimization algorithms in enhancing SVR performance, their results were compared to the hybrid of pattern search and grid search (HPG) which is conventionally employed for optimizing SVR. The results demonstrated that the CS algorithm achieved further improvement on prediction accuracy of SVR compared to the GA and HPG as well. Moreover, the predictive model derived from back propagation neural network (BPNN), which is the traditional approach for estimating ROP, is selected for comparisons with CSSVR. The comparative results revealed the superiority of CSSVR. This study inferred that CSSVR is a viable option for precise estimation of ROP.

Prediction of GWL with the help of GRACE TWS for unevenly spaced time series data in India : Analysis of comparative performances of SVR, ANN and LRM

Science.gov (United States)

Mukherjee, Amritendu; Ramachandran, Parthasarathy

2018-03-01

Prediction of Ground Water Level (GWL) is extremely important for sustainable use and management of ground water resource. The motivations for this work is to understand the relationship between Gravity Recovery and Climate Experiment (GRACE) derived terrestrial water change (ΔTWS) data and GWL, so that ΔTWS could be used as a proxy measurement for GWL. In our study, we have selected five observation wells from different geographic regions in India. The datasets are unevenly spaced time series data which restricts us from applying standard time series methodologies and therefore in order to model and predict GWL with the help of ΔTWS, we have built Linear Regression Model (LRM), Support Vector Regression (SVR) and Artificial Neural Network (ANN). Comparative performances of LRM, SVR and ANN have been evaluated with the help of correlation coefficient (ρ) and Root Mean Square Error (RMSE) between the actual and fitted (for training dataset) or predicted (for test dataset) values of GWL. It has been observed in our study that ΔTWS is highly significant variable to model GWL and the amount of total variations in GWL that could be explained with the help of ΔTWS varies from 36.48% to 74.28% (0.3648 ⩽R2 ⩽ 0.7428) . We have found that for the model GWL ∼ Δ TWS, for both training and test dataset, performances of SVR and ANN are better than that of LRM in terms of ρ and RMSE. It also has been found in our study that with the inclusion of meteorological variables along with ΔTWS as input parameters to model GWL, the performance of SVR improves and it performs better than ANN. These results imply that for modelling irregular time series GWL data, ΔTWS could be very useful.

Computing confidence and prediction intervals of industrial equipment degradation by bootstrapped support vector regression

International Nuclear Information System (INIS)

Lins, Isis Didier; Droguett, Enrique López; Moura, Márcio das Chagas; Zio, Enrico; Jacinto, Carlos Magno

2015-01-01

Data-driven learning methods for predicting the evolution of the degradation processes affecting equipment are becoming increasingly attractive in reliability and prognostics applications. Among these, we consider here Support Vector Regression (SVR), which has provided promising results in various applications. Nevertheless, the predictions provided by SVR are point estimates whereas in order to take better informed decisions, an uncertainty assessment should be also carried out. For this, we apply bootstrap to SVR so as to obtain confidence and prediction intervals, without having to make any assumption about probability distributions and with good performance even when only a small data set is available. The bootstrapped SVR is first verified on Monte Carlo experiments and then is applied to a real case study concerning the prediction of degradation of a component from the offshore oil industry. The results obtained indicate that the bootstrapped SVR is a promising tool for providing reliable point and interval estimates, which can inform maintenance-related decisions on degrading components. - Highlights: • Bootstrap (pairs/residuals) and SVR are used as an uncertainty analysis framework. • Numerical experiments are performed to assess accuracy and coverage properties. • More bootstrap replications does not significantly improve performance. • Degradation of equipment of offshore oil wells is estimated by bootstrapped SVR. • Estimates about the scale growth rate can support maintenance-related decisions

Probability Distribution and Deviation Information Fusion Driven Support Vector Regression Model and Its Application

Directory of Open Access Journals (Sweden)

Changhao Fan

2017-01-01

Full Text Available In modeling, only information from the deviation between the output of the support vector regression (SVR model and the training sample is considered, whereas the other prior information of the training sample, such as probability distribution information, is ignored. Probabilistic distribution information describes the overall distribution of sample data in a training sample that contains different degrees of noise and potential outliers, as well as helping develop a high-accuracy model. To mine and use the probability distribution information of a training sample, a new support vector regression model that incorporates probability distribution information weight SVR (PDISVR is proposed. In the PDISVR model, the probability distribution of each sample is considered as the weight and is then introduced into the error coefficient and slack variables of SVR. Thus, the deviation and probability distribution information of the training sample are both used in the PDISVR model to eliminate the influence of noise and outliers in the training sample and to improve predictive performance. Furthermore, examples with different degrees of noise were employed to demonstrate the performance of PDISVR, which was then compared with those of three SVR-based methods. The results showed that PDISVR performs better than the three other methods.

Efficient design of gain-flattened multi-pump Raman fiber amplifiers using least squares support vector regression

Science.gov (United States)

Chen, Jing; Qiu, Xiaojie; Yin, Cunyi; Jiang, Hao

2018-02-01

An efficient method to design the broadband gain-flattened Raman fiber amplifier with multiple pumps is proposed based on least squares support vector regression (LS-SVR). A multi-input multi-output LS-SVR model is introduced to replace the complicated solving process of the nonlinear coupled Raman amplification equation. The proposed approach contains two stages: offline training stage and online optimization stage. During the offline stage, the LS-SVR model is trained. Owing to the good generalization capability of LS-SVR, the net gain spectrum can be directly and accurately obtained when inputting any combination of the pump wavelength and power to the well-trained model. During the online stage, we incorporate the LS-SVR model into the particle swarm optimization algorithm to find the optimal pump configuration. The design results demonstrate that the proposed method greatly shortens the computation time and enhances the efficiency of the pump parameter optimization for Raman fiber amplifier design.

Reference Function Based Spatiotemporal Fuzzy Logic Control Design Using Support Vector Regression Learning

Directory of Open Access Journals (Sweden)

Xian-Xia Zhang

2013-01-01

Full Text Available This paper presents a reference function based 3D FLC design methodology using support vector regression (SVR learning. The concept of reference function is introduced to 3D FLC for the generation of 3D membership functions (MF, which enhance the capability of the 3D FLC to cope with more kinds of MFs. The nonlinear mathematical expression of the reference function based 3D FLC is derived, and spatial fuzzy basis functions are defined. Via relating spatial fuzzy basis functions of a 3D FLC to kernel functions of an SVR, an equivalence relationship between a 3D FLC and an SVR is established. Therefore, a 3D FLC can be constructed using the learned results of an SVR. Furthermore, the universal approximation capability of the proposed 3D fuzzy system is proven in terms of the finite covering theorem. Finally, the proposed method is applied to a catalytic packed-bed reactor and simulation results have verified its effectiveness.

Multiple local feature representations and their fusion based on an SVR model for iris recognition using optimized Gabor filters

Science.gov (United States)

He, Fei; Liu, Yuanning; Zhu, Xiaodong; Huang, Chun; Han, Ye; Dong, Hongxing

2014-12-01

Gabor descriptors have been widely used in iris texture representations. However, fixed basic Gabor functions cannot match the changing nature of diverse iris datasets. Furthermore, a single form of iris feature cannot overcome difficulties in iris recognition, such as illumination variations, environmental conditions, and device variations. This paper provides multiple local feature representations and their fusion scheme based on a support vector regression (SVR) model for iris recognition using optimized Gabor filters. In our iris system, a particle swarm optimization (PSO)- and a Boolean particle swarm optimization (BPSO)-based algorithm is proposed to provide suitable Gabor filters for each involved test dataset without predefinition or manual modulation. Several comparative experiments on JLUBR-IRIS, CASIA-I, and CASIA-V4-Interval iris datasets are conducted, and the results show that our work can generate improved local Gabor features by using optimized Gabor filters for each dataset. In addition, our SVR fusion strategy may make full use of their discriminative ability to improve accuracy and reliability. Other comparative experiments show that our approach may outperform other popular iris systems.

Wind Power Ramp Events Prediction with Hybrid Machine Learning Regression Techniques and Reanalysis Data

Directory of Open Access Journals (Sweden)

Laura Cornejo-Bueno

2017-11-01

Full Text Available Wind Power Ramp Events (WPREs are large fluctuations of wind power in a short time interval, which lead to strong, undesirable variations in the electric power produced by a wind farm. Its accurate prediction is important in the effort of efficiently integrating wind energy in the electric system, without affecting considerably its stability, robustness and resilience. In this paper, we tackle the problem of predicting WPREs by applying Machine Learning (ML regression techniques. Our approach consists of using variables from atmospheric reanalysis data as predictive inputs for the learning machine, which opens the possibility of hybridizing numerical-physical weather models with ML techniques for WPREs prediction in real systems. Specifically, we have explored the feasibility of a number of state-of-the-art ML regression techniques, such as support vector regression, artificial neural networks (multi-layer perceptrons and extreme learning machines and Gaussian processes to solve the problem. Furthermore, the ERA-Interim reanalysis from the European Center for Medium-Range Weather Forecasts is the one used in this paper because of its accuracy and high resolution (in both spatial and temporal domains. Aiming at validating the feasibility of our predicting approach, we have carried out an extensive experimental work using real data from three wind farms in Spain, discussing the performance of the different ML regression tested in this wind power ramp event prediction problem.

Multiobjective Optimization for Fixture Locating Layout of Sheet Metal Part Using SVR and NSGA-II

Directory of Open Access Journals (Sweden)

Yuan Yang

2017-01-01

Full Text Available Fixture plays a significant role in determining the sheet metal part (SMP spatial position and restraining its excessive deformation in many manufacturing operations. However, it is still a difficult task to design and optimize SMP fixture locating layout at present because there exist multiple conflicting objectives and excessive computational cost of finite element analysis (FEA during the optimization process. To this end, a new multiobjective optimization method for SMP fixture locating layout is proposed in this paper based on the support vector regression (SVR surrogate model and the elitist nondominated sorting genetic algorithm (NSGA-II. By using ABAQUS™ Python script interface, a parametric FEA model is established. And the fixture locating layout is treated as design variables, while the overall deformation and maximum deformation of SMP under external forces are as the multiple objective functions. First, a limited number of training and testing samples are generated by combining Latin hypercube design (LHD with FEA. Second, two SVR prediction models corresponding to the multiple objectives are established by learning from the limited training samples and are integrated as the multiobjective optimization surrogate model. Third, NSGA-II is applied to determine the Pareto optimal solutions of SMP fixture locating layout. Finally, a multiobjective optimization for fixture locating layout of an aircraft fuselage skin case is conducted to illustrate and verify the proposed method.

Machine learning based switching model for electricity load forecasting

Energy Technology Data Exchange (ETDEWEB)

Fan, Shu; Lee, Wei-Jen [Energy Systems Research Center, The University of Texas at Arlington, 416 S. College Street, Arlington, TX 76019 (United States); Chen, Luonan [Department of Electronics, Information and Communication Engineering, Osaka Sangyo University, 3-1-1 Nakagaito, Daito, Osaka 574-0013 (Japan)

2008-06-15

In deregulated power markets, forecasting electricity loads is one of the most essential tasks for system planning, operation and decision making. Based on an integration of two machine learning techniques: Bayesian clustering by dynamics (BCD) and support vector regression (SVR), this paper proposes a novel forecasting model for day ahead electricity load forecasting. The proposed model adopts an integrated architecture to handle the non-stationarity of time series. Firstly, a BCD classifier is applied to cluster the input data set into several subsets by the dynamics of the time series in an unsupervised manner. Then, groups of SVRs are used to fit the training data of each subset in a supervised way. The effectiveness of the proposed model is demonstrated with actual data taken from the New York ISO and the Western Farmers Electric Cooperative in Oklahoma. (author)

Machine learning based switching model for electricity load forecasting

Energy Technology Data Exchange (ETDEWEB)

Fan Shu [Energy Systems Research Center, University of Texas at Arlington, 416 S. College Street, Arlington, TX 76019 (United States); Chen Luonan [Department of Electronics, Information and Communication Engineering, Osaka Sangyo University, 3-1-1 Nakagaito, Daito, Osaka 574-0013 (Japan); Lee, Weijen [Energy Systems Research Center, University of Texas at Arlington, 416 S. College Street, Arlington, TX 76019 (United States)], E-mail: wlee@uta.edu

2008-06-15

In deregulated power markets, forecasting electricity loads is one of the most essential tasks for system planning, operation and decision making. Based on an integration of two machine learning techniques: Bayesian clustering by dynamics (BCD) and support vector regression (SVR), this paper proposes a novel forecasting model for day ahead electricity load forecasting. The proposed model adopts an integrated architecture to handle the non-stationarity of time series. Firstly, a BCD classifier is applied to cluster the input data set into several subsets by the dynamics of the time series in an unsupervised manner. Then, groups of SVRs are used to fit the training data of each subset in a supervised way. The effectiveness of the proposed model is demonstrated with actual data taken from the New York ISO and the Western Farmers Electric Cooperative in Oklahoma.

Machine learning based switching model for electricity load forecasting

International Nuclear Information System (INIS)

Fan Shu; Chen Luonan; Lee, Weijen

2008-01-01

In deregulated power markets, forecasting electricity loads is one of the most essential tasks for system planning, operation and decision making. Based on an integration of two machine learning techniques: Bayesian clustering by dynamics (BCD) and support vector regression (SVR), this paper proposes a novel forecasting model for day ahead electricity load forecasting. The proposed model adopts an integrated architecture to handle the non-stationarity of time series. Firstly, a BCD classifier is applied to cluster the input data set into several subsets by the dynamics of the time series in an unsupervised manner. Then, groups of SVRs are used to fit the training data of each subset in a supervised way. The effectiveness of the proposed model is demonstrated with actual data taken from the New York ISO and the Western Farmers Electric Cooperative in Oklahoma

Predicting Jakarta composite index using hybrid of fuzzy time series and support vector regression models

Science.gov (United States)

Febrian Umbara, Rian; Tarwidi, Dede; Budi Setiawan, Erwin

2018-03-01

The paper discusses the prediction of Jakarta Composite Index (JCI) in Indonesia Stock Exchange. The study is based on JCI historical data for 1286 days to predict the value of JCI one day ahead. This paper proposes predictions done in two stages., The first stage using Fuzzy Time Series (FTS) to predict values of ten technical indicators, and the second stage using Support Vector Regression (SVR) to predict the value of JCI one day ahead, resulting in a hybrid prediction model FTS-SVR. The performance of this combined prediction model is compared with the performance of the single stage prediction model using SVR only. Ten technical indicators are used as input for each model.

Support vector regression to predict porosity and permeability: Effect of sample size

Science.gov (United States)

Al-Anazi, A. F.; Gates, I. D.

2012-02-01

Porosity and permeability are key petrophysical parameters obtained from laboratory core analysis. Cores, obtained from drilled wells, are often few in number for most oil and gas fields. Porosity and permeability correlations based on conventional techniques such as linear regression or neural networks trained with core and geophysical logs suffer poor generalization to wells with only geophysical logs. The generalization problem of correlation models often becomes pronounced when the training sample size is small. This is attributed to the underlying assumption that conventional techniques employing the empirical risk minimization (ERM) inductive principle converge asymptotically to the true risk values as the number of samples increases. In small sample size estimation problems, the available training samples must span the complexity of the parameter space so that the model is able both to match the available training samples reasonably well and to generalize to new data. This is achieved using the structural risk minimization (SRM) inductive principle by matching the capability of the model to the available training data. One method that uses SRM is support vector regression (SVR) network. In this research, the capability of SVR to predict porosity and permeability in a heterogeneous sandstone reservoir under the effect of small sample size is evaluated. Particularly, the impact of Vapnik's ɛ-insensitivity loss function and least-modulus loss function on generalization performance was empirically investigated. The results are compared to the multilayer perception (MLP) neural network, a widely used regression method, which operates under the ERM principle. The mean square error and correlation coefficients were used to measure the quality of predictions. The results demonstrate that SVR yields consistently better predictions of the porosity and permeability with small sample size than the MLP method. Also, the performance of SVR depends on both kernel function

Failure prognostics by support vector regression of time series data under stationary/nonstationary environmental and operational conditions

International Nuclear Information System (INIS)

Liu, Jie

2015-01-01

This Ph. D. work is motivated by the possibility of monitoring the conditions of components of energy systems for their extended and safe use, under proper practice of operation and adequate policies of maintenance. The aim is to develop a Support Vector Regression (SVR)-based framework for predicting time series data under stationary/nonstationary environmental and operational conditions. Single SVR and SVR-based ensemble approaches are developed to tackle the prediction problem based on both small and large datasets. Strategies are proposed for adaptively updating the single SVR and SVR-based ensemble models in the existence of pattern drifts. Comparisons with other online learning approaches for kernel-based modelling are provided with reference to time series data from a critical component in Nuclear Power Plants (NPPs) provided by Electricite de France (EDF). The results show that the proposed approaches achieve comparable prediction results, considering the Mean Squared Error (MSE) and Mean Relative Error (MRE), in much less computation time. Furthermore, by analyzing the geometrical meaning of the Feature Vector Selection (FVS) method proposed in the literature, a novel geometrically interpretable kernel method, named Reduced Rank Kernel Ridge Regression-II (RRKRR-II), is proposed to describe the linear relations between a predicted value and the predicted values of the Feature Vectors (FVs) selected by FVS. Comparisons with several kernel methods on a number of public datasets prove the good prediction accuracy and the easy-of-tuning of the hyper-parameters of RRKRR-II. (author)

Evaluation of svr: a wireless sensor network routing protocol

International Nuclear Information System (INIS)

Baloch, J.; Khanzada, T.J.S.

2014-01-01

The advancement in technology has made it possible to create small in size, low cost sensor nodes. However, the small size and low cost of such nodes comesat at price that is, reduced processing power, low memory and significantly small battery energy storage. WSNs (Wireless Sensor Networks) are inherently ad hoc in nature and are assumed to work in the toughest terrain. The network lifetime plays a pivotal role in a wireless sensor network. A long network lifetime, could be achieved by either making significant changes in these low cost devices, which is not a feasible solution or by improving the means of communication throughout the network. The communication in such networks could be improved by employing energy efficient routing protocols, to route the data throughout the network. In this paper the SVR (Spatial Vector Routing) protocol is compared against the most common WSN routing protocols, and from the results it could be inferred that the SVR protocol out performs its counterparts. The protocol provides an energy efficient means of communication in the network. (author)

Evaluation of modulation transfer function of optical lens system by support vector regression methodologies - A comparative study

Science.gov (United States)

Petković, Dalibor; Shamshirband, Shahaboddin; Saboohi, Hadi; Ang, Tan Fong; Anuar, Nor Badrul; Rahman, Zulkanain Abdul; Pavlović, Nenad T.

2014-07-01

The quantitative assessment of image quality is an important consideration in any type of imaging system. The modulation transfer function (MTF) is a graphical description of the sharpness and contrast of an imaging system or of its individual components. The MTF is also known and spatial frequency response. The MTF curve has different meanings according to the corresponding frequency. The MTF of an optical system specifies the contrast transmitted by the system as a function of image size, and is determined by the inherent optical properties of the system. In this study, the polynomial and radial basis function (RBF) are applied as the kernel function of Support Vector Regression (SVR) to estimate and predict estimate MTF value of the actual optical system according to experimental tests. Instead of minimizing the observed training error, SVR_poly and SVR_rbf attempt to minimize the generalization error bound so as to achieve generalized performance. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the SVR_rbf approach in compare to SVR_poly soft computing methodology.

Extreme Learning Machine and Moving Least Square Regression Based Solar Panel Vision Inspection

Directory of Open Access Journals (Sweden)

Heng Liu

2017-01-01

Full Text Available In recent years, learning based machine intelligence has aroused a lot of attention across science and engineering. Particularly in the field of automatic industry inspection, the machine learning based vision inspection plays a more and more important role in defect identification and feature extraction. Through learning from image samples, many features of industry objects, such as shapes, positions, and orientations angles, can be obtained and then can be well utilized to determine whether there is defect or not. However, the robustness and the quickness are not easily achieved in such inspection way. In this work, for solar panel vision inspection, we present an extreme learning machine (ELM and moving least square regression based approach to identify solder joint defect and detect the panel position. Firstly, histogram peaks distribution (HPD and fractional calculus are applied for image preprocessing. Then an ELM-based defective solder joints identification is discussed in detail. Finally, moving least square regression (MLSR algorithm is introduced for solar panel position determination. Experimental results and comparisons show that the proposed ELM and MLSR based inspection method is efficient not only in detection accuracy but also in processing speed.

Predictive based monitoring of nuclear plant component degradation using support vector regression

International Nuclear Information System (INIS)

Agarwal, Vivek; Alamaniotis, Miltiadis; Tsoukalas, Lefteri H.

2015-01-01

Nuclear power plants (NPPs) are large installations comprised of many active and passive assets. Degradation monitoring of all these assets is expensive (labor cost) and highly demanding task. In this paper a framework based on Support Vector Regression (SVR) for online surveillance of critical parameter degradation of NPP components is proposed. In this case, on time replacement or maintenance of components will prevent potential plant malfunctions, and reduce the overall operational cost. In the current work, we apply SVR equipped with a Gaussian kernel function to monitor components. Monitoring includes the one-step-ahead prediction of the component's respective operational quantity using the SVR model, while the SVR model is trained using a set of previous recorded degradation histories of similar components. Predictive capability of the model is evaluated upon arrival of a sensor measurement, which is compared to the component failure threshold. A maintenance decision is based on a fuzzy inference system that utilizes three parameters: (i) prediction evaluation in the previous steps, (ii) predicted value of the current step, (iii) and difference of current predicted value with components failure thresholds. The proposed framework will be tested on turbine blade degradation data.

A glucose model based on support vector regression for the prediction of hypoglycemic events under free-living conditions.

Science.gov (United States)

Georga, Eleni I; Protopappas, Vasilios C; Ardigò, Diego; Polyzos, Demosthenes; Fotiadis, Dimitrios I

2013-08-01

The prevention of hypoglycemic events is of paramount importance in the daily management of insulin-treated diabetes. The use of short-term prediction algorithms of the subcutaneous (s.c.) glucose concentration may contribute significantly toward this direction. The literature suggests that, although the recent glucose profile is a prominent predictor of hypoglycemia, the overall patient's context greatly impacts its accurate estimation. The objective of this study is to evaluate the performance of a support vector for regression (SVR) s.c. glucose method on hypoglycemia prediction. We extend our SVR model to predict separately the nocturnal events during sleep and the non-nocturnal (i.e., diurnal) ones over 30-min and 60-min horizons using information on recent glucose profile, meals, insulin intake, and physical activities for a hypoglycemic threshold of 70 mg/dL. We also introduce herein additional variables accounting for recurrent nocturnal hypoglycemia due to antecedent hypoglycemia, exercise, and sleep. SVR predictions are compared with those from two other machine learning techniques. The method is assessed on a dataset of 15 patients with type 1 diabetes under free-living conditions. Nocturnal hypoglycemic events are predicted with 94% sensitivity for both horizons and with time lags of 5.43 min and 4.57 min, respectively. As concerns the diurnal events, when physical activities are not considered, the sensitivity is 92% and 96% for a 30-min and 60-min horizon, respectively, with both time lags being less than 5 min. However, when such information is introduced, the diurnal sensitivity decreases by 8% and 3%, respectively. Both nocturnal and diurnal predictions show a high (>90%) precision. Results suggest that hypoglycemia prediction using SVR can be accurate and performs better in most diurnal and nocturnal cases compared with other techniques. It is advised that the problem of hypoglycemia prediction should be handled differently for nocturnal

Comparison of ν-support vector regression and logistic equation for ...

African Journals Online (AJOL)

Due to the complexity and high non-linearity of bioprocess, most simple mathematical models fail to describe the exact behavior of biochemistry systems. As a novel type of learning method, support vector regression (SVR) owns the powerful capability to characterize problems via small sample, nonlinearity, high dimension ...

A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting

Directory of Open Access Journals (Sweden)

Zhaoxuan Li

2016-01-01

Full Text Available We evaluate and compare two common methods, artificial neural networks (ANN and support vector regression (SVR, for predicting energy productions from a solar photovoltaic (PV system in Florida 15 min, 1 h and 24 h ahead of time. A hierarchical approach is proposed based on the machine learning algorithms tested. The production data used in this work corresponds to 15 min averaged power measurements collected from 2014. The accuracy of the model is determined using computing error statistics such as mean bias error (MBE, mean absolute error (MAE, root mean square error (RMSE, relative MBE (rMBE, mean percentage error (MPE and relative RMSE (rRMSE. This work provides findings on how forecasts from individual inverters will improve the total solar power generation forecast of the PV system.

Estimation of algal colonization growth on mortar surface using a ...

Indian Academy of Sciences (India)

Thu-Hien Tran

a hybridization of machine learning and metaheuristic optimization ... support vector regression (LS-SVR) for modelling the growth time of the green alga Klebsormidium flaccidum ...... 2012 Landslide susceptibility assessment in the Hoa Binh.

Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges.

Science.gov (United States)

Goldstein, Benjamin A; Navar, Ann Marie; Carter, Rickey E

2017-06-14

Risk prediction plays an important role in clinical cardiology research. Traditionally, most risk models have been based on regression models. While useful and robust, these statistical methods are limited to using a small number of predictors which operate in the same way on everyone, and uniformly throughout their range. The purpose of this review is to illustrate the use of machine-learning methods for development of risk prediction models. Typically presented as black box approaches, most machine-learning methods are aimed at solving particular challenges that arise in data analysis that are not well addressed by typical regression approaches. To illustrate these challenges, as well as how different methods can address them, we consider trying to predicting mortality after diagnosis of acute myocardial infarction. We use data derived from our institution's electronic health record and abstract data on 13 regularly measured laboratory markers. We walk through different challenges that arise in modelling these data and then introduce different machine-learning approaches. Finally, we discuss general issues in the application of machine-learning methods including tuning parameters, loss functions, variable importance, and missing data. Overall, this review serves as an introduction for those working on risk modelling to approach the diffuse field of machine learning. © The Author 2016. Published by Oxford University Press on behalf of the European Society of Cardiology.

Modification of textural and acidic properties of -SVR zeolite by desilication

Czech Academy of Sciences Publication Activity Database

Kubů, Martin; Opanasenko, Maksym; Shamzhy, Mariya

2014-01-01

Roč. 227, MAY 2014 (2014), s. 26-32 ISSN 0920-5861 R&D Projects: GA ČR GP13-17593P Institutional support: RVO:61388955 Keywords : -SVR zeolite * desilication * hierarchical materials Subject RIV: CF - Physical ; Theoretical Chemistry Impact factor: 3.893, year: 2014

Genome-wide prediction of discrete traits using bayesian regressions and machine learning

Directory of Open Access Journals (Sweden)

Forni Selma

2011-02-01

Full Text Available Abstract Background Genomic selection has gained much attention and the main goal is to increase the predictive accuracy and the genetic gain in livestock using dense marker information. Most methods dealing with the large p (number of covariates small n (number of observations problem have dealt only with continuous traits, but there are many important traits in livestock that are recorded in a discrete fashion (e.g. pregnancy outcome, disease resistance. It is necessary to evaluate alternatives to analyze discrete traits in a genome-wide prediction context. Methods This study shows two threshold versions of Bayesian regressions (Bayes A and Bayesian LASSO and two machine learning algorithms (boosting and random forest to analyze discrete traits in a genome-wide prediction context. These methods were evaluated using simulated and field data to predict yet-to-be observed records. Performances were compared based on the models' predictive ability. Results The simulation showed that machine learning had some advantages over Bayesian regressions when a small number of QTL regulated the trait under pure additivity. However, differences were small and disappeared with a large number of QTL. Bayesian threshold LASSO and boosting achieved the highest accuracies, whereas Random Forest presented the highest classification performance. Random Forest was the most consistent method in detecting resistant and susceptible animals, phi correlation was up to 81% greater than Bayesian regressions. Random Forest outperformed other methods in correctly classifying resistant and susceptible animals in the two pure swine lines evaluated. Boosting and Bayes A were more accurate with crossbred data. Conclusions The results of this study suggest that the best method for genome-wide prediction may depend on the genetic basis of the population analyzed. All methods were less accurate at correctly classifying intermediate animals than extreme animals. Among the different

Retrieving Tract Variables From Acoustics: A Comparison of Different Machine Learning Strategies.

Science.gov (United States)

Mitra, Vikramjit; Nam, Hosung; Espy-Wilson, Carol Y; Saltzman, Elliot; Goldstein, Louis

2010-09-13

Many different studies have claimed that articulatory information can be used to improve the performance of automatic speech recognition systems. Unfortunately, such articulatory information is not readily available in typical speaker-listener situations. Consequently, such information has to be estimated from the acoustic signal in a process which is usually termed "speech-inversion." This study aims to propose and compare various machine learning strategies for speech inversion: Trajectory mixture density networks (TMDNs), feedforward artificial neural networks (FF-ANN), support vector regression (SVR), autoregressive artificial neural network (AR-ANN), and distal supervised learning (DSL). Further, using a database generated by the Haskins Laboratories speech production model, we test the claim that information regarding constrictions produced by the distinct organs of the vocal tract (vocal tract variables) is superior to flesh-point information (articulatory pellet trajectories) for the inversion process.

Data-Driven Machine-Learning Model in District Heating System for Heat Load Prediction: A Comparison Study

Directory of Open Access Journals (Sweden)

Fisnik Dalipi

2016-01-01

Full Text Available We present our data-driven supervised machine-learning (ML model to predict heat load for buildings in a district heating system (DHS. Even though ML has been used as an approach to heat load prediction in literature, it is hard to select an approach that will qualify as a solution for our case as existing solutions are quite problem specific. For that reason, we compared and evaluated three ML algorithms within a framework on operational data from a DH system in order to generate the required prediction model. The algorithms examined are Support Vector Regression (SVR, Partial Least Square (PLS, and random forest (RF. We use the data collected from buildings at several locations for a period of 29 weeks. Concerning the accuracy of predicting the heat load, we evaluate the performance of the proposed algorithms using mean absolute error (MAE, mean absolute percentage error (MAPE, and correlation coefficient. In order to determine which algorithm had the best accuracy, we conducted performance comparison among these ML algorithms. The comparison of the algorithms indicates that, for DH heat load prediction, SVR method presented in this paper is the most efficient one out of the three also compared to other methods found in the literature.

Estimation of Electrically-Evoked Knee Torque from Mechanomyography Using Support Vector Regression

Directory of Open Access Journals (Sweden)

Morufu Olusola Ibitoye

2016-07-01

Full Text Available The difficulty of real-time muscle force or joint torque estimation during neuromuscular electrical stimulation (NMES in physical therapy and exercise science has motivated recent research interest in torque estimation from other muscle characteristics. This study investigated the accuracy of a computational intelligence technique for estimating NMES-evoked knee extension torque based on the Mechanomyographic signals (MMG of contracting muscles that were recorded from eight healthy males. Simulation of the knee torque was modelled via Support Vector Regression (SVR due to its good generalization ability in related fields. Inputs to the proposed model were MMG amplitude characteristics, the level of electrical stimulation or contraction intensity, and knee angle. Gaussian kernel function, as well as its optimal parameters were identified with the best performance measure and were applied as the SVR kernel function to build an effective knee torque estimation model. To train and test the model, the data were partitioned into training (70% and testing (30% subsets, respectively. The SVR estimation accuracy, based on the coefficient of determination (R2 between the actual and the estimated torque values was up to 94% and 89% during the training and testing cases, with root mean square errors (RMSE of 9.48 and 12.95, respectively. The knee torque estimations obtained using SVR modelling agreed well with the experimental data from an isokinetic dynamometer. These findings support the realization of a closed-loop NMES system for functional tasks using MMG as the feedback signal source and an SVR algorithm for joint torque estimation.

Support vector regression-guided unravelling: antioxidant capacity and quantitative structure-activity relationship predict reduction and promotion effects of flavonoids on acrylamide formation

Science.gov (United States)

Huang, Mengmeng; Wei, Yan; Wang, Jun; Zhang, Yu

2016-09-01

We used the support vector regression (SVR) approach to predict and unravel reduction/promotion effect of characteristic flavonoids on the acrylamide formation under a low-moisture Maillard reaction system. Results demonstrated the reduction/promotion effects by flavonoids at addition levels of 1-10000 μmol/L. The maximal inhibition rates (51.7%, 68.8% and 26.1%) and promote rates (57.7%, 178.8% and 27.5%) caused by flavones, flavonols and isoflavones were observed at addition levels of 100 μmol/L and 10000 μmol/L, respectively. The reduction/promotion effects were closely related to the change of trolox equivalent antioxidant capacity (ΔTEAC) and well predicted by triple ΔTEAC measurements via SVR models (R: 0.633-0.900). Flavonols exhibit stronger effects on the acrylamide formation than flavones and isoflavones as well as their O-glycosides derivatives, which may be attributed to the number and position of phenolic and 3-enolic hydroxyls. The reduction/promotion effects were well predicted by using optimized quantitative structure-activity relationship (QSAR) descriptors and SVR models (R: 0.926-0.994). Compared to artificial neural network and multi-linear regression models, SVR models exhibited better fitting performance for both TEAC-dependent and QSAR descriptor-dependent predicting work. These observations demonstrated that the SVR models are competent for predicting our understanding on the future use of natural antioxidants for decreasing the acrylamide formation.

Multivariate Time Series Forecasting of Crude Palm Oil Price Using Machine Learning Techniques

Science.gov (United States)

Kanchymalay, Kasturi; Salim, N.; Sukprasert, Anupong; Krishnan, Ramesh; Raba'ah Hashim, Ummi

2017-08-01

The aim of this paper was to study the correlation between crude palm oil (CPO) price, selected vegetable oil prices (such as soybean oil, coconut oil, and olive oil, rapeseed oil and sunflower oil), crude oil and the monthly exchange rate. Comparative analysis was then performed on CPO price forecasting results using the machine learning techniques. Monthly CPO prices, selected vegetable oil prices, crude oil prices and monthly exchange rate data from January 1987 to February 2017 were utilized. Preliminary analysis showed a positive and high correlation between the CPO price and soy bean oil price and also between CPO price and crude oil price. Experiments were conducted using multi-layer perception, support vector regression and Holt Winter exponential smoothing techniques. The results were assessed by using criteria of root mean square error (RMSE), means absolute error (MAE), means absolute percentage error (MAPE) and Direction of accuracy (DA). Among these three techniques, support vector regression(SVR) with Sequential minimal optimization (SMO) algorithm showed relatively better results compared to multi-layer perceptron and Holt Winters exponential smoothing method.

Exploring the Potential of WorldView-2 Red-Edge Band-Based Vegetation Indices for Estimation of Mangrove Leaf Area Index with Machine Learning Algorithms

Directory of Open Access Journals (Sweden)

Yuanhui Zhu

2017-10-01

Full Text Available To accurately estimate leaf area index (LAI in mangrove areas, the selection of appropriate models and predictor variables is critical. However, there is a major challenge in quantifying and mapping LAI using multi-spectral sensors due to the saturation effects of traditional vegetation indices (VIs for mangrove forests. WorldView-2 (WV2 imagery has proven to be effective to estimate LAI of grasslands and forests, but the sensitivity of its vegetation indices (VIs has been uncertain for mangrove forests. Furthermore, the single model may exhibit certain randomness and instability in model calibration and estimation accuracy. Therefore, this study aims to explore the sensitivity of WV2 VIs for estimating mangrove LAI by comparing artificial neural network regression (ANNR, support vector regression (SVR and random forest regression (RFR. The results suggest that the RFR algorithm yields the best results (RMSE = 0.45, 14.55% of the average LAI, followed by ANNR (RMSE = 0.49, 16.04% of the average LAI, and then SVR (RMSE = 0.51, 16.56% of the average LAI algorithms using 5-fold cross validation (CV using all VIs. Quantification of the variable importance shows that the VIs derived from the red-edge band consistently remain the most important contributor to LAI estimation. When the red-edge band-derived VIs are removed from the models, estimation accuracies measured in relative RMSE (RMSEr decrease by 3.79%, 2.70% and 4.47% for ANNR, SVR and RFR models respectively. VIs derived from red-edge band also yield better accuracy compared with other traditional bands of WV2, such as near-infrared-1 and near-infrared-2 band. Furthermore, the estimated LAI values vary significantly across different mangrove species. The study demonstrates the utility of VIs of WV2 imagery and the selected machine-learning algorithms in developing LAI models in mangrove forests. The results indicate that the red-edge band of WV2 imagery can help alleviate the saturation

A Short-Term and High-Resolution System Load Forecasting Approach Using Support Vector Regression with Hybrid Parameters Optimization

Energy Technology Data Exchange (ETDEWEB)

Jiang, Huaiguang [National Renewable Energy Laboratory (NREL), Golden, CO (United States)

2017-08-25

This work proposes an approach for distribution system load forecasting, which aims to provide highly accurate short-term load forecasting with high resolution utilizing a support vector regression (SVR) based forecaster and a two-step hybrid parameters optimization method. Specifically, because the load profiles in distribution systems contain abrupt deviations, a data normalization is designed as the pretreatment for the collected historical load data. Then an SVR model is trained by the load data to forecast the future load. For better performance of SVR, a two-step hybrid optimization algorithm is proposed to determine the best parameters. In the first step of the hybrid optimization algorithm, a designed grid traverse algorithm (GTA) is used to narrow the parameters searching area from a global to local space. In the second step, based on the result of the GTA, particle swarm optimization (PSO) is used to determine the best parameters in the local parameter space. After the best parameters are determined, the SVR model is used to forecast the short-term load deviation in the distribution system.

Research and Application of a Novel Hybrid Model Based on Data Selection and Artificial Intelligence Algorithm for Short Term Load Forecasting

Directory of Open Access Journals (Sweden)

Wendong Yang

2017-01-01

Full Text Available Machine learning plays a vital role in several modern economic and industrial fields, and selecting an optimized machine learning method to improve time series’ forecasting accuracy is challenging. Advanced machine learning methods, e.g., the support vector regression (SVR model, are widely employed in forecasting fields, but the individual SVR pays no attention to the significance of data selection, signal processing and optimization, which cannot always satisfy the requirements of time series forecasting. By preprocessing and analyzing the original time series, in this paper, a hybrid SVR model is developed, considering periodicity, trend and randomness, and combined with data selection, signal processing and an optimization algorithm for short-term load forecasting. Case studies of electricity power data from New South Wales and Singapore are regarded as exemplifications to estimate the performance of the developed novel model. The experimental results demonstrate that the proposed hybrid method is not only robust but also capable of achieving significant improvement compared with the traditional single models and can be an effective and efficient tool for power load forecasting.

A computationally efficient electricity price forecasting model for real time energy markets

International Nuclear Information System (INIS)

Feijoo, Felipe; Silva, Walter; Das, Tapas K.

2016-01-01

Highlights: • A fast hybrid forecast model for electricity prices. • Accurate forecast model that combines K-means and machine learning techniques. • Low computational effort by elimination of feature selection techniques. • New benchmark results by using market data for year 2012 and 2015. - Abstract: Increased significance of demand response and proliferation of distributed energy resources will continue to demand faster and more accurate models for forecasting locational marginal prices. This paper presents such a model (named K-SVR). While yielding prediction accuracy comparable with the best known models in the literature, K-SVR requires a significantly reduced computational time. The computational reduction is attained by eliminating the use of a feature selection process, which is commonly used by the existing models in the literature. K-SVR is a hybrid model that combines clustering algorithms, support vector machine, and support vector regression. K-SVR is tested using Pennsylvania–New Jersey–Maryland market data from the periods 2005–6, 2011–12, and 2014–15. Market data from 2006 has been used to measure performance of many of the existing models. Authors chose these models to compare performance and demonstrate strengths of K-SVR. Results obtained from K-SVR using the market data from 2012 and 2015 are new, and will serve as benchmark for future models.

Hybrid support vector regression and autoregressive integrated moving average models improved by particle swarm optimization for property crime rates forecasting with economic indicators.

Science.gov (United States)

Alwee, Razana; Shamsuddin, Siti Mariyam Hj; Sallehuddin, Roselina

2013-01-01

Crimes forecasting is an important area in the field of criminology. Linear models, such as regression and econometric models, are commonly applied in crime forecasting. However, in real crimes data, it is common that the data consists of both linear and nonlinear components. A single model may not be sufficient to identify all the characteristics of the data. The purpose of this study is to introduce a hybrid model that combines support vector regression (SVR) and autoregressive integrated moving average (ARIMA) to be applied in crime rates forecasting. SVR is very robust with small training data and high-dimensional problem. Meanwhile, ARIMA has the ability to model several types of time series. However, the accuracy of the SVR model depends on values of its parameters, while ARIMA is not robust to be applied to small data sets. Therefore, to overcome this problem, particle swarm optimization is used to estimate the parameters of the SVR and ARIMA models. The proposed hybrid model is used to forecast the property crime rates of the United State based on economic indicators. The experimental results show that the proposed hybrid model is able to produce more accurate forecasting results as compared to the individual models.

Hybrid Support Vector Regression and Autoregressive Integrated Moving Average Models Improved by Particle Swarm Optimization for Property Crime Rates Forecasting with Economic Indicators

Directory of Open Access Journals (Sweden)

Razana Alwee

2013-01-01

Full Text Available Crimes forecasting is an important area in the field of criminology. Linear models, such as regression and econometric models, are commonly applied in crime forecasting. However, in real crimes data, it is common that the data consists of both linear and nonlinear components. A single model may not be sufficient to identify all the characteristics of the data. The purpose of this study is to introduce a hybrid model that combines support vector regression (SVR and autoregressive integrated moving average (ARIMA to be applied in crime rates forecasting. SVR is very robust with small training data and high-dimensional problem. Meanwhile, ARIMA has the ability to model several types of time series. However, the accuracy of the SVR model depends on values of its parameters, while ARIMA is not robust to be applied to small data sets. Therefore, to overcome this problem, particle swarm optimization is used to estimate the parameters of the SVR and ARIMA models. The proposed hybrid model is used to forecast the property crime rates of the United State based on economic indicators. The experimental results show that the proposed hybrid model is able to produce more accurate forecasting results as compared to the individual models.

Predicting Taxi-Out Time at Congested Airports with Optimization-Based Support Vector Regression Methods

Directory of Open Access Journals (Sweden)

Guan Lian

2018-01-01

Full Text Available Accurate prediction of taxi-out time is significant precondition for improving the operationality of the departure process at an airport, as well as reducing the long taxi-out time, congestion, and excessive emission of greenhouse gases. Unfortunately, several of the traditional methods of predicting taxi-out time perform unsatisfactorily at congested airports. This paper describes and tests three of those conventional methods which include Generalized Linear Model, Softmax Regression Model, and Artificial Neural Network method and two improved Support Vector Regression (SVR approaches based on swarm intelligence algorithm optimization, which include Particle Swarm Optimization (PSO and Firefly Algorithm. In order to improve the global searching ability of Firefly Algorithm, adaptive step factor and Lévy flight are implemented simultaneously when updating the location function. Six factors are analysed, of which delay is identified as one significant factor in congested airports. Through a series of specific dynamic analyses, a case study of Beijing International Airport (PEK is tested with historical data. The performance measures show that the proposed two SVR approaches, especially the Improved Firefly Algorithm (IFA optimization-based SVR method, not only perform as the best modelling measures and accuracy rate compared with the representative forecast models, but also can achieve a better predictive performance when dealing with abnormal taxi-out time states.

[Extraction Optimization of Rhizome of Curcuma longa by Response Surface Methodology and Support Vector Regression].

Science.gov (United States)

Zhou, Pei-pei; Shan, Jin-feng; Jiang, Jian-lan

2015-12-01

To optimize the optimal microwave-assisted extraction method of curcuminoids from Curcuma longa. On the base of single factor experiment, the ethanol concentration, the ratio of liquid to solid and the microwave time were selected for further optimization. Support Vector Regression (SVR) and Central Composite Design-Response Surface Methodology (CCD) algorithm were utilized to design and establish models respectively, while Particle Swarm Optimization (PSO) was introduced to optimize the parameters of SVR models and to search optimal points of models. The evaluation indicator, the sum of curcumin, demethoxycurcumin and bisdemethoxycurcumin by HPLC, were used. The optimal parameters of microwave-assisted extraction were as follows: ethanol concentration of 69%, ratio of liquid to solid of 21 : 1, microwave time of 55 s. On those conditions, the sum of three curcuminoids was 28.97 mg/g (per gram of rhizomes powder). Both the CCD model and the SVR model were credible, for they have predicted the similar process condition and the deviation of yield were less than 1.2%.

A hybrid approach of stepwise regression, logistic regression, support vector machine, and decision tree for forecasting fraudulent financial statements.

Science.gov (United States)

Chen, Suduan; Goo, Yeong-Jia James; Shen, Zone-De

2014-01-01

As the fraudulent financial statement of an enterprise is increasingly serious with each passing day, establishing a valid forecasting fraudulent financial statement model of an enterprise has become an important question for academic research and financial practice. After screening the important variables using the stepwise regression, the study also matches the logistic regression, support vector machine, and decision tree to construct the classification models to make a comparison. The study adopts financial and nonfinancial variables to assist in establishment of the forecasting fraudulent financial statement model. Research objects are the companies to which the fraudulent and nonfraudulent financial statement happened between years 1998 to 2012. The findings are that financial and nonfinancial information are effectively used to distinguish the fraudulent financial statement, and decision tree C5.0 has the best classification effect 85.71%.

Laplacian embedded regression for scalable manifold regularization.

Science.gov (United States)

Chen, Lin; Tsang, Ivor W; Xu, Dong

2012-06-01

Semi-supervised learning (SSL), as a powerful tool to learn from a limited number of labeled data and a large number of unlabeled data, has been attracting increasing attention in the machine learning community. In particular, the manifold regularization framework has laid solid theoretical foundations for a large family of SSL algorithms, such as Laplacian support vector machine (LapSVM) and Laplacian regularized least squares (LapRLS). However, most of these algorithms are limited to small scale problems due to the high computational cost of the matrix inversion operation involved in the optimization problem. In this paper, we propose a novel framework called Laplacian embedded regression by introducing an intermediate decision variable into the manifold regularization framework. By using ∈-insensitive loss, we obtain the Laplacian embedded support vector regression (LapESVR) algorithm, which inherits the sparse solution from SVR. Also, we derive Laplacian embedded RLS (LapERLS) corresponding to RLS under the proposed framework. Both LapESVR and LapERLS possess a simpler form of a transformed kernel, which is the summation of the original kernel and a graph kernel that captures the manifold structure. The benefits of the transformed kernel are two-fold: (1) we can deal with the original kernel matrix and the graph Laplacian matrix in the graph kernel separately and (2) if the graph Laplacian matrix is sparse, we only need to perform the inverse operation for a sparse matrix, which is much more efficient when compared with that for a dense one. Inspired by kernel principal component analysis, we further propose to project the introduced decision variable into a subspace spanned by a few eigenvectors of the graph Laplacian matrix in order to better reflect the data manifold, as well as accelerate the calculation of the graph kernel, allowing our methods to efficiently and effectively cope with large scale SSL problems. Extensive experiments on both toy and real

Mutations in circularly permuted GTPase family genes AtNOA1/RIF1/SVR10 and BPG2 suppress var2-mediated leaf variegation in Arabidopsis thaliana.

Science.gov (United States)

Qi, Yafei; Zhao, Jun; An, Rui; Zhang, Juan; Liang, Shuang; Shao, Jingxia; Liu, Xiayan; An, Lijun; Yu, Fei

2016-03-01

Leaf variegation mutants constitute a unique group of chloroplast development mutants and are ideal genetic materials to dissect the regulation of chloroplast development. We have utilized the Arabidopsis yellow variegated (var2) mutant and genetic suppressor analysis to probe the mechanisms of chloroplast development. Here we report the isolation of a new var2 suppressor locus SUPPRESSOR OF VARIEGATION (SVR10). Genetic mapping and molecular complementation indicated that SVR10 encodes a circularly permuted GTPase that has been reported as Arabidopsis thaliana NITRIC OXIDE ASSOCIATED 1 (AtNOA1) and RESISTANT TO INHIBITION BY FOSMIDOMYCIN 1 (RIF1). Biochemical evidence showed that SVR10/AtNOA1/RIF1 likely localizes to the chloroplast stroma. We further demonstrate that the mutant of a close homologue of SVR10/AtNOA1/RIF1, BRASSINAZOLE INSENSITIVE PALE GREEN 2 (BPG2), can also suppress var2 leaf variegation. Mutants of SVR10 and BPG2 are impaired in photosynthesis and the accumulation of chloroplast proteins. Interestingly, two-dimensional blue native gel analysis showed that mutants of SVR10 and BPG2 display defects in the assembly of thylakoid membrane complexes including reduced levels of major photosynthetic complexes and the abnormal accumulation of a chlorophyll-protein supercomplex containing photosystem I. Taken together, our findings suggest that SVR10 and BPG2 are functionally related with VAR2, likely through their potential roles in regulating chloroplast protein homeostasis, and both SVR10 and BPG2 are required for efficient thylakoid protein complex assembly and photosynthesis.

Applications of the Chaotic Quantum Genetic Algorithm with Support Vector Regression in Load Forecasting

Directory of Open Access Journals (Sweden)

Cheng-Wen Lee

2017-11-01

Full Text Available Accurate electricity forecasting is still the critical issue in many energy management fields. The applications of hybrid novel algorithms with support vector regression (SVR models to overcome the premature convergence problem and improve forecasting accuracy levels also deserve to be widely explored. This paper applies chaotic function and quantum computing concepts to address the embedded drawbacks including crossover and mutation operations of genetic algorithms. Then, this paper proposes a novel electricity load forecasting model by hybridizing chaotic function and quantum computing with GA in an SVR model (named SVRCQGA to achieve more satisfactory forecasting accuracy levels. Experimental examples demonstrate that the proposed SVRCQGA model is superior to other competitive models.

A Hybrid Approach of Stepwise Regression, Logistic Regression, Support Vector Machine, and Decision Tree for Forecasting Fraudulent Financial Statements

Directory of Open Access Journals (Sweden)

Suduan Chen

2014-01-01

Full Text Available As the fraudulent financial statement of an enterprise is increasingly serious with each passing day, establishing a valid forecasting fraudulent financial statement model of an enterprise has become an important question for academic research and financial practice. After screening the important variables using the stepwise regression, the study also matches the logistic regression, support vector machine, and decision tree to construct the classification models to make a comparison. The study adopts financial and nonfinancial variables to assist in establishment of the forecasting fraudulent financial statement model. Research objects are the companies to which the fraudulent and nonfraudulent financial statement happened between years 1998 to 2012. The findings are that financial and nonfinancial information are effectively used to distinguish the fraudulent financial statement, and decision tree C5.0 has the best classification effect 85.71%.

Aplicación de los instrumentos de reincidencia en violencia HCR-20 y SVR-20 en dos grupos de delincuentes colombianos

Directory of Open Access Journals (Sweden)

Ángela Tapias Saldaña

2011-06-01

Full Text Available Esta investigación, de tipo exploratorio, cuenta con un diseño no experimental y transversal o transeccional; tuvo por objeto determinar si los instrumentos de evaluación psicológica forense HCR-20 y SVR-20 discriminan entre un grupo de reincidentes en delitos de acceso carnal violento y un grupo de sujetos judicializados por delitos menores. Hubo presencia de los indicadores, tanto del HCR-20 como del SVR-20, en los grupos. Se encontraron diferencias significativas en los puntajes de los grupos para el SVR- 20, pero no para el HCR-20. Finalmente, se observaron nuevos factores de riesgo, que podrían incluirse en instrumentos forenses.

[Study on the Recognition of Liquor Age of Gujing Based on Raman Spectra and Support Vector Regression].

Science.gov (United States)

Wang, Guo-xiang; Wang, Hai-yan; Wang, Hu; Zhang, Zheng-yong; Liu, Jun

2016-03-01

It is an important and difficult research point to recognize the age of Chinese liquor rapidly and exactly in the field of liquor analyzing, which is also of great significance to the healthy development of the liquor industry and protection of the legitimate rights and interests of consumers. Spectroscopy together with the pattern recognition technology is a preferred method of achieving rapid identification of wine quality, in which the Raman Spectroscopy is promising because of its little affection of water and little or free of sample pretreatment. So, in this paper, Raman spectra and support vector regression (SVR) are used to recognize different ages and different storing time of the liquor of the same age. The innovation of this paper is mainly reflected in the following three aspects. First, the application of Raman in the area of liquor analysis is rarely reported till now. Second, the concentration of studying the recognition of wine age, while most studies focus on studying specific components of liquor and studies together with the pattern recognition method focus more on the identification of brands or different types of base wine. The third one is the application of regression analysis framework, which cannot be only used to identify different years of liquor, but also can be used to analyze different storing time, which has theoretical and practical significance to the research and quality control of liquor. Three kinds of experiments are conducted in this paper. Firstly, SVR is used to recognize different ages of 5, 8, 16 and 26 years of the Gujing Liquor; secondly, SVR is also used to classify the storing time of the 8-years liquor; thirdly, certain group of train data is deleted form the train set and put into the test set to simulate the actual situation of liquor age recognition. Results show that the SVR model has good train and predict performance in these experiments, and it has better performance than other non-liner regression method such

New data-driven estimation of terrestrial CO2 fluxes in Asia using a standardized database of eddy covariance measurements, remote sensing data, and support vector regression

Science.gov (United States)

Ichii, Kazuhito; Ueyama, Masahito; Kondo, Masayuki; Saigusa, Nobuko; Kim, Joon; Alberto, Ma. Carmelita; Ardö, Jonas; Euskirchen, Eugénie S.; Kang, Minseok; Hirano, Takashi; Joiner, Joanna; Kobayashi, Hideki; Marchesini, Luca Belelli; Merbold, Lutz; Miyata, Akira; Saitoh, Taku M.; Takagi, Kentaro; Varlagin, Andrej; Bret-Harte, M. Syndonia; Kitamura, Kenzo; Kosugi, Yoshiko; Kotani, Ayumi; Kumar, Kireet; Li, Sheng-Gong; Machimura, Takashi; Matsuura, Yojiro; Mizoguchi, Yasuko; Ohta, Takeshi; Mukherjee, Sandipan; Yanagi, Yuji; Yasuda, Yukio; Zhang, Yiping; Zhao, Fenghua

2017-04-01

The lack of a standardized database of eddy covariance observations has been an obstacle for data-driven estimation of terrestrial CO2 fluxes in Asia. In this study, we developed such a standardized database using 54 sites from various databases by applying consistent postprocessing for data-driven estimation of gross primary productivity (GPP) and net ecosystem CO2 exchange (NEE). Data-driven estimation was conducted by using a machine learning algorithm: support vector regression (SVR), with remote sensing data for 2000 to 2015 period. Site-level evaluation of the estimated CO2 fluxes shows that although performance varies in different vegetation and climate classifications, GPP and NEE at 8 days are reproduced (e.g., r2 = 0.73 and 0.42 for 8 day GPP and NEE). Evaluation of spatially estimated GPP with Global Ozone Monitoring Experiment 2 sensor-based Sun-induced chlorophyll fluorescence shows that monthly GPP variations at subcontinental scale were reproduced by SVR (r2 = 1.00, 0.94, 0.91, and 0.89 for Siberia, East Asia, South Asia, and Southeast Asia, respectively). Evaluation of spatially estimated NEE with net atmosphere-land CO2 fluxes of Greenhouse Gases Observing Satellite (GOSAT) Level 4A product shows that monthly variations of these data were consistent in Siberia and East Asia; meanwhile, inconsistency was found in South Asia and Southeast Asia. Furthermore, differences in the land CO2 fluxes from SVR-NEE and GOSAT Level 4A were partially explained by accounting for the differences in the definition of land CO2 fluxes. These data-driven estimates can provide a new opportunity to assess CO2 fluxes in Asia and evaluate and constrain terrestrial ecosystem models.

Deep Support Vector Machines for Regression Problems

NARCIS (Netherlands)

Wiering, Marco; Schutten, Marten; Millea, Adrian; Meijster, Arnold; Schomaker, Lambertus

2013-01-01

In this paper we describe a novel extension of the support vector machine, called the deep support vector machine (DSVM). The original SVM has a single layer with kernel functions and is therefore a shallow model. The DSVM can use an arbitrary number of layers, in which lower-level layers contain

Sadhana | Indian Academy of Sciences

Indian Academy of Sciences (India)

Lifetime and latency analysis of IEEE 802.15.6 WBAN with interrupted sleep mechanism ... Estimation of stochastic environment force for master–slave robotic system ... squares support vector regression (LS-SVR) for modelling the growth time of the ... Mathematical modeling and analysis of WEDM machining parameters of ...

Comparing Machine Learning Classifiers and Linear/Logistic Regression to Explore the Relationship between Hand Dimensions and Demographic Characteristics.

Science.gov (United States)

Miguel-Hurtado, Oscar; Guest, Richard; Stevenage, Sarah V; Neil, Greg J; Black, Sue

2016-01-01

Understanding the relationship between physiological measurements from human subjects and their demographic data is important within both the biometric and forensic domains. In this paper we explore the relationship between measurements of the human hand and a range of demographic features. We assess the ability of linear regression and machine learning classifiers to predict demographics from hand features, thereby providing evidence on both the strength of relationship and the key features underpinning this relationship. Our results show that we are able to predict sex, height, weight and foot size accurately within various data-range bin sizes, with machine learning classification algorithms out-performing linear regression in most situations. In addition, we identify the features used to provide these relationships applicable across multiple applications.

Unmanned Aerial System (UAS)-based phenotyping of soybean using multi-sensor data fusion and extreme learning machine

Science.gov (United States)

Maimaitijiang, Maitiniyazi; Ghulam, Abduwasit; Sidike, Paheding; Hartling, Sean; Maimaitiyiming, Matthew; Peterson, Kyle; Shavers, Ethan; Fishman, Jack; Peterson, Jim; Kadam, Suhas; Burken, Joel; Fritschi, Felix

2017-12-01

Estimating crop biophysical and biochemical parameters with high accuracy at low-cost is imperative for high-throughput phenotyping in precision agriculture. Although fusion of data from multiple sensors is a common application in remote sensing, less is known on the contribution of low-cost RGB, multispectral and thermal sensors to rapid crop phenotyping. This is due to the fact that (1) simultaneous collection of multi-sensor data using satellites are rare and (2) multi-sensor data collected during a single flight have not been accessible until recent developments in Unmanned Aerial Systems (UASs) and UAS-friendly sensors that allow efficient information fusion. The objective of this study was to evaluate the power of high spatial resolution RGB, multispectral and thermal data fusion to estimate soybean (Glycine max) biochemical parameters including chlorophyll content and nitrogen concentration, and biophysical parameters including Leaf Area Index (LAI), above ground fresh and dry biomass. Multiple low-cost sensors integrated on UASs were used to collect RGB, multispectral, and thermal images throughout the growing season at a site established near Columbia, Missouri, USA. From these images, vegetation indices were extracted, a Crop Surface Model (CSM) was advanced, and a model to extract the vegetation fraction was developed. Then, spectral indices/features were combined to model and predict crop biophysical and biochemical parameters using Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), and Extreme Learning Machine based Regression (ELR) techniques. Results showed that: (1) For biochemical variable estimation, multispectral and thermal data fusion provided the best estimate for nitrogen concentration and chlorophyll (Chl) a content (RMSE of 9.9% and 17.1%, respectively) and RGB color information based indices and multispectral data fusion exhibited the largest RMSE 22.6%; the highest accuracy for Chl a + b content estimation was

Performance Comparison Between Support Vector Regression and Artificial Neural Network for Prediction of Oil Palm Production

Directory of Open Access Journals (Sweden)

Mustakim Mustakim

2016-02-01

Full Text Available The largest region that produces oil palm in Indonesia has an important role in improving the welfare of society and economy. Oil palm has increased significantly in Riau Province in every period, to determine the production development for the next few years with the functions and benefits of oil palm carried prediction production results that were seen from time series data last 8 years (2005-2013. In its prediction implementation, it was done by comparing the performance of Support Vector Regression (SVR method and Artificial Neural Network (ANN. From the experiment, SVR produced the best model compared with ANN. It is indicated by the correlation coefficient of 95% and 6% for MSE in the kernel Radial Basis Function (RBF, whereas ANN produced only 74% for R2 and 9% for MSE on the 8th experiment with hiden neuron 20 and learning rate 0,1. SVR model generates predictions for next 3 years which increased between 3% - 6% from actual data and RBF model predictions.

A Bayesian least squares support vector machines based framework for fault diagnosis and failure prognosis

Science.gov (United States)

Khawaja, Taimoor Saleem

and any abnormal or novel data during real-time operation. The results of the scheme are interpreted as a posterior probability of health (1 - probability of fault). As shown through two case studies in Chapter 3, the scheme is well suited for diagnosing imminent faults in dynamical non-linear systems. Finally, the failure prognosis scheme is based on an incremental weighted Bayesian LS-SVR machine. It is particularly suited for online deployment given the incremental nature of the algorithm and the quick optimization problem solved in the LS-SVR algorithm. By way of kernelization and a Gaussian Mixture Modeling (GMM) scheme, the algorithm can estimate "possibly" non-Gaussian posterior distributions for complex non-linear systems. An efficient regression scheme associated with the more rigorous core algorithm allows for long-term predictions, fault growth estimation with confidence bounds and remaining useful life (RUL) estimation after a fault is detected. The leading contributions of this thesis are (a) the development of a novel Bayesian Anomaly Detector for efficient and reliable Fault Detection and Identification (FDI) based on Least Squares Support Vector Machines, (b) the development of a data-driven real-time architecture for long-term Failure Prognosis using Least Squares Support Vector Machines, (c) Uncertainty representation and management using Bayesian Inference for posterior distribution estimation and hyper-parameter tuning, and finally (d) the statistical characterization of the performance of diagnosis and prognosis algorithms in order to relate the efficiency and reliability of the proposed schemes.

Sadhana | Indian Academy of Sciences

Indian Academy of Sciences (India)

This research proposes a machine learning method based on the least squares support vector regression (LS-SVR) for modelling the growth time of the green alga Klebsormidium ... These facts demonstrate that the hybrid model is a promising tool for assisting the decision-making process in building maintenance planning ...

Support vector regression and artificial neural network models for stability indicating analysis of mebeverine hydrochloride and sulpiride mixtures in pharmaceutical preparation: A comparative study

Science.gov (United States)

Naguib, Ibrahim A.; Darwish, Hany W.

2012-02-01

A comparison between support vector regression (SVR) and Artificial Neural Networks (ANNs) multivariate regression methods is established showing the underlying algorithm for each and making a comparison between them to indicate the inherent advantages and limitations. In this paper we compare SVR to ANN with and without variable selection procedure (genetic algorithm (GA)). To project the comparison in a sensible way, the methods are used for the stability indicating quantitative analysis of mixtures of mebeverine hydrochloride and sulpiride in binary mixtures as a case study in presence of their reported impurities and degradation products (summing up to 6 components) in raw materials and pharmaceutical dosage form via handling the UV spectral data. For proper analysis, a 6 factor 5 level experimental design was established resulting in a training set of 25 mixtures containing different ratios of the interfering species. An independent test set consisting of 5 mixtures was used to validate the prediction ability of the suggested models. The proposed methods (linear SVR (without GA) and linear GA-ANN) were successfully applied to the analysis of pharmaceutical tablets containing mebeverine hydrochloride and sulpiride mixtures. The results manifest the problem of nonlinearity and how models like the SVR and ANN can handle it. The methods indicate the ability of the mentioned multivariate calibration models to deconvolute the highly overlapped UV spectra of the 6 components' mixtures, yet using cheap and easy to handle instruments like the UV spectrophotometer.

Towards smart energy systems: application of kernel machine regression for medium term electricity load forecasting.

Science.gov (United States)

Alamaniotis, Miltiadis; Bargiotas, Dimitrios; Tsoukalas, Lefteri H

2016-01-01

Integration of energy systems with information technologies has facilitated the realization of smart energy systems that utilize information to optimize system operation. To that end, crucial in optimizing energy system operation is the accurate, ahead-of-time forecasting of load demand. In particular, load forecasting allows planning of system expansion, and decision making for enhancing system safety and reliability. In this paper, the application of two types of kernel machines for medium term load forecasting (MTLF) is presented and their performance is recorded based on a set of historical electricity load demand data. The two kernel machine models and more specifically Gaussian process regression (GPR) and relevance vector regression (RVR) are utilized for making predictions over future load demand. Both models, i.e., GPR and RVR, are equipped with a Gaussian kernel and are tested on daily predictions for a 30-day-ahead horizon taken from the New England Area. Furthermore, their performance is compared to the ARMA(2,2) model with respect to mean average percentage error and squared correlation coefficient. Results demonstrate the superiority of RVR over the other forecasting models in performing MTLF.

Prediction of diffuse solar irradiance using machine learning and multivariable regression

International Nuclear Information System (INIS)

Lou, Siwei; Li, Danny H.W.; Lam, Joseph C.; Chan, Wilco W.H.

2016-01-01

Highlights: • 54.9% of the annual global irradiance is composed by its diffuse part in HK. • Hourly diffuse irradiance was predicted by accessible variables. • The importance of variable in prediction was assessed by machine learning. • Simple prediction equations were developed with the knowledge of variable importance. - Abstract: The paper studies the horizontal global, direct-beam and sky-diffuse solar irradiance data measured in Hong Kong from 2008 to 2013. A machine learning algorithm was employed to predict the horizontal sky-diffuse irradiance and conduct sensitivity analysis for the meteorological variables. Apart from the clearness index (horizontal global/extra atmospheric solar irradiance), we found that predictors including solar altitude, air temperature, cloud cover and visibility are also important in predicting the diffuse component. The mean absolute error (MAE) of the logistic regression using the aforementioned predictors was less than 21.5 W/m"2 and 30 W/m"2 for Hong Kong and Denver, USA, respectively. With the systematic recording of the five variables for more than 35 years, the proposed model would be appropriate to estimate of long-term diffuse solar radiation, study climate change and develope typical meteorological year in Hong Kong and places with similar climates.

Application of support vector regression (SVR) for stream flow prediction on the Amazon basin

CSIR Research Space (South Africa)

Du Toit, Melise

2016-10-01

Full Text Available regression technique is used in this study to analyse historical stream flow occurrences and predict stream flow values for the Amazon basin. Up to twelve month predictions are made and the coefficient of determination and root-mean-square error are used...

Modeling of Isomerization of C8 Aromatics by Online Least Squares Support Vector Machine%在线最小二乘支持向量机及其在C8芳烃异构化建模中的应用

Institute of Scientific and Technical Information of China (English)

李丽娟; 苏宏业; 褚建

2009-01-01

Trie least squares support vector regression (LS-SVR) is usually used for the modeling of single output system, but it is not well suitable for the actual multi-input-multi-output system. The paper aims at the modeling of multi-output systems by LS-SVR. The multi-output LS-SVR is derived in detail. To avoid the inversion of large matrix, the recursive algorithm of the parameters is given, which makes the online algorithm of LS-SVR practical. Since the computing time increases with the number of training samples, the sparseness is studied based on the pro jection of online LS-SVR. The residual of projection less than a threshold is omitted, so that a lot of samples are kept out of the training set and the sparseness is obtained. The standard LS-SVR, nonsparse online LS-SVR and sparse online LS-SVR with different threshold are used for modeling the isomerization of Cj aromatics. The root-mean-square-error (RMSE), number of support vectors and running time of three algorithms are compared and the result indicates that the performance of sparse online LS-SVR is more favorable.

Distributed collaborative probabilistic design for turbine blade-tip radial running clearance using support vector machine of regression

Science.gov (United States)

Fei, Cheng-Wei; Bai, Guang-Chen

2014-12-01

To improve the computational precision and efficiency of probabilistic design for mechanical dynamic assembly like the blade-tip radial running clearance (BTRRC) of gas turbine, a distribution collaborative probabilistic design method-based support vector machine of regression (SR)(called as DCSRM) is proposed by integrating distribution collaborative response surface method and support vector machine regression model. The mathematical model of DCSRM is established and the probabilistic design idea of DCSRM is introduced. The dynamic assembly probabilistic design of aeroengine high-pressure turbine (HPT) BTRRC is accomplished to verify the proposed DCSRM. The analysis results reveal that the optimal static blade-tip clearance of HPT is gained for designing BTRRC, and improving the performance and reliability of aeroengine. The comparison of methods shows that the DCSRM has high computational accuracy and high computational efficiency in BTRRC probabilistic analysis. The present research offers an effective way for the reliability design of mechanical dynamic assembly and enriches mechanical reliability theory and method.

Real-time prediction of respiratory motion using a cascade structure of an extended Kalman filter and support vector regression.

Science.gov (United States)

Hong, S-M; Bukhari, W

2014-07-07

The motion of thoracic and abdominal tumours induced by respiratory motion often exceeds 20 mm, and can significantly compromise dose conformality. Motion-adaptive radiotherapy aims to deliver a conformal dose distribution to the tumour with minimal normal tissue exposure by compensating for the tumour motion. This adaptive radiotherapy, however, requires the prediction of the tumour movement that can occur over the system latency period. In general, motion prediction approaches can be classified into two groups: model-based and model-free. Model-based approaches utilize a motion model in predicting respiratory motion. These approaches are computationally efficient and responsive to irregular changes in respiratory motion. Model-free approaches do not assume an explicit model of motion dynamics, and predict future positions by learning from previous observations. Artificial neural networks (ANNs) and support vector regression (SVR) are examples of model-free approaches. In this article, we present a prediction algorithm that combines a model-based and a model-free approach in a cascade structure. The algorithm, which we call EKF-SVR, first employs a model-based algorithm (named LCM-EKF) to predict the respiratory motion, and then uses a model-free SVR algorithm to estimate and correct the error of the LCM-EKF prediction. Extensive numerical experiments based on a large database of 304 respiratory motion traces are performed. The experimental results demonstrate that the EKF-SVR algorithm successfully reduces the prediction error of the LCM-EKF, and outperforms the model-free ANN and SVR algorithms in terms of prediction accuracy across lookahead lengths of 192, 384, and 576 ms.

Real-time prediction of respiratory motion using a cascade structure of an extended Kalman filter and support vector regression

International Nuclear Information System (INIS)

Hong, S-M; Bukhari, W

2014-01-01

The motion of thoracic and abdominal tumours induced by respiratory motion often exceeds 20 mm, and can significantly compromise dose conformality. Motion-adaptive radiotherapy aims to deliver a conformal dose distribution to the tumour with minimal normal tissue exposure by compensating for the tumour motion. This adaptive radiotherapy, however, requires the prediction of the tumour movement that can occur over the system latency period. In general, motion prediction approaches can be classified into two groups: model-based and model-free. Model-based approaches utilize a motion model in predicting respiratory motion. These approaches are computationally efficient and responsive to irregular changes in respiratory motion. Model-free approaches do not assume an explicit model of motion dynamics, and predict future positions by learning from previous observations. Artificial neural networks (ANNs) and support vector regression (SVR) are examples of model-free approaches. In this article, we present a prediction algorithm that combines a model-based and a model-free approach in a cascade structure. The algorithm, which we call EKF–SVR, first employs a model-based algorithm (named LCM–EKF) to predict the respiratory motion, and then uses a model-free SVR algorithm to estimate and correct the error of the LCM–EKF prediction. Extensive numerical experiments based on a large database of 304 respiratory motion traces are performed. The experimental results demonstrate that the EKF–SVR algorithm successfully reduces the prediction error of the LCM–EKF, and outperforms the model-free ANN and SVR algorithms in terms of prediction accuracy across lookahead lengths of 192, 384, and 576 ms. (paper)

Estimation of the laser cutting operating cost by support vector regression methodology

Science.gov (United States)

Jović, Srđan; Radović, Aleksandar; Šarkoćević, Živče; Petković, Dalibor; Alizamir, Meysam

2016-09-01

Laser cutting is a popular manufacturing process utilized to cut various types of materials economically. The operating cost is affected by laser power, cutting speed, assist gas pressure, nozzle diameter and focus point position as well as the workpiece material. In this article, the process factors investigated were: laser power, cutting speed, air pressure and focal point position. The aim of this work is to relate the operating cost to the process parameters mentioned above. CO2 laser cutting of stainless steel of medical grade AISI316L has been investigated. The main goal was to analyze the operating cost through the laser power, cutting speed, air pressure, focal point position and material thickness. Since the laser operating cost is a complex, non-linear task, soft computing optimization algorithms can be used. Intelligent soft computing scheme support vector regression (SVR) was implemented. The performance of the proposed estimator was confirmed with the simulation results. The SVR results are then compared with artificial neural network and genetic programing. According to the results, a greater improvement in estimation accuracy can be achieved through the SVR compared to other soft computing methodologies. The new optimization methods benefit from the soft computing capabilities of global optimization and multiobjective optimization rather than choosing a starting point by trial and error and combining multiple criteria into a single criterion.

A land use regression model for ambient ultrafine particles in Montreal, Canada: A comparison of linear regression and a machine learning approach.

Science.gov (United States)

Weichenthal, Scott; Ryswyk, Keith Van; Goldstein, Alon; Bagg, Scott; Shekkarizfard, Maryam; Hatzopoulou, Marianne

2016-04-01

Existing evidence suggests that ambient ultrafine particles (UFPs) (regression model for UFPs in Montreal, Canada using mobile monitoring data collected from 414 road segments during the summer and winter months between 2011 and 2012. Two different approaches were examined for model development including standard multivariable linear regression and a machine learning approach (kernel-based regularized least squares (KRLS)) that learns the functional form of covariate impacts on ambient UFP concentrations from the data. The final models included parameters for population density, ambient temperature and wind speed, land use parameters (park space and open space), length of local roads and rail, and estimated annual average NOx emissions from traffic. The final multivariable linear regression model explained 62% of the spatial variation in ambient UFP concentrations whereas the KRLS model explained 79% of the variance. The KRLS model performed slightly better than the linear regression model when evaluated using an external dataset (R(2)=0.58 vs. 0.55) or a cross-validation procedure (R(2)=0.67 vs. 0.60). In general, our findings suggest that the KRLS approach may offer modest improvements in predictive performance compared to standard multivariable linear regression models used to estimate spatial variations in ambient UFPs. However, differences in predictive performance were not statistically significant when evaluated using the cross-validation procedure. Crown Copyright © 2015. Published by Elsevier Inc. All rights reserved.

Mixed kernel function support vector regression for global sensitivity analysis

Science.gov (United States)

Cheng, Kai; Lu, Zhenzhou; Wei, Yuhao; Shi, Yan; Zhou, Yicheng

2017-11-01

Global sensitivity analysis (GSA) plays an important role in exploring the respective effects of input variables on an assigned output response. Amongst the wide sensitivity analyses in literature, the Sobol indices have attracted much attention since they can provide accurate information for most models. In this paper, a mixed kernel function (MKF) based support vector regression (SVR) model is employed to evaluate the Sobol indices at low computational cost. By the proposed derivation, the estimation of the Sobol indices can be obtained by post-processing the coefficients of the SVR meta-model. The MKF is constituted by the orthogonal polynomials kernel function and Gaussian radial basis kernel function, thus the MKF possesses both the global characteristic advantage of the polynomials kernel function and the local characteristic advantage of the Gaussian radial basis kernel function. The proposed approach is suitable for high-dimensional and non-linear problems. Performance of the proposed approach is validated by various analytical functions and compared with the popular polynomial chaos expansion (PCE). Results demonstrate that the proposed approach is an efficient method for global sensitivity analysis.

Use seismic colored inversion and power law committee machine based on imperial competitive algorithm for improving porosity prediction in a heterogeneous reservoir

Science.gov (United States)

Ansari, Hamid Reza

2014-09-01

In this paper we propose a new method for predicting rock porosity based on a combination of several artificial intelligence systems. The method focuses on one of the Iranian carbonate fields in the Persian Gulf. Because there is strong heterogeneity in carbonate formations, estimation of rock properties experiences more challenge than sandstone. For this purpose, seismic colored inversion (SCI) and a new approach of committee machine are used in order to improve porosity estimation. The study comprises three major steps. First, a series of sample-based attributes is calculated from 3D seismic volume. Acoustic impedance is an important attribute that is obtained by the SCI method in this study. Second, porosity log is predicted from seismic attributes using common intelligent computation systems including: probabilistic neural network (PNN), radial basis function network (RBFN), multi-layer feed forward network (MLFN), ε-support vector regression (ε-SVR) and adaptive neuro-fuzzy inference system (ANFIS). Finally, a power law committee machine (PLCM) is constructed based on imperial competitive algorithm (ICA) to combine the results of all previous predictions in a single solution. This technique is called PLCM-ICA in this paper. The results show that PLCM-ICA model improved the results of neural networks, support vector machine and neuro-fuzzy system.

Applying Different Independent Component Analysis Algorithms and Support Vector Regression for IT Chain Store Sales Forecasting

Science.gov (United States)

Dai, Wensheng

2014-01-01

Sales forecasting is one of the most important issues in managing information technology (IT) chain store sales since an IT chain store has many branches. Integrating feature extraction method and prediction tool, such as support vector regression (SVR), is a useful method for constructing an effective sales forecasting scheme. Independent component analysis (ICA) is a novel feature extraction technique and has been widely applied to deal with various forecasting problems. But, up to now, only the basic ICA method (i.e., temporal ICA model) was applied to sale forecasting problem. In this paper, we utilize three different ICA methods including spatial ICA (sICA), temporal ICA (tICA), and spatiotemporal ICA (stICA) to extract features from the sales data and compare their performance in sales forecasting of IT chain store. Experimental results from a real sales data show that the sales forecasting scheme by integrating stICA and SVR outperforms the comparison models in terms of forecasting error. The stICA is a promising tool for extracting effective features from branch sales data and the extracted features can improve the prediction performance of SVR for sales forecasting. PMID:25165740

Applying different independent component analysis algorithms and support vector regression for IT chain store sales forecasting.

Science.gov (United States)

Dai, Wensheng; Wu, Jui-Yu; Lu, Chi-Jie

2014-01-01

Sales forecasting is one of the most important issues in managing information technology (IT) chain store sales since an IT chain store has many branches. Integrating feature extraction method and prediction tool, such as support vector regression (SVR), is a useful method for constructing an effective sales forecasting scheme. Independent component analysis (ICA) is a novel feature extraction technique and has been widely applied to deal with various forecasting problems. But, up to now, only the basic ICA method (i.e., temporal ICA model) was applied to sale forecasting problem. In this paper, we utilize three different ICA methods including spatial ICA (sICA), temporal ICA (tICA), and spatiotemporal ICA (stICA) to extract features from the sales data and compare their performance in sales forecasting of IT chain store. Experimental results from a real sales data show that the sales forecasting scheme by integrating stICA and SVR outperforms the comparison models in terms of forecasting error. The stICA is a promising tool for extracting effective features from branch sales data and the extracted features can improve the prediction performance of SVR for sales forecasting.

Applying Different Independent Component Analysis Algorithms and Support Vector Regression for IT Chain Store Sales Forecasting

Directory of Open Access Journals (Sweden)

Wensheng Dai

2014-01-01

Full Text Available Sales forecasting is one of the most important issues in managing information technology (IT chain store sales since an IT chain store has many branches. Integrating feature extraction method and prediction tool, such as support vector regression (SVR, is a useful method for constructing an effective sales forecasting scheme. Independent component analysis (ICA is a novel feature extraction technique and has been widely applied to deal with various forecasting problems. But, up to now, only the basic ICA method (i.e., temporal ICA model was applied to sale forecasting problem. In this paper, we utilize three different ICA methods including spatial ICA (sICA, temporal ICA (tICA, and spatiotemporal ICA (stICA to extract features from the sales data and compare their performance in sales forecasting of IT chain store. Experimental results from a real sales data show that the sales forecasting scheme by integrating stICA and SVR outperforms the comparison models in terms of forecasting error. The stICA is a promising tool for extracting effective features from branch sales data and the extracted features can improve the prediction performance of SVR for sales forecasting.

Forecast daily indices of solar activity, F10.7, using support vector regression method

International Nuclear Information System (INIS)

Huang Cong; Liu Dandan; Wang Jingsong

2009-01-01

The 10.7 cm solar radio flux (F10.7), the value of the solar radio emission flux density at a wavelength of 10.7 cm, is a useful index of solar activity as a proxy for solar extreme ultraviolet radiation. It is meaningful and important to predict F10.7 values accurately for both long-term (months-years) and short-term (days) forecasting, which are often used as inputs in space weather models. This study applies a novel neural network technique, support vector regression (SVR), to forecasting daily values of F10.7. The aim of this study is to examine the feasibility of SVR in short-term F10.7 forecasting. The approach, based on SVR, reduces the dimension of feature space in the training process by using a kernel-based learning algorithm. Thus, the complexity of the calculation becomes lower and a small amount of training data will be sufficient. The time series of F10.7 from 2002 to 2006 are employed as the data sets. The performance of the approach is estimated by calculating the norm mean square error and mean absolute percentage error. It is shown that our approach can perform well by using fewer training data points than the traditional neural network. (research paper)

Failure and reliability prediction by support vector machines regression of time series data

International Nuclear Information System (INIS)

Chagas Moura, Marcio das; Zio, Enrico; Lins, Isis Didier; Droguett, Enrique

2011-01-01

Support Vector Machines (SVMs) are kernel-based learning methods, which have been successfully adopted for regression problems. However, their use in reliability applications has not been widely explored. In this paper, a comparative analysis is presented in order to evaluate the SVM effectiveness in forecasting time-to-failure and reliability of engineered components based on time series data. The performance on literature case studies of SVM regression is measured against other advanced learning methods such as the Radial Basis Function, the traditional MultiLayer Perceptron model, Box-Jenkins autoregressive-integrated-moving average and the Infinite Impulse Response Locally Recurrent Neural Networks. The comparison shows that in the analyzed cases, SVM outperforms or is comparable to other techniques. - Highlights: → Realistic modeling of reliability demands complex mathematical formulations. → SVM is proper when the relation input/output is unknown or very costly to be obtained. → Results indicate the potential of SVM for reliability time series prediction. → Reliability estimates support the establishment of adequate maintenance strategies.

Application of support vector regression for optimization of vibration flow field of high-density polyethylene melts characterized by small angle light scattering

Science.gov (United States)

Xian, Guangming

2018-03-01

In this paper, the vibration flow field parameters of polymer melts in a visual slit die are optimized by using intelligent algorithm. Experimental small angle light scattering (SALS) patterns are shown to characterize the processing process. In order to capture the scattered light, a polarizer and an analyzer are placed before and after the polymer melts. The results reported in this study are obtained using high-density polyethylene (HDPE) with rotation speed at 28 rpm. In addition, support vector regression (SVR) analytical method is introduced for optimization the parameters of vibration flow field. This work establishes the general applicability of SVR for predicting the optimal parameters of vibration flow field.

Machine learning of swimming data via wisdom of crowd and regression analysis.

Science.gov (United States)

Xie, Jiang; Xu, Junfu; Nie, Celine; Nie, Qing

2017-04-01

Every performance, in an officially sanctioned meet, by a registered USA swimmer is recorded into an online database with times dating back to 1980. For the first time, statistical analysis and machine learning methods are systematically applied to 4,022,631 swim records. In this study, we investigate performance features for all strokes as a function of age and gender. The variances in performance of males and females for different ages and strokes were studied, and the correlations of performances for different ages were estimated using the Pearson correlation. Regression analysis show the performance trends for both males and females at different ages and suggest critical ages for peak training. Moreover, we assess twelve popular machine learning methods to predict or classify swimmer performance. Each method exhibited different strengths or weaknesses in different cases, indicating no one method could predict well for all strokes. To address this problem, we propose a new method by combining multiple inference methods to derive Wisdom of Crowd Classifier (WoCC). Our simulation experiments demonstrate that the WoCC is a consistent method with better overall prediction accuracy. Our study reveals several new age-dependent trends in swimming and provides an accurate method for classifying and predicting swimming times.

Noise reduction by support vector regression with a Ricker wavelet kernel

International Nuclear Information System (INIS)

Deng, Xiaoying; Yang, Dinghui; Xie, Jing

2009-01-01

We propose a noise filtering technology based on the least-squares support vector regression (LS-SVR), to improve the signal-to-noise ratio (SNR) of seismic data. We modified it by using an admissible support vector (SV) kernel, namely the Ricker wavelet kernel, to replace the conventional radial basis function (RBF) kernel in seismic data processing. We investigated the selection of the regularization parameter for the LS-SVR and derived a concise selecting formula directly from the noisy data. We used the proposed method for choosing the regularization parameter which not only had the advantage of high speed but could also obtain almost the same effectiveness as an optimal parameter method. We conducted experiments using synthetic data corrupted by the random noise of different types and levels, and found that our method was superior to the wavelet transform-based approach and the Wiener filtering. We also applied the method to two field seismic data sets and concluded that it was able to effectively suppress the random noise and improve the data quality in terms of SNR

Noise reduction by support vector regression with a Ricker wavelet kernel

Science.gov (United States)

Deng, Xiaoying; Yang, Dinghui; Xie, Jing

2009-06-01

We propose a noise filtering technology based on the least-squares support vector regression (LS-SVR), to improve the signal-to-noise ratio (SNR) of seismic data. We modified it by using an admissible support vector (SV) kernel, namely the Ricker wavelet kernel, to replace the conventional radial basis function (RBF) kernel in seismic data processing. We investigated the selection of the regularization parameter for the LS-SVR and derived a concise selecting formula directly from the noisy data. We used the proposed method for choosing the regularization parameter which not only had the advantage of high speed but could also obtain almost the same effectiveness as an optimal parameter method. We conducted experiments using synthetic data corrupted by the random noise of different types and levels, and found that our method was superior to the wavelet transform-based approach and the Wiener filtering. We also applied the method to two field seismic data sets and concluded that it was able to effectively suppress the random noise and improve the data quality in terms of SNR.

A Machine-Learning and Filtering Based Data Assimilation Framework for Geologic Carbon Sequestration Monitoring Optimization

Science.gov (United States)

Chen, B.; Harp, D. R.; Lin, Y.; Keating, E. H.; Pawar, R.

2017-12-01

Monitoring is a crucial aspect of geologic carbon sequestration (GCS) risk management. It has gained importance as a means to ensure CO2 is safely and permanently stored underground throughout the lifecycle of a GCS project. Three issues are often involved in a monitoring project: (i) where is the optimal location to place the monitoring well(s), (ii) what type of data (pressure, rate and/or CO2 concentration) should be measured, and (iii) What is the optimal frequency to collect the data. In order to address these important issues, a filtering-based data assimilation procedure is developed to perform the monitoring optimization. The optimal monitoring strategy is selected based on the uncertainty reduction of the objective of interest (e.g., cumulative CO2 leak) for all potential monitoring strategies. To reduce the computational cost of the filtering-based data assimilation process, two machine-learning algorithms: Support Vector Regression (SVR) and Multivariate Adaptive Regression Splines (MARS) are used to develop the computationally efficient reduced-order-models (ROMs) from full numerical simulations of CO2 and brine flow. The proposed framework for GCS monitoring optimization is demonstrated with two examples: a simple 3D synthetic case and a real field case named Rock Spring Uplift carbon storage site in Southwestern Wyoming.

A Hybrid Seasonal Mechanism with a Chaotic Cuckoo Search Algorithm with a Support Vector Regression Model for Electric Load Forecasting

Directory of Open Access Journals (Sweden)

Yongquan Dong

2018-04-01

Full Text Available Providing accurate electric load forecasting results plays a crucial role in daily energy management of the power supply system. Due to superior forecasting performance, the hybridizing support vector regression (SVR model with evolutionary algorithms has received attention and deserves to continue being explored widely. The cuckoo search (CS algorithm has the potential to contribute more satisfactory electric load forecasting results. However, the original CS algorithm suffers from its inherent drawbacks, such as parameters that require accurate setting, loss of population diversity, and easy trapping in local optima (i.e., premature convergence. Therefore, proposing some critical improvement mechanisms and employing an improved CS algorithm to determine suitable parameter combinations for an SVR model is essential. This paper proposes the SVR with chaotic cuckoo search (SVRCCS model based on using a tent chaotic mapping function to enrich the cuckoo search space and diversify the population to avoid trapping in local optima. In addition, to deal with the cyclic nature of electric loads, a seasonal mechanism is combined with the SVRCCS model, namely giving a seasonal SVR with chaotic cuckoo search (SSVRCCS model, to produce more accurate forecasting performances. The numerical results, tested by using the datasets from the National Electricity Market (NEM, Queensland, Australia and the New York Independent System Operator (NYISO, NY, USA, show that the proposed SSVRCCS model outperforms other alternative models.

Prediction of Agriculture Drought Using Support Vector Regression Incorporating with Climatology Indices

Science.gov (United States)

Tian, Y.; Xu, Y. P.

2017-12-01

In this paper, the Support Vector Regression (SVR) model incorporating climate indices and drought indices are developed to predict agriculture drought in Xiangjiang River basin, Central China. The agriculture droughts are presented with the Precipitation-Evapotranspiration Index (SPEI). According to the analysis of the relationship between SPEI with different time scales and soil moisture, it is found that SPEI of six months time scales (SPEI-6) could reflect the soil moisture better than that of three and one month time scale from the drought features including drought duration, severity and peak. Climate forcing like El Niño Southern Oscillation and western Pacific subtropical high (WPSH) are represented by climate indices such as MEI and series indices of WPSH. Ridge Point of WPSH is found to be the key factor that influences the agriculture drought mainly through the control of temperature. Based on the climate indices analysis, the predictions of SPEI-6 are conducted using the SVR model. The results show that the SVR model incorperating climate indices, especially ridge point of WPSH, could improve the prediction accuracy compared to that using drought index only. The improvement was more significant for the prediction of one month lead time than that of three months lead time. However, it needs to be cautious in selection of the input parameters, since adding more useless information could have a counter effect in attaining a better prediction.

Novel qsar combination forecast model for insect repellent coupling support vector regression and k-nearest-neighbor

International Nuclear Information System (INIS)

Wang, L.F.; Bai, L.Y.

2013-01-01

To improve the precision of quantitative structure-activity relationship (QSAR) modeling for aromatic carboxylic acid derivatives insect repellent, a novel nonlinear combination forecast model was proposed integrating support vector regression (SVR) and K-nearest neighbor (KNN): Firstly, search optimal kernel function and nonlinearly select molecular descriptors by the rule of minimum MSE value using SVR. Secondly, illuminate the effects of all descriptors on biological activity by multi-round enforcement resistance-selection. Thirdly, construct the sub-models with predicted values of different KNN. Then, get the optimal kernel and corresponding retained sub-models through subtle selection. Finally, make prediction with leave-one-out (LOO) method in the basis of reserved sub-models. Compared with previous widely used models, our work shows significant improvement in modeling performance, which demonstrates the superiority of the present combination forecast model. (author)

A Novel Hybrid Model Based on Extreme Learning Machine, k-Nearest Neighbor Regression and Wavelet Denoising Applied to Short-Term Electric Load Forecasting

Directory of Open Access Journals (Sweden)

Weide Li

2017-05-01

Full Text Available Electric load forecasting plays an important role in electricity markets and power systems. Because electric load time series are complicated and nonlinear, it is very difficult to achieve a satisfactory forecasting accuracy. In this paper, a hybrid model, Wavelet Denoising-Extreme Learning Machine optimized by k-Nearest Neighbor Regression (EWKM, which combines k-Nearest Neighbor (KNN and Extreme Learning Machine (ELM based on a wavelet denoising technique is proposed for short-term load forecasting. The proposed hybrid model decomposes the time series into a low frequency-associated main signal and some detailed signals associated with high frequencies at first, then uses KNN to determine the independent and dependent variables from the low-frequency signal. Finally, the ELM is used to get the non-linear relationship between these variables to get the final prediction result for the electric load. Compared with three other models, Extreme Learning Machine optimized by k-Nearest Neighbor Regression (EKM, Wavelet Denoising-Extreme Learning Machine (WKM and Wavelet Denoising-Back Propagation Neural Network optimized by k-Nearest Neighbor Regression (WNNM, the model proposed in this paper can improve the accuracy efficiently. New South Wales is the economic powerhouse of Australia, so we use the proposed model to predict electric demand for that region. The accurate prediction has a significant meaning.

Development of Easily Accessible Electricity Consumption Model Using Open Data and GA-SVR

Directory of Open Access Journals (Sweden)

Seunghyeon Wang

2018-02-01

Full Text Available In many countries, DR (Demand Response has been developed for which customers are motivated to save electricity by themselves during peak time to prevent grand-scale blackouts. One of the common methods in DR, is CPP (Critical Peak Pricing. Predicting energy consumption is recognized as one of the tool for dealing with CPP. There are a variety of studies in developing the model of energy consumption, which is based on energy simulation, data-driven model or metamodelling. However, it is difficult for general users to use these models due to requirement of various sensing data and expertise. And it also takes long time to simulate the models. These limitations can be an obstacle for achieving CPP’s purpose that encourages general users to manage their energy usage by themselves. As an alternative, this research suggests to use open data and GA (Genetic Algorithm–SVR (Support Vector Regression. The model is applied to a hospital in Korea and 34,636 data sets (1 year are collected while 31,756 (11 months sets are used for training and 2880 sets (1 month are used for validation. As a result, the performance of proposed model is 14.17% in CV (RMSE, which satisfies the Korea Energy Agency’s and ASHRAE (American Society of Heating, Refrigerating and Air-Conditioning Engineers error allowance range of ±30%, and ±20% respectively.

A fuzzy regression with support vector machine approach to the estimation of horizontal global solar radiation

International Nuclear Information System (INIS)

Baser, Furkan; Demirhan, Haydar

2017-01-01

Accurate estimation of the amount of horizontal global solar radiation for a particular field is an important input for decision processes in solar radiation investments. In this article, we focus on the estimation of yearly mean daily horizontal global solar radiation by using an approach that utilizes fuzzy regression functions with support vector machine (FRF-SVM). This approach is not seriously affected by outlier observations and does not suffer from the over-fitting problem. To demonstrate the utility of the FRF-SVM approach in the estimation of horizontal global solar radiation, we conduct an empirical study over a dataset collected in Turkey and applied the FRF-SVM approach with several kernel functions. Then, we compare the estimation accuracy of the FRF-SVM approach to an adaptive neuro-fuzzy system and a coplot supported-genetic programming approach. We observe that the FRF-SVM approach with a Gaussian kernel function is not affected by both outliers and over-fitting problem and gives the most accurate estimates of horizontal global solar radiation among the applied approaches. Consequently, the use of hybrid fuzzy functions and support vector machine approaches is found beneficial in long-term forecasting of horizontal global solar radiation over a region with complex climatic and terrestrial characteristics. - Highlights: • A fuzzy regression functions with support vector machines approach is proposed. • The approach is robust against outlier observations and over-fitting problem. • Estimation accuracy of the model is superior to several existent alternatives. • A new solar radiation estimation model is proposed for the region of Turkey. • The model is useful under complex terrestrial and climatic conditions.

Predictive validity of the SVR-20 and Static-99 in a Dutch sample of treated sex offenders

NARCIS (Netherlands)

de Vogel, V.; de Ruiter, C.; van Beek, D.; Mead, G.

2004-01-01

In this retrospective study, the interrater reliability and redictive validity of 2 risk assessment instruments for sexual violence are presented. The SVR-20, an instrument for structured professional judgment, and the Static-99, an actuarial risk assessment instrument, were coded from file

The application of artificial neural networks and support vector regression for simultaneous spectrophotometric determination of commercial eye drop contents

Science.gov (United States)

Valizadeh, Maryam; Sohrabi, Mahmoud Reza

2018-03-01

In the present study, artificial neural networks (ANNs) and support vector regression (SVR) as intelligent methods coupled with UV spectroscopy for simultaneous quantitative determination of Dorzolamide (DOR) and Timolol (TIM) in eye drop. Several synthetic mixtures were analyzed for validating the proposed methods. At first, neural network time series, which one type of network from the artificial neural network was employed and its efficiency was evaluated. Afterwards, the radial basis network was applied as another neural network. Results showed that the performance of this method is suitable for predicting. Finally, support vector regression was proposed to construct the Zilomole prediction model. Also, root mean square error (RMSE) and mean recovery (%) were calculated for SVR method. Moreover, the proposed methods were compared to the high-performance liquid chromatography (HPLC) as a reference method. One way analysis of variance (ANOVA) test at the 95% confidence level applied to the comparison results of suggested and reference methods that there were no significant differences between them. Also, the effect of interferences was investigated in spike solutions.

Modeling and Predicting the Electrical Conductivity of Composite Cathode for Solid Oxide Fuel Cell by Using Support Vector Regression

Science.gov (United States)

Tang, J. L.; Cai, C. Z.; Xiao, T. T.; Huang, S. J.

2012-07-01

The electrical conductivity of solid oxide fuel cell (SOFC) cathode is one of the most important indices affecting the efficiency of SOFC. In order to improve the performance of fuel cell system, it is advantageous to have accurate model with which one can predict the electrical conductivity. In this paper, a model utilizing support vector regression (SVR) approach combined with particle swarm optimization (PSO) algorithm for its parameter optimization was established to modeling and predicting the electrical conductivity of Ba0.5Sr0.5Co0.8Fe0.2 O3-δ-xSm0.5Sr0.5CoO3-δ (BSCF-xSSC) composite cathode under two influence factors, including operating temperature (T) and SSC content (x) in BSCF-xSSC composite cathode. The leave-one-out cross validation (LOOCV) test result by SVR strongly supports that the generalization ability of SVR model is high enough. The absolute percentage error (APE) of 27 samples does not exceed 0.05%. The mean absolute percentage error (MAPE) of all 30 samples is only 0.09% and the correlation coefficient (R2) as high as 0.999. This investigation suggests that the hybrid PSO-SVR approach may be not only a promising and practical methodology to simulate the properties of fuel cell system, but also a powerful tool to be used for optimal designing or controlling the operating process of a SOFC system.

QSAR models for prediction study of HIV protease inhibitors using support vector machines, neural networks and multiple linear regression

Directory of Open Access Journals (Sweden)

Rachid Darnag

2017-02-01

Full Text Available Support vector machines (SVM represent one of the most promising Machine Learning (ML tools that can be applied to develop a predictive quantitative structure–activity relationship (QSAR models using molecular descriptors. Multiple linear regression (MLR and artificial neural networks (ANNs were also utilized to construct quantitative linear and non linear models to compare with the results obtained by SVM. The prediction results are in good agreement with the experimental value of HIV activity; also, the results reveal the superiority of the SVM over MLR and ANN model. The contribution of each descriptor to the structure–activity relationships was evaluated.

SNOW DEPTH ESTIMATION USING TIME SERIES PASSIVE MICROWAVE IMAGERY VIA GENETICALLY SUPPORT VECTOR REGRESSION (CASE STUDY URMIA LAKE BASIN

Directory of Open Access Journals (Sweden)

N. Zahir

2015-12-01

Full Text Available Lake Urmia is one of the most important ecosystems of the country which is on the verge of elimination. Many factors contribute to this crisis among them is the precipitation, paly important roll. Precipitation has many forms one of them is in the form of snow. The snow on Sahand Mountain is one of the main and important sources of the Lake Urmia’s water. Snow Depth (SD is vital parameters for estimating water balance for future year. In this regards, this study is focused on SD parameter using Special Sensor Microwave/Imager (SSM/I instruments on board the Defence Meteorological Satellite Program (DMSP F16. The usual statistical methods for retrieving SD include linear and non-linear ones. These methods used least square procedure to estimate SD model. Recently, kernel base methods widely used for modelling statistical problem. From these methods, the support vector regression (SVR is achieved the high performance for modelling the statistical problem. Examination of the obtained data shows the existence of outlier in them. For omitting these outliers, wavelet denoising method is applied. After the omission of the outliers it is needed to select the optimum bands and parameters for SVR. To overcome these issues, feature selection methods have shown a direct effect on improving the regression performance. We used genetic algorithm (GA for selecting suitable features of the SSMI bands in order to estimate SD model. The results for the training and testing data in Sahand mountain is [R²_TEST=0.9049 and RMSE= 6.9654] that show the high SVR performance.

Fruit fly optimization based least square support vector regression for blind image restoration

Science.gov (United States)

Zhang, Jiao; Wang, Rui; Li, Junshan; Yang, Yawei

2014-11-01

The goal of image restoration is to reconstruct the original scene from a degraded observation. It is a critical and challenging task in image processing. Classical restorations require explicit knowledge of the point spread function and a description of the noise as priors. However, it is not practical for many real image processing. The recovery processing needs to be a blind image restoration scenario. Since blind deconvolution is an ill-posed problem, many blind restoration methods need to make additional assumptions to construct restrictions. Due to the differences of PSF and noise energy, blurring images can be quite different. It is difficult to achieve a good balance between proper assumption and high restoration quality in blind deconvolution. Recently, machine learning techniques have been applied to blind image restoration. The least square support vector regression (LSSVR) has been proven to offer strong potential in estimating and forecasting issues. Therefore, this paper proposes a LSSVR-based image restoration method. However, selecting the optimal parameters for support vector machine is essential to the training result. As a novel meta-heuristic algorithm, the fruit fly optimization algorithm (FOA) can be used to handle optimization problems, and has the advantages of fast convergence to the global optimal solution. In the proposed method, the training samples are created from a neighborhood in the degraded image to the central pixel in the original image. The mapping between the degraded image and the original image is learned by training LSSVR. The two parameters of LSSVR are optimized though FOA. The fitness function of FOA is calculated by the restoration error function. With the acquired mapping, the degraded image can be recovered. Experimental results show the proposed method can obtain satisfactory restoration effect. Compared with BP neural network regression, SVR method and Lucy-Richardson algorithm, it speeds up the restoration rate and

A planning quality evaluation tool for prostate adaptive IMRT based on machine learning

International Nuclear Information System (INIS)

Zhu Xiaofeng; Ge Yaorong; Li Taoran; Thongphiew, Danthai; Yin Fangfang; Wu, Q Jackie

2011-01-01

Purpose: To ensure plan quality for adaptive IMRT of the prostate, we developed a quantitative evaluation tool using a machine learning approach. This tool generates dose volume histograms (DVHs) of organs-at-risk (OARs) based on prior plans as a reference, to be compared with the adaptive plan derived from fluence map deformation. Methods: Under the same configuration using seven-field 15 MV photon beams, DVHs of OARs (bladder and rectum) were estimated based on anatomical information of the patient and a model learned from a database of high quality prior plans. In this study, the anatomical information was characterized by the organ volumes and distance-to-target histogram (DTH). The database consists of 198 high quality prostate plans and was validated with 14 cases outside the training pool. Principal component analysis (PCA) was applied to DVHs and DTHs to quantify their salient features. Then, support vector regression (SVR) was implemented to establish the correlation between the features of the DVH and the anatomical information. Results: DVH/DTH curves could be characterized sufficiently just using only two or three truncated principal components, thus, patient anatomical information was quantified with reduced numbers of variables. The evaluation of the model using the test data set demonstrated its accuracy ∼80% in prediction and effectiveness in improving ART planning quality. Conclusions: An adaptive IMRT plan quality evaluation tool based on machine learning has been developed, which estimates OAR sparing and provides reference in evaluating ART.

Interferon-free treatment for patients with chronic hepatitis C and autoimmune liver disease: higher SVR rates with special precautions for deterioration of autoimmune hepatitis.

Science.gov (United States)

Kanda, Tatsuo; Yasui, Shin; Nakamura, Masato; Nakamoto, Shingo; Takahashi, Koji; Wu, Shuang; Sasaki, Reina; Haga, Yuki; Ogasawara, Sadahisa; Saito, Tomoko; Kobayashi, Kazufumi; Kiyono, Soichiro; Ooka, Yoshihiko; Suzuki, Eiichiro; Chiba, Tetsuhiro; Maruyama, Hitoshi; Imazeki, Fumio; Moriyama, Mitsuhiko; Kato, Naoya

2018-02-20

Interferon-free treatment can achieve higher sustained virological response (SVR) rates, even in patients in whom hepatitis C virus (HCV) could not be eradicated in the interferon treatment era. Immune restoration in the liver is occasionally associated with HCV infection. We examined the safety and effects of interferon-free regimens on HCV patients with autoimmune liver diseases. All 7 HCV patients with autoimmune hepatitis (AIH) completed treatment and achieved SVR. Three patients took prednisolone (PSL) at baseline, and 3 did not take PSL during interferon-free treatment. In one HCV patient with AIH and cirrhosis, PSL were not administered at baseline, but she needed to take 40 mg/day PSL at week 8 for liver dysfunction. She also complained back pain and was diagnosed with vasospastic angina by coronary angiography at week 11. However, she completed interferon-free treatment. All 5 HCV patients with primary biliary cholangitis (PBC) completed treatment and achieved SVR. Three of these HCV patients with PBC were treated with UDCA during interferon-free treatment. Interferon-free regimens could result in higher SVR rates in HCV patients with autoimmune liver diseases. As interferon-free treatment for HCV may have an effect on hepatic immunity and activity of the autoimmune liver diseases, careful attention should be paid to unexpected adverse events in their treatments. Total 12 patients with HCV and autoimmune liver diseases [7 AIH and PBC], who were treated with interferon-free regimens, were retrospectively analyzed.

Regression model of support vector machines for least squares prediction of crystallinity of cracking catalysts by infrared spectroscopy

International Nuclear Information System (INIS)

Comesanna Garcia, Yumirka; Dago Morales, Angel; Talavera Bustamante, Isneri

2010-01-01

The recently introduction of the least squares support vector machines method for regression purposes in the field of Chemometrics has provided several advantages to linear and nonlinear multivariate calibration methods. The objective of the paper was to propose the use of the least squares support vector machine as an alternative multivariate calibration method for the prediction of the percentage of crystallinity of fluidized catalytic cracking catalysts, by means of Fourier transform mid-infrared spectroscopy. A linear kernel was used in the calculations of the regression model. The optimization of its gamma parameter was carried out using the leave-one-out cross-validation procedure. The root mean square error of prediction was used to measure the performance of the model. The accuracy of the results obtained with the application of the method is in accordance with the uncertainty of the X-ray powder diffraction reference method. To compare the generalization capability of the developed method, a comparison study was carried out, taking into account the results achieved with the new model and those reached through the application of linear calibration methods. The developed method can be easily implemented in refinery laboratories

Novel Automatic Filter-Class Feature Selection for Machine Learning Regression

DEFF Research Database (Denmark)

Wollsen, Morten Gill; Hallam, John; Jørgensen, Bo Nørregaard

2017-01-01

With the increased focus on application of Big Data in all sectors of society, the performance of machine learning becomes essential. Efficient machine learning depends on efficient feature selection algorithms. Filter feature selection algorithms are model-free and therefore very fast, but require...... model in the feature selection process. PCA is often used in machine learning litterature and can be considered the default feature selection method. RDESF outperformed PCA in both experiments in both prediction error and computational speed. RDESF is a new step into filter-based automatic feature...

Laser-induced Breakdown spectroscopy quantitative analysis method via adaptive analytical line selection and relevance vector machine regression model

International Nuclear Information System (INIS)

Yang, Jianhong; Yi, Cancan; Xu, Jinwu; Ma, Xianghong

2015-01-01

A new LIBS quantitative analysis method based on analytical line adaptive selection and Relevance Vector Machine (RVM) regression model is proposed. First, a scheme of adaptively selecting analytical line is put forward in order to overcome the drawback of high dependency on a priori knowledge. The candidate analytical lines are automatically selected based on the built-in characteristics of spectral lines, such as spectral intensity, wavelength and width at half height. The analytical lines which will be used as input variables of regression model are determined adaptively according to the samples for both training and testing. Second, an LIBS quantitative analysis method based on RVM is presented. The intensities of analytical lines and the elemental concentrations of certified standard samples are used to train the RVM regression model. The predicted elemental concentration analysis results will be given with a form of confidence interval of probabilistic distribution, which is helpful for evaluating the uncertainness contained in the measured spectra. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples have been carried out. The multiple correlation coefficient of the prediction was up to 98.85%, and the average relative error of the prediction was 4.01%. The experiment results showed that the proposed LIBS quantitative analysis method achieved better prediction accuracy and better modeling robustness compared with the methods based on partial least squares regression, artificial neural network and standard support vector machine. - Highlights: • Both training and testing samples are considered for analytical lines selection. • The analytical lines are auto-selected based on the built-in characteristics of spectral lines. • The new method can achieve better prediction accuracy and modeling robustness. • Model predictions are given with confidence interval of probabilistic distribution

A hybrid sales forecasting scheme by combining independent component analysis with K-means clustering and support vector regression.

Science.gov (United States)

Lu, Chi-Jie; Chang, Chi-Chang

2014-01-01

Sales forecasting plays an important role in operating a business since it can be used to determine the required inventory level to meet consumer demand and avoid the problem of under/overstocking. Improving the accuracy of sales forecasting has become an important issue of operating a business. This study proposes a hybrid sales forecasting scheme by combining independent component analysis (ICA) with K-means clustering and support vector regression (SVR). The proposed scheme first uses the ICA to extract hidden information from the observed sales data. The extracted features are then applied to K-means algorithm for clustering the sales data into several disjoined clusters. Finally, the SVR forecasting models are applied to each group to generate final forecasting results. Experimental results from information technology (IT) product agent sales data reveal that the proposed sales forecasting scheme outperforms the three comparison models and hence provides an efficient alternative for sales forecasting.

Lagged kernel machine regression for identifying time windows of susceptibility to exposures of complex mixtures.

Science.gov (United States)

Liu, Shelley H; Bobb, Jennifer F; Lee, Kyu Ha; Gennings, Chris; Claus Henn, Birgit; Bellinger, David; Austin, Christine; Schnaas, Lourdes; Tellez-Rojo, Martha M; Hu, Howard; Wright, Robert O; Arora, Manish; Coull, Brent A

2018-07-01

The impact of neurotoxic chemical mixtures on children's health is a critical public health concern. It is well known that during early life, toxic exposures may impact cognitive function during critical time intervals of increased vulnerability, known as windows of susceptibility. Knowledge on time windows of susceptibility can help inform treatment and prevention strategies, as chemical mixtures may affect a developmental process that is operating at a specific life phase. There are several statistical challenges in estimating the health effects of time-varying exposures to multi-pollutant mixtures, such as: multi-collinearity among the exposures both within time points and across time points, and complex exposure-response relationships. To address these concerns, we develop a flexible statistical method, called lagged kernel machine regression (LKMR). LKMR identifies critical exposure windows of chemical mixtures, and accounts for complex non-linear and non-additive effects of the mixture at any given exposure window. Specifically, LKMR estimates how the effects of a mixture of exposures change with the exposure time window using a Bayesian formulation of a grouped, fused lasso penalty within a kernel machine regression (KMR) framework. A simulation study demonstrates the performance of LKMR under realistic exposure-response scenarios, and demonstrates large gains over approaches that consider each time window separately, particularly when serial correlation among the time-varying exposures is high. Furthermore, LKMR demonstrates gains over another approach that inputs all time-specific chemical concentrations together into a single KMR. We apply LKMR to estimate associations between neurodevelopment and metal mixtures in Early Life Exposures in Mexico and Neurotoxicology, a prospective cohort study of child health in Mexico City.

Soft-sensing model of temperature for aluminum reduction cell on improved twin support vector regression

Science.gov (United States)

Li, Tao

2018-06-01

The complexity of aluminum electrolysis process leads the temperature for aluminum reduction cells hard to measure directly. However, temperature is the control center of aluminum production. To solve this problem, combining some aluminum plant's practice data, this paper presents a Soft-sensing model of temperature for aluminum electrolysis process on Improved Twin Support Vector Regression (ITSVR). ITSVR eliminates the slow learning speed of Support Vector Regression (SVR) and the over-fit risk of Twin Support Vector Regression (TSVR) by introducing a regularization term into the objective function of TSVR, which ensures the structural risk minimization principle and lower computational complexity. Finally, the model with some other parameters as auxiliary variable, predicts the temperature by ITSVR. The simulation result shows Soft-sensing model based on ITSVR has short time-consuming and better generalization.

A Gaussian mixture copula model based localized Gaussian process regression approach for long-term wind speed prediction

International Nuclear Information System (INIS)

Yu, Jie; Chen, Kuilin; Mori, Junichi; Rashid, Mudassir M.

2013-01-01

Optimizing wind power generation and controlling the operation of wind turbines to efficiently harness the renewable wind energy is a challenging task due to the intermittency and unpredictable nature of wind speed, which has significant influence on wind power production. A new approach for long-term wind speed forecasting is developed in this study by integrating GMCM (Gaussian mixture copula model) and localized GPR (Gaussian process regression). The time series of wind speed is first classified into multiple non-Gaussian components through the Gaussian mixture copula model and then Bayesian inference strategy is employed to incorporate the various non-Gaussian components using the posterior probabilities. Further, the localized Gaussian process regression models corresponding to different non-Gaussian components are built to characterize the stochastic uncertainty and non-stationary seasonality of the wind speed data. The various localized GPR models are integrated through the posterior probabilities as the weightings so that a global predictive model is developed for the prediction of wind speed. The proposed GMCM–GPR approach is demonstrated using wind speed data from various wind farm locations and compared against the GMCM-based ARIMA (auto-regressive integrated moving average) and SVR (support vector regression) methods. In contrast to GMCM–ARIMA and GMCM–SVR methods, the proposed GMCM–GPR model is able to well characterize the multi-seasonality and uncertainty of wind speed series for accurate long-term prediction. - Highlights: • A novel predictive modeling method is proposed for long-term wind speed forecasting. • Gaussian mixture copula model is estimated to characterize the multi-seasonality. • Localized Gaussian process regression models can deal with the random uncertainty. • Multiple GPR models are integrated through Bayesian inference strategy. • The proposed approach shows higher prediction accuracy and reliability

Estimation of residual stress in welding of dissimilar metals at nuclear power plants using cascaded support vetor regression

Energy Technology Data Exchange (ETDEWEB)

Koo, Young Do; Yoo, Kwae Hwan; Na, Man Gyun [Dept. of Nuclear Engineering, Chosun University, Gwangju (Korea, Republic of)

2017-06-15

Residual stress is a critical element in determining the integrity of parts and the lifetime of welded structures. It is necessary to estimate the residual stress of a welding zone because residual stress is a major reason for the generation of primary water stress corrosion cracking in nuclear power plants. That is, it is necessary to estimate the distribution of the residual stress in welding of dissimilar metals under manifold welding conditions. In this study, a cascaded support vector regression (CSVR) model was presented to estimate the residual stress of a welding zone. The CSVR model was serially and consecutively structured in terms of SVR modules. Using numerical data obtained from finite element analysis by a subtractive clustering method, learning data that explained the characteristic behavior of the residual stress of a welding zone were selected to optimize the proposed model. The results suggest that the CSVR model yielded a better estimation performance when compared with a classic SVR model.

Prediction of Five Softwood Paper Properties from its Density using Support Vector Machine Regression Techniques

Directory of Open Access Journals (Sweden)

Esperanza García-Gonzalo

2016-01-01

Full Text Available Predicting paper properties based on a limited number of measured variables can be an important tool for the industry. Mathematical models were developed to predict mechanical and optical properties from the corresponding paper density for some softwood papers using support vector machine regression with the Radial Basis Function Kernel. A dataset of different properties of paper handsheets produced from pulps of pine (Pinus pinaster and P. sylvestris and cypress species (Cupressus lusitanica, C. sempervirens, and C. arizonica beaten at 1000, 4000, and 7000 revolutions was used. The results show that it is possible to obtain good models (with high coefficient of determination with two variables: the numerical variable density and the categorical variable species.

New machine learning tools for predictive vegetation mapping after climate change: Bagging and Random Forest perform better than Regression Tree Analysis

Science.gov (United States)

L.R. Iverson; A.M. Prasad; A. Liaw

2004-01-01

More and better machine learning tools are becoming available for landscape ecologists to aid in understanding species-environment relationships and to map probable species occurrence now and potentially into the future. To thal end, we evaluated three statistical models: Regression Tree Analybib (RTA), Bagging Trees (BT) and Random Forest (RF) for their utility in...

Spatial prediction of landslides using a hybrid machine learning approach based on Random Subspace and Classification and Regression Trees

Science.gov (United States)

Pham, Binh Thai; Prakash, Indra; Tien Bui, Dieu

2018-02-01

A hybrid machine learning approach of Random Subspace (RSS) and Classification And Regression Trees (CART) is proposed to develop a model named RSSCART for spatial prediction of landslides. This model is a combination of the RSS method which is known as an efficient ensemble technique and the CART which is a state of the art classifier. The Luc Yen district of Yen Bai province, a prominent landslide prone area of Viet Nam, was selected for the model development. Performance of the RSSCART model was evaluated through the Receiver Operating Characteristic (ROC) curve, statistical analysis methods, and the Chi Square test. Results were compared with other benchmark landslide models namely Support Vector Machines (SVM), single CART, Naïve Bayes Trees (NBT), and Logistic Regression (LR). In the development of model, ten important landslide affecting factors related with geomorphology, geology and geo-environment were considered namely slope angles, elevation, slope aspect, curvature, lithology, distance to faults, distance to rivers, distance to roads, and rainfall. Performance of the RSSCART model (AUC = 0.841) is the best compared with other popular landslide models namely SVM (0.835), single CART (0.822), NBT (0.821), and LR (0.723). These results indicate that performance of the RSSCART is a promising method for spatial landslide prediction.

Linear support vector regression and partial least squares chemometric models for determination of Hydrochlorothiazide and Benazepril hydrochloride in presence of related impurities: A comparative study

Science.gov (United States)

Naguib, Ibrahim A.; Abdelaleem, Eglal A.; Draz, Mohammed E.; Zaazaa, Hala E.

2014-09-01

Partial least squares regression (PLSR) and support vector regression (SVR) are two popular chemometric models that are being subjected to a comparative study in the presented work. The comparison shows their characteristics via applying them to analyze Hydrochlorothiazide (HCZ) and Benazepril hydrochloride (BZ) in presence of HCZ impurities; Chlorothiazide (CT) and Salamide (DSA) as a case study. The analysis results prove to be valid for analysis of the two active ingredients in raw materials and pharmaceutical dosage form through handling UV spectral data in range (220-350 nm). For proper analysis a 4 factor 4 level experimental design was established resulting in a training set consisting of 16 mixtures containing different ratios of interfering species. An independent test set consisting of 8 mixtures was used to validate the prediction ability of the suggested models. The results presented indicate the ability of mentioned multivariate calibration models to analyze HCZ and BZ in presence of HCZ impurities CT and DSA with high selectivity and accuracy of mean percentage recoveries of (101.01 ± 0.80) and (100.01 ± 0.87) for HCZ and BZ respectively using PLSR model and of (99.78 ± 0.80) and (99.85 ± 1.08) for HCZ and BZ respectively using SVR model. The analysis results of the dosage form were statistically compared to the reference HPLC method with no significant differences regarding accuracy and precision. SVR model gives more accurate results compared to PLSR model and show high generalization ability, however, PLSR still keeps the advantage of being fast to optimize and implement.

Modeling and prediction of flotation performance using support vector regression

Directory of Open Access Journals (Sweden)

Despotović Vladimir

2017-01-01

Full Text Available Continuous efforts have been made in recent year to improve the process of paper recycling, as it is of critical importance for saving the wood, water and energy resources. Flotation deinking is considered to be one of the key methods for separation of ink particles from the cellulose fibres. Attempts to model the flotation deinking process have often resulted in complex models that are difficult to implement and use. In this paper a model for prediction of flotation performance based on Support Vector Regression (SVR, is presented. Representative data samples were created in laboratory, under a variety of practical control variables for the flotation deinking process, including different reagents, pH values and flotation residence time. Predictive model was created that was trained on these data samples, and the flotation performance was assessed showing that Support Vector Regression is a promising method even when dataset used for training the model is limited.

Applying machine learning methods for characterization of hexagonal prisms from their 2D scattering patterns - an investigation using modelled scattering data

Science.gov (United States)

Salawu, Emmanuel Oluwatobi; Hesse, Evelyn; Stopford, Chris; Davey, Neil; Sun, Yi

2017-11-01

Better understanding and characterization of cloud particles, whose properties and distributions affect climate and weather, are essential for the understanding of present climate and climate change. Since imaging cloud probes have limitations of optical resolution, especially for small particles (with diameter < 25 μm), instruments like the Small Ice Detector (SID) probes, which capture high-resolution spatial light scattering patterns from individual particles down to 1 μm in size, have been developed. In this work, we have proposed a method using Machine Learning techniques to estimate simulated particles' orientation-averaged projected sizes (PAD) and aspect ratio from their 2D scattering patterns. The two-dimensional light scattering patterns (2DLSP) of hexagonal prisms are computed using the Ray Tracing with Diffraction on Facets (RTDF) model. The 2DLSP cover the same angular range as the SID probes. We generated 2DLSP for 162 hexagonal prisms at 133 orientations for each. In a first step, the 2DLSP were transformed into rotation-invariant Zernike moments (ZMs), which are particularly suitable for analyses of pattern symmetry. Then we used ZMs, summed intensities, and root mean square contrast as inputs to the advanced Machine Learning methods. We created one random forests classifier for predicting prism orientation, 133 orientation-specific (OS) support vector classification models for predicting the prism aspect-ratios, 133 OS support vector regression models for estimating prism sizes, and another 133 OS Support Vector Regression (SVR) models for estimating the size PADs. We have achieved a high accuracy of 0.99 in predicting prism aspect ratios, and a low value of normalized mean square error of 0.004 for estimating the particle's size and size PADs.

Urban Heat Island Growth Modeling Using Artificial Neural Networks and Support Vector Regression: A case study of Tehran, Iran

Science.gov (United States)

Sherafati, Sh. A.; Saradjian, M. R.; Niazmardi, S.

2013-09-01

Numerous investigations on Urban Heat Island (UHI) show that land cover change is the main factor of increasing Land Surface Temperature (LST) in urban areas. Therefore, to achieve a model which is able to simulate UHI growth, urban expansion should be concerned first. Considerable researches on urban expansion modeling have been done based on cellular automata. Accordingly the objective of this paper is to implement CA method for trend detection of Tehran UHI spatiotemporal growth based on urban sprawl parameters (such as Distance to nearest road, Digital Elevation Model (DEM), Slope and Aspect ratios). It should be mentioned that UHI growth modeling may have more complexities in comparison with urban expansion, since the amount of each pixel's temperature should be investigated instead of its state (urban and non-urban areas). The most challenging part of CA model is the definition of Transfer Rules. Here, two methods have used to find appropriate transfer Rules which are Artificial Neural Networks (ANN) and Support Vector Regression (SVR). The reason of choosing these approaches is that artificial neural networks and support vector regression have significant abilities to handle the complications of such a spatial analysis in comparison with other methods like Genetic or Swarm intelligence. In this paper, UHI change trend has discussed between 1984 and 2007. For this purpose, urban sprawl parameters in 1984 have calculated and added to the retrieved LST of this year. In order to achieve LST, Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM+) night-time images have exploited. The reason of implementing night-time images is that UHI phenomenon is more obvious during night hours. After that multilayer feed-forward neural networks and support vector regression have used separately to find the relationship between this data and the retrieved LST in 2007. Since the transfer rules might not be the same in different regions, the satellite image of the city has

Detection of Buried Objects by Means of a SAP Technique: Comparing MUSIC- and SVR-Based Approaches

Science.gov (United States)

Meschino, S.; Pajewski, L.; Pastorino, M.; Randazzo, A.; Schettini, G.

2012-04-01

This work is focused on the application of a Sub-Array Processing (SAP) technique to the detection of metallic cylindrical objects embedded in a dielectric half-space. The identification of buried cables, pipes, conduits, and other cylindrical utilities, is an important problem that has been extensively studied in the last years. Most commonly used approaches are based on the use of electromagnetic sensing: a set of antennas illuminates the ground and the collected echo is analyzed in order to extract information about the scenario and to localize the sought objects [1]. In a SAP approach, algorithms for the estimation of Directions of Arrival (DOAs) are employed [2]: they assume that the sources (in this paper, currents induced on buried targets) are in the far-field region of the receiving array, so that the received wavefront can be considered as planar, and the main angular direction of the field can be estimated. However, in electromagnetic sensing of buried objects, the scatterers are usually quite near to the antennas. Nevertheless, by dividing the whole receiving array in a suitable number of sub-arrays, and by finding a dominant DOA for each one, it is possible to localize objects that are in the far-field of the sub-array, although being in the near-field of the array. The DOAs found by the sub-arrays can be triangulated, obtaining a set of crossings with intersections condensed around object locations. In this work, the performances of two different DOA algorithms are compared. In particular, a MUltiple SIgnal Classification (MUSIC)-type method [3] and Support Vector Regression (SVR) based approach [4] are employed. The results of a Cylindrical-Wave Approach forward solver are used as input data of the detection procedure [5]. To process the crossing pattern, the region of interest is divided in small windows, and a Poisson model is adopted for the statistical distribution of intersections in the windows. Hypothesis testing procedures are used (imposing

Short-term wind speed prediction using an unscented Kalman filter based state-space support vector regression approach

International Nuclear Information System (INIS)

Chen, Kuilin; Yu, Jie

2014-01-01

Highlights: • A novel hybrid modeling method is proposed for short-term wind speed forecasting. • Support vector regression model is constructed to formulate nonlinear state-space framework. • Unscented Kalman filter is adopted to recursively update states under random uncertainty. • The new SVR–UKF approach is compared to several conventional methods for short-term wind speed prediction. • The proposed method demonstrates higher prediction accuracy and reliability. - Abstract: Accurate wind speed forecasting is becoming increasingly important to improve and optimize renewable wind power generation. Particularly, reliable short-term wind speed prediction can enable model predictive control of wind turbines and real-time optimization of wind farm operation. However, this task remains challenging due to the strong stochastic nature and dynamic uncertainty of wind speed. In this study, unscented Kalman filter (UKF) is integrated with support vector regression (SVR) based state-space model in order to precisely update the short-term estimation of wind speed sequence. In the proposed SVR–UKF approach, support vector regression is first employed to formulate a nonlinear state-space model and then unscented Kalman filter is adopted to perform dynamic state estimation recursively on wind sequence with stochastic uncertainty. The novel SVR–UKF method is compared with artificial neural networks (ANNs), SVR, autoregressive (AR) and autoregressive integrated with Kalman filter (AR-Kalman) approaches for predicting short-term wind speed sequences collected from three sites in Massachusetts, USA. The forecasting results indicate that the proposed method has much better performance in both one-step-ahead and multi-step-ahead wind speed predictions than the other approaches across all the locations

Persistence of hepatocellular carcinoma risk in hepatitis C patients with a response to IFN and cirrhosis regression.

Science.gov (United States)

D'Ambrosio, Roberta; Aghemo, Alessio; Rumi, Maria Grazia; Degasperi, Elisabetta; Sangiovanni, Angelo; Maggioni, Marco; Fraquelli, Mirella; Perbellini, Riccardo; Rosenberg, William; Bedossa, Pierre; Colombo, Massimo; Lampertico, Pietro

2018-01-27

In patients with HCV-related cirrhosis, a sustained virological response may lead to cirrhosis regression. Whether histological changes translate into prevention of long-term complications, particularly hepatocellular carcinoma is still unknown. This was investigated in a cohort of histological cirrhotics who had been prospectively followed-up for 10 years after the achievement of a sustained virological response to IFN. In all, 38 sustained virological response cirrhotics who underwent a liver biopsy 5 years post-SVR were prospectively followed to assess the impact of cirrhosis regression on clinical endpoints. During a follow-up of 86 (30-96) months from liver biopsy, no patients developed clinical decompensation, whilst 5 (13%) developed hepatocellular carcinoma after 79 (7-88) months. The 8-year cumulative probability of hepatocellular carcinoma was 17%, without differences between patients with or without cirrhosis regression (19% [95% CI 6%-50%] vs 14% [95% CI 4%-44%], P = .88). Patients who developed or did not an hepatocellular carcinoma had similar rates of residual cirrhosis (P = 1.0), collagen content (P = .48), METAVIR activity (P = .34), portal inflammation (P = .06) and steatosis (P = .17). At baseline, patients who developed an hepatocellular carcinoma had higher γGT (HR 1.03, 95% CI 1.00-1.06; P = .014) and glucose (HR 1.02, 95% CI 1.00-1.02; P = .012) values; moreover, they had increased Forns Score (HR 12.8, 95% CI 1.14-143.9; P = .039), Lok Index (HR 6.24, 95% CI 1.03-37.6; P = .046) and PLF (HR 19.3, 95% CI 1.72-217.6; P = .016) values. One regressor died of lung cancer. The 8-year cumulative survival probability was 97%, independently on cirrhosis regression (96% vs 100%, P = 1.0) or hepatocellular carcinoma (100% vs 97%, P = 1.0). Post-SVR cirrhosis regression does not prevent hepatocellular carcinoma occurrence. © 2018 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Machine Learning Multi-Stage Classification and Regression in the Search for Vector-like Quarks and the Neyman Construction in Signal Searches

CERN Document Server

Leone, Robert Matthew

A search for vector-like quarks (VLQs) decaying to a Z boson using multi-stage machine learning was compared to a search using a standard square cuts search strategy. VLQs are predicted by several new theories beyond the Standard Model. The searches used 20.3 inverse femtobarns of proton-proton collisions at a center-of-mass energy of 8 TeV collected with the ATLAS detector in 2012 at the CERN Large Hadron Collider. CLs upper limits on production cross sections of vector-like top and bottom quarks were computed for VLQs produced singly or in pairs, Tsingle, Bsingle, Tpair, and Bpair. The two stage machine learning classification search strategy did not provide any improvement over the standard square cuts strategy, but for Tpair, Bpair, and Tsingle, a third stage of machine learning regression was able to lower the upper limits of high signal masses by as much as 50%. Additionally, new test statistics were developed for use in the Neyman construction of confidence regions in order to address deficiencies in c...

Near Real-Time Dust Aerosol Detection with Support Vector Machines for Regression

Science.gov (United States)

Rivas-Perea, P.; Rivas-Perea, P. E.; Cota-Ruiz, J.; Aragon Franco, R. A.

2015-12-01

Remote sensing instruments operating in the near-infrared spectrum usually provide the necessary information for further dust aerosol spectral analysis using statistical or machine learning algorithms. Such algorithms have proven to be effective in analyzing very specific case studies or dust events. However, very few make the analysis open to the public on a regular basis, fewer are designed specifically to operate in near real-time to higher resolutions, and almost none give a global daily coverage. In this research we investigated a large-scale approach to a machine learning algorithm called "support vector regression". The algorithm uses four near-infrared spectral bands from NASA MODIS instrument: B20 (3.66-3.84μm), B29 (8.40-8.70μm), B31 (10.78-11.28μm), and B32 (11.77-12.27μm). The algorithm is presented with ground truth from more than 30 distinct reported dust events, from different geographical regions, at different seasons, both over land and sea cover, in the presence of clouds and clear sky, and in the presence of fires. The purpose of our algorithm is to learn to distinguish the dust aerosols spectral signature from other spectral signatures, providing as output an estimate of the probability of a data point being consistent with dust aerosol signatures. During modeling with ground truth, our algorithm achieved more than 90% of accuracy, and the current live performance of the algorithm is remarkable. Moreover, our algorithm is currently operating in near real-time using NASA's Land, Atmosphere Near real-time Capability for EOS (LANCE) servers, providing a high resolution global overview including 64, 32, 16, 8, 4, 2, and 1km. The near real-time analysis of our algorithm is now available to the general public at http://dust.reev.us and archives of the results starting from 2012 are available upon request.

Prediction of retention indices for frequently reported compounds of plant essential oils using multiple linear regression, partial least squares, and support vector machine.

Science.gov (United States)

Yan, Jun; Huang, Jian-Hua; He, Min; Lu, Hong-Bing; Yang, Rui; Kong, Bo; Xu, Qing-Song; Liang, Yi-Zeng

2013-08-01

Retention indices for frequently reported compounds of plant essential oils on three different stationary phases were investigated. Multivariate linear regression, partial least squares, and support vector machine combined with a new variable selection approach called random-frog recently proposed by our group, were employed to model quantitative structure-retention relationships. Internal and external validations were performed to ensure the stability and predictive ability. All the three methods could obtain an acceptable model, and the optimal results by support vector machine based on a small number of informative descriptors with the square of correlation coefficient for cross validation, values of 0.9726, 0.9759, and 0.9331 on the dimethylsilicone stationary phase, the dimethylsilicone phase with 5% phenyl groups, and the PEG stationary phase, respectively. The performances of two variable selection approaches, random-frog and genetic algorithm, are compared. The importance of the variables was found to be consistent when estimated from correlation coefficients in multivariate linear regression equations and selection probability in model spaces. © 2013 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Improved RMR Rock Mass Classification Using Artificial Intelligence Algorithms

Science.gov (United States)

Gholami, Raoof; Rasouli, Vamegh; Alimoradi, Andisheh

2013-09-01

Rock mass classification systems such as rock mass rating (RMR) are very reliable means to provide information about the quality of rocks surrounding a structure as well as to propose suitable support systems for unstable regions. Many correlations have been proposed to relate measured quantities such as wave velocity to rock mass classification systems to limit the associated time and cost of conducting the sampling and mechanical tests conventionally used to calculate RMR values. However, these empirical correlations have been found to be unreliable, as they usually overestimate or underestimate the RMR value. The aim of this paper is to compare the results of RMR classification obtained from the use of empirical correlations versus machine-learning methodologies based on artificial intelligence algorithms. The proposed methods were verified based on two case studies located in northern Iran. Relevance vector regression (RVR) and support vector regression (SVR), as two robust machine-learning methodologies, were used to predict the RMR for tunnel host rocks. RMR values already obtained by sampling and site investigation at one tunnel were taken into account as the output of the artificial networks during training and testing phases. The results reveal that use of empirical correlations overestimates the predicted RMR values. RVR and SVR, however, showed more reliable results, and are therefore suggested for use in RMR classification for design purposes of rock structures.

An Efficient and Simplified Model for Forecasting using SRM

Directory of Open Access Journals (Sweden)

Hafiz Muhammad Shahzad Asif

2014-01-01

Full Text Available Learning form continuous financial systems play a vital role in enterprise operations. One of the most sophisticated non-parametric supervised learning classifiers, SVM (Support Vector Machines, provides robust and accurate results, however it may require intense computation and other resources. The heart of SLT (Statistical Learning Theory, SRM (Structural Risk Minimization Principle can also be used for model selection. In this paper, we focus on comparing the performance of model estimation using SRM with SVR (Support Vector Regression for forecasting the retail sales of consumer products. The potential benefits of an accurate sales forecasting technique in businesses are immense. Retail sales forecasting is an integral part of strategic business planning in areas such as sales planning, marketing research, pricing, production planning and scheduling. Performance comparison of support vector regression with model selection using SRM shows comparable results to SVR but in a computationally efficient manner. This research targeted the real life data to conclude the results after investigating the computer generated datasets for different types of model building

An efficient and simplified model for forecasting using SRM

International Nuclear Information System (INIS)

Asif, H.M.; Hyat, M.F.; Ahmad, T.

2014-01-01

Learning form continuous financial systems play a vital role in enterprise operations. One of the most sophisticated non-parametric supervised learning classifiers, SVM (Support Vector Machines), provides robust and accurate results, however it may require intense computation and other resources. The heart of SLT (Statistical Learning Theory), SRM (Structural Risk Minimization )Principle can also be used for model selection. In this paper, we focus on comparing the performance of model estimation using SRM with SVR (Support Vector Regression) for forecasting the retail sales of consumer products. The potential benefits of an accurate sales forecasting technique in businesses are immense. Retail sales forecasting is an integral part of strategic business planning in areas such as sales planning, marketing research, pricing, production planning and scheduling. Performance comparison of support vector regression with model selection using SRM shows comparable results to SVR but in a computationally efficient manner. This research targeted the real life data to conclude the results after investigating the computer generated datasets for different types of model building. (author)

Least Square Support Vector Machine Classifier vs a Logistic Regression Classifier on the Recognition of Numeric Digits

Directory of Open Access Journals (Sweden)

Danilo A. López-Sarmiento

2013-11-01

Full Text Available In this paper is compared the performance of a multi-class least squares support vector machine (LSSVM mc versus a multi-class logistic regression classifier to problem of recognizing the numeric digits (0-9 handwritten. To develop the comparison was used a data set consisting of 5000 images of handwritten numeric digits (500 images for each number from 0-9, each image of 20 x 20 pixels. The inputs to each of the systems were vectors of 400 dimensions corresponding to each image (not done feature extraction. Both classifiers used OneVsAll strategy to enable multi-classification and a random cross-validation function for the process of minimizing the cost function. The metrics of comparison were precision and training time under the same computational conditions. Both techniques evaluated showed a precision above 95 %, with LS-SVM slightly more accurate. However the computational cost if we found a marked difference: LS-SVM training requires time 16.42 % less than that required by the logistic regression model based on the same low computational conditions.

Virtual machine consolidation enhancement using hybrid regression algorithms

Directory of Open Access Journals (Sweden)

Amany Abdelsamea

2017-11-01

Full Text Available Cloud computing data centers are growing rapidly in both number and capacity to meet the increasing demands for highly-responsive computing and massive storage. Such data centers consume enormous amounts of electrical energy resulting in high operating costs and carbon dioxide emissions. The reason for this extremely high energy consumption is not just the quantity of computing resources and the power inefficiency of hardware, but rather lies in the inefficient usage of these resources. VM consolidation involves live migration of VMs hence the capability of transferring a VM between physical servers with a close to zero down time. It is an effective way to improve the utilization of resources and increase energy efficiency in cloud data centers. VM consolidation consists of host overload/underload detection, VM selection and VM placement. Most of the current VM consolidation approaches apply either heuristic-based techniques, such as static utilization thresholds, decision-making based on statistical analysis of historical data; or simply periodic adaptation of the VM allocation. Most of those algorithms rely on CPU utilization only for host overload detection. In this paper we propose using hybrid factors to enhance VM consolidation. Specifically we developed a multiple regression algorithm that uses CPU utilization, memory utilization and bandwidth utilization for host overload detection. The proposed algorithm, Multiple Regression Host Overload Detection (MRHOD, significantly reduces energy consumption while ensuring a high level of adherence to Service Level Agreements (SLA since it gives a real indication of host utilization based on three parameters (CPU, Memory, Bandwidth utilizations instead of one parameter only (CPU utilization. Through simulations we show that our approach reduces power consumption by 6 times compared to single factor algorithms using random workload. Also using PlanetLab workload traces we show that MRHOD improves

Support Vector Regression-Based Adaptive Divided Difference Filter for Nonlinear State Estimation Problems

Directory of Open Access Journals (Sweden)

Hongjian Wang

2014-01-01

Full Text Available We present a support vector regression-based adaptive divided difference filter (SVRADDF algorithm for improving the low state estimation accuracy of nonlinear systems, which are typically affected by large initial estimation errors and imprecise prior knowledge of process and measurement noises. The derivative-free SVRADDF algorithm is significantly simpler to compute than other methods and is implemented using only functional evaluations. The SVRADDF algorithm involves the use of the theoretical and actual covariance of the innovation sequence. Support vector regression (SVR is employed to generate the adaptive factor to tune the noise covariance at each sampling instant when the measurement update step executes, which improves the algorithm’s robustness. The performance of the proposed algorithm is evaluated by estimating states for (i an underwater nonmaneuvering target bearing-only tracking system and (ii maneuvering target bearing-only tracking in an air-traffic control system. The simulation results show that the proposed SVRADDF algorithm exhibits better performance when compared with a traditional DDF algorithm.

Analysis of an environmental exposure health questionnaire in a metropolitan minority population utilizing logistic regression and Support Vector Machines.

Science.gov (United States)

Chen, Chau-Kuang; Bruce, Michelle; Tyler, Lauren; Brown, Claudine; Garrett, Angelica; Goggins, Susan; Lewis-Polite, Brandy; Weriwoh, Mirabel L; Juarez, Paul D; Hood, Darryl B; Skelton, Tyler

2013-02-01

The goal of this study was to analyze a 54-item instrument for assessment of perception of exposure to environmental contaminants within the context of the built environment, or exposome. This exposome was defined in five domains to include 1) home and hobby, 2) school, 3) community, 4) occupation, and 5) exposure history. Interviews were conducted with child-bearing-age minority women at Metro Nashville General Hospital at Meharry Medical College. Data were analyzed utilizing DTReg software for Support Vector Machine (SVM) modeling followed by an SPSS package for a logistic regression model. The target (outcome) variable of interest was respondent's residence by ZIP code. The results demonstrate that the rank order of important variables with respect to SVM modeling versus traditional logistic regression models is almost identical. This is the first study documenting that SVM analysis has discriminate power for determination of higher-ordered spatial relationships on an environmental exposure history questionnaire.

Addressing uncertainty in atomistic machine learning

DEFF Research Database (Denmark)

Peterson, Andrew A.; Christensen, Rune; Khorshidi, Alireza

2017-01-01

Machine-learning regression has been demonstrated to precisely emulate the potential energy and forces that are output from more expensive electronic-structure calculations. However, to predict new regions of the potential energy surface, an assessment must be made of the credibility of the predi......Machine-learning regression has been demonstrated to precisely emulate the potential energy and forces that are output from more expensive electronic-structure calculations. However, to predict new regions of the potential energy surface, an assessment must be made of the credibility...... of the predictions. In this perspective, we address the types of errors that might arise in atomistic machine learning, the unique aspects of atomistic simulations that make machine-learning challenging, and highlight how uncertainty analysis can be used to assess the validity of machine-learning predictions. We...... suggest this will allow researchers to more fully use machine learning for the routine acceleration of large, high-accuracy, or extended-time simulations. In our demonstrations, we use a bootstrap ensemble of neural network-based calculators, and show that the width of the ensemble can provide an estimate...

A trend fixed on firstly and seasonal adjustment model combined with the ε-SVR for short-term forecasting of electricity demand

International Nuclear Information System (INIS)

Wang Jianzhou; Zhu Wenjin; Zhang Wenyu; Sun Donghuai

2009-01-01

Short-term electricity demand forecasting has always been an essential instrument in power system planning and operation by which an electric utility plans and dispatches loading so as to meet system demand. The accuracy of the dispatching system, derived from the accuracy of demand forecasting and the forecasting algorithm used, will determines the economic of the power system operation as well as the stability of the whole society. This paper presents a combined ε-SVR model considering seasonal proportions based on development tendencies from history data. We use one-order moving averages to produce a comparatively smooth data series, taking the averaging period as the interval that can effectively eliminate the seasonal variation. We used the smoothed data series as the training set input for the ε-SVR model and obtained the corresponding forecasting value. Afterward, we accounted for the previously removed seasonal variation. As a case, we forecast northeast electricity demand of China using the new method. We demonstrated that this simple procedure has very satisfactory overall performance by an analysis of variance with relative verification and validation. Significant reductions in forecast errors were achieved.

A trend fixed on firstly and seasonal adjustment model combined with the epsilon-SVR for short-term forecasting of electricity demand

Energy Technology Data Exchange (ETDEWEB)

Wang Jianzhou [School of Mathematics and Statistics, Lanzhou University, Lanzhou 730000 (China); Zhu Wenjin, E-mail: crying.1@hotmail.co [School of Mathematics and Statistics, Lanzhou University, Lanzhou 730000 (China); Zhang Wenyu [College of Atmospheric Sciences, Lanzhou University, Lanzhou 730000 (China); Sun Donghuai [Key Laboratory of Western Chinas Environmental Systems (Ministry of Education) College of Earth and Environment Sciences, Lanzhou University, Lanzhou 730000 (China)

2009-11-15

Short-term electricity demand forecasting has always been an essential instrument in power system planning and operation by which an electric utility plans and dispatches loading so as to meet system demand. The accuracy of the dispatching system, derived from the accuracy of demand forecasting and the forecasting algorithm used, will determines the economic of the power system operation as well as the stability of the whole society. This paper presents a combined epsilon-SVR model considering seasonal proportions based on development tendencies from history data. We use one-order moving averages to produce a comparatively smooth data series, taking the averaging period as the interval that can effectively eliminate the seasonal variation. We used the smoothed data series as the training set input for the epsilon-SVR model and obtained the corresponding forecasting value. Afterward, we accounted for the previously removed seasonal variation. As a case, we forecast northeast electricity demand of China using the new method. We demonstrated that this simple procedure has very satisfactory overall performance by an analysis of variance with relative verification and validation. Significant reductions in forecast errors were achieved.

A trend fixed on firstly and seasonal adjustment model combined with the {epsilon}-SVR for short-term forecasting of electricity demand

Energy Technology Data Exchange (ETDEWEB)

Wang, Jianzhou; Zhu, Wenjin [School of Mathematics and Statistics, Lanzhou University, Lanzhou 730000 (China); Zhang, Wenyu [College of Atmospheric Sciences, Lanzhou University, Lanzhou 730000 (China); Sun, Donghuai [Key Laboratory of Western Chinas Environmental Systems (Ministry of Education) College of Earth and Environment Sciences, Lanzhou University, Lanzhou 730000 (China)

2009-11-15

Short-term electricity demand forecasting has always been an essential instrument in power system planning and operation by which an electric utility plans and dispatches loading so as to meet system demand. The accuracy of the dispatching system, derived from the accuracy of demand forecasting and the forecasting algorithm used, will determines the economic of the power system operation as well as the stability of the whole society. This paper presents a combined {epsilon}-SVR model considering seasonal proportions based on development tendencies from history data. We use one-order moving averages to produce a comparatively smooth data series, taking the averaging period as the interval that can effectively eliminate the seasonal variation. We used the smoothed data series as the training set input for the {epsilon}-SVR model and obtained the corresponding forecasting value. Afterward, we accounted for the previously removed seasonal variation. As a case, we forecast northeast electricity demand of China using the new method. We demonstrated that this simple procedure has very satisfactory overall performance by an analysis of variance with relative verification and validation. Significant reductions in forecast errors were achieved. (author)

[Screen potential CYP450 2E1 inhibitors from Chinese herbal medicine based on support vector regression and molecular docking method].

Science.gov (United States)

Chen, Xi; Lu, Fang; Jiang, Lu-di; Cai, Yi-Lian; Li, Gong-Yu; Zhang, Yan-Ling

2016-07-01

Inhibition of cytochrome P450 (CYP450) enzymes is the most common reasons for drug interactions, so the study on early prediction of CYPs inhibitors can help to decrease the incidence of adverse reactions caused by drug interactions.CYP450 2E1(CYP2E1), as a key role in drug metabolism process, has broad spectrum of drug metabolism substrate. In this study, 32 CYP2E1 inhibitors were collected for the construction of support vector regression (SVR) model. The test set data were used to verify CYP2E1 quantitative models and obtain the optimal prediction model of CYP2E1 inhibitor. Meanwhile, one molecular docking program, CDOCKER, was utilized to analyze the interaction pattern between positive compounds and active pocket to establish the optimal screening model of CYP2E1 inhibitors.SVR model and molecular docking prediction model were combined to screen traditional Chinese medicine database (TCMD), which could improve the calculation efficiency and prediction accuracy. 6 376 traditional Chinese medicine (TCM) compounds predicted by SVR model were obtained, and in further verification by using molecular docking model, 247 TCM compounds with potential inhibitory activities against CYP2E1 were finally retained. Some of them have been verified by experiments. The results demonstrated that this study could provide guidance for the virtual screening of CYP450 inhibitors and the prediction of CYPs-mediated DDIs, and also provide references for clinical rational drug use. Copyright© by the Chinese Pharmaceutical Association.

Computational Study of Estrogen Receptor-Alpha Antagonist with Three-Dimensional Quantitative Structure-Activity Relationship, Support Vector Regression, and Linear Regression Methods

Directory of Open Access Journals (Sweden)

Ying-Hsin Chang

2013-01-01

Full Text Available Human estrogen receptor (ER isoforms, ERα and ERβ, have long been an important focus in the field of biology. To better understand the structural features associated with the binding of ERα ligands to ERα and modulate their function, several QSAR models, including CoMFA, CoMSIA, SVR, and LR methods, have been employed to predict the inhibitory activity of 68 raloxifene derivatives. In the SVR and LR modeling, 11 descriptors were selected through feature ranking and sequential feature addition/deletion to generate equations to predict the inhibitory activity toward ERα. Among four descriptors that constantly appear in various generated equations, two agree with CoMFA and CoMSIA steric fields and another two can be correlated to a calculated electrostatic potential of ERα.

Temperature-based estimation of global solar radiation using soft computing methodologies

Science.gov (United States)

Mohammadi, Kasra; Shamshirband, Shahaboddin; Danesh, Amir Seyed; Abdullah, Mohd Shahidan; Zamani, Mazdak

2016-07-01

Precise knowledge of solar radiation is indeed essential in different technological and scientific applications of solar energy. Temperature-based estimation of global solar radiation would be appealing owing to broad availability of measured air temperatures. In this study, the potentials of soft computing techniques are evaluated to estimate daily horizontal global solar radiation (DHGSR) from measured maximum, minimum, and average air temperatures ( T max, T min, and T avg) in an Iranian city. For this purpose, a comparative evaluation between three methodologies of adaptive neuro-fuzzy inference system (ANFIS), radial basis function support vector regression (SVR-rbf), and polynomial basis function support vector regression (SVR-poly) is performed. Five combinations of T max, T min, and T avg are served as inputs to develop ANFIS, SVR-rbf, and SVR-poly models. The attained results show that all ANFIS, SVR-rbf, and SVR-poly models provide favorable accuracy. Based upon all techniques, the higher accuracies are achieved by models (5) using T max- T min and T max as inputs. According to the statistical results, SVR-rbf outperforms SVR-poly and ANFIS. For SVR-rbf (5), the mean absolute bias error, root mean square error, and correlation coefficient are 1.1931 MJ/m2, 2.0716 MJ/m2, and 0.9380, respectively. The survey results approve that SVR-rbf can be used efficiently to estimate DHGSR from air temperatures.

Application of the Support Vector Regression Method for Turbidity Assessment with MODIS on a Shallow Coral Reef Lagoon (Voh-Koné-Pouembout, New Caledonia

Directory of Open Access Journals (Sweden)

Guillaume Wattelez

2017-09-01

Full Text Available Particle transport by erosion from ultramafic lands in pristine tropical lagoons is a crucial problem, especially for the benthic and pelagic biodiversity associated with coral reefs. Satellite imagery is useful for assessing particle transport from land to sea. However, in the oligotrophic and shallow waters of tropical lagoons, the bottom reflection of downwelling light usually hampers the use of classical optical algorithms. In order to address this issue, a Support Vector Regression (SVR model was developed and tested. The proposed application concerns the lagoon of New Caledonia—the second longest continuous coral reef in the world—which is frequently exposed to river plumes from ultramafic watersheds. The SVR model is based on a large training sample of in-situ turbidity values representative of the annual variability in the Voh-Koné-Pouembout lagoon (Western Coast of New Caledonia during the 2014–2015 period and on coincident satellite reflectance values from MODerate Resolution Imaging Spectroradiometer (MODIS. It was trained with reflectance and two other explanatory parameters—bathymetry and bottom colour. This approach significantly improved the model’s capacity for retrieving the in-situ turbidity range from MODIS images, as compared with algorithms dedicated to deep oligotrophic or turbid waters, which were shown to be inadequate. This SVR model is applicable to the whole shallow lagoon waters from the Western Coast of New Caledonia and it is now ready to be tested over other oligotrophic shallow lagoon waters worldwide.

Twin support vector machines models, extensions and applications

CERN Document Server

Jayadeva; Chandra, Suresh

2017-01-01

This book provides a systematic and focused study of the various aspects of twin support vector machines (TWSVM) and related developments for classification and regression. In addition to presenting most of the basic models of TWSVM and twin support vector regression (TWSVR) available in the literature, it also discusses the important and challenging applications of this new machine learning methodology. A chapter on “Additional Topics” has been included to discuss kernel optimization and support tensor machine topics, which are comparatively new but have great potential in applications. It is primarily written for graduate students and researchers in the area of machine learning and related topics in computer science, mathematics, electrical engineering, management science and finance.

A method for separating seismo-ionospheric TEC outliers from heliogeomagnetic disturbances by using nu-SVR

Energy Technology Data Exchange (ETDEWEB)

Pattisahusiwa, Asis [Bandung Institute of Technology (Indonesia); Liong, The Houw; Purqon, Acep [Earth physics and complex systems research group, Bandung Institute of Technology (Indonesia)

2015-09-30

Seismo-Ionospheric is a study of ionosphere disturbances associated with seismic activities. In many previous researches, heliogeomagnetic or strong earthquake activities can caused the disturbances in the ionosphere. However, it is difficult to separate these disturbances based on related sources. In this research, we proposed a method to separate these disturbances/outliers by using nu-SVR with the world-wide GPS data. TEC data related to the 26th December 2004 Sumatra and the 11th March 2011 Honshu earthquakes had been analyzed. After analyzed TEC data in several location around the earthquake epicenter and compared with geomagnetic data, the method shows a good result in the average to detect the source of these outliers. This method is promising to use in the future research.

Hybrid Corporate Performance Prediction Model Considering Technical Capability

Directory of Open Access Journals (Sweden)

Joonhyuck Lee

2016-07-01

Full Text Available Many studies have tried to predict corporate performance and stock prices to enhance investment profitability using qualitative approaches such as the Delphi method. However, developments in data processing technology and machine-learning algorithms have resulted in efforts to develop quantitative prediction models in various managerial subject areas. We propose a quantitative corporate performance prediction model that applies the support vector regression (SVR algorithm to solve the problem of the overfitting of training data and can be applied to regression problems. The proposed model optimizes the SVR training parameters based on the training data, using the genetic algorithm to achieve sustainable predictability in changeable markets and managerial environments. Technology-intensive companies represent an increasing share of the total economy. The performance and stock prices of these companies are affected by their financial standing and their technological capabilities. Therefore, we apply both financial indicators and technical indicators to establish the proposed prediction model. Here, we use time series data, including financial, patent, and corporate performance information of 44 electronic and IT companies. Then, we predict the performance of these companies as an empirical verification of the prediction performance of the proposed model.

Detection of Cutting Tool Wear using Statistical Analysis and Regression Model

Science.gov (United States)

Ghani, Jaharah A.; Rizal, Muhammad; Nuawi, Mohd Zaki; Haron, Che Hassan Che; Ramli, Rizauddin

2010-10-01

This study presents a new method for detecting the cutting tool wear based on the measured cutting force signals. A statistical-based method called Integrated Kurtosis-based Algorithm for Z-Filter technique, called I-kaz was used for developing a regression model and 3D graphic presentation of I-kaz 3D coefficient during machining process. The machining tests were carried out using a CNC turning machine Colchester Master Tornado T4 in dry cutting condition. A Kistler 9255B dynamometer was used to measure the cutting force signals, which were transmitted, analyzed, and displayed in the DasyLab software. Various force signals from machining operation were analyzed, and each has its own I-kaz 3D coefficient. This coefficient was examined and its relationship with flank wear lands (VB) was determined. A regression model was developed due to this relationship, and results of the regression model shows that the I-kaz 3D coefficient value decreases as tool wear increases. The result then is used for real time tool wear monitoring.

Deep Restricted Kernel Machines Using Conjugate Feature Duality.

Science.gov (United States)

Suykens, Johan A K

2017-08-01

The aim of this letter is to propose a theory of deep restricted kernel machines offering new foundations for deep learning with kernel machines. From the viewpoint of deep learning, it is partially related to restricted Boltzmann machines, which are characterized by visible and hidden units in a bipartite graph without hidden-to-hidden connections and deep learning extensions as deep belief networks and deep Boltzmann machines. From the viewpoint of kernel machines, it includes least squares support vector machines for classification and regression, kernel principal component analysis (PCA), matrix singular value decomposition, and Parzen-type models. A key element is to first characterize these kernel machines in terms of so-called conjugate feature duality, yielding a representation with visible and hidden units. It is shown how this is related to the energy form in restricted Boltzmann machines, with continuous variables in a nonprobabilistic setting. In this new framework of so-called restricted kernel machine (RKM) representations, the dual variables correspond to hidden features. Deep RKM are obtained by coupling the RKMs. The method is illustrated for deep RKM, consisting of three levels with a least squares support vector machine regression level and two kernel PCA levels. In its primal form also deep feedforward neural networks can be trained within this framework.

Relationship between rice yield and climate variables in southwest Nigeria using multiple linear regression and support vector machine analysis

Science.gov (United States)

Oguntunde, Philip G.; Lischeid, Gunnar; Dietrich, Ottfried

2018-03-01

This study examines the variations of climate variables and rice yield and quantifies the relationships among them using multiple linear regression, principal component analysis, and support vector machine (SVM) analysis in southwest Nigeria. The climate and yield data used was for a period of 36 years between 1980 and 2015. Similar to the observed decrease ( P 1 and explained 83.1% of the total variance of predictor variables. The SVM regression function using the scores of the first principal component explained about 75% of the variance in rice yield data and linear regression about 64%. SVM regression between annual solar radiation values and yield explained 67% of the variance. Only the first component of the principal component analysis (PCA) exhibited a clear long-term trend and sometimes short-term variance similar to that of rice yield. Short-term fluctuations of the scores of the PC1 are closely coupled to those of rice yield during the 1986-1993 and the 2006-2013 periods thereby revealing the inter-annual sensitivity of rice production to climate variability. Solar radiation stands out as the climate variable of highest influence on rice yield, and the influence was especially strong during monsoon and post-monsoon periods, which correspond to the vegetative, booting, flowering, and grain filling stages in the study area. The outcome is expected to provide more in-depth regional-specific climate-rice linkage for screening of better cultivars that can positively respond to future climate fluctuations as well as providing information that may help optimized planting dates for improved radiation use efficiency in the study area.

Improving sub-pixel imperviousness change prediction by ensembling heterogeneous non-linear regression models

Directory of Open Access Journals (Sweden)

Drzewiecki Wojciech

2016-12-01

Full Text Available In this work nine non-linear regression models were compared for sub-pixel impervious surface area mapping from Landsat images. The comparison was done in three study areas both for accuracy of imperviousness coverage evaluation in individual points in time and accuracy of imperviousness change assessment. The performance of individual machine learning algorithms (Cubist, Random Forest, stochastic gradient boosting of regression trees, k-nearest neighbors regression, random k-nearest neighbors regression, Multivariate Adaptive Regression Splines, averaged neural networks, and support vector machines with polynomial and radial kernels was also compared with the performance of heterogeneous model ensembles constructed from the best models trained using particular techniques.

A Unified and Comprehensible View of Parametric and Kernel Methods for Genomic Prediction with Application to Rice.

Science.gov (United States)

Jacquin, Laval; Cao, Tuong-Vi; Ahmadi, Nourollah

2016-01-01

One objective of this study was to provide readers with a clear and unified understanding of parametric statistical and kernel methods, used for genomic prediction, and to compare some of these in the context of rice breeding for quantitative traits. Furthermore, another objective was to provide a simple and user-friendly R package, named KRMM, which allows users to perform RKHS regression with several kernels. After introducing the concept of regularized empirical risk minimization, the connections between well-known parametric and kernel methods such as Ridge regression [i.e., genomic best linear unbiased predictor (GBLUP)] and reproducing kernel Hilbert space (RKHS) regression were reviewed. Ridge regression was then reformulated so as to show and emphasize the advantage of the kernel "trick" concept, exploited by kernel methods in the context of epistatic genetic architectures, over parametric frameworks used by conventional methods. Some parametric and kernel methods; least absolute shrinkage and selection operator (LASSO), GBLUP, support vector machine regression (SVR) and RKHS regression were thereupon compared for their genomic predictive ability in the context of rice breeding using three real data sets. Among the compared methods, RKHS regression and SVR were often the most accurate methods for prediction followed by GBLUP and LASSO. An R function which allows users to perform RR-BLUP of marker effects, GBLUP and RKHS regression, with a Gaussian, Laplacian, polynomial or ANOVA kernel, in a reasonable computation time has been developed. Moreover, a modified version of this function, which allows users to tune kernels for RKHS regression, has also been developed and parallelized for HPC Linux clusters. The corresponding KRMM package and all scripts have been made publicly available.

Improving Accuracy Estimation of Forest Aboveground Biomass Based on Incorporation of ALOS-2 PALSAR-2 and Sentinel-2A Imagery and Machine Learning: A Case Study of the Hyrcanian Forest Area (Iran

Directory of Open Access Journals (Sweden)

Sasan Vafaei

2018-01-01

Full Text Available The main objective of this research is to investigate the potential combination of Sentinel-2A and ALOS-2 PALSAR-2 (Advanced Land Observing Satellite -2 Phased Array type L-band Synthetic Aperture Radar-2 imagery for improving the accuracy of the Aboveground Biomass (AGB measurement. According to the current literature, this kind of investigation has rarely been conducted. The Hyrcanian forest area (Iran is selected as the case study. For this purpose, a total of 149 sample plots for the study area were documented through fieldwork. Using the imagery, three datasets were generated including the Sentinel-2A dataset, the ALOS-2 PALSAR-2 dataset, and the combination of the Sentinel-2A dataset and the ALOS-2 PALSAR-2 dataset (Sentinel-ALOS. Because the accuracy of the AGB estimation is dependent on the method used, in this research, four machine learning techniques were selected and compared, namely Random Forests (RF, Support Vector Regression (SVR, Multi-Layer Perceptron Neural Networks (MPL Neural Nets, and Gaussian Processes (GP. The performance of these AGB models was assessed using the coefficient of determination (R2, the root-mean-square error (RMSE, and the mean absolute error (MAE. The results showed that the AGB models derived from the combination of the Sentinel-2A and the ALOS-2 PALSAR-2 data had the highest accuracy, followed by models using the Sentinel-2A dataset and the ALOS-2 PALSAR-2 dataset. Among the four machine learning models, the SVR model (R2 = 0.73, RMSE = 38.68, and MAE = 32.28 had the highest prediction accuracy, followed by the GP model (R2 = 0.69, RMSE = 40.11, and MAE = 33.69, the RF model (R2 = 0.62, RMSE = 43.13, and MAE = 35.83, and the MPL Neural Nets model (R2 = 0.44, RMSE = 64.33, and MAE = 53.74. Overall, the Sentinel-2A imagery provides a reasonable result while the ALOS-2 PALSAR-2 imagery provides a poor result of the forest AGB estimation. The combination of the Sentinel-2A imagery and the ALOS-2 PALSAR-2

Design optimization of tailor-rolled blank thin-walled structures based on ɛ-support vector regression technique and genetic algorithm

Science.gov (United States)

Duan, Libin; Xiao, Ning-cong; Li, Guangyao; Cheng, Aiguo; Chen, Tao

2017-07-01

Tailor-rolled blank thin-walled (TRB-TH) structures have become important vehicle components owing to their advantages of light weight and crashworthiness. The purpose of this article is to provide an efficient lightweight design for improving the energy-absorbing capability of TRB-TH structures under dynamic loading. A finite element (FE) model for TRB-TH structures is established and validated by performing a dynamic axial crash test. Different material properties for individual parts with different thicknesses are considered in the FE model. Then, a multi-objective crashworthiness design of the TRB-TH structure is constructed based on the ɛ-support vector regression (ɛ-SVR) technique and non-dominated sorting genetic algorithm-II. The key parameters (C, ɛ and σ) are optimized to further improve the predictive accuracy of ɛ-SVR under limited sample points. Finally, the technique for order preference by similarity to the ideal solution method is used to rank the solutions in Pareto-optimal frontiers and find the best compromise optima. The results demonstrate that the light weight and crashworthiness performance of the optimized TRB-TH structures are superior to their uniform thickness counterparts. The proposed approach provides useful guidance for designing TRB-TH energy absorbers for vehicle bodies.

Downscaling of MODIS One Kilometer Evapotranspiration Using Landsat-8 Data and Machine Learning Approaches

Directory of Open Access Journals (Sweden)

Yinghai Ke

2016-03-01

Full Text Available This study presented a MODIS 8-day 1 km evapotranspiration (ET downscaling method based on Landsat 8 data (30 m and machine learning approaches. Eleven indicators including albedo, land surface temperature (LST, and vegetation indices (VIs derived from Landsat 8 data were first upscaled to 1 km resolution. Machine learning algorithms including Support Vector Regression (SVR, Cubist, and Random Forest (RF were used to model the relationship between the Landsat indicators and MODIS 8-day 1 km ET. The models were then used to predict 30 m ET based on Landsat 8 indicators. A total of thirty-two pairs of Landsat 8 images/MODIS ET data were evaluated at four study sites including two in United States and two in South Korea. Among the three models, RF produced the lowest error, with relative Root Mean Square Error (rRMSE less than 20%. Vegetation greenness related indicators such as Normalized Difference Vegetation Index (NDVI, Enhanced Vegetation Index (EVI, Soil Adjusted Vegetation Index (SAVI, and vegetation moisture related indicators such as Normalized Difference Infrared Index—Landsat 8 OLI band 7 (NDIIb7 and Normalized Difference Water Index (NDWI were the five most important features used in RF model. Temperature-based indicators were less important than vegetation greenness and moisture-related indicators because LST could have considerable variation during each 8-day period. The predicted Landsat downscaled ET had good overall agreement with MODIS ET (average rRMSE = 22% and showed a similar temporal trend as MODIS ET. Compared to the MODIS ET product, the downscaled product demonstrated more spatial details, and had better agreement with in situ ET observations (R2 = 0.56. However, we found that the accuracy of MODIS ET was the main control factor of the accuracy of the downscaled product. Improved coarse-resolution ET estimation would result in better finer-resolution estimation. This study proved the potential of using machine learning

A Machine Learning Regression scheme to design a FR-Image Quality Assessment Algorithm

OpenAIRE

Charrier , Christophe; Lezoray , Olivier; Lebrun , Gilles

2012-01-01

International audience; A crucial step in image compression is the evaluation of its performance, and more precisely available ways to measure the quality of compressed images. In this paper, a machine learning expert, providing a quality score is proposed. This quality measure is based on a learned classification process in order to respect that of human observers. The proposed method namely Machine Learning-based Image Quality Measurment (MLIQM) first classifies the quality using multi Supp...

Relationship between rice yield and climate variables in southwest Nigeria using multiple linear regression and support vector machine analysis.

Science.gov (United States)

Oguntunde, Philip G; Lischeid, Gunnar; Dietrich, Ottfried

2018-03-01

This study examines the variations of climate variables and rice yield and quantifies the relationships among them using multiple linear regression, principal component analysis, and support vector machine (SVM) analysis in southwest Nigeria. The climate and yield data used was for a period of 36 years between 1980 and 2015. Similar to the observed decrease (P  1 and explained 83.1% of the total variance of predictor variables. The SVM regression function using the scores of the first principal component explained about 75% of the variance in rice yield data and linear regression about 64%. SVM regression between annual solar radiation values and yield explained 67% of the variance. Only the first component of the principal component analysis (PCA) exhibited a clear long-term trend and sometimes short-term variance similar to that of rice yield. Short-term fluctuations of the scores of the PC1 are closely coupled to those of rice yield during the 1986-1993 and the 2006-2013 periods thereby revealing the inter-annual sensitivity of rice production to climate variability. Solar radiation stands out as the climate variable of highest influence on rice yield, and the influence was especially strong during monsoon and post-monsoon periods, which correspond to the vegetative, booting, flowering, and grain filling stages in the study area. The outcome is expected to provide more in-depth regional-specific climate-rice linkage for screening of better cultivars that can positively respond to future climate fluctuations as well as providing information that may help optimized planting dates for improved radiation use efficiency in the study area.

Machine learning in the string landscape

Science.gov (United States)

Carifio, Jonathan; Halverson, James; Krioukov, Dmitri; Nelson, Brent D.

2017-09-01

We utilize machine learning to study the string landscape. Deep data dives and conjecture generation are proposed as useful frameworks for utilizing machine learning in the landscape, and examples of each are presented. A decision tree accurately predicts the number of weak Fano toric threefolds arising from reflexive polytopes, each of which determines a smooth F-theory compactification, and linear regression generates a previously proven conjecture for the gauge group rank in an ensemble of 4/3× 2.96× {10}^{755} F-theory compactifications. Logistic regression generates a new conjecture for when E 6 arises in the large ensemble of F-theory compactifications, which is then rigorously proven. This result may be relevant for the appearance of visible sectors in the ensemble. Through conjecture generation, machine learning is useful not only for numerics, but also for rigorous results.

A comparison of regression algorithms for wind speed forecasting at Alexander Bay

CSIR Research Space (South Africa)

Botha, Nicolene

2016-12-01

Full Text Available to forecast 1 to 24 hours ahead, in hourly intervals. Predictions are performed on a wind speed time series with three machine learning regression algorithms, namely support vector regression, ordinary least squares and Bayesian ridge regression. The resulting...

Application of chaotic ant swarm optimization in electric load forecasting

International Nuclear Information System (INIS)

Hong, W.-C.

2010-01-01

Support vector regression (SVR) had revealed strong potential in accurate electric load forecasting, particularly by employing effective evolutionary algorithms to determine suitable values of its three parameters. Based on previous research results, however, these employed evolutionary algorithms themselves have several drawbacks, such as converging prematurely, reaching slowly the global optimal solution, and trapping into a local optimum. This investigation presents an SVR-based electric load forecasting model that applied a novel algorithm, namely chaotic ant swarm optimization (CAS), to improve the forecasting performance by searching its suitable parameters combination. The proposed CAS combines with the chaotic behavior of single ant and self-organization behavior of ant colony in the foraging process to overcome premature local optimum. The empirical results indicate that the SVR model with CAS (SVRCAS) results in better forecasting performance than the other alternative methods, namely SVRCPSO (SVR with chaotic PSO), SVRCGA (SVR with chaotic GA), regression model, and ANN model.

A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods

Directory of Open Access Journals (Sweden)

Gwo-Fong Lin

2016-01-01

Full Text Available This study describes the development of a reservoir inflow forecasting model for typhoon events to improve short lead-time flood forecasting performance. To strengthen the forecasting ability of the original support vector machines (SVMs model, the self-organizing map (SOM is adopted to group inputs into different clusters in advance of the proposed SOM-SVM model. Two different input methods are proposed for the SVM-based forecasting method, namely, SOM-SVM1 and SOM-SVM2. The methods are applied to an actual reservoir watershed to determine the 1 to 3 h ahead inflow forecasts. For 1, 2, and 3 h ahead forecasts, improvements in mean coefficient of efficiency (MCE due to the clusters obtained from SOM-SVM1 are 21.5%, 18.5%, and 23.0%, respectively. Furthermore, improvement in MCE for SOM-SVM2 is 20.9%, 21.2%, and 35.4%, respectively. Another SOM-SVM2 model increases the SOM-SVM1 model for 1, 2, and 3 h ahead forecasts obtained improvement increases of 0.33%, 2.25%, and 10.08%, respectively. These results show that the performance of the proposed model can provide improved forecasts of hourly inflow, especially in the proposed SOM-SVM2 model. In conclusion, the proposed model, which considers limit and higher related inputs instead of all inputs, can generate better forecasts in different clusters than are generated from the SOM process. The SOM-SVM2 model is recommended as an alternative to the original SVR (Support Vector Regression model because of its accuracy and robustness.

Blood glucose level prediction based on support vector regression using mobile platforms.

Science.gov (United States)

Reymann, Maximilian P; Dorschky, Eva; Groh, Benjamin H; Martindale, Christine; Blank, Peter; Eskofier, Bjoern M

2016-08-01

The correct treatment of diabetes is vital to a patient's health: Staying within defined blood glucose levels prevents dangerous short- and long-term effects on the body. Mobile devices informing patients about their future blood glucose levels could enable them to take counter-measures to prevent hypo or hyper periods. Previous work addressed this challenge by predicting the blood glucose levels using regression models. However, these approaches required a physiological model, representing the human body's response to insulin and glucose intake, or are not directly applicable to mobile platforms (smart phones, tablets). In this paper, we propose an algorithm for mobile platforms to predict blood glucose levels without the need for a physiological model. Using an online software simulator program, we trained a Support Vector Regression (SVR) model and exported the parameter settings to our mobile platform. The prediction accuracy of our mobile platform was evaluated with pre-recorded data of a type 1 diabetes patient. The blood glucose level was predicted with an error of 19 % compared to the true value. Considering the permitted error of commercially used devices of 15 %, our algorithm is the basis for further development of mobile prediction algorithms.

Estimation of perceptible water vapor of atmosphere using artificial neural network, support vector machine and multiple linear regression algorithm and their comparative study

Science.gov (United States)

Shastri, Niket; Pathak, Kamlesh

2018-05-01

The water vapor content in atmosphere plays very important role in climate. In this paper the application of GPS signal in meteorology is discussed, which is useful technique that is used to estimate the perceptible water vapor of atmosphere. In this paper various algorithms like artificial neural network, support vector machine and multiple linear regression are use to predict perceptible water vapor. The comparative studies in terms of root mean square error and mean absolute errors are also carried out for all the algorithms.

Determination of foodborne pathogenic bacteria by multiplex PCR-microchip capillary electrophoresis with genetic algorithm-support vector regression optimization.

Science.gov (United States)

Li, Yongxin; Li, Yuanqian; Zheng, Bo; Qu, Lingli; Li, Can

2009-06-08

A rapid and sensitive method based on microchip capillary electrophoresis with condition optimization of genetic algorithm-support vector regression (GA-SVR) was developed and applied to simultaneous analysis of multiplex PCR products of four foodborne pathogenic bacteria. Four pairs of oligonucleotide primers were designed to exclusively amplify the targeted gene of Vibrio parahemolyticus, Salmonella, Escherichia coli (E. coli) O157:H7, Shigella and the quadruplex PCR parameters were optimized. At the same time, GA-SVR was employed to optimize the separation conditions of DNA fragments in microchip capillary electrophoresis. The proposed method was applied to simultaneously detect the multiplex PCR products of four foodborne pathogenic bacteria under the optimal conditions within 8 min. The levels of detection were as low as 1.2 x 10(2) CFU mL(-1) of Vibrio parahemolyticus, 2.9 x 10(2) CFU mL(-1) of Salmonella, 8.7 x 10(1) CFU mL(-1) of E. coli O157:H7 and 5.2 x 10(1) CFU mL(-1) of Shigella, respectively. The relative standard deviation of migration time was in the range of 0.74-2.09%. The results demonstrated that the good resolution and less analytical time were achieved due to the application of the multivariate strategy. This study offers an efficient alternative to routine foodborne pathogenic bacteria detection in a fast, reliable, and sensitive way.

Machine learning in virtual screening.

Science.gov (United States)

Melville, James L; Burke, Edmund K; Hirst, Jonathan D

2009-05-01

In this review, we highlight recent applications of machine learning to virtual screening, focusing on the use of supervised techniques to train statistical learning algorithms to prioritize databases of molecules as active against a particular protein target. Both ligand-based similarity searching and structure-based docking have benefited from machine learning algorithms, including naïve Bayesian classifiers, support vector machines, neural networks, and decision trees, as well as more traditional regression techniques. Effective application of these methodologies requires an appreciation of data preparation, validation, optimization, and search methodologies, and we also survey developments in these areas.

EVALUATION OF VARIOUS SPECTRAL INPUTS FOR ESTIMATION OF FOREST BIOCHEMICAL AND STRUCTURAL PROPERTIES FROM AIRBORNE IMAGING SPECTROSCOPY DATA

Directory of Open Access Journals (Sweden)

L. Homolová

2016-06-01

Full Text Available In this study we evaluated various spectral inputs for retrieval of forest chlorophyll content (Cab and leaf area index (LAI from high spectral and spatial resolution airborne imaging spectroscopy data collected for two forest study sites in the Czech Republic (beech forest at Štítná nad Vláří and spruce forest at Bílý Kříž. The retrieval algorithm was based on a machine learning method – support vector regression (SVR. Performance of the four spectral inputs used to train SVR was evaluated: a all available hyperspectral bands, b continuum removal (CR 645 – 710 nm, c CR 705 – 780 nm, and d CR 680 – 800 nm. Spectral inputs and corresponding SVR models were first assessed at the level of spectral databases simulated by combined leaf-canopy radiative transfer models PROSPECT and DART. At this stage, SVR models using all spectral inputs provided good performance (RMSE for Cab −2 and for LAI < 1.5, with consistently better performance for beech over spruce site. Since application of trained SVRs on airborne hyperspectral images of the spruce site produced unacceptably overestimated values, only the beech site results were analysed. The best performance for the Cab estimation was found for CR bands in range of 645 – 710 nm, whereas CR bands in range of 680 – 800 nm were the most suitable for LAI retrieval. The CR transformation reduced the across-track bidirectional reflectance effect present in airborne images due to large sensor field of view.

Using Machine Learning to Predict Student Performance

OpenAIRE

Pojon, Murat

2017-01-01

This thesis examines the application of machine learning algorithms to predict whether a student will be successful or not. The specific focus of the thesis is the comparison of machine learning methods and feature engineering techniques in terms of how much they improve the prediction performance. Three different machine learning methods were used in this thesis. They are linear regression, decision trees, and naïve Bayes classification. Feature engineering, the process of modification ...

Bidirectional extreme learning machine for regression problem and its learning effectiveness.

Science.gov (United States)

Yang, Yimin; Wang, Yaonan; Yuan, Xiaofang

2012-09-01

It is clear that the learning effectiveness and learning speed of neural networks are in general far slower than required, which has been a major bottleneck for many applications. Recently, a simple and efficient learning method, referred to as extreme learning machine (ELM), was proposed by Huang , which has shown that, compared to some conventional methods, the training time of neural networks can be reduced by a thousand times. However, one of the open problems in ELM research is whether the number of hidden nodes can be further reduced without affecting learning effectiveness. This brief proposes a new learning algorithm, called bidirectional extreme learning machine (B-ELM), in which some hidden nodes are not randomly selected. In theory, this algorithm tends to reduce network output error to 0 at an extremely early learning stage. Furthermore, we find a relationship between the network output error and the network output weights in the proposed B-ELM. Simulation results demonstrate that the proposed method can be tens to hundreds of times faster than other incremental ELM algorithms.

Using Support Vector Regression and Hyperspectral Imaging for the Prediction of Oenological Parameters on Different Vintages and Varieties of Wine Grape Berries

Directory of Open Access Journals (Sweden)

Rui Silva

2018-02-01

Full Text Available The performance of a support vector regression (SVR model with a Gaussian radial basis kernel to predict anthocyanin concentration, pH index and sugar content in whole grape berries, using spectroscopic measurements obtained in reflectance mode, was evaluated. Each sample contained a small number of whole berries and the spectrum of each sample was collected during ripening using hyperspectral imaging in the range of 380–1028 nm. Touriga Franca (TF variety samples were collected for the 2012–2015 vintages, and Touriga Nacional (TN and Tinta Barroca (TB variety samples were collected for the 2013 vintage. These TF vintages were independently used to train, validate and test the SVR methodology; different combinations of TF vintages were used to train and test each model to assess the performance differences under wider and more variable datasets; the varieties that were not employed in the model training and validation (TB and TN were used to test the generalization ability of the SVR approach. Each case was tested using an external independent set (with data not included in the model training or validation steps. The best R2 results obtained with varieties and vintages not employed in the model’s training step were 0.89, 0.81 and 0.90, with RMSE values of 35.6 mg·L−1, 0.25 and 3.19 °Brix, for anthocyanin concentration, pH index and sugar content, respectively. The present results indicate a good overall performance for all cases, improving the state-of-the-art results for external test sets, and suggesting that a robust model, with a generalization capacity over different varieties and harvest years may be obtainable without further training, which makes this a very competitive approach when compared to the models from other authors, since it makes the problem significantly simpler and more cost-effective.

Risk estimation using probability machines

Science.gov (United States)

2014-01-01

Background Logistic regression has been the de facto, and often the only, model used in the description and analysis of relationships between a binary outcome and observed features. It is widely used to obtain the conditional probabilities of the outcome given predictors, as well as predictor effect size estimates using conditional odds ratios. Results We show how statistical learning machines for binary outcomes, provably consistent for the nonparametric regression problem, can be used to provide both consistent conditional probability estimation and conditional effect size estimates. Effect size estimates from learning machines leverage our understanding of counterfactual arguments central to the interpretation of such estimates. We show that, if the data generating model is logistic, we can recover accurate probability predictions and effect size estimates with nearly the same efficiency as a correct logistic model, both for main effects and interactions. We also propose a method using learning machines to scan for possible interaction effects quickly and efficiently. Simulations using random forest probability machines are presented. Conclusions The models we propose make no assumptions about the data structure, and capture the patterns in the data by just specifying the predictors involved and not any particular model structure. So they do not run the same risks of model mis-specification and the resultant estimation biases as a logistic model. This methodology, which we call a “risk machine”, will share properties from the statistical machine that it is derived from. PMID:24581306

Short-term load forecasting with increment regression tree

Energy Technology Data Exchange (ETDEWEB)

Yang, Jingfei; Stenzel, Juergen [Darmstadt University of Techonology, Darmstadt 64283 (Germany)

2006-06-15

This paper presents a new regression tree method for short-term load forecasting. Both increment and non-increment tree are built according to the historical data to provide the data space partition and input variable selection. Support vector machine is employed to the samples of regression tree nodes for further fine regression. Results of different tree nodes are integrated through weighted average method to obtain the comprehensive forecasting result. The effectiveness of the proposed method is demonstrated through its application to an actual system. (author)

Machine Learning of Musical Gestures

OpenAIRE

Caramiaux, Baptiste; Tanaka, Atau

2013-01-01

We present an overview of machine learning (ML) techniques and theirapplication in interactive music and new digital instruments design. We firstgive to the non-specialist reader an introduction to two ML tasks,classification and regression, that are particularly relevant for gesturalinteraction. We then present a review of the literature in current NIMEresearch that uses ML in musical gesture analysis and gestural sound control.We describe the ways in which machine learning is useful for cre...

Comparison of ν-support vector regression and logistic equation for ...

African Journals Online (AJOL)

Jane

2011-07-04

Jul 4, 2011 ... In this paper, we developed a ν-SVR model with genetic algorithms (GA) ..... bioinformatics, proteomics and system biology. Current ... for gluconic acid fermentation by Aspergillus niger. ... 2D-MH: A web-server for generating.

Agricultural drought prediction using climate indices based on Support Vector Regression in Xiangjiang River basin.

Science.gov (United States)

Tian, Ye; Xu, Yue-Ping; Wang, Guoqing

2018-05-01

Drought can have a substantial impact on the ecosystem and agriculture of the affected region and does harm to local economy. This study aims to analyze the relation between soil moisture and drought and predict agricultural drought in Xiangjiang River basin. The agriculture droughts are presented with the Precipitation-Evapotranspiration Index (SPEI). The Support Vector Regression (SVR) model incorporating climate indices is developed to predict the agricultural droughts. Analysis of climate forcing including El Niño Southern Oscillation and western Pacific subtropical high (WPSH) are carried out to select climate indices. The results show that SPEI of six months time scales (SPEI-6) represents the soil moisture better than that of three and one month time scale on drought duration, severity and peaks. The key factor that influences the agriculture drought is the Ridge Point of WPSH, which mainly controls regional temperature. The SVR model incorporating climate indices, especially ridge point of WPSH, could improve the prediction accuracy compared to that solely using drought index by 4.4% in training and 5.1% in testing measured by Nash Sutcliffe efficiency coefficient (NSE) for three month lead time. The improvement is more significant for the prediction with one month lead (15.8% in training and 27.0% in testing) than that with three months lead time. However, it needs to be cautious in selection of the input parameters, since adding redundant information could have a counter effect in attaining a better prediction. Copyright © 2017 Elsevier B.V. All rights reserved.

Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy

International Nuclear Information System (INIS)

Jain, Rishee K.; Smith, Kevin M.; Culligan, Patricia J.; Taylor, John E.

2014-01-01

Highlights: • We develop a building energy forecasting model using support vector regression. • Model is applied to data from a multi-family residential building in New York City. • We extend sensor based energy forecasting to multi-family residential buildings. • We examine the impact temporal and spatial granularity has on model accuracy. • Optimal granularity occurs at the by floor in hourly temporal intervals. - Abstract: Buildings are the dominant source of energy consumption and environmental emissions in urban areas. Therefore, the ability to forecast and characterize building energy consumption is vital to implementing urban energy management and efficiency initiatives required to curb emissions. Advances in smart metering technology have enabled researchers to develop “sensor based” approaches to forecast building energy consumption that necessitate less input data than traditional methods. Sensor-based forecasting utilizes machine learning techniques to infer the complex relationships between consumption and influencing variables (e.g., weather, time of day, previous consumption). While sensor-based forecasting has been studied extensively for commercial buildings, there is a paucity of research applying this data-driven approach to the multi-family residential sector. In this paper, we build a sensor-based forecasting model using Support Vector Regression (SVR), a commonly used machine learning technique, and apply it to an empirical data-set from a multi-family residential building in New York City. We expand our study to examine the impact of temporal (i.e., daily, hourly, 10 min intervals) and spatial (i.e., whole building, by floor, by unit) granularity have on the predictive power of our single-step model. Results indicate that sensor based forecasting models can be extended to multi-family residential buildings and that the optimal monitoring granularity occurs at the by floor level in hourly intervals. In addition to implications for

Improving model predictions for RNA interference activities that use support vector machine regression by combining and filtering features

Directory of Open Access Journals (Sweden)

Peek Andrew S

2007-06-01

Full Text Available Abstract Background RNA interference (RNAi is a naturally occurring phenomenon that results in the suppression of a target RNA sequence utilizing a variety of possible methods and pathways. To dissect the factors that result in effective siRNA sequences a regression kernel Support Vector Machine (SVM approach was used to quantitatively model RNA interference activities. Results Eight overall feature mapping methods were compared in their abilities to build SVM regression models that predict published siRNA activities. The primary factors in predictive SVM models are position specific nucleotide compositions. The secondary factors are position independent sequence motifs (N-grams and guide strand to passenger strand sequence thermodynamics. Finally, the factors that are least contributory but are still predictive of efficacy are measures of intramolecular guide strand secondary structure and target strand secondary structure. Of these, the site of the 5' most base of the guide strand is the most informative. Conclusion The capacity of specific feature mapping methods and their ability to build predictive models of RNAi activity suggests a relative biological importance of these features. Some feature mapping methods are more informative in building predictive models and overall t-test filtering provides a method to remove some noisy features or make comparisons among datasets. Together, these features can yield predictive SVM regression models with increased predictive accuracy between predicted and observed activities both within datasets by cross validation, and between independently collected RNAi activity datasets. Feature filtering to remove features should be approached carefully in that it is possible to reduce feature set size without substantially reducing predictive models, but the features retained in the candidate models become increasingly distinct. Software to perform feature prediction and SVM training and testing on nucleic acid

Modeling of Soil Aggregate Stability using Support Vector Machines and Multiple Linear Regression

Directory of Open Access Journals (Sweden)

Ali Asghar Besalatpour

2016-02-01

Full Text Available Introduction: Soil aggregate stability is a key factor in soil resistivity to mechanical stresses, including the impacts of rainfall and surface runoff, and thus to water erosion (Canasveras et al., 2010. Various indicators have been proposed to characterize and quantify soil aggregate stability, for example percentage of water-stable aggregates (WSA, mean weight diameter (MWD, geometric mean diameter (GMD of aggregates, and water-dispersible clay (WDC content (Calero et al., 2008. Unfortunately, the experimental methods available to determine these indicators are laborious, time-consuming and difficult to standardize (Canasveras et al., 2010. Therefore, it would be advantageous if aggregate stability could be predicted indirectly from more easily available data (Besalatpour et al., 2014. The main objective of this study is to investigate the potential use of support vector machines (SVMs method for estimating soil aggregate stability (as quantified by GMD as compared to multiple linear regression approach. Materials and Methods: The study area was part of the Bazoft watershed (31° 37′ to 32° 39′ N and 49° 34′ to 50° 32′ E, which is located in the Northern part of the Karun river basin in central Iran. A total of 160 soil samples were collected from the top 5 cm of soil surface. Some easily available characteristics including topographic, vegetation, and soil properties were used as inputs. Soil organic matter (SOM content was determined by the Walkley-Black method (Nelson & Sommers, 1986. Particle size distribution in the soil samples (clay, silt, sand, fine sand, and very fine sand were measured using the procedure described by Gee & Bauder (1986 and calcium carbonate equivalent (CCE content was determined by the back-titration method (Nelson, 1982. The modified Kemper & Rosenau (1986 method was used to determine wet-aggregate stability (GMD. The topographic attributes of elevation, slope, and aspect were characterized using a 20-m

2D Quantitative Structure-Property Relationship Study of Mycotoxins by Multiple Linear Regression and Support Vector Machine

Directory of Open Access Journals (Sweden)

Fereshteh Shiri

2010-08-01

Full Text Available In the present work, support vector machines (SVMs and multiple linear regression (MLR techniques were used for quantitative structure–property relationship (QSPR studies of retention time (tR in standardized liquid chromatography–UV–mass spectrometry of 67 mycotoxins (aflatoxins, trichothecenes, roquefortines and ochratoxins based on molecular descriptors calculated from the optimized 3D structures. By applying missing value, zero and multicollinearity tests with a cutoff value of 0.95, and genetic algorithm method of variable selection, the most relevant descriptors were selected to build QSPR models. MLRand SVMs methods were employed to build QSPR models. The robustness of the QSPR models was characterized by the statistical validation and applicability domain (AD. The prediction results from the MLR and SVM models are in good agreement with the experimental values. The correlation and predictability measure by r2 and q2 are 0.931 and 0.932, repectively, for SVM and 0.923 and 0.915, respectively, for MLR. The applicability domain of the model was investigated using William’s plot. The effects of different descriptors on the retention times are described.

Broiler chickens can benefit from machine learning: support vector machine analysis of observational epidemiological data.

Science.gov (United States)

Hepworth, Philip J; Nefedov, Alexey V; Muchnik, Ilya B; Morgan, Kenton L

2012-08-07

Machine-learning algorithms pervade our daily lives. In epidemiology, supervised machine learning has the potential for classification, diagnosis and risk factor identification. Here, we report the use of support vector machine learning to identify the features associated with hock burn on commercial broiler farms, using routinely collected farm management data. These data lend themselves to analysis using machine-learning techniques. Hock burn, dermatitis of the skin over the hock, is an important indicator of broiler health and welfare. Remarkably, this classifier can predict the occurrence of high hock burn prevalence with accuracy of 0.78 on unseen data, as measured by the area under the receiver operating characteristic curve. We also compare the results with those obtained by standard multi-variable logistic regression and suggest that this technique provides new insights into the data. This novel application of a machine-learning algorithm, embedded in poultry management systems could offer significant improvements in broiler health and welfare worldwide.

Probability Machines: Consistent Probability Estimation Using Nonparametric Learning Machines

Science.gov (United States)

Malley, J. D.; Kruppa, J.; Dasgupta, A.; Malley, K. G.; Ziegler, A.

2011-01-01

Summary Background Most machine learning approaches only provide a classification for binary responses. However, probabilities are required for risk estimation using individual patient characteristics. It has been shown recently that every statistical learning machine known to be consistent for a nonparametric regression problem is a probability machine that is provably consistent for this estimation problem. Objectives The aim of this paper is to show how random forests and nearest neighbors can be used for consistent estimation of individual probabilities. Methods Two random forest algorithms and two nearest neighbor algorithms are described in detail for estimation of individual probabilities. We discuss the consistency of random forests, nearest neighbors and other learning machines in detail. We conduct a simulation study to illustrate the validity of the methods. We exemplify the algorithms by analyzing two well-known data sets on the diagnosis of appendicitis and the diagnosis of diabetes in Pima Indians. Results Simulations demonstrate the validity of the method. With the real data application, we show the accuracy and practicality of this approach. We provide sample code from R packages in which the probability estimation is already available. This means that all calculations can be performed using existing software. Conclusions Random forest algorithms as well as nearest neighbor approaches are valid machine learning methods for estimating individual probabilities for binary responses. Freely available implementations are available in R and may be used for applications. PMID:21915433

Estimation of a Reactor Core Power Peaking Factor Using Support Vector Regression and Uncertainty Analysis

International Nuclear Information System (INIS)

Bae, In Ho; Naa, Man Gyun; Lee, Yoon Joon; Park, Goon Cherl

2009-01-01

The monitoring of detailed 3-dimensional (3D) reactor core power distribution is a prerequisite in the operation of nuclear power reactors to ensure that various safety limits imposed on the LPD and DNBR, are not violated during nuclear power reactor operation. The LPD and DNBR should be calculated in order to perform the two major functions of the core protection calculator system (CPCS) and the core operation limit supervisory system (COLSS). The LPD at the hottest part of a hot fuel rod, which is related to the power peaking factor (PPF, F q ), is more important than the LPD at any other position in a reactor core. The LPD needs to be estimated accurately to prevent nuclear fuel rods from melting. In this study, support vector regression (SVR) and uncertainty analysis have been applied to estimation of reactor core power peaking factor

Applying machine learning techniques for forecasting flexibility of virtual power plants

DEFF Research Database (Denmark)

MacDougall, Pamela; Kosek, Anna Magdalena; Bindner, Henrik W.

2016-01-01

network as well as the multi-variant linear regression. It is found that it is possible to estimate the longevity of flexibility with machine learning. The linear regression algorithm is, on average, able to estimate the longevity with a 15% error. However, there was a significant improvement with the ANN...... approach to investigating the longevity of aggregated response of a virtual power plant using historic bidding and aggregated behaviour with machine learning techniques. The two supervised machine learning techniques investigated and compared in this paper are, multivariate linear regression and single...... algorithm achieving, on average, a 5.3% error. This is lowered 2.4% when learning for the same virtual power plant. With this information it would be possible to accurately offer residential VPP flexibility for market operations to safely avoid causing further imbalances and financial penalties....

Aircraft Engine Thrust Estimator Design Based on GSA-LSSVM

Science.gov (United States)

Sheng, Hanlin; Zhang, Tianhong

2017-08-01

In view of the necessity of highly precise and reliable thrust estimator to achieve direct thrust control of aircraft engine, based on support vector regression (SVR), as well as least square support vector machine (LSSVM) and a new optimization algorithm - gravitational search algorithm (GSA), by performing integrated modelling and parameter optimization, a GSA-LSSVM-based thrust estimator design solution is proposed. The results show that compared to particle swarm optimization (PSO) algorithm, GSA can find unknown optimization parameter better and enables the model developed with better prediction and generalization ability. The model can better predict aircraft engine thrust and thus fulfills the need of direct thrust control of aircraft engine.

Height and Weight Estimation From Anthropometric Measurements Using Machine Learning Regressions.

Science.gov (United States)

Rativa, Diego; Fernandes, Bruno J T; Roque, Alexandre

2018-01-01

Height and weight are measurements explored to tracking nutritional diseases, energy expenditure, clinical conditions, drug dosages, and infusion rates. Many patients are not ambulant or may be unable to communicate, and a sequence of these factors may not allow accurate estimation or measurements; in those cases, it can be estimated approximately by anthropometric means. Different groups have proposed different linear or non-linear equations which coefficients are obtained by using single or multiple linear regressions. In this paper, we present a complete study of the application of different learning models to estimate height and weight from anthropometric measurements: support vector regression, Gaussian process, and artificial neural networks. The predicted values are significantly more accurate than that obtained with conventional linear regressions. In all the cases, the predictions are non-sensitive to ethnicity, and to gender, if more than two anthropometric parameters are analyzed. The learning model analysis creates new opportunities for anthropometric applications in industry, textile technology, security, and health care.

Identifying predictive features in drug response using machine learning: opportunities and challenges.

Science.gov (United States)

Vidyasagar, Mathukumalli

2015-01-01

This article reviews several techniques from machine learning that can be used to study the problem of identifying a small number of features, from among tens of thousands of measured features, that can accurately predict a drug response. Prediction problems are divided into two categories: sparse classification and sparse regression. In classification, the clinical parameter to be predicted is binary, whereas in regression, the parameter is a real number. Well-known methods for both classes of problems are briefly discussed. These include the SVM (support vector machine) for classification and various algorithms such as ridge regression, LASSO (least absolute shrinkage and selection operator), and EN (elastic net) for regression. In addition, several well-established methods that do not directly fall into machine learning theory are also reviewed, including neural networks, PAM (pattern analysis for microarrays), SAM (significance analysis for microarrays), GSEA (gene set enrichment analysis), and k-means clustering. Several references indicative of the application of these methods to cancer biology are discussed.

Outsmarting neural networks: an alternative paradigm for machine learning

Energy Technology Data Exchange (ETDEWEB)

Protopopescu, V.; Rao, N.S.V.

1996-10-01

We address three problems in machine learning, namely: (i) function learning, (ii) regression estimation, and (iii) sensor fusion, in the Probably and Approximately Correct (PAC) framework. We show that, under certain conditions, one can reduce the three problems above to the regression estimation. The latter is usually tackled with artificial neural networks (ANNs) that satisfy the PAC criteria, but have high computational complexity. We propose several computationally efficient PAC alternatives to ANNs to solve the regression estimation. Thereby we also provide efficient PAC solutions to the function learning and sensor fusion problems. The approach is based on cross-fertilizing concepts and methods from statistical estimation, nonlinear algorithms, and the theory of computational complexity, and is designed as part of a new, coherent paradigm for machine learning.

Predicting the dissolution kinetics of silicate glasses using machine learning

Science.gov (United States)

Anoop Krishnan, N. M.; Mangalathu, Sujith; Smedskjaer, Morten M.; Tandia, Adama; Burton, Henry; Bauchy, Mathieu

2018-05-01

Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, thanks to its inherent ability to handle non-linear data. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.

Comparison of several measure-correlate-predict models using support vector regression techniques to estimate wind power densities. A case study

International Nuclear Information System (INIS)

Díaz, Santiago; Carta, José A.; Matías, José M.

2017-01-01

Highlights: • Eight measure-correlate-predict (MCP) models used to estimate the wind power densities (WPDs) at a target site are compared. • Support vector regressions are used as the main prediction techniques in the proposed MCPs. • The most precise MCP uses two sub-models which predict wind speed and air density in an unlinked manner. • The most precise model allows to construct a bivariable (wind speed and air density) WPD probability density function. • MCP models trained to minimise wind speed prediction error do not minimise WPD prediction error. - Abstract: The long-term annual mean wind power density (WPD) is an important indicator of wind as a power source which is usually included in regional wind resource maps as useful prior information to identify potentially attractive sites for the installation of wind projects. In this paper, a comparison is made of eight proposed Measure-Correlate-Predict (MCP) models to estimate the WPDs at a target site. Seven of these models use the Support Vector Regression (SVR) and the eighth the Multiple Linear Regression (MLR) technique, which serves as a basis to compare the performance of the other models. In addition, a wrapper technique with 10-fold cross-validation has been used to select the optimal set of input features for the SVR and MLR models. Some of the eight models were trained to directly estimate the mean hourly WPDs at a target site. Others, however, were firstly trained to estimate the parameters on which the WPD depends (i.e. wind speed and air density) and then, using these parameters, the target site mean hourly WPDs. The explanatory features considered are different combinations of the mean hourly wind speeds, wind directions and air densities recorded in 2014 at ten weather stations in the Canary Archipelago (Spain). The conclusions that can be drawn from the study undertaken include the argument that the most accurate method for the long-term estimation of WPDs requires the execution of a

Machinability of structural steels with calcium addition

International Nuclear Information System (INIS)

Pytel, S.; Zadecki, M.

2003-01-01

The machinability of the plain carbon and low alloy structural steels with carbon content of 0.1-0.6% is briefly discussed in the first part of the paper. In the experimental part a dependence between the addition of calcium and some changes in sulphide and oxide inclusions morphology is presented. The Volvo test for measurement of machinability index B i has been applied. Using the multiple regression methods two relationships between machinability index B i and stereological parameters of non-metallic inclusions as well as hardness of the steels have been calculated. The authors have reached the conclusion that owing to the changes in inclusion chemical composition and geometry as result of calcium addition the machinability index of the steel can be higher. (author)

Validation of the Simple View of Reading in Hebrew--A Semitic Language

Science.gov (United States)

Joshi, R. Malatesha; Ji, Xuejun Ryan; Breznitz, Zvia; Amiel, Meirav; Yulia, Astri

2015-01-01

The Simple View of Reading (SVR) in Hebrew was tested by administering decoding, listening comprehension, and reading comprehension measures to 1,002 students from Grades 2 to 10 in the northern part of Israel. Results from hierarchical regression analyses supported the SVR in Hebrew with decoding and listening comprehension measures explaining…

Machine learning in geosciences and remote sensing

Directory of Open Access Journals (Sweden)

David J. Lary

2016-01-01

Full Text Available Learning incorporates a broad range of complex procedures. Machine learning (ML is a subdivision of artificial intelligence based on the biological learning process. The ML approach deals with the design of algorithms to learn from machine readable data. ML covers main domains such as data mining, difficult-to-program applications, and software applications. It is a collection of a variety of algorithms (e.g. neural networks, support vector machines, self-organizing map, decision trees, random forests, case-based reasoning, genetic programming, etc. that can provide multivariate, nonlinear, nonparametric regression or classification. The modeling capabilities of the ML-based methods have resulted in their extensive applications in science and engineering. Herein, the role of ML as an effective approach for solving problems in geosciences and remote sensing will be highlighted. The unique features of some of the ML techniques will be outlined with a specific attention to genetic programming paradigm. Furthermore, nonparametric regression and classification illustrative examples are presented to demonstrate the efficiency of ML for tackling the geosciences and remote sensing problems.

Real estate value prediction using multivariate regression models

Science.gov (United States)

Manjula, R.; Jain, Shubham; Srivastava, Sharad; Rajiv Kher, Pranav

2017-11-01

The real estate market is one of the most competitive in terms of pricing and the same tends to vary significantly based on a lot of factors, hence it becomes one of the prime fields to apply the concepts of machine learning to optimize and predict the prices with high accuracy. Therefore in this paper, we present various important features to use while predicting housing prices with good accuracy. We have described regression models, using various features to have lower Residual Sum of Squares error. While using features in a regression model some feature engineering is required for better prediction. Often a set of features (multiple regressions) or polynomial regression (applying a various set of powers in the features) is used for making better model fit. For these models are expected to be susceptible towards over fitting ridge regression is used to reduce it. This paper thus directs to the best application of regression models in addition to other techniques to optimize the result.

A Machine Learning Framework for Plan Payment Risk Adjustment.

Science.gov (United States)

Rose, Sherri

2016-12-01

To introduce cross-validation and a nonparametric machine learning framework for plan payment risk adjustment and then assess whether they have the potential to improve risk adjustment. 2011-2012 Truven MarketScan database. We compare the performance of multiple statistical approaches within a broad machine learning framework for estimation of risk adjustment formulas. Total annual expenditure was predicted using age, sex, geography, inpatient diagnoses, and hierarchical condition category variables. The methods included regression, penalized regression, decision trees, neural networks, and an ensemble super learner, all in concert with screening algorithms that reduce the set of variables considered. The performance of these methods was compared based on cross-validated R 2 . Our results indicate that a simplified risk adjustment formula selected via this nonparametric framework maintains much of the efficiency of a traditional larger formula. The ensemble approach also outperformed classical regression and all other algorithms studied. The implementation of cross-validated machine learning techniques provides novel insight into risk adjustment estimation, possibly allowing for a simplified formula, thereby reducing incentives for increased coding intensity as well as the ability of insurers to "game" the system with aggressive diagnostic upcoding. © Health Research and Educational Trust.

A Comparative Study of Pairwise Learning Methods Based on Kernel Ridge Regression.

Science.gov (United States)

Stock, Michiel; Pahikkala, Tapio; Airola, Antti; De Baets, Bernard; Waegeman, Willem

2018-06-12

Many machine learning problems can be formulated as predicting labels for a pair of objects. Problems of that kind are often referred to as pairwise learning, dyadic prediction, or network inference problems. During the past decade, kernel methods have played a dominant role in pairwise learning. They still obtain a state-of-the-art predictive performance, but a theoretical analysis of their behavior has been underexplored in the machine learning literature. In this work we review and unify kernel-based algorithms that are commonly used in different pairwise learning settings, ranging from matrix filtering to zero-shot learning. To this end, we focus on closed-form efficient instantiations of Kronecker kernel ridge regression. We show that independent task kernel ridge regression, two-step kernel ridge regression, and a linear matrix filter arise naturally as a special case of Kronecker kernel ridge regression, implying that all these methods implicitly minimize a squared loss. In addition, we analyze universality, consistency, and spectral filtering properties. Our theoretical results provide valuable insights into assessing the advantages and limitations of existing pairwise learning methods.

Identification and Severity Determination of Wheat Stripe Rust and Wheat Leaf Rust Based on Hyperspectral Data Acquired Using a Black-Paper-Based Measuring Method

Science.gov (United States)

Ruan, Liu; Wang, Rui; Liu, Qi; Ma, Zhanhong; Li, Xiaolong; Cheng, Pei; Wang, Haiguang

2016-01-01

It is important to implement detection and assessment of plant diseases based on remotely sensed data for disease monitoring and control. Hyperspectral data of healthy leaves, leaves in incubation period and leaves in diseased period of wheat stripe rust and wheat leaf rust were collected under in-field conditions using a black-paper-based measuring method developed in this study. After data preprocessing, the models to identify the diseases were built using distinguished partial least squares (DPLS) and support vector machine (SVM), and the disease severity inversion models of stripe rust and the disease severity inversion models of leaf rust were built using quantitative partial least squares (QPLS) and support vector regression (SVR). All the models were validated by using leave-one-out cross validation and external validation. The diseases could be discriminated using both distinguished partial least squares and support vector machine with the accuracies of more than 99%. For each wheat rust, disease severity levels were accurately retrieved using both the optimal QPLS models and the optimal SVR models with the coefficients of determination (R2) of more than 0.90 and the root mean square errors (RMSE) of less than 0.15. The results demonstrated that identification and severity evaluation of stripe rust and leaf rust at the leaf level could be implemented based on the hyperspectral data acquired using the developed method. A scientific basis was provided for implementing disease monitoring by using aerial and space remote sensing technologies. PMID:27128464

Identification and Severity Determination of Wheat Stripe Rust and Wheat Leaf Rust Based on Hyperspectral Data Acquired Using a Black-Paper-Based Measuring Method.

Science.gov (United States)

Wang, Hui; Qin, Feng; Ruan, Liu; Wang, Rui; Liu, Qi; Ma, Zhanhong; Li, Xiaolong; Cheng, Pei; Wang, Haiguang

2016-01-01

It is important to implement detection and assessment of plant diseases based on remotely sensed data for disease monitoring and control. Hyperspectral data of healthy leaves, leaves in incubation period and leaves in diseased period of wheat stripe rust and wheat leaf rust were collected under in-field conditions using a black-paper-based measuring method developed in this study. After data preprocessing, the models to identify the diseases were built using distinguished partial least squares (DPLS) and support vector machine (SVM), and the disease severity inversion models of stripe rust and the disease severity inversion models of leaf rust were built using quantitative partial least squares (QPLS) and support vector regression (SVR). All the models were validated by using leave-one-out cross validation and external validation. The diseases could be discriminated using both distinguished partial least squares and support vector machine with the accuracies of more than 99%. For each wheat rust, disease severity levels were accurately retrieved using both the optimal QPLS models and the optimal SVR models with the coefficients of determination (R2) of more than 0.90 and the root mean square errors (RMSE) of less than 0.15. The results demonstrated that identification and severity evaluation of stripe rust and leaf rust at the leaf level could be implemented based on the hyperspectral data acquired using the developed method. A scientific basis was provided for implementing disease monitoring by using aerial and space remote sensing technologies.

Modeling of Temperature Effect on Modal Frequency of Concrete Beam Based on Field Monitoring Data

Directory of Open Access Journals (Sweden)

Wenchen Shan

2018-01-01

Full Text Available Temperature variation has been widely demonstrated to produce significant effect on modal frequencies that even exceed the effect of actual damage. In order to eliminate the temperature effect on modal frequency, an effective method is to construct quantitative models which accurately predict the modal frequency corresponding to temperature variation. In this paper, principal component analysis (PCA is conducted on the temperatures taken from all embedded thermocouples for extracting input parameters of regression models. Three regression-based numerical models using multiple linear regression (MLR, back-propagation neural network (BPNN, and support vector regression (SVR techniques are constructed to capture the relationships between modal frequencies and temperature distributions from measurements of a concrete beam during a period of forty days of monitoring. A comparison with respect to the performance of various optimally configured regression models has been performed on measurement data. Results indicate that the SVR exhibits a better reproduction and prediction capability than BPNN and MLR models for predicting the modal frequencies with respect to nonuniformly distributed temperatures. It is succeeded that temperature effects on modal frequencies can be effectively eliminated based on the optimally formulated SVR model.

A novel improved fuzzy support vector machine based stock price trend forecast model

OpenAIRE

Wang, Shuheng; Li, Guohao; Bao, Yifan

2018-01-01

Application of fuzzy support vector machine in stock price forecast. Support vector machine is a new type of machine learning method proposed in 1990s. It can deal with classification and regression problems very successfully. Due to the excellent learning performance of support vector machine, the technology has become a hot research topic in the field of machine learning, and it has been successfully applied in many fields. However, as a new technology, there are many limitations to support...

Pileup Subtraction and Jet Energy Prediction Using Machine Learning

OpenAIRE

Kong, Vein S; Li, Jiakun; Zhang, Yujia

2015-01-01

In the Large Hardron Collider (LHC), multiple proton-proton collisions cause pileup in reconstructing energy information for a single primary collision (jet). This project aims to select the most important features and create a model to accurately estimate jet energy. Different machine learning methods were explored, including linear regression, support vector regression and decision tree. The best result is obtained by linear regression with predictive features and the performance is improve...

MULGRES: a computer program for stepwise multiple regression analysis

Science.gov (United States)

A. Jeff Martin

1971-01-01

MULGRES is a computer program source deck that is designed for multiple regression analysis employing the technique of stepwise deletion in the search for most significant variables. The features of the program, along with inputs and outputs, are briefly described, with a note on machine compatibility.

Better Autologistic Regression

Directory of Open Access Journals (Sweden)

Mark A. Wolters

2017-11-01

Full Text Available Autologistic regression is an important probability model for dichotomous random variables observed along with covariate information. It has been used in various fields for analyzing binary data possessing spatial or network structure. The model can be viewed as an extension of the autologistic model (also known as the Ising model, quadratic exponential binary distribution, or Boltzmann machine to include covariates. It can also be viewed as an extension of logistic regression to handle responses that are not independent. Not all authors use exactly the same form of the autologistic regression model. Variations of the model differ in two respects. First, the variable coding—the two numbers used to represent the two possible states of the variables—might differ. Common coding choices are (zero, one and (minus one, plus one. Second, the model might appear in either of two algebraic forms: a standard form, or a recently proposed centered form. Little attention has been paid to the effect of these differences, and the literature shows ambiguity about their importance. It is shown here that changes to either coding or centering in fact produce distinct, non-nested probability models. Theoretical results, numerical studies, and analysis of an ecological data set all show that the differences among the models can be large and practically significant. Understanding the nature of the differences and making appropriate modeling choices can lead to significantly improved autologistic regression analyses. The results strongly suggest that the standard model with plus/minus coding, which we call the symmetric autologistic model, is the most natural choice among the autologistic variants.

Thorough statistical comparison of machine learning regression models and their ensembles for sub-pixel imperviousness and imperviousness change mapping

Directory of Open Access Journals (Sweden)

Drzewiecki Wojciech

2017-12-01

Full Text Available We evaluated the performance of nine machine learning regression algorithms and their ensembles for sub-pixel estimation of impervious areas coverages from Landsat imagery. The accuracy of imperviousness mapping in individual time points was assessed based on RMSE, MAE and R2. These measures were also used for the assessment of imperviousness change intensity estimations. The applicability for detection of relevant changes in impervious areas coverages at sub-pixel level was evaluated using overall accuracy, F-measure and ROC Area Under Curve. The results proved that Cubist algorithm may be advised for Landsat-based mapping of imperviousness for single dates. Stochastic gradient boosting of regression trees (GBM may be also considered for this purpose. However, Random Forest algorithm is endorsed for both imperviousness change detection and mapping of its intensity. In all applications the heterogeneous model ensembles performed at least as well as the best individual models or better. They may be recommended for improving the quality of sub-pixel imperviousness and imperviousness change mapping. The study revealed also limitations of the investigated methodology for detection of subtle changes of imperviousness inside the pixel. None of the tested approaches was able to reliably classify changed and non-changed pixels if the relevant change threshold was set as one or three percent. Also for fi ve percent change threshold most of algorithms did not ensure that the accuracy of change map is higher than the accuracy of random classifi er. For the threshold of relevant change set as ten percent all approaches performed satisfactory.

Thorough statistical comparison of machine learning regression models and their ensembles for sub-pixel imperviousness and imperviousness change mapping

Science.gov (United States)

Drzewiecki, Wojciech

2017-12-01

We evaluated the performance of nine machine learning regression algorithms and their ensembles for sub-pixel estimation of impervious areas coverages from Landsat imagery. The accuracy of imperviousness mapping in individual time points was assessed based on RMSE, MAE and R2. These measures were also used for the assessment of imperviousness change intensity estimations. The applicability for detection of relevant changes in impervious areas coverages at sub-pixel level was evaluated using overall accuracy, F-measure and ROC Area Under Curve. The results proved that Cubist algorithm may be advised for Landsat-based mapping of imperviousness for single dates. Stochastic gradient boosting of regression trees (GBM) may be also considered for this purpose. However, Random Forest algorithm is endorsed for both imperviousness change detection and mapping of its intensity. In all applications the heterogeneous model ensembles performed at least as well as the best individual models or better. They may be recommended for improving the quality of sub-pixel imperviousness and imperviousness change mapping. The study revealed also limitations of the investigated methodology for detection of subtle changes of imperviousness inside the pixel. None of the tested approaches was able to reliably classify changed and non-changed pixels if the relevant change threshold was set as one or three percent. Also for fi ve percent change threshold most of algorithms did not ensure that the accuracy of change map is higher than the accuracy of random classifi er. For the threshold of relevant change set as ten percent all approaches performed satisfactory.

Modelling daily dissolved oxygen concentration using least square support vector machine, multivariate adaptive regression splines and M5 model tree

Science.gov (United States)

Heddam, Salim; Kisi, Ozgur

2018-04-01

In the present study, three types of artificial intelligence techniques, least square support vector machine (LSSVM), multivariate adaptive regression splines (MARS) and M5 model tree (M5T) are applied for modeling daily dissolved oxygen (DO) concentration using several water quality variables as inputs. The DO concentration and water quality variables data from three stations operated by the United States Geological Survey (USGS) were used for developing the three models. The water quality data selected consisted of daily measured of water temperature (TE, °C), pH (std. unit), specific conductance (SC, μS/cm) and discharge (DI cfs), are used as inputs to the LSSVM, MARS and M5T models. The three models were applied for each station separately and compared to each other. According to the results obtained, it was found that: (i) the DO concentration could be successfully estimated using the three models and (ii) the best model among all others differs from one station to another.

Bayesian nonlinear regression for large small problems

KAUST Repository

Chakraborty, Sounak; Ghosh, Malay; Mallick, Bani K.

2012-01-01

Statistical modeling and inference problems with sample sizes substantially smaller than the number of available covariates are challenging. This is known as large p small n problem. Furthermore, the problem is more complicated when we have multiple correlated responses. We develop multivariate nonlinear regression models in this setup for accurate prediction. In this paper, we introduce a full Bayesian support vector regression model with Vapnik's ε-insensitive loss function, based on reproducing kernel Hilbert spaces (RKHS) under the multivariate correlated response setup. This provides a full probabilistic description of support vector machine (SVM) rather than an algorithm for fitting purposes. We have also introduced a multivariate version of the relevance vector machine (RVM). Instead of the original treatment of the RVM relying on the use of type II maximum likelihood estimates of the hyper-parameters, we put a prior on the hyper-parameters and use Markov chain Monte Carlo technique for computation. We have also proposed an empirical Bayes method for our RVM and SVM. Our methods are illustrated with a prediction problem in the near-infrared (NIR) spectroscopy. A simulation study is also undertaken to check the prediction accuracy of our models. © 2012 Elsevier Inc.

Bayesian nonlinear regression for large small problems

KAUST Repository

Chakraborty, Sounak

2012-07-01

Statistical modeling and inference problems with sample sizes substantially smaller than the number of available covariates are challenging. This is known as large p small n problem. Furthermore, the problem is more complicated when we have multiple correlated responses. We develop multivariate nonlinear regression models in this setup for accurate prediction. In this paper, we introduce a full Bayesian support vector regression model with Vapnik\\'s ε-insensitive loss function, based on reproducing kernel Hilbert spaces (RKHS) under the multivariate correlated response setup. This provides a full probabilistic description of support vector machine (SVM) rather than an algorithm for fitting purposes. We have also introduced a multivariate version of the relevance vector machine (RVM). Instead of the original treatment of the RVM relying on the use of type II maximum likelihood estimates of the hyper-parameters, we put a prior on the hyper-parameters and use Markov chain Monte Carlo technique for computation. We have also proposed an empirical Bayes method for our RVM and SVM. Our methods are illustrated with a prediction problem in the near-infrared (NIR) spectroscopy. A simulation study is also undertaken to check the prediction accuracy of our models. © 2012 Elsevier Inc.

Swarm Intelligence-Based Hybrid Models for Short-Term Power Load Prediction

Directory of Open Access Journals (Sweden)

Jianzhou Wang

2014-01-01

Full Text Available Swarm intelligence (SI is widely and successfully applied in the engineering field to solve practical optimization problems because various hybrid models, which are based on the SI algorithm and statistical models, are developed to further improve the predictive abilities. In this paper, hybrid intelligent forecasting models based on the cuckoo search (CS as well as the singular spectrum analysis (SSA, time series, and machine learning methods are proposed to conduct short-term power load prediction. The forecasting performance of the proposed models is augmented by a rolling multistep strategy over the prediction horizon. The test results are representative of the out-performance of the SSA and CS in tuning the seasonal autoregressive integrated moving average (SARIMA and support vector regression (SVR in improving load forecasting, which indicates that both the SSA-based data denoising and SI-based intelligent optimization strategy can effectively improve the model’s predictive performance. Additionally, the proposed CS-SSA-SARIMA and CS-SSA-SVR models provide very impressive forecasting results, demonstrating their strong robustness and universal forecasting capacities in terms of short-term power load prediction 24 hours in advance.

Source localization in an ocean waveguide using supervised machine learning.

Science.gov (United States)

Niu, Haiqiang; Reeves, Emma; Gerstoft, Peter

2017-09-01

Source localization in ocean acoustics is posed as a machine learning problem in which data-driven methods learn source ranges directly from observed acoustic data. The pressure received by a vertical linear array is preprocessed by constructing a normalized sample covariance matrix and used as the input for three machine learning methods: feed-forward neural networks (FNN), support vector machines (SVM), and random forests (RF). The range estimation problem is solved both as a classification problem and as a regression problem by these three machine learning algorithms. The results of range estimation for the Noise09 experiment are compared for FNN, SVM, RF, and conventional matched-field processing and demonstrate the potential of machine learning for underwater source localization.

Probability estimation with machine learning methods for dichotomous and multicategory outcome: theory.

Science.gov (United States)

Kruppa, Jochen; Liu, Yufeng; Biau, Gérard; Kohler, Michael; König, Inke R; Malley, James D; Ziegler, Andreas

2014-07-01

Probability estimation for binary and multicategory outcome using logistic and multinomial logistic regression has a long-standing tradition in biostatistics. However, biases may occur if the model is misspecified. In contrast, outcome probabilities for individuals can be estimated consistently with machine learning approaches, including k-nearest neighbors (k-NN), bagged nearest neighbors (b-NN), random forests (RF), and support vector machines (SVM). Because machine learning methods are rarely used by applied biostatisticians, the primary goal of this paper is to explain the concept of probability estimation with these methods and to summarize recent theoretical findings. Probability estimation in k-NN, b-NN, and RF can be embedded into the class of nonparametric regression learning machines; therefore, we start with the construction of nonparametric regression estimates and review results on consistency and rates of convergence. In SVMs, outcome probabilities for individuals are estimated consistently by repeatedly solving classification problems. For SVMs we review classification problem and then dichotomous probability estimation. Next we extend the algorithms for estimating probabilities using k-NN, b-NN, and RF to multicategory outcomes and discuss approaches for the multicategory probability estimation problem using SVM. In simulation studies for dichotomous and multicategory dependent variables we demonstrate the general validity of the machine learning methods and compare it with logistic regression. However, each method fails in at least one simulation scenario. We conclude with a discussion of the failures and give recommendations for selecting and tuning the methods. Applications to real data and example code are provided in a companion article (doi:10.1002/bimj.201300077). © 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Classifying machinery condition using oil samples and binary logistic regression

Science.gov (United States)

Phillips, J.; Cripps, E.; Lau, John W.; Hodkiewicz, M. R.

2015-08-01

The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically "black box" approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.

A comparison of machine learning techniques for predicting downstream acid mine drainage

CSIR Research Space (South Africa)

van Zyl, TL

2014-07-01

Full Text Available windowing approach over historical values to generate a prediction for the current value. We evaluate a number of Machine Learning techniques as regressors including Support Vector Regression, Random Forests, Stochastic Gradient Decent Regression, Linear...

Estimating transmitted waves of floating breakwater using support vector regression model

Digital Repository Service at National Institute of Oceanography (India)

Mandal, S.; Hegde, A.V.; Kumar, V.; Patil, S.G.

is first mapped onto an m-dimensional feature space using some fixed (nonlinear) mapping, and then a linear model is constructed in this feature space (Ivanciuc Ovidiu 2007). Using mathematical notation, the linear model in the feature space f(x, w... regressive vector machines, Ocean Engineering Journal, Vol – 36, pp 339 – 347, 2009. 3. Ivanciuc Ovidiu, Applications of support vector machines in chemistry, Review in Computational Chemistry, Eds K. B. Lipkouitz and T. R. Cundari, Vol – 23...

Continuous-variable quantum Gaussian process regression and quantum singular value decomposition of nonsparse low-rank matrices

Science.gov (United States)

Das, Siddhartha; Siopsis, George; Weedbrook, Christian

2018-02-01

With the significant advancement in quantum computation during the past couple of decades, the exploration of machine-learning subroutines using quantum strategies has become increasingly popular. Gaussian process regression is a widely used technique in supervised classical machine learning. Here we introduce an algorithm for Gaussian process regression using continuous-variable quantum systems that can be realized with technology based on photonic quantum computers under certain assumptions regarding distribution of data and availability of efficient quantum access. Our algorithm shows that by using a continuous-variable quantum computer a dramatic speedup in computing Gaussian process regression can be achieved, i.e., the possibility of exponentially reducing the time to compute. Furthermore, our results also include a continuous-variable quantum-assisted singular value decomposition method of nonsparse low rank matrices and forms an important subroutine in our Gaussian process regression algorithm.

Approximating prediction uncertainty for random forest regression models

Science.gov (United States)

John W. Coulston; Christine E. Blinn; Valerie A. Thomas; Randolph H. Wynne

2016-01-01

Machine learning approaches such as random forest have increased for the spatial modeling and mapping of continuous variables. Random forest is a non-parametric ensemble approach, and unlike traditional regression approaches there is no direct quantification of prediction error. Understanding prediction uncertainty is important when using model-based continuous maps as...

Precision Obtained Using an Artificial Neural Network for Predicting the Material Removal Rate in Ultrasonic Machining

Directory of Open Access Journals (Sweden)

Gaoyan Zhong

2017-12-01

Full Text Available The present study proposes a back propagation artificial neural network (BPANN to provide improved precision for predicting the material removal rate (MRR in ultrasonic machining. The BPANN benefits from the advantage of artificial neural networks (ANNs in dealing with complex input-output relationships without explicit mathematical functions. In our previous study, a conventional linear regression model and improved nonlinear regression model were established for modelling the MRR in ultrasonic machining to reflect the influence of machining parameters on process response. In the present work, we quantitatively compare the prediction precision obtained by the previously proposed regression models and the presently proposed BPANN model. The results of detailed analyses indicate that the BPANN model provided the highest prediction precision of the three models considered. The present work makes a positive contribution to expanding the applications of ANNs and can be considered as a guide for modelling complex problems of general machining.

Steganalysis using logistic regression

Science.gov (United States)

Lubenko, Ivans; Ker, Andrew D.

2011-02-01

We advocate Logistic Regression (LR) as an alternative to the Support Vector Machine (SVM) classifiers commonly used in steganalysis. LR offers more information than traditional SVM methods - it estimates class probabilities as well as providing a simple classification - and can be adapted more easily and efficiently for multiclass problems. Like SVM, LR can be kernelised for nonlinear classification, and it shows comparable classification accuracy to SVM methods. This work is a case study, comparing accuracy and speed of SVM and LR classifiers in detection of LSB Matching and other related spatial-domain image steganography, through the state-of-art 686-dimensional SPAM feature set, in three image sets.

Deep ensemble learning of sparse regression models for brain disease diagnosis.

Science.gov (United States)

Suk, Heung-Il; Lee, Seong-Whan; Shen, Dinggang

2017-04-01

Recent studies on brain imaging analysis witnessed the core roles of machine learning techniques in computer-assisted intervention for brain disease diagnosis. Of various machine-learning techniques, sparse regression models have proved their effectiveness in handling high-dimensional data but with a small number of training samples, especially in medical problems. In the meantime, deep learning methods have been making great successes by outperforming the state-of-the-art performances in various applications. In this paper, we propose a novel framework that combines the two conceptually different methods of sparse regression and deep learning for Alzheimer's disease/mild cognitive impairment diagnosis and prognosis. Specifically, we first train multiple sparse regression models, each of which is trained with different values of a regularization control parameter. Thus, our multiple sparse regression models potentially select different feature subsets from the original feature set; thereby they have different powers to predict the response values, i.e., clinical label and clinical scores in our work. By regarding the response values from our sparse regression models as target-level representations, we then build a deep convolutional neural network for clinical decision making, which thus we call 'Deep Ensemble Sparse Regression Network.' To our best knowledge, this is the first work that combines sparse regression models with deep neural network. In our experiments with the ADNI cohort, we validated the effectiveness of the proposed method by achieving the highest diagnostic accuracies in three classification tasks. We also rigorously analyzed our results and compared with the previous studies on the ADNI cohort in the literature. Copyright © 2017 Elsevier B.V. All rights reserved.

Predicting subject-driven actions and sensory experience in a virtual world with relevance vector machine regression of fMRI data.

Science.gov (United States)

Valente, Giancarlo; De Martino, Federico; Esposito, Fabrizio; Goebel, Rainer; Formisano, Elia

2011-05-15

In this work we illustrate the approach of the Maastricht Brain Imaging Center to the PBAIC 2007 competition, where participants had to predict, based on fMRI measurements of brain activity, subject driven actions and sensory experience in a virtual world. After standard pre-processing (slice scan time correction, motion correction), we generated rating predictions based on linear Relevance Vector Machine (RVM) learning from all brain voxels. Spatial and temporal filtering of the time series was optimized rating by rating. For some of the ratings (e.g. Instructions, Hits, Faces, Velocity), linear RVM regression was accurate and very consistent within and between subjects. For other ratings (e.g. Arousal, Valence) results were less satisfactory. Our approach ranked overall second. To investigate the role of different brain regions in ratings prediction we generated predictive maps, i.e. maps of the weighted contribution of each voxel to the predicted rating. These maps generally included (but were not limited to) "specialized" regions which are consistent with results from conventional neuroimaging studies and known functional neuroanatomy. In conclusion, Sparse Bayesian Learning models, such as RVM, appear to be a valuable approach to the multivariate regression of fMRI time series. The implementation of the Automatic Relevance Determination criterion is particularly suitable and provides a good generalization, despite the limited number of samples which is typically available in fMRI. Predictive maps allow disclosing multi-voxel patterns of brain activity that predict perceptual and behavioral subjective experience. Copyright © 2010 Elsevier Inc. All rights reserved.

Predicting the concentration of residual methanol in industrial formalin using machine learning

OpenAIRE

Heidkamp, William

2016-01-01

In this thesis, a machine learning approach was used to develop a predictive model for residual methanol concentration in industrial formalin produced at the Akzo Nobel factory in Kristinehamn, Sweden. The MATLABTM computational environment supplemented with the Statistics and Machine LearningTM toolbox from the MathWorks were used to test various machine learning algorithms on the formalin production data from Akzo Nobel. As a result, the Gaussian Process Regression algorithm was found to pr...

A Comparison of the Effects of K-Anonymity on Machine Learning Algorithms

OpenAIRE

Hayden Wimmer; Loreen Powell

2014-01-01

While research has been conducted in machine learning algorithms and in privacy preserving in data mining (PPDM), a gap in the literature exists which combines the aforementioned areas to determine how PPDM affects common machine learning algorithms. The aim of this research is to narrow this literature gap by investigating how a common PPDM algorithm, K-Anonymity, affects common machine learning and data mining algorithms, namely neural networks, logistic regression, decision trees, and Baye...

Modeling DNA affinity landscape through two-round support vector regression with weighted degree kernels

KAUST Repository

Wang, Xiaolei

2014-12-12

Background: A quantitative understanding of interactions between transcription factors (TFs) and their DNA binding sites is key to the rational design of gene regulatory networks. Recent advances in high-throughput technologies have enabled high-resolution measurements of protein-DNA binding affinity. Importantly, such experiments revealed the complex nature of TF-DNA interactions, whereby the effects of nucleotide changes on the binding affinity were observed to be context dependent. A systematic method to give high-quality estimates of such complex affinity landscapes is, thus, essential to the control of gene expression and the advance of synthetic biology. Results: Here, we propose a two-round prediction method that is based on support vector regression (SVR) with weighted degree (WD) kernels. In the first round, a WD kernel with shifts and mismatches is used with SVR to detect the importance of subsequences with different lengths at different positions. The subsequences identified as important in the first round are then fed into a second WD kernel to fit the experimentally measured affinities. To our knowledge, this is the first attempt to increase the accuracy of the affinity prediction by applying two rounds of string kernels and by identifying a small number of crucial k-mers. The proposed method was tested by predicting the binding affinity landscape of Gcn4p in Saccharomyces cerevisiae using datasets from HiTS-FLIP. Our method explicitly identified important subsequences and showed significant performance improvements when compared with other state-of-the-art methods. Based on the identified important subsequences, we discovered two surprisingly stable 10-mers and one sensitive 10-mer which were not reported before. Further test on four other TFs in S. cerevisiae demonstrated the generality of our method. Conclusion: We proposed in this paper a two-round method to quantitatively model the DNA binding affinity landscape. Since the ability to modify

A robust regression based on weighted LSSVM and penalized trimmed squares

International Nuclear Information System (INIS)

Liu, Jianyong; Wang, Yong; Fu, Chengqun; Guo, Jie; Yu, Qin

2016-01-01

Least squares support vector machine (LS-SVM) for nonlinear regression is sensitive to outliers in the field of machine learning. Weighted LS-SVM (WLS-SVM) overcomes this drawback by adding weight to each training sample. However, as the number of outliers increases, the accuracy of WLS-SVM may decrease. In order to improve the robustness of WLS-SVM, a new robust regression method based on WLS-SVM and penalized trimmed squares (WLSSVM–PTS) has been proposed. The algorithm comprises three main stages. The initial parameters are obtained by least trimmed squares at first. Then, the significant outliers are identified and eliminated by the Fast-PTS algorithm. The remaining samples with little outliers are estimated by WLS-SVM at last. The statistical tests of experimental results carried out on numerical datasets and real-world datasets show that the proposed WLSSVM–PTS is significantly robust than LS-SVM, WLS-SVM and LSSVM–LTS.

Support vector machine for diagnosis cancer disease: A comparative study

Directory of Open Access Journals (Sweden)

Nasser H. Sweilam

2010-12-01

Full Text Available Support vector machine has become an increasingly popular tool for machine learning tasks involving classification, regression or novelty detection. Training a support vector machine requires the solution of a very large quadratic programming problem. Traditional optimization methods cannot be directly applied due to memory restrictions. Up to now, several approaches exist for circumventing the above shortcomings and work well. Another learning algorithm, particle swarm optimization, Quantum-behave Particle Swarm for training SVM is introduced. Another approach named least square support vector machine (LSSVM and active set strategy are introduced. The obtained results by these methods are tested on a breast cancer dataset and compared with the exact solution model problem.

Modeling Personalized Email Prioritization: Classification-based and Regression-based Approaches

Energy Technology Data Exchange (ETDEWEB)

Yoo S.; Yang, Y.; Carbonell, J.

2011-10-24

Email overload, even after spam filtering, presents a serious productivity challenge for busy professionals and executives. One solution is automated prioritization of incoming emails to ensure the most important are read and processed quickly, while others are processed later as/if time permits in declining priority levels. This paper presents a study of machine learning approaches to email prioritization into discrete levels, comparing ordinal regression versus classier cascades. Given the ordinal nature of discrete email priority levels, SVM ordinal regression would be expected to perform well, but surprisingly a cascade of SVM classifiers significantly outperforms ordinal regression for email prioritization. In contrast, SVM regression performs well -- better than classifiers -- on selected UCI data sets. This unexpected performance inversion is analyzed and results are presented, providing core functionality for email prioritization systems.

A comparison of six metamodeling techniques applied to building performance simulations

DEFF Research Database (Denmark)

Østergård, Torben; Jensen, Rasmus Lund; Maagaard, Steffen Enersen

2018-01-01

Highlights •Linear regression (OLS), support vector regression (SVR), regression splines (MARS). •Random forest (RF), Gaussian processes (GPR), neural network (NN). •Accuracy, time, interpretability, ease-of-use, model selection, and robustness. •13 problems modelled for 9 training set sizes...

Support vector machine regression (LS-SVM)--an alternative to artificial neural networks (ANNs) for the analysis of quantum chemistry data?

Science.gov (United States)

Balabin, Roman M; Lomakina, Ekaterina I

2011-06-28

A multilayer feed-forward artificial neural network (MLP-ANN) with a single, hidden layer that contains a finite number of neurons can be regarded as a universal non-linear approximator. Today, the ANN method and linear regression (MLR) model are widely used for quantum chemistry (QC) data analysis (e.g., thermochemistry) to improve their accuracy (e.g., Gaussian G2-G4, B3LYP/B3-LYP, X1, or W1 theoretical methods). In this study, an alternative approach based on support vector machines (SVMs) is used, the least squares support vector machine (LS-SVM) regression. It has been applied to ab initio (first principle) and density functional theory (DFT) quantum chemistry data. So, QC + SVM methodology is an alternative to QC + ANN one. The task of the study was to estimate the Møller-Plesset (MPn) or DFT (B3LYP, BLYP, BMK) energies calculated with large basis sets (e.g., 6-311G(3df,3pd)) using smaller ones (6-311G, 6-311G*, 6-311G**) plus molecular descriptors. A molecular set (BRM-208) containing a total of 208 organic molecules was constructed and used for the LS-SVM training, cross-validation, and testing. MP2, MP3, MP4(DQ), MP4(SDQ), and MP4/MP4(SDTQ) ab initio methods were tested. Hartree-Fock (HF/SCF) results were also reported for comparison. Furthermore, constitutional (CD: total number of atoms and mole fractions of different atoms) and quantum-chemical (QD: HOMO-LUMO gap, dipole moment, average polarizability, and quadrupole moment) molecular descriptors were used for the building of the LS-SVM calibration model. Prediction accuracies (MADs) of 1.62 ± 0.51 and 0.85 ± 0.24 kcal mol(-1) (1 kcal mol(-1) = 4.184 kJ mol(-1)) were reached for SVM-based approximations of ab initio and DFT energies, respectively. The LS-SVM model was more accurate than the MLR model. A comparison with the artificial neural network approach shows that the accuracy of the LS-SVM method is similar to the accuracy of ANN. The extrapolation and interpolation results show that LS-SVM is

Empirical model for estimating the surface roughness of machined ...

African Journals Online (AJOL)

Empirical model for estimating the surface roughness of machined ... as well as surface finish is one of the most critical quality measure in mechanical products. ... various cutting speed have been developed using regression analysis software.

Machine-z: Rapid Machine-Learned Redshift Indicator for Swift Gamma-Ray Bursts

Science.gov (United States)

Ukwatta, T. N.; Wozniak, P. R.; Gehrels, N.

2016-01-01

Studies of high-redshift gamma-ray bursts (GRBs) provide important information about the early Universe such as the rates of stellar collapsars and mergers, the metallicity content, constraints on the re-ionization period, and probes of the Hubble expansion. Rapid selection of high-z candidates from GRB samples reported in real time by dedicated space missions such as Swift is the key to identifying the most distant bursts before the optical afterglow becomes too dim to warrant a good spectrum. Here, we introduce 'machine-z', a redshift prediction algorithm and a 'high-z' classifier for Swift GRBs based on machine learning. Our method relies exclusively on canonical data commonly available within the first few hours after the GRB trigger. Using a sample of 284 bursts with measured redshifts, we trained a randomized ensemble of decision trees (random forest) to perform both regression and classification. Cross-validated performance studies show that the correlation coefficient between machine-z predictions and the true redshift is nearly 0.6. At the same time, our high-z classifier can achieve 80 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve approximately 100 per cent recall. The most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.

Machine Learning Principles Can Improve Hip Fracture Prediction

DEFF Research Database (Denmark)

Kruse, Christian; Eiken, Pia; Vestergaard, Peter

2017-01-01

Apply machine learning principles to predict hip fractures and estimate predictor importance in Dual-energy X-ray absorptiometry (DXA)-scanned men and women. Dual-energy X-ray absorptiometry data from two Danish regions between 1996 and 2006 were combined with national Danish patient data.......89 [0.82; 0.95], but with poor calibration in higher probabilities. A ten predictor subset (BMD, biochemical cholesterol and liver function tests, penicillin use and osteoarthritis diagnoses) achieved a test AUC of 0.86 [0.78; 0.94] using an “xgbTree” model. Machine learning can improve hip fracture...... prediction beyond logistic regression using ensemble models. Compiling data from international cohorts of longer follow-up and performing similar machine learning procedures has the potential to further improve discrimination and calibration....

Identifying Environmental and Social Factors Predisposing to Pathological Gambling Combining Standard Logistic Regression and Logic Learning Machine.

Science.gov (United States)

Parodi, Stefano; Dosi, Corrado; Zambon, Antonella; Ferrari, Enrico; Muselli, Marco

2017-12-01

Identifying potential risk factors for problem gambling (PG) is of primary importance for planning preventive and therapeutic interventions. We illustrate a new approach based on the combination of standard logistic regression and an innovative method of supervised data mining (Logic Learning Machine or LLM). Data were taken from a pilot cross-sectional study to identify subjects with PG behaviour, assessed by two internationally validated scales (SOGS and Lie/Bet). Information was obtained from 251 gamblers recruited in six betting establishments. Data on socio-demographic characteristics, lifestyle and cognitive-related factors, and type, place and frequency of preferred gambling were obtained by a self-administered questionnaire. The following variables associated with PG were identified: instant gratification games, alcohol abuse, cognitive distortion, illegal behaviours and having started gambling with a relative or a friend. Furthermore, the combination of LLM and LR indicated the presence of two different types of PG, namely: (a) daily gamblers, more prone to illegal behaviour, with poor money management skills and who started gambling at an early age, and (b) non-daily gamblers, characterised by superstitious beliefs and a higher preference for immediate reward games. Finally, instant gratification games were strongly associated with the number of games usually played. Studies on gamblers habitually frequently betting shops are rare. The finding of different types of PG by habitual gamblers deserves further analysis in larger studies. Advanced data mining algorithms, like LLM, are powerful tools and potentially useful in identifying risk factors for PG.

An Integrated Approach to Battery Health Monitoring using Bayesian Regression, Classification and State Estimation

Data.gov (United States)

National Aeronautics and Space Administration — The application of the Bayesian theory of managing uncertainty and complexity to regression and classification in the form of Relevance Vector Machine (RVM), and to...

Support vector machines optimization based theory, algorithms, and extensions

CERN Document Server

Deng, Naiyang; Zhang, Chunhua

2013-01-01

Support Vector Machines: Optimization Based Theory, Algorithms, and Extensions presents an accessible treatment of the two main components of support vector machines (SVMs)-classification problems and regression problems. The book emphasizes the close connection between optimization theory and SVMs since optimization is one of the pillars on which SVMs are built.The authors share insight on many of their research achievements. They give a precise interpretation of statistical leaning theory for C-support vector classification. They also discuss regularized twi

An IL28B genotype-based clinical prediction model for treatment of chronic hepatitis C.

Directory of Open Access Journals (Sweden)

Thomas R O'Brien

Full Text Available Genetic variation in IL28B and other factors are associated with sustained virological response (SVR after pegylated-interferon/ribavirin treatment for chronic hepatitis C (CHC. Using data from the HALT-C Trial, we developed a model to predict a patient's probability of SVR based on IL28B genotype and clinical variables.HALT-C enrolled patients with advanced CHC who had failed previous interferon-based treatment. Subjects were re-treated with pegylated-interferon/ribavirin during trial lead-in. We used step-wise logistic regression to calculate adjusted odds ratios (aOR and create the predictive model. Leave-one-out cross-validation was used to predict a priori probabilities of SVR and determine area under the receiver operator characteristics curve (AUC.Among 646 HCV genotype 1-infected European American patients, 14.2% achieved SVR. IL28B rs12979860-CC genotype was the strongest predictor of SVR (aOR, 7.56; p10% (43.3% of subjects had an SVR rate of 27.9% and accounted for 84.8% of subjects actually achieving SVR. To verify that consideration of both IL28B genotype and clinical variables is required for treatment decisions, we calculated AUC values from published data for the IDEAL Study.A clinical prediction model based on IL28B genotype and clinical variables can yield useful individualized predictions of the probability of treatment success that could increase SVR rates and decrease the frequency of futile treatment among patients with CHC.

An alternative approach to the determination of scaling law expressions for the L–H transition in Tokamaks utilizing classification tools instead of regression

International Nuclear Information System (INIS)

Gaudio, P; Gelfusa, M; Lupelli, I; Murari, A; Vega, J

2014-01-01

A new approach to determine the power law expressions for the threshold between the H and L mode of confinement is presented. The method is based on two powerful machine learning tools for classification: neural networks and support vector machines. Using as inputs clear examples of the systems on either side of the transition, the machine learning tools learn the input–output mapping corresponding to the equations of the boundary separating the confinement regimes. Systematic tests with synthetic data show that the machine learning tools provide results competitive with traditional statistical regression and more robust against random noise and systematic errors. The developed tools have then been applied to the multi-machine International Tokamak Physics Activity International Global Threshold Database of validated ITER-like Tokamak discharges. The machine learning tools converge on the same scaling law parameters obtained with non-linear regression. On the other hand, the developed tools allow a reduction of 50% of the uncertainty in the extrapolations to ITER. Therefore the proposed approach can effectively complement traditional regression since its application poses much less stringent requirements on the experimental data, to be used to determine the scaling laws, because they do not require examples exactly at the moment of the transition. (paper)

Runtime Optimizations for Tree-Based Machine Learning Models

NARCIS (Netherlands)

N. Asadi; J.J.P. Lin (Jimmy); A.P. de Vries (Arjen)

2014-01-01

htmlabstractTree-based models have proven to be an effective solution for web ranking as well as other machine learning problems in diverse domains. This paper focuses on optimizing the runtime performance of applying such models to make predictions, specifically using gradient-boosted regression

Multivariate Linear Regression and CART Regression Analysis of TBM Performance at Abu Hamour Phase-I Tunnel

Science.gov (United States)

Jakubowski, J.; Stypulkowski, J. B.; Bernardeau, F. G.

2017-12-01

The first phase of the Abu Hamour drainage and storm tunnel was completed in early 2017. The 9.5 km long, 3.7 m diameter tunnel was excavated with two Earth Pressure Balance (EPB) Tunnel Boring Machines from Herrenknecht. TBM operation processes were monitored and recorded by Data Acquisition and Evaluation System. The authors coupled collected TBM drive data with available information on rock mass properties, cleansed, completed with secondary variables and aggregated by weeks and shifts. Correlations and descriptive statistics charts were examined. Multivariate Linear Regression and CART regression tree models linking TBM penetration rate (PR), penetration per revolution (PPR) and field penetration index (FPI) with TBM operational and geotechnical characteristics were performed for the conditions of the weak/soft rock of Doha. Both regression methods are interpretable and the data were screened with different computational approaches allowing enriched insight. The primary goal of the analysis was to investigate empirical relations between multiple explanatory and responding variables, to search for best subsets of explanatory variables and to evaluate the strength of linear and non-linear relations. For each of the penetration indices, a predictive model coupling both regression methods was built and validated. The resultant models appeared to be stronger than constituent ones and indicated an opportunity for more accurate and robust TBM performance predictions.

Machine learning enhanced optical distance sensor

Science.gov (United States)

Amin, M. Junaid; Riza, N. A.

2018-01-01

Presented for the first time is a machine learning enhanced optical distance sensor. The distance sensor is based on our previously demonstrated distance measurement technique that uses an Electronically Controlled Variable Focus Lens (ECVFL) with a laser source to illuminate a target plane with a controlled optical beam spot. This spot with varying spot sizes is viewed by an off-axis camera and the spot size data is processed to compute the distance. In particular, proposed and demonstrated in this paper is the use of a regularized polynomial regression based supervised machine learning algorithm to enhance the accuracy of the operational sensor. The algorithm uses the acquired features and corresponding labels that are the actual target distance values to train a machine learning model. The optimized training model is trained over a 1000 mm (or 1 m) experimental target distance range. Using the machine learning algorithm produces a training set and testing set distance measurement errors of learning. Applications for the proposed sensor include industrial scenario distance sensing where target material specific training models can be generated to realize low <1% measurement error distance measurements.

Robust analysis of trends in noisy tokamak confinement data using geodesic least squares regression

Energy Technology Data Exchange (ETDEWEB)

Verdoolaege, G., E-mail: geert.verdoolaege@ugent.be [Department of Applied Physics, Ghent University, B-9000 Ghent (Belgium); Laboratory for Plasma Physics, Royal Military Academy, B-1000 Brussels (Belgium); Shabbir, A. [Department of Applied Physics, Ghent University, B-9000 Ghent (Belgium); Max Planck Institute for Plasma Physics, Boltzmannstr. 2, 85748 Garching (Germany); Hornung, G. [Department of Applied Physics, Ghent University, B-9000 Ghent (Belgium)

2016-11-15

Regression analysis is a very common activity in fusion science for unveiling trends and parametric dependencies, but it can be a difficult matter. We have recently developed the method of geodesic least squares (GLS) regression that is able to handle errors in all variables, is robust against data outliers and uncertainty in the regression model, and can be used with arbitrary distribution models and regression functions. We here report on first results of application of GLS to estimation of the multi-machine scaling law for the energy confinement time in tokamaks, demonstrating improved consistency of the GLS results compared to standard least squares.

Soft computing techniques toward modeling the water supplies of Cyprus.

Science.gov (United States)

Iliadis, L; Maris, F; Tachos, S

2011-10-01

This research effort aims in the application of soft computing techniques toward water resources management. More specifically, the target is the development of reliable soft computing models capable of estimating the water supply for the case of "Germasogeia" mountainous watersheds in Cyprus. Initially, ε-Regression Support Vector Machines (ε-RSVM) and fuzzy weighted ε-RSVMR models have been developed that accept five input parameters. At the same time, reliable artificial neural networks have been developed to perform the same job. The 5-fold cross validation approach has been employed in order to eliminate bad local behaviors and to produce a more representative training data set. Thus, the fuzzy weighted Support Vector Regression (SVR) combined with the fuzzy partition has been employed in an effort to enhance the quality of the results. Several rational and reliable models have been produced that can enhance the efficiency of water policy designers. Copyright © 2011 Elsevier Ltd. All rights reserved.

High Resolution Mapping of Soil Properties Using Remote Sensing Variables in South-Western Burkina Faso: A Comparison of Machine Learning and Multiple Linear Regression Models.

Science.gov (United States)

Forkuor, Gerald; Hounkpatin, Ozias K L; Welp, Gerhard; Thiel, Michael

2017-01-01

Accurate and detailed spatial soil information is essential for environmental modelling, risk assessment and decision making. The use of Remote Sensing data as secondary sources of information in digital soil mapping has been found to be cost effective and less time consuming compared to traditional soil mapping approaches. But the potentials of Remote Sensing data in improving knowledge of local scale soil information in West Africa have not been fully explored. This study investigated the use of high spatial resolution satellite data (RapidEye and Landsat), terrain/climatic data and laboratory analysed soil samples to map the spatial distribution of six soil properties-sand, silt, clay, cation exchange capacity (CEC), soil organic carbon (SOC) and nitrogen-in a 580 km2 agricultural watershed in south-western Burkina Faso. Four statistical prediction models-multiple linear regression (MLR), random forest regression (RFR), support vector machine (SVM), stochastic gradient boosting (SGB)-were tested and compared. Internal validation was conducted by cross validation while the predictions were validated against an independent set of soil samples considering the modelling area and an extrapolation area. Model performance statistics revealed that the machine learning techniques performed marginally better than the MLR, with the RFR providing in most cases the highest accuracy. The inability of MLR to handle non-linear relationships between dependent and independent variables was found to be a limitation in accurately predicting soil properties at unsampled locations. Satellite data acquired during ploughing or early crop development stages (e.g. May, June) were found to be the most important spectral predictors while elevation, temperature and precipitation came up as prominent terrain/climatic variables in predicting soil properties. The results further showed that shortwave infrared and near infrared channels of Landsat8 as well as soil specific indices of redness

Machine learning approaches to the social determinants of health in the health and retirement study.

Science.gov (United States)

Seligman, Benjamin; Tuljapurkar, Shripad; Rehkopf, David

2018-04-01

Social and economic factors are important predictors of health and of recognized importance for health systems. However, machine learning, used elsewhere in the biomedical literature, has not been extensively applied to study relationships between society and health. We investigate how machine learning may add to our understanding of social determinants of health using data from the Health and Retirement Study. A linear regression of age and gender, and a parsimonious theory-based regression additionally incorporating income, wealth, and education, were used to predict systolic blood pressure, body mass index, waist circumference, and telomere length. Prediction, fit, and interpretability were compared across four machine learning methods: linear regression, penalized regressions, random forests, and neural networks. All models had poor out-of-sample prediction. Most machine learning models performed similarly to the simpler models. However, neural networks greatly outperformed the three other methods. Neural networks also had good fit to the data ( R 2 between 0.4-0.6, versus learning models, nine variables were frequently selected or highly weighted as predictors: dental visits, current smoking, self-rated health, serial-seven subtractions, probability of receiving an inheritance, probability of leaving an inheritance of at least $10,000, number of children ever born, African-American race, and gender. Some of the machine learning methods do not improve prediction or fit beyond simpler models, however, neural networks performed well. The predictors identified across models suggest underlying social factors that are important predictors of biological indicators of chronic disease, and that the non-linear and interactive relationships between variables fundamental to the neural network approach may be important to consider.

Sample-Based Extreme Learning Machine with Missing Data

Directory of Open Access Journals (Sweden)

Hang Gao

2015-01-01

Full Text Available Extreme learning machine (ELM has been extensively studied in machine learning community during the last few decades due to its high efficiency and the unification of classification, regression, and so forth. Though bearing such merits, existing ELM algorithms cannot efficiently handle the issue of missing data, which is relatively common in practical applications. The problem of missing data is commonly handled by imputation (i.e., replacing missing values with substituted values according to available information. However, imputation methods are not always effective. In this paper, we propose a sample-based learning framework to address this issue. Based on this framework, we develop two sample-based ELM algorithms for classification and regression, respectively. Comprehensive experiments have been conducted in synthetic data sets, UCI benchmark data sets, and a real world fingerprint image data set. As indicated, without introducing extra computational complexity, the proposed algorithms do more accurate and stable learning than other state-of-the-art ones, especially in the case of higher missing ratio.

Modelling tick abundance using machine learning techniques and satellite imagery

DEFF Research Database (Denmark)

Kjær, Lene Jung; Korslund, L.; Kjelland, V.

satellite images to run Boosted Regression Tree machine learning algorithms to predict overall distribution (presence/absence of ticks) and relative tick abundance of nymphs and larvae in southern Scandinavia. For nymphs, the predicted abundance had a positive correlation with observed abundance...... the predicted distribution of larvae was mostly even throughout Denmark, it was primarily around the coastlines in Norway and Sweden. Abundance was fairly low overall except in some fragmented patches corresponding to forested habitats in the region. Machine learning techniques allow us to predict for larger...... the collected ticks for pathogens and using the same machine learning techniques to develop prevalence maps of the ScandTick region....

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks

OpenAIRE

Rui Zhao; Ruqiang Yan; Jinjiang Wang; Kezhi Mao

2017-01-01

In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression mode...

Exploring prediction uncertainty of spatial data in geostatistical and machine learning Approaches

Science.gov (United States)

Klump, J. F.; Fouedjio, F.

2017-12-01

Geostatistical methods such as kriging with external drift as well as machine learning techniques such as quantile regression forest have been intensively used for modelling spatial data. In addition to providing predictions for target variables, both approaches are able to deliver a quantification of the uncertainty associated with the prediction at a target location. Geostatistical approaches are, by essence, adequate for providing such prediction uncertainties and their behaviour is well understood. However, they often require significant data pre-processing and rely on assumptions that are rarely met in practice. Machine learning algorithms such as random forest regression, on the other hand, require less data pre-processing and are non-parametric. This makes the application of machine learning algorithms to geostatistical problems an attractive proposition. The objective of this study is to compare kriging with external drift and quantile regression forest with respect to their ability to deliver reliable prediction uncertainties of spatial data. In our comparison we use both simulated and real world datasets. Apart from classical performance indicators, comparisons make use of accuracy plots, probability interval width plots, and the visual examinations of the uncertainty maps provided by the two approaches. By comparing random forest regression to kriging we found that both methods produced comparable maps of estimated values for our variables of interest. However, the measure of uncertainty provided by random forest seems to be quite different to the measure of uncertainty provided by kriging. In particular, the lack of spatial context can give misleading results in areas without ground truth data. These preliminary results raise questions about assessing the risks associated with decisions based on the predictions from geostatistical and machine learning algorithms in a spatial context, e.g. mineral exploration.

Improving sub-pixel imperviousness change prediction by ensembling heterogeneous non-linear regression models

Science.gov (United States)

Drzewiecki, Wojciech

2016-12-01

In this work nine non-linear regression models were compared for sub-pixel impervious surface area mapping from Landsat images. The comparison was done in three study areas both for accuracy of imperviousness coverage evaluation in individual points in time and accuracy of imperviousness change assessment. The performance of individual machine learning algorithms (Cubist, Random Forest, stochastic gradient boosting of regression trees, k-nearest neighbors regression, random k-nearest neighbors regression, Multivariate Adaptive Regression Splines, averaged neural networks, and support vector machines with polynomial and radial kernels) was also compared with the performance of heterogeneous model ensembles constructed from the best models trained using particular techniques. The results proved that in case of sub-pixel evaluation the most accurate prediction of change may not necessarily be based on the most accurate individual assessments. When single methods are considered, based on obtained results Cubist algorithm may be advised for Landsat based mapping of imperviousness for single dates. However, Random Forest may be endorsed when the most reliable evaluation of imperviousness change is the primary goal. It gave lower accuracies for individual assessments, but better prediction of change due to more correlated errors of individual predictions. Heterogeneous model ensembles performed for individual time points assessments at least as well as the best individual models. In case of imperviousness change assessment the ensembles always outperformed single model approaches. It means that it is possible to improve the accuracy of sub-pixel imperviousness change assessment using ensembles of heterogeneous non-linear regression models.

Exploring Machine Learning to Correct Satellite-Derived Sea Surface Temperatures

Directory of Open Access Journals (Sweden)

Stéphane Saux Picart

2018-02-01

Full Text Available Machine learning techniques are attractive tools to establish statistical models with a high degree of non linearity. They require a large amount of data to be trained and are therefore particularly suited to analysing remote sensing data. This work is an attempt at using advanced statistical methods of machine learning to predict the bias between Sea Surface Temperature (SST derived from infrared remote sensing and ground “truth” from drifting buoy measurements. A large dataset of collocation between satellite SST and in situ SST is explored. Four regression models are used: Simple multi-linear regression, Least Square Shrinkage and Selection Operator (LASSO, Generalised Additive Model (GAM and random forest. In the case of geostationary satellites for which a large number of collocations is available, results show that the random forest model is the best model to predict the systematic errors and it is computationally fast, making it a good candidate for operational processing. It is able to explain nearly 31% of the total variance of the bias (in comparison to about 24% for the multi-linear regression model.

Predicting Antitumor Activity of Peptides by Consensus of Regression Models Trained on a Small Data Sample

Directory of Open Access Journals (Sweden)

Ivanka Jerić

2011-11-01

Full Text Available Predicting antitumor activity of compounds using regression models trained on a small number of compounds with measured biological activity is an ill-posed inverse problem. Yet, it occurs very often within the academic community. To counteract, up to some extent, overfitting problems caused by a small training data, we propose to use consensus of six regression models for prediction of biological activity of virtual library of compounds. The QSAR descriptors of 22 compounds related to the opioid growth factor (OGF, Tyr-Gly-Gly-Phe-Met with known antitumor activity were used to train regression models: the feed-forward artificial neural network, the k-nearest neighbor, sparseness constrained linear regression, the linear and nonlinear (with polynomial and Gaussian kernel support vector machine. Regression models were applied on a virtual library of 429 compounds that resulted in six lists with candidate compounds ranked by predicted antitumor activity. The highly ranked candidate compounds were synthesized, characterized and tested for an antiproliferative activity. Some of prepared peptides showed more pronounced activity compared with the native OGF; however, they were less active than highly ranked compounds selected previously by the radial basis function support vector machine (RBF SVM regression model. The ill-posedness of the related inverse problem causes unstable behavior of trained regression models on test data. These results point to high complexity of prediction based on the regression models trained on a small data sample.

Fusing Data Mining, Machine Learning and Traditional Statistics to Detect Biomarkers Associated with Depression

Science.gov (United States)

Dipnall, Joanna F.

2016-01-01

Background Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study. Methods The study used a three-step methodology amalgamating multiple imputation, a machine learning boosted regression algorithm and logistic regression, to identify key biomarkers associated with depression in the National Health and Nutrition Examination Study (2009–2010). Depression was measured using the Patient Health Questionnaire-9 and 67 biomarkers were analysed. Covariates in this study included gender, age, race, smoking, food security, Poverty Income Ratio, Body Mass Index, physical activity, alcohol use, medical conditions and medications. The final imputed weighted multiple logistic regression model included possible confounders and moderators. Results After the creation of 20 imputation data sets from multiple chained regression sequences, machine learning boosted regression initially identified 21 biomarkers associated with depression. Using traditional logistic regression methods, including controlling for possible confounders and moderators, a final set of three biomarkers were selected. The final three biomarkers from the novel hybrid variable selection methodology were red cell distribution width (OR 1.15; 95% CI 1.01, 1.30), serum glucose (OR 1.01; 95% CI 1.00, 1.01) and total bilirubin (OR 0.12; 95% CI 0.05, 0.28). Significant interactions were found between total bilirubin with Mexican American/Hispanic group (p = 0.016), and current smokers (p<0.001). Conclusion The systematic use of a hybrid methodology for variable selection, fusing data mining techniques using a machine learning algorithm with traditional statistical modelling, accounted for missing data and

Fusing Data Mining, Machine Learning and Traditional Statistics to Detect Biomarkers Associated with Depression.

Directory of Open Access Journals (Sweden)

Joanna F Dipnall

Full Text Available Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study.The study used a three-step methodology amalgamating multiple imputation, a machine learning boosted regression algorithm and logistic regression, to identify key biomarkers associated with depression in the National Health and Nutrition Examination Study (2009-2010. Depression was measured using the Patient Health Questionnaire-9 and 67 biomarkers were analysed. Covariates in this study included gender, age, race, smoking, food security, Poverty Income Ratio, Body Mass Index, physical activity, alcohol use, medical conditions and medications. The final imputed weighted multiple logistic regression model included possible confounders and moderators.After the creation of 20 imputation data sets from multiple chained regression sequences, machine learning boosted regression initially identified 21 biomarkers associated with depression. Using traditional logistic regression methods, including controlling for possible confounders and moderators, a final set of three biomarkers were selected. The final three biomarkers from the novel hybrid variable selection methodology were red cell distribution width (OR 1.15; 95% CI 1.01, 1.30, serum glucose (OR 1.01; 95% CI 1.00, 1.01 and total bilirubin (OR 0.12; 95% CI 0.05, 0.28. Significant interactions were found between total bilirubin with Mexican American/Hispanic group (p = 0.016, and current smokers (p<0.001.The systematic use of a hybrid methodology for variable selection, fusing data mining techniques using a machine learning algorithm with traditional statistical modelling, accounted for missing data and complex survey sampling

Investigation of Pear Drying Performance by Different Methods and Regression of Convective Heat Transfer Coefficient with Support Vector Machine

Directory of Open Access Journals (Sweden)

Mehmet Das

2018-01-01

Full Text Available In this study, an air heated solar collector (AHSC dryer was designed to determine the drying characteristics of the pear. Flat pear slices of 10 mm thickness were used in the experiments. The pears were dried both in the AHSC dryer and under the sun. Panel glass temperature, panel floor temperature, panel inlet temperature, panel outlet temperature, drying cabinet inlet temperature, drying cabinet outlet temperature, drying cabinet temperature, drying cabinet moisture, solar radiation, pear internal temperature, air velocity and mass loss of pear were measured at 30 min intervals. Experiments were carried out during the periods of June 2017 in Elazig, Turkey. The experiments started at 8:00 a.m. and continued till 18:00. The experiments were continued until the weight changes in the pear slices stopped. Wet basis moisture content (MCw, dry basis moisture content (MCd, adjustable moisture ratio (MR, drying rate (DR, and convective heat transfer coefficient (hc were calculated with both in the AHSC dryer and the open sun drying experiment data. It was found that the values of hc in both drying systems with a range 12.4 and 20.8 W/m2 °C. Three different kernel models were used in the support vector machine (SVM regression to construct the predictive model of the calculated hc values for both systems. The mean absolute error (MAE, root mean squared error (RMSE, relative absolute error (RAE and root relative absolute error (RRAE analysis were performed to indicate the predictive model’s accuracy. As a result, the rate of drying of the pear was examined for both systems and it was observed that the pear had dried earlier in the AHSC drying system. A predictive model was obtained using the SVM regression for the calculated hc values for the pear in the AHSC drying system. The normalized polynomial kernel was determined as the best kernel model in SVM for estimating the hc values.

Analysis of machining and machine tools

CERN Document Server

Liang, Steven Y

2016-01-01

This book delivers the fundamental science and mechanics of machining and machine tools by presenting systematic and quantitative knowledge in the form of process mechanics and physics. It gives readers a solid command of machining science and engineering, and familiarizes them with the geometry and functionality requirements of creating parts and components in today’s markets. The authors address traditional machining topics, such as: single and multiple point cutting processes grinding components accuracy and metrology shear stress in cutting cutting temperature and analysis chatter They also address non-traditional machining, such as: electrical discharge machining electrochemical machining laser and electron beam machining A chapter on biomedical machining is also included. This book is appropriate for advanced undergraduate and graduate mechani cal engineering students, manufacturing engineers, and researchers. Each chapter contains examples, exercises and their solutions, and homework problems that re...

Kernel Methods for Machine Learning with Life Science Applications

DEFF Research Database (Denmark)

Abrahamsen, Trine Julie

Kernel methods refer to a family of widely used nonlinear algorithms for machine learning tasks like classification, regression, and feature extraction. By exploiting the so-called kernel trick straightforward extensions of classical linear algorithms are enabled as long as the data only appear a...

Random Forest as a Predictive Analytics Alternative to Regression in Institutional Research

Science.gov (United States)

He, Lingjun; Levine, Richard A.; Fan, Juanjuan; Beemer, Joshua; Stronach, Jeanne

2018-01-01

In institutional research, modern data mining approaches are seldom considered to address predictive analytics problems. The goal of this paper is to highlight the advantages of tree-based machine learning algorithms over classic (logistic) regression methods for data-informed decision making in higher education problems, and stress the success of…

A review of machine learning in obesity.

Science.gov (United States)

DeGregory, K W; Kuiper, P; DeSilvio, T; Pleuss, J D; Miller, R; Roginski, J W; Fisher, C B; Harness, D; Viswanath, S; Heymsfield, S B; Dungan, I; Thomas, D M

2018-05-01

Rich sources of obesity-related data arising from sensors, smartphone apps, electronic medical health records and insurance data can bring new insights for understanding, preventing and treating obesity. For such large datasets, machine learning provides sophisticated and elegant tools to describe, classify and predict obesity-related risks and outcomes. Here, we review machine learning methods that predict and/or classify such as linear and logistic regression, artificial neural networks, deep learning and decision tree analysis. We also review methods that describe and characterize data such as cluster analysis, principal component analysis, network science and topological data analysis. We introduce each method with a high-level overview followed by examples of successful applications. The algorithms were then applied to National Health and Nutrition Examination Survey to demonstrate methodology, utility and outcomes. The strengths and limitations of each method were also evaluated. This summary of machine learning algorithms provides a unique overview of the state of data analysis applied specifically to obesity. © 2018 World Obesity Federation.

Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution

Science.gov (United States)

Kisi, Ozgur; Parmar, Kulwinder Singh

2016-03-01

This study investigates the accuracy of least square support vector machine (LSSVM), multivariate adaptive regression splines (MARS) and M5 model tree (M5Tree) in modeling river water pollution. Various combinations of water quality parameters, Free Ammonia (AMM), Total Kjeldahl Nitrogen (TKN), Water Temperature (WT), Total Coliform (TC), Fecal Coliform (FC) and Potential of Hydrogen (pH) monitored at Nizamuddin, Delhi Yamuna River in India were used as inputs to the applied models. Results indicated that the LSSVM and MARS models had almost same accuracy and they performed better than the M5Tree model in modeling monthly chemical oxygen demand (COD). The average root mean square error (RMSE) of the LSSVM and M5Tree models was decreased by 1.47% and 19.1% using MARS model, respectively. Adding TC input to the models did not increase their accuracy in modeling COD while adding FC and pH inputs to the models generally decreased the accuracy. The overall results indicated that the MARS and LSSVM models could be successfully used in estimating monthly river water pollution level by using AMM, TKN and WT parameters as inputs.

Exploration of machine learning techniques in predicting multiple sclerosis disease course

OpenAIRE

Zhao, Yijun; Healy, Brian C.; Rotstein, Dalia; Guttmann, Charles R. G.; Bakshi, Rohit; Weiner, Howard L.; Brodley, Carla E.; Chitnis, Tanuja

2017-01-01

Objective To explore the value of machine learning methods for predicting multiple sclerosis disease course. Methods 1693 CLIMB study patients were classified as increased EDSS?1.5 (worsening) or not (non-worsening) at up to five years after baseline visit. Support vector machines (SVM) were used to build the classifier, and compared to logistic regression (LR) using demographic, clinical and MRI data obtained at years one and two to predict EDSS at five years follow-up. Results Baseline data...

Time Series Analysis and Forecasting for Wind Speeds Using Support Vector Regression Coupled with Artificial Intelligent Algorithms

Directory of Open Access Journals (Sweden)

Ping Jiang

2015-01-01

Full Text Available Wind speed/power has received increasing attention around the earth due to its renewable nature as well as environmental friendliness. With the global installed wind power capacity rapidly increasing, wind industry is growing into a large-scale business. Reliable short-term wind speed forecasts play a practical and crucial role in wind energy conversion systems, such as the dynamic control of wind turbines and power system scheduling. In this paper, an intelligent hybrid model for short-term wind speed prediction is examined; the model is based on cross correlation (CC analysis and a support vector regression (SVR model that is coupled with brainstorm optimization (BSO and cuckoo search (CS algorithms, which are successfully utilized for parameter determination. The proposed hybrid models were used to forecast short-term wind speeds collected from four wind turbines located on a wind farm in China. The forecasting results demonstrate that the intelligent hybrid models outperform single models for short-term wind speed forecasting, which mainly results from the superiority of BSO and CS for parameter optimization.

Multi-Parameter Analysis of Surface Finish in Electro-Discharge Machining of Tool Steels

Directory of Open Access Journals (Sweden)

Cornelia Victoria Anghel

2006-10-01

Full Text Available The paper presents a multi- parameter analysis of surface finish imparted to tool-steel plates by electro-discharge machining (EDM is presented. The interrelationship between surface texture parameters and process parameters is emphasized. An increased number of parameters is studied including amplitude, spacing, hybrid and fractal parameters,, as well. The correlation of these parameters with the machining conditions is investigated. Observed characteristics become more pronounced, when intensifying machining conditions. Close correlation exists between certain surface finish parameters and EDM input variables and single and multiple statistical regression models are developed.

Secure and Efficient Regression Analysis Using a Hybrid Cryptographic Framework: Development and Evaluation.

Science.gov (United States)

Sadat, Md Nazmus; Jiang, Xiaoqian; Aziz, Md Momin Al; Wang, Shuang; Mohammed, Noman

2018-03-05

Machine learning is an effective data-driven tool that is being widely used to extract valuable patterns and insights from data. Specifically, predictive machine learning models are very important in health care for clinical data analysis. The machine learning algorithms that generate predictive models often require pooling data from different sources to discover statistical patterns or correlations among different attributes of the input data. The primary challenge is to fulfill one major objective: preserving the privacy of individuals while discovering knowledge from data. Our objective was to develop a hybrid cryptographic framework for performing regression analysis over distributed data in a secure and efficient way. Existing secure computation schemes are not suitable for processing the large-scale data that are used in cutting-edge machine learning applications. We designed, developed, and evaluated a hybrid cryptographic framework, which can securely perform regression analysis, a fundamental machine learning algorithm using somewhat homomorphic encryption and a newly introduced secure hardware component of Intel Software Guard Extensions (Intel SGX) to ensure both privacy and efficiency at the same time. Experimental results demonstrate that our proposed method provides a better trade-off in terms of security and efficiency than solely secure hardware-based methods. Besides, there is no approximation error. Computed model parameters are exactly similar to plaintext results. To the best of our knowledge, this kind of secure computation model using a hybrid cryptographic framework, which leverages both somewhat homomorphic encryption and Intel SGX, is not proposed or evaluated to this date. Our proposed framework ensures data security and computational efficiency at the same time. ©Md Nazmus Sadat, Xiaoqian Jiang, Md Momin Al Aziz, Shuang Wang, Noman Mohammed. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 05.03.2018.

Evaluation of Machine Learning Methods for LHC Optics Measurements and Corrections Software

CERN Document Server

AUTHOR|(CDS)2206853; Henning, Peter

The field of artificial intelligence is driven by the goal to provide machines with human-like intelligence. However modern science is currently facing problems with high complexity that cannot be solved by humans in the same timescale as by machines. Therefore there is a demand on automation of complex tasks. To identify the category of tasks which can be performed by machines in the domain of optics measurements and correction on the Large Hadron Collider (LHC) is one of the central research subjects of this thesis. The application of machine learning methods and concepts of artificial intelligence can be found in various industry and scientific branches. In High Energy Physics these concepts are mostly used in offline analysis of experiments data and to perform regression tasks. In Accelerator Physics the machine learning approach has not found a wide application yet. Therefore potential tasks for machine learning solutions can be specified in this domain. The appropriate methods and their suitability for...

Predicting Solar Activity Using Machine-Learning Methods

Science.gov (United States)

Bobra, M.

2017-12-01

Of all the activity observed on the Sun, two of the most energetic events are flares and coronal mass ejections. However, we do not, as of yet, fully understand the physical mechanism that triggers solar eruptions. A machine-learning algorithm, which is favorable in cases where the amount of data is large, is one way to [1] empirically determine the signatures of this mechanism in solar image data and [2] use them to predict solar activity. In this talk, we discuss the application of various machine learning algorithms - specifically, a Support Vector Machine, a sparse linear regression (Lasso), and Convolutional Neural Network - to image data from the photosphere, chromosphere, transition region, and corona taken by instruments aboard the Solar Dynamics Observatory in order to predict solar activity on a variety of time scales. Such an approach may be useful since, at the present time, there are no physical models of flares available for real-time prediction. We discuss our results (Bobra and Couvidat, 2015; Bobra and Ilonidis, 2016; Jonas et al., 2017) as well as other attempts to predict flares using machine-learning (e.g. Ahmed et al., 2013; Nishizuka et al. 2017) and compare these results with the more traditional techniques used by the NOAA Space Weather Prediction Center (Crown, 2012). We also discuss some of the challenges in using machine-learning algorithms for space science applications.

Support vector machines classifiers of physical activities in preschoolers

Science.gov (United States)

The goal of this study is to develop, test, and compare multinomial logistic regression (MLR) and support vector machines (SVM) in classifying preschool-aged children physical activity data acquired from an accelerometer. In this study, 69 children aged 3-5 years old were asked to participate in a s...

The Improved Relevance Voxel Machine

DEFF Research Database (Denmark)

Ganz, Melanie; Sabuncu, Mert; Van Leemput, Koen

The concept of sparse Bayesian learning has received much attention in the machine learning literature as a means of achieving parsimonious representations of features used in regression and classification. It is an important family of algorithms for sparse signal recovery and compressed sensing....... Hence in its current form it is reminiscent of a greedy forward feature selection algorithm. In this report, we aim to solve the problems of the original RVoxM algorithm in the spirit of [7] (FastRVM).We call the new algorithm Improved Relevance Voxel Machine (IRVoxM). Our contributions...... and enables basis selection from overcomplete dictionaries. One of the trailblazers of Bayesian learning is MacKay who already worked on the topic in his PhD thesis in 1992 [1]. Later on Tipping and Bishop developed the concept of sparse Bayesian learning [2, 3] and Tipping published the Relevance Vector...

Machine learning in updating predictive models of planning and scheduling transportation projects

Science.gov (United States)

1997-01-01

A method combining machine learning and regression analysis to automatically and intelligently update predictive models used in the Kansas Department of Transportations (KDOTs) internal management system is presented. The predictive models used...

High Resolution Mapping of Soil Properties Using Remote Sensing Variables in South-Western Burkina Faso: A Comparison of Machine Learning and Multiple Linear Regression Models.

Directory of Open Access Journals (Sweden)

Gerald Forkuor

Full Text Available Accurate and detailed spatial soil information is essential for environmental modelling, risk assessment and decision making. The use of Remote Sensing data as secondary sources of information in digital soil mapping has been found to be cost effective and less time consuming compared to traditional soil mapping approaches. But the potentials of Remote Sensing data in improving knowledge of local scale soil information in West Africa have not been fully explored. This study investigated the use of high spatial resolution satellite data (RapidEye and Landsat, terrain/climatic data and laboratory analysed soil samples to map the spatial distribution of six soil properties-sand, silt, clay, cation exchange capacity (CEC, soil organic carbon (SOC and nitrogen-in a 580 km2 agricultural watershed in south-western Burkina Faso. Four statistical prediction models-multiple linear regression (MLR, random forest regression (RFR, support vector machine (SVM, stochastic gradient boosting (SGB-were tested and compared. Internal validation was conducted by cross validation while the predictions were validated against an independent set of soil samples considering the modelling area and an extrapolation area. Model performance statistics revealed that the machine learning techniques performed marginally better than the MLR, with the RFR providing in most cases the highest accuracy. The inability of MLR to handle non-linear relationships between dependent and independent variables was found to be a limitation in accurately predicting soil properties at unsampled locations. Satellite data acquired during ploughing or early crop development stages (e.g. May, June were found to be the most important spectral predictors while elevation, temperature and precipitation came up as prominent terrain/climatic variables in predicting soil properties. The results further showed that shortwave infrared and near infrared channels of Landsat8 as well as soil specific indices

Analyzing Big Data with the Hybrid Interval Regression Methods

Directory of Open Access Journals (Sweden)

Chia-Hui Huang

2014-01-01

Full Text Available Big data is a new trend at present, forcing the significant impacts on information technologies. In big data applications, one of the most concerned issues is dealing with large-scale data sets that often require computation resources provided by public cloud services. How to analyze big data efficiently becomes a big challenge. In this paper, we collaborate interval regression with the smooth support vector machine (SSVM to analyze big data. Recently, the smooth support vector machine (SSVM was proposed as an alternative of the standard SVM that has been proved more efficient than the traditional SVM in processing large-scale data. In addition the soft margin method is proposed to modify the excursion of separation margin and to be effective in the gray zone that the distribution of data becomes hard to be described and the separation margin between classes.

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

Science.gov (United States)

Kai, Joe; Garibaldi, Jonathan M.; Qureshi, Nadeem

2017-01-01

Background Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. Methods Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the ‘receiver operating curve’ (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). Findings 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723–0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739–0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755–0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755–0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759–0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. Conclusions Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others

Optimization of classification and regression analysis of four monoclonal antibodies from Raman spectra using collaborative machine learning approach.

Science.gov (United States)

Le, Laetitia Minh Maï; Kégl, Balázs; Gramfort, Alexandre; Marini, Camille; Nguyen, David; Cherti, Mehdi; Tfaili, Sana; Tfayli, Ali; Baillet-Guffroy, Arlette; Prognon, Patrice; Chaminade, Pierre; Caudron, Eric

2018-07-01

The use of monoclonal antibodies (mAbs) constitutes one of the most important strategies to treat patients suffering from cancers such as hematological malignancies and solid tumors. These antibodies are prescribed by the physician and prepared by hospital pharmacists. An analytical control enables the quality of the preparations to be ensured. The aim of this study was to explore the development of a rapid analytical method for quality control. The method used four mAbs (Infliximab, Bevacizumab, Rituximab and Ramucirumab) at various concentrations and was based on recording Raman data and coupling them to a traditional chemometric and machine learning approach for data analysis. Compared to conventional linear approach, prediction errors are reduced with a data-driven approach using statistical machine learning methods. In the latter, preprocessing and predictive models are jointly optimized. An additional original aspect of the work involved on submitting the problem to a collaborative data challenge platform called Rapid Analytics and Model Prototyping (RAMP). This allowed using solutions from about 300 data scientists in collaborative work. Using machine learning, the prediction of the four mAbs samples was considerably improved. The best predictive model showed a combined error of 2.4% versus 14.6% using linear approach. The concentration and classification errors were 5.8% and 0.7%, only three spectra were misclassified over the 429 spectra of the test set. This large improvement obtained with machine learning techniques was uniform for all molecules but maximal for Bevacizumab with an 88.3% reduction on combined errors (2.1% versus 17.9%). Copyright © 2018 Elsevier B.V. All rights reserved.

Machine learning and statistical methods for the prediction of maximal oxygen uptake: recent advances

Directory of Open Access Journals (Sweden)

Abut F

2015-08-01

Full Text Available Fatih Abut, Mehmet Fatih AkayDepartment of Computer Engineering, Çukurova University, Adana, TurkeyAbstract: Maximal oxygen uptake (VO2max indicates how many milliliters of oxygen the body can consume in a state of intense exercise per minute. VO2max plays an important role in both sport and medical sciences for different purposes, such as indicating the endurance capacity of athletes or serving as a metric in estimating the disease risk of a person. In general, the direct measurement of VO2max provides the most accurate assessment of aerobic power. However, despite a high level of accuracy, practical limitations associated with the direct measurement of VO2max, such as the requirement of expensive and sophisticated laboratory equipment or trained staff, have led to the development of various regression models for predicting VO2max. Consequently, a lot of studies have been conducted in the last years to predict VO2max of various target audiences, ranging from soccer athletes, nonexpert swimmers, cross-country skiers to healthy-fit adults, teenagers, and children. Numerous prediction models have been developed using different sets of predictor variables and a variety of machine learning and statistical methods, including support vector machine, multilayer perceptron, general regression neural network, and multiple linear regression. The purpose of this study is to give a detailed overview about the data-driven modeling studies for the prediction of VO2max conducted in recent years and to compare the performance of various VO2max prediction models reported in related literature in terms of two well-known metrics, namely, multiple correlation coefficient (R and standard error of estimate. The survey results reveal that with respect to regression methods used to develop prediction models, support vector machine, in general, shows better performance than other methods, whereas multiple linear regression exhibits the worst performance

Machine rates for selected forest harvesting machines

Science.gov (United States)

R.W. Brinker; J. Kinard; Robert Rummer; B. Lanford

2002-01-01

Very little new literature has been published on the subject of machine rates and machine cost analysis since 1989 when the Alabama Agricultural Experiment Station Circular 296, Machine Rates for Selected Forest Harvesting Machines, was originally published. Many machines discussed in the original publication have undergone substantial changes in various aspects, not...

Stochastic subset selection for learning with kernel machines.

Science.gov (United States)

Rhinelander, Jason; Liu, Xiaoping P

2012-06-01

Kernel machines have gained much popularity in applications of machine learning. Support vector machines (SVMs) are a subset of kernel machines and generalize well for classification, regression, and anomaly detection tasks. The training procedure for traditional SVMs involves solving a quadratic programming (QP) problem. The QP problem scales super linearly in computational effort with the number of training samples and is often used for the offline batch processing of data. Kernel machines operate by retaining a subset of observed data during training. The data vectors contained within this subset are referred to as support vectors (SVs). The work presented in this paper introduces a subset selection method for the use of kernel machines in online, changing environments. Our algorithm works by using a stochastic indexing technique when selecting a subset of SVs when computing the kernel expansion. The work described here is novel because it separates the selection of kernel basis functions from the training algorithm used. The subset selection algorithm presented here can be used in conjunction with any online training technique. It is important for online kernel machines to be computationally efficient due to the real-time requirements of online environments. Our algorithm is an important contribution because it scales linearly with the number of training samples and is compatible with current training techniques. Our algorithm outperforms standard techniques in terms of computational efficiency and provides increased recognition accuracy in our experiments. We provide results from experiments using both simulated and real-world data sets to verify our algorithm.

Measurement of food colour in L*a*b* units from RGB digital image using least squares support vector machine regression

Directory of Open Access Journals (Sweden)

Roberto Romaniello

2015-12-01

Full Text Available The aim of this work is to evaluate the potential of least squares support vector machine (LS-SVM regression to develop an efficient method to measure the colour of food materials in L*a*b* units by means of a computer vision systems (CVS. A laboratory CVS, based on colour digital camera (CDC, was implemented and three LS-SVM models were trained and validated, one for each output variables (L*, a*, and b* required by this problem, using the RGB signals generated by the CDC as input variables to these models. The colour target-based approach was used to camera characterization and a standard reference target of 242 colour samples was acquired using the CVS and a colorimeter. This data set was split in two sets of equal sizes, for training and validating the LS-SVM models. An effective two-stage grid search process on the parameters space was performed in MATLAB to tune the regularization parameters γ and the kernel parameters σ2 of the three LS-SVM models. A 3-8-3 multilayer feed-forward neural network (MFNN, according to the research conducted by León et al. (2006, was also trained in order to compare its performance with those of LS-SVM models. The LS-SVM models developed in this research have been shown better generalization capability then the MFNN, allowed to obtain high correlations between L*a*b* data acquired using the colorimeter and the corresponding data obtained by transformation of the RGB data acquired by the CVS. In particular, for the validation set, R2 values equal to 0.9989, 0.9987, and 0.9994 for L*, a* and b* parameters were obtained. The root mean square error values were 0.6443, 0.3226, and 0.2702 for L*, a*, and b* respectively, and the average of colour differences ΔEab was 0.8232±0.5033 units. Thus, LS-SVM regression seems to be a useful tool to measurement of food colour using a low cost CVS.

Fusing Data Mining, Machine Learning and Traditional Statistics to Detect Biomarkers Associated with Depression.

Science.gov (United States)

Dipnall, Joanna F; Pasco, Julie A; Berk, Michael; Williams, Lana J; Dodd, Seetal; Jacka, Felice N; Meyer, Denny

2016-01-01

Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study. The study used a three-step methodology amalgamating multiple imputation, a machine learning boosted regression algorithm and logistic regression, to identify key biomarkers associated with depression in the National Health and Nutrition Examination Study (2009-2010). Depression was measured using the Patient Health Questionnaire-9 and 67 biomarkers were analysed. Covariates in this study included gender, age, race, smoking, food security, Poverty Income Ratio, Body Mass Index, physical activity, alcohol use, medical conditions and medications. The final imputed weighted multiple logistic regression model included possible confounders and moderators. After the creation of 20 imputation data sets from multiple chained regression sequences, machine learning boosted regression initially identified 21 biomarkers associated with depression. Using traditional logistic regression methods, including controlling for possible confounders and moderators, a final set of three biomarkers were selected. The final three biomarkers from the novel hybrid variable selection methodology were red cell distribution width (OR 1.15; 95% CI 1.01, 1.30), serum glucose (OR 1.01; 95% CI 1.00, 1.01) and total bilirubin (OR 0.12; 95% CI 0.05, 0.28). Significant interactions were found between total bilirubin with Mexican American/Hispanic group (p = 0.016), and current smokers (pmachine learning algorithm with traditional statistical modelling, accounted for missing data and complex survey sampling methodology and was demonstrated to be a useful tool for detecting three biomarkers associated with depression for future

Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research.

Science.gov (United States)

Carnahan, Brian; Meyer, Gérard; Kuntz, Lois-Ann

2003-01-01

Multivariate classification models play an increasingly important role in human factors research. In the past, these models have been based primarily on discriminant analysis and logistic regression. Models developed from machine learning research offer the human factors professional a viable alternative to these traditional statistical classification methods. To illustrate this point, two machine learning approaches--genetic programming and decision tree induction--were used to construct classification models designed to predict whether or not a student truck driver would pass his or her commercial driver license (CDL) examination. The models were developed and validated using the curriculum scores and CDL exam performances of 37 student truck drivers who had completed a 320-hr driver training course. Results indicated that the machine learning classification models were superior to discriminant analysis and logistic regression in terms of predictive accuracy. Actual or potential applications of this research include the creation of models that more accurately predict human performance outcomes.

Accuracy of Bayes and Logistic Regression Subscale Probabilities for Educational and Certification Tests

Science.gov (United States)

Rudner, Lawrence

2016-01-01

In the machine learning literature, it is commonly accepted as fact that as calibration sample sizes increase, Naïve Bayes classifiers initially outperform Logistic Regression classifiers in terms of classification accuracy. Applied to subtests from an on-line final examination and from a highly regarded certification examination, this study shows…

Principal components based support vector regression model for on-line instrument calibration monitoring in NPPs

International Nuclear Information System (INIS)

Seo, In Yong; Ha, Bok Nam; Lee, Sung Woo; Shin, Chang Hoon; Kim, Seong Jun

2010-01-01

In nuclear power plants (NPPs), periodic sensor calibrations are required to assure that sensors are operating correctly. By checking the sensor's operating status at every fuel outage, faulty sensors may remain undetected for periods of up to 24 months. Moreover, typically, only a few faulty sensors are found to be calibrated. For the safe operation of NPP and the reduction of unnecessary calibration, on-line instrument calibration monitoring is needed. In this study, principal component based auto-associative support vector regression (PCSVR) using response surface methodology (RSM) is proposed for the sensor signal validation of NPPs. This paper describes the design of a PCSVR-based sensor validation system for a power generation system. RSM is employed to determine the optimal values of SVR hyperparameters and is compared to the genetic algorithm (GA). The proposed PCSVR model is confirmed with the actual plant data of Kori Nuclear Power Plant Unit 3 and is compared with the Auto-Associative support vector regression (AASVR) and the auto-associative neural network (AANN) model. The auto-sensitivity of AASVR is improved by around six times by using a PCA, resulting in good detection of sensor drift. Compared to AANN, accuracy and cross-sensitivity are better while the auto-sensitivity is almost the same. Meanwhile, the proposed RSM for the optimization of the PCSVR algorithm performs even better in terms of accuracy, auto-sensitivity, and averaged maximum error, except in averaged RMS error, and this method is much more time efficient compared to the conventional GA method

Comparative study of computational intelligence approaches for NOx reduction of coal-fired boiler

International Nuclear Information System (INIS)

Wei, Zhongbao; Li, Xiaolu; Xu, Lijun; Cheng, Yanting

2013-01-01

This paper focuses on NO x emission prediction and operating parameters optimization for coal-fired boilers. Support Vector Regression (SVR) model based on CGA (Conventional Genetic Algorithm) was proposed to model the relationship between the operating parameters and the concentration of NO x emission. Then CGA and two modified algorithms, the Quantum Genetic Algorithm (QGA) and SAGA (Simulated Annealing Genetic Algorithm), were employed to optimize the operating parameters of the coal-fired boiler to reduce NO x emission. The results showed that the proposed SVR model was more accurate than the widely used Artificial Neural Network (ANN) model when employed to predict the concentration of NO x emission. The mean relative error and correlation coefficient calculated by the proposed SVR model were 2.08% and 0.95, respectively. Among the three optimization algorithms implemented in this paper, the SAGA showed superiority to the other two algorithms considering the quality of solution within a given computing time. The SVR plus SAGA method was preferable to predict the concentration of NO x emission and further to optimize the operating parameters to achieve low NO x emission for coal-fired boilers. - Highlights: • The CGA based SVR model is proposed to predict the concentration of NO x emission. • The CGA based SVR model performs better than the widely used ANN model. • CGA and two modified algorithms are compared to optimize the parameters. • The SAGA is preferable for its high quality of solution and low computing time. • The SVR plus SAGA is successfully employed to optimize the operating parameters

A New Approach for Mobile Advertising Click-Through Rate Estimation Based on Deep Belief Nets.

Science.gov (United States)

Chen, Jie-Hao; Zhao, Zi-Qian; Shi, Ji-Yun; Zhao, Chong

2017-01-01

In recent years, with the rapid development of mobile Internet and its business applications, mobile advertising Click-Through Rate (CTR) estimation has become a hot research direction in the field of computational advertising, which is used to achieve accurate advertisement delivery for the best benefits in the three-side game between media, advertisers, and audiences. Current research on the estimation of CTR mainly uses the methods and models of machine learning, such as linear model or recommendation algorithms. However, most of these methods are insufficient to extract the data features and cannot reflect the nonlinear relationship between different features. In order to solve these problems, we propose a new model based on Deep Belief Nets to predict the CTR of mobile advertising, which combines together the powerful data representation and feature extraction capability of Deep Belief Nets, with the advantage of simplicity of traditional Logistic Regression models. Based on the training dataset with the information of over 40 million mobile advertisements during a period of 10 days, our experiments show that our new model has better estimation accuracy than the classic Logistic Regression (LR) model by 5.57% and Support Vector Regression (SVR) model by 5.80%.

A New Approach for Mobile Advertising Click-Through Rate Estimation Based on Deep Belief Nets

Science.gov (United States)

Zhao, Zi-Qian; Shi, Ji-Yun; Zhao, Chong

2017-01-01

In recent years, with the rapid development of mobile Internet and its business applications, mobile advertising Click-Through Rate (CTR) estimation has become a hot research direction in the field of computational advertising, which is used to achieve accurate advertisement delivery for the best benefits in the three-side game between media, advertisers, and audiences. Current research on the estimation of CTR mainly uses the methods and models of machine learning, such as linear model or recommendation algorithms. However, most of these methods are insufficient to extract the data features and cannot reflect the nonlinear relationship between different features. In order to solve these problems, we propose a new model based on Deep Belief Nets to predict the CTR of mobile advertising, which combines together the powerful data representation and feature extraction capability of Deep Belief Nets, with the advantage of simplicity of traditional Logistic Regression models. Based on the training dataset with the information of over 40 million mobile advertisements during a period of 10 days, our experiments show that our new model has better estimation accuracy than the classic Logistic Regression (LR) model by 5.57% and Support Vector Regression (SVR) model by 5.80%. PMID:29209363

QUALITY LOSS FUNCTION FOR MACHINING PROCESS ACCURACY

Directory of Open Access Journals (Sweden)

Adrian Stere PARIS

2017-05-01

Full Text Available The main goal of the paper is to propose new quality loss models for machining process accuracy in the classical case “zero the best”, MMF and Harris type. In addition a numerical example illustrates that the choose regression functions are directly linked with the quality loss of manufacturing process. The proposed models can be adapted for the “maximal the best” and “nominal the best” cases.

A comparative study of machine learning models for ethnicity classification

Science.gov (United States)

Trivedi, Advait; Bessie Amali, D. Geraldine

2017-11-01

This paper endeavours to adopt a machine learning approach to solve the problem of ethnicity recognition. Ethnicity identification is an important vision problem with its use cases being extended to various domains. Despite the multitude of complexity involved, ethnicity identification comes naturally to humans. This meta information can be leveraged to make several decisions, be it in target marketing or security. With the recent development of intelligent systems a sub module to efficiently capture ethnicity would be useful in several use cases. Several attempts to identify an ideal learning model to represent a multi-ethnic dataset have been recorded. A comparative study of classifiers such as support vector machines, logistic regression has been documented. Experimental results indicate that the logical classifier provides a much accurate classification than the support vector machine.

Voice based gender classification using machine learning

Science.gov (United States)

Raahul, A.; Sapthagiri, R.; Pankaj, K.; Vijayarajan, V.

2017-11-01

Gender identification is one of the major problem speech analysis today. Tracing the gender from acoustic data i.e., pitch, median, frequency etc. Machine learning gives promising results for classification problem in all the research domains. There are several performance metrics to evaluate algorithms of an area. Our Comparative model algorithm for evaluating 5 different machine learning algorithms based on eight different metrics in gender classification from acoustic data. Agenda is to identify gender, with five different algorithms: Linear Discriminant Analysis (LDA), K-Nearest Neighbour (KNN), Classification and Regression Trees (CART), Random Forest (RF), and Support Vector Machine (SVM) on basis of eight different metrics. The main parameter in evaluating any algorithms is its performance. Misclassification rate must be less in classification problems, which says that the accuracy rate must be high. Location and gender of the person have become very crucial in economic markets in the form of AdSense. Here with this comparative model algorithm, we are trying to assess the different ML algorithms and find the best fit for gender classification of acoustic data.

Accelerated Monte Carlo system reliability analysis through machine-learning-based surrogate models of network connectivity

International Nuclear Information System (INIS)

Stern, R.E.; Song, J.; Work, D.B.

2017-01-01

The two-terminal reliability problem in system reliability analysis is known to be computationally intractable for large infrastructure graphs. Monte Carlo techniques can estimate the probability of a disconnection between two points in a network by selecting a representative sample of network component failure realizations and determining the source-terminal connectivity of each realization. To reduce the runtime required for the Monte Carlo approximation, this article proposes an approximate framework in which the connectivity check of each sample is estimated using a machine-learning-based classifier. The framework is implemented using both a support vector machine (SVM) and a logistic regression based surrogate model. Numerical experiments are performed on the California gas distribution network using the epicenter and magnitude of the 1989 Loma Prieta earthquake as well as randomly-generated earthquakes. It is shown that the SVM and logistic regression surrogate models are able to predict network connectivity with accuracies of 99% for both methods, and are 1–2 orders of magnitude faster than using a Monte Carlo method with an exact connectivity check. - Highlights: • Surrogate models of network connectivity are developed by machine-learning algorithms. • Developed surrogate models can reduce the runtime required for Monte Carlo simulations. • Support vector machine and logistic regressions are employed to develop surrogate models. • Numerical example of California gas distribution network demonstrate the proposed approach. • The developed models have accuracies 99%, and are 1–2 orders of magnitude faster than MCS.

Penalized regression procedures for variable selection in the potential outcomes framework.

Science.gov (United States)

Ghosh, Debashis; Zhu, Yeying; Coffman, Donna L

2015-05-10

A recent topic of much interest in causal inference is model selection. In this article, we describe a framework in which to consider penalized regression approaches to variable selection for causal effects. The framework leads to a simple 'impute, then select' class of procedures that is agnostic to the type of imputation algorithm as well as penalized regression used. It also clarifies how model selection involves a multivariate regression model for causal inference problems and that these methods can be applied for identifying subgroups in which treatment effects are homogeneous. Analogies and links with the literature on machine learning methods, missing data, and imputation are drawn. A difference least absolute shrinkage and selection operator algorithm is defined, along with its multiple imputation analogs. The procedures are illustrated using a well-known right-heart catheterization dataset. Copyright © 2015 John Wiley & Sons, Ltd.

Statistical analysis of surface roughness of machined graphite by means of CNC milling

Directory of Open Access Journals (Sweden)

Orquídea Sánchez López

2016-09-01

Full Text Available The aim of this research is to analyze the influence of cutting speed, feed rate and cutting depth on the surface finish of grade GSP-70 graphite specimens for use in electrical discharge machining (EDM for material removal by means of Computer Numerical Control (CNC milling with low-speed machining (LSM. A two-level factorial design for each of the three established factors was used for the statistical analysis. The analysis of variance (ANOVA indicates that cutting speed and feed rate are the two most significant factors with regard to the roughness obtained with grade GSP-70 graphite by means of CNC milling. A second order regression analysis was also conducted to estimate the roughness average (Ra in terms of the cutting speed, feed rate and cutting depth. Finally, the comparison between predicted roughness by means of a second order regression model and the roughness obtained by machined specimens considering the combinations of low and high levels of roughness is also presented.

Taxi-Out Time Prediction for Departures at Charlotte Airport Using Machine Learning Techniques

Science.gov (United States)

Lee, Hanbong; Malik, Waqar; Jung, Yoon C.

2016-01-01

Predicting the taxi-out times of departures accurately is important for improving airport efficiency and takeoff time predictability. In this paper, we attempt to apply machine learning techniques to actual traffic data at Charlotte Douglas International Airport for taxi-out time prediction. To find the key factors affecting aircraft taxi times, surface surveillance data is first analyzed. From this data analysis, several variables, including terminal concourse, spot, runway, departure fix and weight class, are selected for taxi time prediction. Then, various machine learning methods such as linear regression, support vector machines, k-nearest neighbors, random forest, and neural networks model are applied to actual flight data. Different traffic flow and weather conditions at Charlotte airport are also taken into account for more accurate prediction. The taxi-out time prediction results show that linear regression and random forest techniques can provide the most accurate prediction in terms of root-mean-square errors. We also discuss the operational complexity and uncertainties that make it difficult to predict the taxi times accurately.

Comparative adoption of cone beam computed tomography and panoramic radiography machines across Australia.

Science.gov (United States)

Zhang, A; Critchley, S; Monsour, P A

2016-12-01

The aim of the present study was to assess the current adoption of cone beam computed tomography (CBCT) and panoramic radiography (PR) machines across Australia. Information regarding registered CBCT and PR machines was obtained from radiation regulators across Australia. The number of X-ray machines was correlated with the population size, the number of dentists, and the gross state product (GSP) per capita, to determine the best fitting regression model(s). In 2014, there were 232 CBCT and 1681 PR machines registered in Australia. Based on absolute counts, Queensland had the largest number of CBCT and PR machines whereas the Northern Territory had the smallest number. However, when based on accessibility in terms of the population size and the number of dentists, the Australian Capital Territory had the most CBCT machines and Western Australia had the most PR machines. The number of X-ray machines correlated strongly with both the population size and the number of dentists, but not with the GSP per capita. In 2014, the ratio of PR to CBCT machines was approximately 7:1. Projected increases in either the population size or the number of dentists could positively impact on the adoption of PR and CBCT machines in Australia. © 2016 Australian Dental Association.

Support vector methods for survival analysis: a comparison between ranking and regression approaches.

Science.gov (United States)

Van Belle, Vanya; Pelckmans, Kristiaan; Van Huffel, Sabine; Suykens, Johan A K

2011-10-01

To compare and evaluate ranking, regression and combined machine learning approaches for the analysis of survival data. The literature describes two approaches based on support vector machines to deal with censored observations. In the first approach the key idea is to rephrase the task as a ranking problem via the concordance index, a problem which can be solved efficiently in a context of structural risk minimization and convex optimization techniques. In a second approach, one uses a regression approach, dealing with censoring by means of inequality constraints. The goal of this paper is then twofold: (i) introducing a new model combining the ranking and regression strategy, which retains the link with existing survival models such as the proportional hazards model via transformation models; and (ii) comparison of the three techniques on 6 clinical and 3 high-dimensional datasets and discussing the relevance of these techniques over classical approaches fur survival data. We compare svm-based survival models based on ranking constraints, based on regression constraints and models based on both ranking and regression constraints. The performance of the models is compared by means of three different measures: (i) the concordance index, measuring the model's discriminating ability; (ii) the logrank test statistic, indicating whether patients with a prognostic index lower than the median prognostic index have a significant different survival than patients with a prognostic index higher than the median; and (iii) the hazard ratio after normalization to restrict the prognostic index between 0 and 1. Our results indicate a significantly better performance for models including regression constraints above models only based on ranking constraints. This work gives empirical evidence that svm-based models using regression constraints perform significantly better than svm-based models based on ranking constraints. Our experiments show a comparable performance for methods

EVALUATION WITH INADEQUATE DATA: THE IMPACT OF THE FRENCH VENDING MACHINE BAN

OpenAIRE

Capacci, Sara; Mazzocchi, Mario; Shankar, Bhavani

2012-01-01

We estimate the effects of the 2005 ban on vending machines in French schools using the 1998 and 2006 INCA nutrition surveys. These surveys contain no information on the presence of vending machines in schools attended by respondents, but the adoption of a Difference-in-Difference design, and a Regression Discontinuity Design enable us to obtain indirect estimates of the policy impact. Results are consistent and suggest that the measure has had a small but significant impact on teenager nutri...

[A new machinability test machine and the machinability of composite resins for core built-up].

Science.gov (United States)

Iwasaki, N

2001-06-01

A new machinability test machine especially for dental materials was contrived. The purpose of this study was to evaluate the effects of grinding conditions on machinability of core built-up resins using this machine, and to confirm the relationship between machinability and other properties of composite resins. The experimental machinability test machine consisted of a dental air-turbine handpiece, a control weight unit, a driving unit of the stage fixing the test specimen, and so on. The machinability was evaluated as the change in volume after grinding using a diamond point. Five kinds of core built-up resins and human teeth were used in this study. The machinabilities of these composite resins increased with an increasing load during grinding, and decreased with repeated grinding. There was no obvious correlation between the machinability and Vickers' hardness; however, a negative correlation was observed between machinability and scratch width.

SVR

Data.gov (United States)

National Oceanic and Atmospheric Administration, Department of Commerce — Severe Thunderstorm Warnings (SVRs) are issued by NWS Weather Forecast Office (WFO) meteorologists when there is radar of satellite indication and/or reliable...

Hepatitis C virus cure does not impact kidney function decline in HIV co-infected patients.

Science.gov (United States)

Rossi, Carmine; Saeed, Sahar; Cox, Joseph; Vachon, Marie-Louise; Martel-Laferrière, Valérie; Walmsley, Sharon L; Cooper, Curtis; Gill, M John; Hull, Mark; Moodie, Erica E M; Klein, Marina B

2018-03-27

To examine the impact of sustained virologic response (SVR) and illicit (injection and noninjection) drug use on kidney function among hepatitis C virus (HCV) and HIV co-infected individuals. Longitudinal observational cohort study of HCV-HIV co-infected patients. Data from 1631 patients enrolled in the Canadian Co-Infection Cohort between 2003 and 2016 were analyzed. Patients who achieved SVR were matched 1 : 2 with chronically infected patients using time-dependent propensity scores. Linear regression with generalized estimating equations was used to model differences in estimated glomerular filtration rates (eGFR) between chronic HCV-infected patients and those achieving SVR. The relationship between illicit drug use and eGFR was explored in patients who achieved SVR. We identified 384 co-infected patients who achieved SVR (53% treated with interferon-free antiviral regimens) and 768 propensity-score matched patients with chronic HCV infection. Most patients were men (78%) and white (87%), with a median age of 51 years (interquartile range: 45-56). During 1767 person-years of follow-up, 4041 eGFR measurements were available for analysis. Annual rates of decline in eGFR were similar between patients with SVR [-1.32 (ml/min per 1.73 m)/year, 95% confidence interval (CI) -1.75 to -0.90] and chronic infection [-1.19 (ml/min per 1.73 m) per year, 95% CI -1.55 to -0.84]. Among SVR patients, recent injection cocaine use was associated with rapid eGFR decline [-2.16 (ml/min per 1.73 m)/year, 95% CI -4.17 to -0.16]. SVR did not reduce the rate of kidney function decline among HCV-HIV co-infected patients. Increased risk of chronic kidney disease in co-infection may not be related to persistent HCV replication but to ongoing injection cocaine use.

Predicting Market Impact Costs Using Nonparametric Machine Learning Models.

Science.gov (United States)

Park, Saerom; Lee, Jaewook; Son, Youngdoo

2016-01-01

Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.

Multi-Response Optimization and Regression Analysis of Process Parameters for Wire-EDMed HCHCr Steel Using Taguchi’s Technique

Directory of Open Access Journals (Sweden)

K. Srujay Varma

2017-04-01

Full Text Available In this study, effect of machining process parameters viz. pulse-on time, pulse-off time, current and servo-voltage for machining High Carbon High Chromium Steel (HCHCr using copper electrode in wire EDM was investigated. High Carbon High Chromium Steel is a difficult to machine alloy, which has many applications in low temperature manufacturing, and copper is chosen as electrode as it has good electrical conductivity and most frequently used electrode all over the world. Tool making culture of copper has made many shops in Europe and Japan to used copper electrode. Experiments were conducted according to Taguchi’s technique by varying the machining process parameters at three levels. Taguchi’s method based on L9 orthogonal array was followed and number of experiments was limited to 9. Experimental cost and time consumption was reduced by following this statistical technique. Targeted output parameters are Material Removal Rate (MRR, Vickers Hardness (HV and Surface Roughness (SR. Analysis of Variance (ANOVA and Regression Analysis was performed using Minitab 17 software to optimize the parameters and draw relationship between input and output process parameters. Regression models were developed relating input and output parameters. It was observed that most influential factor for MRR, Hardness and SR are Ton, Toff and SV.

Prediction of outcome in internet-delivered cognitive behaviour therapy for paediatric obsessive-compulsive disorder: A machine learning approach.

Science.gov (United States)

Lenhard, Fabian; Sauer, Sebastian; Andersson, Erik; Månsson, Kristoffer Nt; Mataix-Cols, David; Rück, Christian; Serlachius, Eva

2018-03-01

There are no consistent predictors of treatment outcome in paediatric obsessive-compulsive disorder (OCD). One reason for this might be the use of suboptimal statistical methodology. Machine learning is an approach to efficiently analyse complex data. Machine learning has been widely used within other fields, but has rarely been tested in the prediction of paediatric mental health treatment outcomes. To test four different machine learning methods in the prediction of treatment response in a sample of paediatric OCD patients who had received Internet-delivered cognitive behaviour therapy (ICBT). Participants were 61 adolescents (12-17 years) who enrolled in a randomized controlled trial and received ICBT. All clinical baseline variables were used to predict strictly defined treatment response status three months after ICBT. Four machine learning algorithms were implemented. For comparison, we also employed a traditional logistic regression approach. Multivariate logistic regression could not detect any significant predictors. In contrast, all four machine learning algorithms performed well in the prediction of treatment response, with 75 to 83% accuracy. The results suggest that machine learning algorithms can successfully be applied to predict paediatric OCD treatment outcome. Validation studies and studies in other disorders are warranted. Copyright © 2017 John Wiley & Sons, Ltd.

Improving virtual screening predictive accuracy of Human kallikrein 5 inhibitors using machine learning models.

Science.gov (United States)

Fang, Xingang; Bagui, Sikha; Bagui, Subhash

2017-08-01

The readily available high throughput screening (HTS) data from the PubChem database provides an opportunity for mining of small molecules in a variety of biological systems using machine learning techniques. From the thousands of available molecular descriptors developed to encode useful chemical information representing the characteristics of molecules, descriptor selection is an essential step in building an optimal quantitative structural-activity relationship (QSAR) model. For the development of a systematic descriptor selection strategy, we need the understanding of the relationship between: (i) the descriptor selection; (ii) the choice of the machine learning model; and (iii) the characteristics of the target bio-molecule. In this work, we employed the Signature descriptor to generate a dataset on the Human kallikrein 5 (hK 5) inhibition confirmatory assay data and compared multiple classification models including logistic regression, support vector machine, random forest and k-nearest neighbor. Under optimal conditions, the logistic regression model provided extremely high overall accuracy (98%) and precision (90%), with good sensitivity (65%) in the cross validation test. In testing the primary HTS screening data with more than 200K molecular structures, the logistic regression model exhibited the capability of eliminating more than 99.9% of the inactive structures. As part of our exploration of the descriptor-model-target relationship, the excellent predictive performance of the combination of the Signature descriptor and the logistic regression model on the assay data of the Human kallikrein 5 (hK 5) target suggested a feasible descriptor/model selection strategy on similar targets. Copyright © 2017 Elsevier Ltd. All rights reserved.

The Machine within the Machine

CERN Multimedia

Katarina Anthony

2014-01-01

Although Virtual Machines are widespread across CERN, you probably won't have heard of them unless you work for an experiment. Virtual machines - known as VMs - allow you to create a separate machine within your own, allowing you to run Linux on your Mac, or Windows on your Linux - whatever combination you need.   Using a CERN Virtual Machine, a Linux analysis software runs on a Macbook. When it comes to LHC data, one of the primary issues collaborations face is the diversity of computing environments among collaborators spread across the world. What if an institute cannot run the analysis software because they use different operating systems? "That's where the CernVM project comes in," says Gerardo Ganis, PH-SFT staff member and leader of the CernVM project. "We were able to respond to experimentalists' concerns by providing a virtual machine package that could be used to run experiment software. This way, no matter what hardware they have ...

Wind turbine power coefficient estimation by soft computing methodologies: Comparative study

International Nuclear Information System (INIS)

Shamshirband, Shahaboddin; Petković, Dalibor; Saboohi, Hadi; Anuar, Nor Badrul; Inayat, Irum; Akib, Shatirah; Ćojbašić, Žarko; Nikolić, Vlastimir; Mat Kiah, Miss Laiha; Gani, Abdullah

2014-01-01

Highlights: • Variable speed operation of wind turbine to increase power generation. • Changeability and fluctuation of wind has to be accounted. • To build an effective prediction model of wind turbine power coefficient. • The impact of the variation in the blade pitch angle and tip speed ratio. • Support vector regression methodology application as predictive methodology. - Abstract: Wind energy has become a large contender of traditional fossil fuel energy, particularly with the successful operation of multi-megawatt sized wind turbines. However, reasonable wind speed is not adequately sustainable everywhere to build an economical wind farm. In wind energy conversion systems, one of the operational problems is the changeability and fluctuation of wind. In most cases, wind speed can vacillate rapidly. Hence, quality of produced energy becomes an important problem in wind energy conversion plants. Several control techniques have been applied to improve the quality of power generated from wind turbines. In this study, the polynomial and radial basis function (RBF) are applied as the kernel function of support vector regression (SVR) to estimate optimal power coefficient value of the wind turbines. Instead of minimizing the observed training error, SVR p oly and SVR r bf attempt to minimize the generalization error bound so as to achieve generalized performance. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the SVR approach in compare to other soft computing methodologies

An appraisal of wind speed distribution prediction by soft computing methodologies: A comparative study

International Nuclear Information System (INIS)

Petković, Dalibor; Shamshirband, Shahaboddin; Anuar, Nor Badrul; Saboohi, Hadi; Abdul Wahab, Ainuddin Wahid; Protić, Milan; Zalnezhad, Erfan; Mirhashemi, Seyed Mohammad Amin

2014-01-01

Highlights: • Probabilistic distribution functions of wind speed. • Two parameter Weibull probability distribution. • To build an effective prediction model of distribution of wind speed. • Support vector regression application as probability function for wind speed. - Abstract: The probabilistic distribution of wind speed is among the more significant wind characteristics in examining wind energy potential and the performance of wind energy conversion systems. When the wind speed probability distribution is known, the wind energy distribution can be easily obtained. Therefore, the probability distribution of wind speed is a very important piece of information required in assessing wind energy potential. For this reason, a large number of studies have been established concerning the use of a variety of probability density functions to describe wind speed frequency distributions. Although the two-parameter Weibull distribution comprises a widely used and accepted method, solving the function is very challenging. In this study, the polynomial and radial basis functions (RBF) are applied as the kernel function of support vector regression (SVR) to estimate two parameters of the Weibull distribution function according to previously established analytical methods. Rather than minimizing the observed training error, SVR p oly and SVR r bf attempt to minimize the generalization error bound, so as to achieve generalized performance. According to the experimental results, enhanced predictive accuracy and capability of generalization can be achieved using the SVR approach compared to other soft computing methodologies

Application of data mining in three-dimensional space time reactor model

International Nuclear Information System (INIS)

Jiang Botao; Zhao Fuyu

2011-01-01

A high-fidelity three-dimensional space time nodal method has been developed to simulate the dynamics of the reactor core for real time simulation. This three-dimensional reactor core mathematical model can be composed of six sub-models, neutron kinetics model, cay heat model, fuel conduction model, thermal hydraulics model, lower plenum model, and core flow distribution model. During simulation of each sub-model some operation data will be produced and lots of valuable, important information reflecting the reactor core operation status could be hidden in, so how to discovery these information becomes the primary mission people concern. Under this background, data mining (DM) is just created and developed to solve this problem, no matter what engineering aspects or business fields. Generally speaking, data mining is a process of finding some useful and interested information from huge data pool. Support Vector Machine (SVM) is a new technique of data mining appeared in recent years, and SVR is a transformed method of SVM which is applied in regression cases. This paper presents only two significant sub-models of three-dimensional reactor core mathematical model, the nodal space time neutron kinetics model and the thermal hydraulics model, based on which the neutron flux and enthalpy distributions of the core are obtained by solving the three-dimensional nodal space time kinetics equations and energy equations for both single and two-phase flows respectively. Moreover, it describes that the three-dimensional reactor core model can also be used to calculate and determine the reactivity effects of the moderator temperature, boron concentration, fuel temperature, coolant void, xenon worth, samarium worth, control element positions (CEAs) and core burnup status. Besides these, the main mathematic theory of SVR is introduced briefly next, on the basis of which SVR is applied to dealing with the data generated by two sample calculation, rod ejection transient and axial

Changes in liver stiffness measurement using acoustic radiation force impulse elastography after antiviral therapy in patients with chronic hepatitis C.

Directory of Open Access Journals (Sweden)

Sheng-Hung Chen

Full Text Available To compare on-treatment and off-treatment parameters acquired using acoustic radiation force impulse elastography, the Fibrosis-4 (FIB-4 index, and aspartate aminotransferase-to-platelet ratio index (APRI in patients with chronic hepatitis C (CHC.Patients received therapies based on pegylated interferon or direct-acting antiviral agents. The changes in paired patient parameters, including liver stiffness (LS values, the FIB-4 index, and APRI, from baseline to sustained virologic response (SVR visit (24 weeks after the end of treatment were compared. Multiple regression models were used to identify significant factors that explained the correlations with LS, FIB-4, and APRI values and SVR.A total of 256 patients were included, of which 219 (85.5% achieved SVR. The paired LS values declined significantly from baseline to SVR visit in all groups and subgroups except the nonresponder subgroup (n = 10. Body mass index (P = 0.0062 and baseline LS (P < 0.0001 were identified as independent factors that explained the LS declines. Likewise, the baseline FIB-4 (P < 0.0001 and APRI (P < 0.0001 values independently explained the declines in the FIB-4 index and APRI, respectively. Moreover, interleukin-28B polymorphisms, baseline LS, and rapid virologic response were identified as independent correlates with SVR.Paired LS measurements in patients treated for CHC exhibited significant declines comparable to those in FIB-4 and APRI values. These declines may have correlated with the resolution of necroinflammation. Baseline LS values predicted SVR.

Computational neural network regression model for Host based Intrusion Detection System

Directory of Open Access Journals (Sweden)

Sunil Kumar Gautam

2016-09-01

Full Text Available The current scenario of information gathering and storing in secure system is a challenging task due to increasing cyber-attacks. There exists computational neural network techniques designed for intrusion detection system, which provide security to single machine and entire network's machine. In this paper, we have used two types of computational neural network models, namely, Generalized Regression Neural Network (GRNN model and Multilayer Perceptron Neural Network (MPNN model for Host based Intrusion Detection System using log files that are generated by a single personal computer. The simulation results show correctly classified percentage of normal and abnormal (intrusion class using confusion matrix. On the basis of results and discussion, we found that the Host based Intrusion Systems Model (HISM significantly improved the detection accuracy while retaining minimum false alarm rate.

Machine learning and statistical methods for the prediction of maximal oxygen uptake: recent advances.

Science.gov (United States)

Abut, Fatih; Akay, Mehmet Fatih

2015-01-01

Maximal oxygen uptake (VO2max) indicates how many milliliters of oxygen the body can consume in a state of intense exercise per minute. VO2max plays an important role in both sport and medical sciences for different purposes, such as indicating the endurance capacity of athletes or serving as a metric in estimating the disease risk of a person. In general, the direct measurement of VO2max provides the most accurate assessment of aerobic power. However, despite a high level of accuracy, practical limitations associated with the direct measurement of VO2max, such as the requirement of expensive and sophisticated laboratory equipment or trained staff, have led to the development of various regression models for predicting VO2max. Consequently, a lot of studies have been conducted in the last years to predict VO2max of various target audiences, ranging from soccer athletes, nonexpert swimmers, cross-country skiers to healthy-fit adults, teenagers, and children. Numerous prediction models have been developed using different sets of predictor variables and a variety of machine learning and statistical methods, including support vector machine, multilayer perceptron, general regression neural network, and multiple linear regression. The purpose of this study is to give a detailed overview about the data-driven modeling studies for the prediction of VO2max conducted in recent years and to compare the performance of various VO2max prediction models reported in related literature in terms of two well-known metrics, namely, multiple correlation coefficient (R) and standard error of estimate. The survey results reveal that with respect to regression methods used to develop prediction models, support vector machine, in general, shows better performance than other methods, whereas multiple linear regression exhibits the worst performance.

Reviewing the connection between speech and obstructive sleep apnea.

Science.gov (United States)

Espinoza-Cuadros, Fernando; Fernández-Pozo, Rubén; Toledano, Doroteo T; Alcázar-Ramírez, José D; López-Gonzalo, Eduardo; Hernández-Gómez, Luis A

2016-02-20

Sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). The altered UA structure or function in OSA speakers has led to hypothesize the automatic analysis of speech for OSA assessment. In this paper we critically review several approaches using speech analysis and machine learning techniques for OSA detection, and discuss the limitations that can arise when using machine learning techniques for diagnostic applications. A large speech database including 426 male Spanish speakers suspected to suffer OSA and derived to a sleep disorders unit was used to study the clinical validity of several proposals using machine learning techniques to predict the apnea-hypopnea index (AHI) or classify individuals according to their OSA severity. AHI describes the severity of patients' condition. We first evaluate AHI prediction using state-of-the-art speaker recognition technologies: speech spectral information is modelled using supervectors or i-vectors techniques, and AHI is predicted through support vector regression (SVR). Using the same database we then critically review several OSA classification approaches previously proposed. The influence and possible interference of other clinical variables or characteristics available for our OSA population: age, height, weight, body mass index, and cervical perimeter, are also studied. The poor results obtained when estimating AHI using supervectors or i-vectors followed by SVR contrast with the positive results reported by previous research. This fact prompted us to a careful review of these approaches, also testing some reported results over our database. Several methodological limitations and deficiencies were detected that may have led to overoptimistic results. The methodological deficiencies observed after critically reviewing previous research can be relevant examples of potential pitfalls when using machine learning techniques for

Prediction of tunnel boring machine performance using machine and rock mass data

International Nuclear Information System (INIS)

Dastgir, G.

2012-01-01

Performance of the tunnel boring machine and its prediction by different methods has been a hot issue since the first TBM came into being. For the sake of safe and sound transport, improvement of hydro-power, mining, civil and many other tunneling projects that cannot be driven efficiently and economically by conventional drill and blast, TBMs are quite frequently used. TBM parameters and rock mass properties, which heavily influence machine performance, should be estimated or known before choice of TBM-type and start of excavation. By applying linear regression analysis (SPSS19), fuzzy logic tools and a special Math-Lab code on actual field data collected from seven TBM driven tunnels (Hieflau expansion, Queen water tunnel, Vereina, Hemerwald, Maen, Pieve and Varzo tunnel), an attempt was made to provide prediction of rock mass class (RMC), rock fracture class (RFC), penetration rate (PR) and advance rate (AR). For detailed analysis of TBM performance, machine parameters (thrust, machine rpm, torque, power etc.), machine types and specification and rock mass properties (UCS, discontinuity in rock mass, RMC, RFC, RMR, etc.) were analyzed by 3-D surface plotting using statistical software R. Correlations between machine parameters and rock mass properties which effectively influence prediction models, are presented as well. In Hieflau expansion tunnel AR linearly decreases with increase of thrust due to high dependence of machine advance rate upon rock strength. For Hieflau expansion tunnel three types of data (TBM, rock mass and seismic data e.g. amplitude, pseudo velocity etc.) were coupled and simultaneously analyzed by plotting 3-D surfaces. No appreciable correlation between seismic data (Amplitude and Pseudo velocity) and rock mass properties and machine parameters could be found. Tool wear as a function of TBM operational parameters was analyzed which revealed that tool wear is minimum if applied thrust is moderate and that tool wear is high when thrust is

Toward Automating HIV Identification: Machine Learning for Rapid Identification of HIV-Related Social Media Data.

Science.gov (United States)

Young, Sean D; Yu, Wenchao; Wang, Wei

2017-02-01

"Social big data" from technologies such as social media, wearable devices, and online searches continue to grow and can be used as tools for HIV research. Although researchers can uncover patterns and insights associated with HIV trends and transmission, the review process is time consuming and resource intensive. Machine learning methods derived from computer science might be used to assist HIV domain experts by learning how to rapidly and accurately identify patterns associated with HIV from a large set of social data. Using an existing social media data set that was associated with HIV and coded by an HIV domain expert, we tested whether 4 commonly used machine learning methods could learn the patterns associated with HIV risk behavior. We used the 10-fold cross-validation method to examine the speed and accuracy of these models in applying that knowledge to detect HIV content in social media data. Logistic regression and random forest resulted in the highest accuracy in detecting HIV-related social data (85.3%), whereas the Ridge Regression Classifier resulted in the lowest accuracy. Logistic regression yielded the fastest processing time (16.98 seconds). Machine learning can enable social big data to become a new and important tool in HIV research, helping to create a new field of "digital HIV epidemiology." If a domain expert can identify patterns in social data associated with HIV risk or HIV transmission, machine learning models could quickly and accurately learn those associations and identify potential HIV patterns in large social data sets.

A meta-regression analysis of 41 Australian problem gambling prevalence estimates and their relationship to total spending on electronic gaming machines

Directory of Open Access Journals (Sweden)

Francis Markham

2017-05-01

Full Text Available Abstract Background Many jurisdictions regularly conduct surveys to estimate the prevalence of problem gambling in their adult populations. However, the comparison of such estimates is problematic due to methodological variations between studies. Total consumption theory suggests that an association between mean electronic gaming machine (EGM and casino gambling losses and problem gambling prevalence estimates may exist. If this is the case, then changes in EGM losses may be used as a proxy indicator for changes in problem gambling prevalence. To test for this association this study examines the relationship between aggregated losses on electronic gaming machines (EGMs and problem gambling prevalence estimates for Australian states and territories between 1994 and 2016. Methods A Bayesian meta-regression analysis of 41 cross-sectional problem gambling prevalence estimates was undertaken using EGM gambling losses, year of survey and methodological variations as predictor variables. General population studies of adults in Australian states and territory published before 1 July 2016 were considered in scope. 41 studies were identified, with a total of 267,367 participants. Problem gambling prevalence, moderate-risk problem gambling prevalence, problem gambling screen, administration mode and frequency threshold were extracted from surveys. Administrative data on EGM and casino gambling loss data were extracted from government reports and expressed as the proportion of household disposable income lost. Results Money lost on EGMs is correlated with problem gambling prevalence. An increase of 1% of household disposable income lost on EGMs and in casinos was associated with problem gambling prevalence estimates that were 1.33 times higher [95% credible interval 1.04, 1.71]. There was no clear association between EGM losses and moderate-risk problem gambling prevalence estimates. Moderate-risk problem gambling prevalence estimates were not explained by

A meta-regression analysis of 41 Australian problem gambling prevalence estimates and their relationship to total spending on electronic gaming machines.

Science.gov (United States)

Markham, Francis; Young, Martin; Doran, Bruce; Sugden, Mark

2017-05-23

Many jurisdictions regularly conduct surveys to estimate the prevalence of problem gambling in their adult populations. However, the comparison of such estimates is problematic due to methodological variations between studies. Total consumption theory suggests that an association between mean electronic gaming machine (EGM) and casino gambling losses and problem gambling prevalence estimates may exist. If this is the case, then changes in EGM losses may be used as a proxy indicator for changes in problem gambling prevalence. To test for this association this study examines the relationship between aggregated losses on electronic gaming machines (EGMs) and problem gambling prevalence estimates for Australian states and territories between 1994 and 2016. A Bayesian meta-regression analysis of 41 cross-sectional problem gambling prevalence estimates was undertaken using EGM gambling losses, year of survey and methodological variations as predictor variables. General population studies of adults in Australian states and territory published before 1 July 2016 were considered in scope. 41 studies were identified, with a total of 267,367 participants. Problem gambling prevalence, moderate-risk problem gambling prevalence, problem gambling screen, administration mode and frequency threshold were extracted from surveys. Administrative data on EGM and casino gambling loss data were extracted from government reports and expressed as the proportion of household disposable income lost. Money lost on EGMs is correlated with problem gambling prevalence. An increase of 1% of household disposable income lost on EGMs and in casinos was associated with problem gambling prevalence estimates that were 1.33 times higher [95% credible interval 1.04, 1.71]. There was no clear association between EGM losses and moderate-risk problem gambling prevalence estimates. Moderate-risk problem gambling prevalence estimates were not explained by the models (I 2  ≥ 0.97; R 2  ≤ 0.01). The

AN EFFECTIVE HYBRID SUPPORT VECTOR REGRESSION WITH CHAOS-EMBEDDED BIOGEOGRAPHY-BASED OPTIMIZATION STRATEGY FOR PREDICTION OF EARTHQUAKE-TRIGGERED SLOPE DEFORMATIONS

Directory of Open Access Journals (Sweden)

A. A. Heidari

2015-12-01

Full Text Available Earthquake can pose earth-shattering health hazards to the natural slops and land infrastructures. One of the chief consequences of the earthquakes can be land sliding, which is instigated by durable shaking. In this research, an efficient procedure is proposed to assist the prediction of earthquake-originated slope displacements (EIDS. New hybrid SVM-CBBO strategy is implemented to predict the EIDS. For this purpose, first, chaos paradigm is combined with initialization of BBO to enhance the diversification and intensification capacity of the conventional BBO optimizer. Then, chaotic BBO is developed as the searching scheme to investigate the best values of SVR parameters. In this paper, it will be confirmed that how the new computing approach is effective in prediction of EIDS. The outcomes affirm that the SVR-BBO strategy with chaos can be employed effectively as a predicting tool for evaluating the EIDS.

Predicting Market Impact Costs Using Nonparametric Machine Learning Models.

Directory of Open Access Journals (Sweden)

Saerom Park

Full Text Available Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.

Effect of Machining Velocity in Nanoscale Machining Operations

International Nuclear Information System (INIS)

Islam, Sumaiya; Khondoker, Noman; Ibrahim, Raafat

2015-01-01

The aim of this study is to investigate the generated forces and deformations of single crystal Cu with (100), (110) and (111) crystallographic orientations at nanoscale machining operation. A nanoindenter equipped with nanoscratching attachment was used for machining operations and in-situ observation of a nano scale groove. As a machining parameter, the machining velocity was varied to measure the normal and cutting forces. At a fixed machining velocity, different levels of normal and cutting forces were generated due to different crystallographic orientations of the specimens. Moreover, after machining operation percentage of elastic recovery was measured and it was found that both the elastic and plastic deformations were responsible for producing a nano scale groove within the range of machining velocities from 250-1000 nm/s. (paper)

“Investigations on the machinability of Waspaloy under dry environment”

Science.gov (United States)

Deepu, J.; Kuppan, P.; SBalan, A. S.; Oyyaravelu, R.

2016-09-01

Nickel based superalloy, Waspaloy is extensively used in gas turbine, aerospace and automobile industries because of their unique combination of properties like high strength at elevated temperatures, resistance to chemical degradation and excellent wear resistance in many hostile environments. It is considered as one of the difficult to machine superalloy due to excessive tool wear and poor surface finish. The present paper is an attempt for removing cutting fluids from turning process of Waspaloy and to make the processes environmentally safe. For this purpose, the effect of machining parameters such as cutting speed and feed rate on the cutting force, cutting temperature, surface finish and tool wear were investigated barrier. Consequently, the strength and tool wear resistance and tool life increased significantly. Response Surface Methodology (RSM) has been used for developing and analyzing a mathematical model which describes the relationship between machining parameters and output variables. Subsequently ANOVA was used to check the adequacy of the regression model as well as each machining variables. The optimal cutting parameters were determined based on multi-response optimizations by composite desirability approach in order to minimize cutting force, average surface roughness and maximum flank wear. The results obtained from the experiments shown that machining of Waspaloy using coated carbide tool with special ranges of parameters, cutting fluid could be completely removed from machining process

The use of machine learning and nonlinear statistical tools for ADME prediction.

Science.gov (United States)

Sakiyama, Yojiro

2009-02-01

Absorption, distribution, metabolism and excretion (ADME)-related failure of drug candidates is a major issue for the pharmaceutical industry today. Prediction of ADME by in silico tools has now become an inevitable paradigm to reduce cost and enhance efficiency in pharmaceutical research. Recently, machine learning as well as nonlinear statistical tools has been widely applied to predict routine ADME end points. To achieve accurate and reliable predictions, it would be a prerequisite to understand the concepts, mechanisms and limitations of these tools. Here, we have devised a small synthetic nonlinear data set to help understand the mechanism of machine learning by 2D-visualisation. We applied six new machine learning methods to four different data sets. The methods include Naive Bayes classifier, classification and regression tree, random forest, Gaussian process, support vector machine and k nearest neighbour. The results demonstrated that ensemble learning and kernel machine displayed greater accuracy of prediction than classical methods irrespective of the data set size. The importance of interaction with the engineering field is also addressed. The results described here provide insights into the mechanism of machine learning, which will enable appropriate usage in the future.

Comparative study for different statistical models to optimize cutting parameters of CNC end milling machines

International Nuclear Information System (INIS)

El-Berry, A.; El-Berry, A.; Al-Bossly, A.

2010-01-01

In machining operation, the quality of surface finish is an important requirement for many work pieces. Thus, that is very important to optimize cutting parameters for controlling the required manufacturing quality. Surface roughness parameter (Ra) in mechanical parts depends on turning parameters during the turning process. In the development of predictive models, cutting parameters of feed, cutting speed, depth of cut, are considered as model variables. For this purpose, this study focuses on comparing various machining experiments which using CNC vertical machining center, work pieces was aluminum 6061. Multiple regression models are used to predict the surface roughness at different experiments.

Prediction of hourly PM2.5 using a space-time support vector regression model

Science.gov (United States)

Yang, Wentao; Deng, Min; Xu, Feng; Wang, Hang

2018-05-01

Real-time air quality prediction has been an active field of research in atmospheric environmental science. The existing methods of machine learning are widely used to predict pollutant concentrations because of their enhanced ability to handle complex non-linear relationships. However, because pollutant concentration data, as typical geospatial data, also exhibit spatial heterogeneity and spatial dependence, they may violate the assumptions of independent and identically distributed random variables in most of the machine learning methods. As a result, a space-time support vector regression model is proposed to predict hourly PM2.5 concentrations. First, to address spatial heterogeneity, spatial clustering is executed to divide the study area into several homogeneous or quasi-homogeneous subareas. To handle spatial dependence, a Gauss vector weight function is then developed to determine spatial autocorrelation variables as part of the input features. Finally, a local support vector regression model with spatial autocorrelation variables is established for each subarea. Experimental data on PM2.5 concentrations in Beijing are used to verify whether the results of the proposed model are superior to those of other methods.

Analysis and prediction of dimensions and cost of laser micro-machining internal channel fabrication process

Directory of Open Access Journals (Sweden)

Brabazon D.

2010-06-01

Full Text Available This paper presents the utilisation of Response Surface Methodology (RSM as the prediction tool for the laser micro-machining process. Laser internal microchannels machined using pulsed Nd:YVO4 laser in polycarbonate were investigated. The experiments were carried out according to 33 factorial Design of Experiment (DoE. In this work the three input process set as control parameters were laser power, P; pulse repetition frequency, PRF; and sample translation speed, U. Measured responses were the channel width and the micro-machining operating cost per metre of produced microchannels. The responses were sufficiently predicted within the set micro-machining parameters limits. Two factorial interaction (2FI and quadratic polynomial regression equations for both responses were constructed. It is proposed that the developed prediction equations can be used to find locally optimal micro-machining process parameters under experimental and operational conditions.

Differentiating regressed melanoma from regressed lichenoid keratosis.

Science.gov (United States)

Chan, Aegean H; Shulman, Kenneth J; Lee, Bonnie A

2017-04-01

Distinguishing regressed lichen planus-like keratosis (LPLK) from regressed melanoma can be difficult on histopathologic examination, potentially resulting in mismanagement of patients. We aimed to identify histopathologic features by which regressed melanoma can be differentiated from regressed LPLK. Twenty actively inflamed LPLK, 12 LPLK with regression and 15 melanomas with regression were compared and evaluated by hematoxylin and eosin staining as well as Melan-A, microphthalmia transcription factor (MiTF) and cytokeratin (AE1/AE3) immunostaining. (1) A total of 40% of regressed melanomas showed complete or near complete loss of melanocytes within the epidermis with Melan-A and MiTF immunostaining, while 8% of regressed LPLK exhibited this finding. (2) Necrotic keratinocytes were seen in the epidermis in 33% regressed melanomas as opposed to all of the regressed LPLK. (3) A dense infiltrate of melanophages in the papillary dermis was seen in 40% of regressed melanomas, a feature not seen in regressed LPLK. In summary, our findings suggest that a complete or near complete loss of melanocytes within the epidermis strongly favors a regressed melanoma over a regressed LPLK. In addition, necrotic epidermal keratinocytes and the presence of a dense band-like distribution of dermal melanophages can be helpful in differentiating these lesions. © 2016 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Prediction of Machine Tool Condition Using Support Vector Machine

International Nuclear Information System (INIS)

Wang Peigong; Meng Qingfeng; Zhao Jian; Li Junjie; Wang Xiufeng

2011-01-01

Condition monitoring and predicting of CNC machine tools are investigated in this paper. Considering the CNC machine tools are often small numbers of samples, a condition predicting method for CNC machine tools based on support vector machines (SVMs) is proposed, then one-step and multi-step condition prediction models are constructed. The support vector machines prediction models are used to predict the trends of working condition of a certain type of CNC worm wheel and gear grinding machine by applying sequence data of vibration signal, which is collected during machine processing. And the relationship between different eigenvalue in CNC vibration signal and machining quality is discussed. The test result shows that the trend of vibration signal Peak-to-peak value in surface normal direction is most relevant to the trend of surface roughness value. In trends prediction of working condition, support vector machine has higher prediction accuracy both in the short term ('One-step') and long term (multi-step) prediction compared to autoregressive (AR) model and the RBF neural network. Experimental results show that it is feasible to apply support vector machine to CNC machine tool condition prediction.

Applying machine learning to predict patient-specific current CD 4 ...

African Journals Online (AJOL)

This work shows the application of machine learning to predict current CD4 cell count of an HIV-positive patient using genome sequences, viral load and time. A regression model predicting actual CD4 cell counts and a classification model predicting if a patient's CD4 cell count is less than 200 was built using a support ...

Environmentally Friendly Machining

CERN Document Server

Dixit, U S; Davim, J Paulo

2012-01-01

Environment-Friendly Machining provides an in-depth overview of environmentally-friendly machining processes, covering numerous different types of machining in order to identify which practice is the most environmentally sustainable. The book discusses three systems at length: machining with minimal cutting fluid, air-cooled machining and dry machining. Also covered is a way to conserve energy during machining processes, along with useful data and detailed descriptions for developing and utilizing the most efficient modern machining tools. Researchers and engineers looking for sustainable machining solutions will find Environment-Friendly Machining to be a useful volume.

A machine learning model with human cognitive biases capable of learning from small and biased datasets.

Science.gov (United States)

Taniguchi, Hidetaka; Sato, Hiroshi; Shirakawa, Tomohiro

2018-05-09

Human learners can generalize a new concept from a small number of samples. In contrast, conventional machine learning methods require large amounts of data to address the same types of problems. Humans have cognitive biases that promote fast learning. Here, we developed a method to reduce the gap between human beings and machines in this type of inference by utilizing cognitive biases. We implemented a human cognitive model into machine learning algorithms and compared their performance with the currently most popular methods, naïve Bayes, support vector machine, neural networks, logistic regression and random forests. We focused on the task of spam classification, which has been studied for a long time in the field of machine learning and often requires a large amount of data to obtain high accuracy. Our models achieved superior performance with small and biased samples in comparison with other representative machine learning methods.

A New Method of 3D Facial Expression Animation

Directory of Open Access Journals (Sweden)

Shuo Sun

2014-01-01

Full Text Available Animating expressive facial animation is a very challenging topic within the graphics community. In this paper, we introduce a novel ERI (expression ratio image driving framework based on SVR and MPEG-4 for automatic 3D facial expression animation. Through using the method of support vector regression (SVR, the framework can learn and forecast the regression relationship between the facial animation parameters (FAPs and the parameters of expression ratio image. Firstly, we build a 3D face animation system driven by FAP. Secondly, through using the method of principle component analysis (PCA, we generate the parameter sets of eigen-ERI space, which will rebuild reasonable expression ratio image. Then we learn a model with the support vector regression mapping, and facial animation parameters can be synthesized quickly with the parameters of eigen-ERI. Finally, we implement our 3D face animation system driving by the result of FAP and it works effectively.

Support vector regression model for the estimation of γ-ray buildup factors for multi-layer shields

International Nuclear Information System (INIS)

Trontl, Kresimir; Smuc, Tomislav; Pevec, Dubravko

2007-01-01

The accuracy of the point-kernel method, which is a widely used practical tool for γ-ray shielding calculations, strongly depends on the quality and accuracy of buildup factors used in the calculations. Although, buildup factors for single-layer shields comprised of a single material are well known, calculation of buildup factors for stratified shields, each layer comprised of different material or a combination of materials, represent a complex physical problem. Recently, a new compact mathematical model for multi-layer shield buildup factor representation has been suggested for embedding into point-kernel codes thus replacing traditionally generated complex mathematical expressions. The new regression model is based on support vector machines learning technique, which is an extension of Statistical Learning Theory. The paper gives complete description of the novel methodology with results pertaining to realistic engineering multi-layer shielding geometries. The results based on support vector regression machine learning confirm that this approach provides a framework for general, accurate and computationally acceptable multi-layer buildup factor model

An Event-Triggered Machine Learning Approach for Accelerometer-Based Fall Detection.

Science.gov (United States)

Putra, I Putu Edy Suardiyana; Brusey, James; Gaura, Elena; Vesilo, Rein

2017-12-22

The fixed-size non-overlapping sliding window (FNSW) and fixed-size overlapping sliding window (FOSW) approaches are the most commonly used data-segmentation techniques in machine learning-based fall detection using accelerometer sensors. However, these techniques do not segment by fall stages (pre-impact, impact, and post-impact) and thus useful information is lost, which may reduce the detection rate of the classifier. Aligning the segment with the fall stage is difficult, as the segment size varies. We propose an event-triggered machine learning (EvenT-ML) approach that aligns each fall stage so that the characteristic features of the fall stages are more easily recognized. To evaluate our approach, two publicly accessible datasets were used. Classification and regression tree (CART), k -nearest neighbor ( k -NN), logistic regression (LR), and the support vector machine (SVM) were used to train the classifiers. EvenT-ML gives classifier F-scores of 98% for a chest-worn sensor and 92% for a waist-worn sensor, and significantly reduces the computational cost compared with the FNSW- and FOSW-based approaches, with reductions of up to 8-fold and 78-fold, respectively. EvenT-ML achieves a significantly better F-score than existing fall detection approaches. These results indicate that aligning feature segments with fall stages significantly increases the detection rate and reduces the computational cost.

Regression Models and Fuzzy Logic Prediction of TBM Penetration Rate

Directory of Open Access Journals (Sweden)

Minh Vu Trieu

2017-03-01

Full Text Available This paper presents statistical analyses of rock engineering properties and the measured penetration rate of tunnel boring machine (TBM based on the data of an actual project. The aim of this study is to analyze the influence of rock engineering properties including uniaxial compressive strength (UCS, Brazilian tensile strength (BTS, rock brittleness index (BI, the distance between planes of weakness (DPW, and the alpha angle (Alpha between the tunnel axis and the planes of weakness on the TBM rate of penetration (ROP. Four (4 statistical regression models (two linear and two nonlinear are built to predict the ROP of TBM. Finally a fuzzy logic model is developed as an alternative method and compared to the four statistical regression models. Results show that the fuzzy logic model provides better estimations and can be applied to predict the TBM performance. The R-squared value (R2 of the fuzzy logic model scores the highest value of 0.714 over the second runner-up of 0.667 from the multiple variables nonlinear regression model.

Regression Models and Fuzzy Logic Prediction of TBM Penetration Rate

Science.gov (United States)

Minh, Vu Trieu; Katushin, Dmitri; Antonov, Maksim; Veinthal, Renno

2017-03-01

This paper presents statistical analyses of rock engineering properties and the measured penetration rate of tunnel boring machine (TBM) based on the data of an actual project. The aim of this study is to analyze the influence of rock engineering properties including uniaxial compressive strength (UCS), Brazilian tensile strength (BTS), rock brittleness index (BI), the distance between planes of weakness (DPW), and the alpha angle (Alpha) between the tunnel axis and the planes of weakness on the TBM rate of penetration (ROP). Four (4) statistical regression models (two linear and two nonlinear) are built to predict the ROP of TBM. Finally a fuzzy logic model is developed as an alternative method and compared to the four statistical regression models. Results show that the fuzzy logic model provides better estimations and can be applied to predict the TBM performance. The R-squared value (R2) of the fuzzy logic model scores the highest value of 0.714 over the second runner-up of 0.667 from the multiple variables nonlinear regression model.

Privacy-Preserving Distributed Linear Regression on High-Dimensional Data

Directory of Open Access Journals (Sweden)

Gascón Adrià

2017-10-01

Full Text Available We propose privacy-preserving protocols for computing linear regression models, in the setting where the training dataset is vertically distributed among several parties. Our main contribution is a hybrid multi-party computation protocol that combines Yao’s garbled circuits with tailored protocols for computing inner products. Like many machine learning tasks, building a linear regression model involves solving a system of linear equations. We conduct a comprehensive evaluation and comparison of different techniques for securely performing this task, including a new Conjugate Gradient Descent (CGD algorithm. This algorithm is suitable for secure computation because it uses an efficient fixed-point representation of real numbers while maintaining accuracy and convergence rates comparable to what can be obtained with a classical solution using floating point numbers. Our technique improves on Nikolaenko et al.’s method for privacy-preserving ridge regression (S&P 2013, and can be used as a building block in other analyses. We implement a complete system and demonstrate that our approach is highly scalable, solving data analysis problems with one million records and one hundred features in less than one hour of total running time.

Hepatitis C treatment among racial and ethnic groups in the IDEAL trial.

Science.gov (United States)

Muir, A J; Hu, K-Q; Gordon, S C; Koury, K; Boparai, N; Noviello, S; Albrecht, J K; Sulkowski, M S; McCone, J

2011-04-01

Previous studies of chronic hepatitis C virus (HCV) treatment have demonstrated variations in response among racial and ethnic groups including poorer efficacy rates among African American and Hispanic patients. The individualized dosing efficacy vs flat dosing to assess optimaL pegylated interferon therapy (IDEAL) trial enrolled 3070 patients from 118 United States centres to compare treatment with peginterferon (PEG-IFN) alfa-2a and ribavirin (RBV) and two doses of PEG-IFN alfa-2b and RBV. This analysis examines treatment response among the major racial and ethnic groups in the trial. Overall, sustained virologic response (SVR) rates were 44% for white, 22% for African American, 38% for Hispanic and 59% for Asian American patients. For patients with undetectable HCV RNA at treatment week 4, the positive predictive value of SVR was 86% for white, 92% for African American, 83% for Hispanic and 89% for Asian American patients. The positive predictive values of SVR in those with undetectable HCV RNA at treatment week 12 ranged from 72% to 81%. Multivariate regression analysis using baseline characteristics demonstrated that treatment regimen was not a predictor of SVR. Despite wide-ranging SVR rates among the different racial and ethnic groups, white and Hispanic patients had similar SVR rates. In all groups, treatment response was largely determined by antiviral activity in the first 12 weeks of treatment. Therefore, decisions regarding HCV treatment should consider the predictive value of the early on-treatment response, not just baseline characteristics, such as race and ethnicity. © 2010 Blackwell Publishing Ltd.

Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests

Directory of Open Access Journals (Sweden)

Santana Isabel

2011-08-01

Full Text Available Abstract Background Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI, but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test. Results Press' Q test showed that all classifiers performed better than chance alone (p Conclusions When taking into account sensitivity, specificity and overall classification accuracy Random Forests and Linear Discriminant analysis rank first among all the classifiers tested in prediction of dementia using several neuropsychological tests. These methods may be used to improve accuracy, sensitivity and specificity of Dementia predictions from neuropsychological testing.

Hybrid machining processes perspectives on machining and finishing

CERN Document Server

Gupta, Kapil; Laubscher, R F

2016-01-01

This book describes various hybrid machining and finishing processes. It gives a critical review of the past work based on them as well as the current trends and research directions. For each hybrid machining process presented, the authors list the method of material removal, machining system, process variables and applications. This book provides a deep understanding of the need, application and mechanism of hybrid machining processes.

WekaPyScript: Classification, Regression, and Filter Schemes for WEKA Implemented in Python

Directory of Open Access Journals (Sweden)

Christopher Beckham

2016-08-01

Full Text Available WekaPyScript is a package for the machine learning software WEKA that allows learning algorithms and preprocessing methods for classification and regression to be written in Python, as opposed to WEKA’s implementation language, Java. This opens up WEKA to its machine learning and scientific computing ecosystem. Furthermore, due to Python’s minimalist syntax, learning algorithms and preprocessing methods can be prototyped easily and utilised from within WEKA. WekaPyScript works by running a local Python server using the host’s installation of Python; as a result, any libraries installed in the host installation can be leveraged when writing a script for WekaPyScript. Three example scripts (two learning algorithms and one preprocessing method are presented.

Machine learning action parameters in lattice quantum chromodynamics

Science.gov (United States)

Shanahan, Phiala E.; Trewartha, Daniel; Detmold, William

2018-05-01

Numerical lattice quantum chromodynamics studies of the strong interaction are important in many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. The high information content and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.

Machine learning derived risk prediction of anorexia nervosa.

Science.gov (United States)

Guo, Yiran; Wei, Zhi; Keating, Brendan J; Hakonarson, Hakon

2016-01-20

Anorexia nervosa (AN) is a complex psychiatric disease with a moderate to strong genetic contribution. In addition to conventional genome wide association (GWA) studies, researchers have been using machine learning methods in conjunction with genomic data to predict risk of diseases in which genetics play an important role. In this study, we collected whole genome genotyping data on 3940 AN cases and 9266 controls from the Genetic Consortium for Anorexia Nervosa (GCAN), the Wellcome Trust Case Control Consortium 3 (WTCCC3), Price Foundation Collaborative Group and the Children's Hospital of Philadelphia (CHOP), and applied machine learning methods for predicting AN disease risk. The prediction performance is measured by area under the receiver operating characteristic curve (AUC), indicating how well the model distinguishes cases from unaffected control subjects. Logistic regression model with the lasso penalty technique generated an AUC of 0.693, while Support Vector Machines and Gradient Boosted Trees reached AUC's of 0.691 and 0.623, respectively. Using different sample sizes, our results suggest that larger datasets are required to optimize the machine learning models and achieve higher AUC values. To our knowledge, this is the first attempt to assess AN risk based on genome wide genotype level data. Future integration of genomic, environmental and family-based information is likely to improve the AN risk evaluation process, eventually benefitting AN patients and families in the clinical setting.

Support Vector Machine and Application in Seizure Prediction

KAUST Repository

Qiu, Simeng

2018-04-01

Nowadays, Machine learning (ML) has been utilized in various kinds of area which across the range from engineering field to business area. In this paper, we first present several kernel machine learning methods of solving classification, regression and clustering problems. These have good performance but also have some limitations. We present examples to each method and analyze the advantages and disadvantages for solving different scenarios. Then we focus on one of the most popular classification methods, Support Vectors Machine (SVM). In addition, we introduce the basic theory, advantages and scenarios of using Support Vector Machine (SVM) deal with classification problems. We also explain a convenient approach of tacking SVM problems which are called Sequential Minimal Optimization (SMO). Moreover, one class SVM can be understood in a different way which is called Support Vector Data Description (SVDD). This is a famous non-linear model problem compared with SVM problems, SVDD can be solved by utilizing Gaussian RBF kernel function combined with SMO. At last, we compared the difference and performance of SVM-SMO implementation and SVM-SVDD implementation. About the application part, we utilized SVM method to handle seizure forecasting in canine epilepsy, after comparing the results from different methods such as random forest, extremely randomized tree, and SVM to classify preictal (pre-seizure) and interictal (interval-seizure) binary data. We draw the conclusion that SVM has the best performance.

Twin Support Vector Machine: A review from 2007 to 2014

Directory of Open Access Journals (Sweden)

Divya Tomar

2015-03-01

Full Text Available Twin Support Vector Machine (TWSVM is an emerging machine learning method suitable for both classification and regression problems. It utilizes the concept of Generalized Eigen-values Proximal Support Vector Machine (GEPSVM and finds two non-parallel planes for each class by solving a pair of Quadratic Programming Problems. It enhances the computational speed as compared to the traditional Support Vector Machine (SVM. TWSVM was initially constructed to solve binary classification problems; later researchers successfully extended it for multi-class problem domain. TWSVM always gives promising empirical results, due to which it has many attractive features which enhance its applicability. This paper presents the research development of TWSVM in recent years. This study is divided into two main broad categories - variant based and multi-class based TWSVM methods. The paper primarily discusses the basic concept of TWSVM and highlights its applications in recent years. A comparative analysis of various research contributions based on TWSVM is also presented. This is helpful for researchers to effectively utilize the TWSVM as an emergent research methodology and encourage them to work further in the performance enhancement of TWSVM.

Real-world cure rates for hepatitis C virus treatments that include simeprevir and/or sofosbuvir are comparable to clinical trial results.

Science.gov (United States)

Bichoupan, Kian; Tandon, Neeta; Crismale, James F; Hartman, Joshua; Del Bello, David; Patel, Neal; Chekuri, Sweta; Harty, Alyson; Ng, Michel; Sigel, Keith M; Bansal, Meena B; Grewal, Priya; Chang, Charissa Y; Leong, Jennifer; Im, Gene Y; Liu, Lawrence U; Odin, Joseph A; Bach, Nancy; Friedman, Scott L; Schiano, Thomas D; Perumalswami, Ponni V; Dieterich, Douglas T; Branch, Andrea D

2017-11-12

To assess the real-world effectiveness and cost of simeprevir (SMV), and/or sofosbuvir (SOF)-based therapy for chronic hepatitis C virus (HCV) infection. The real-world performance of patients treated with SMV/SOF ± ribavirin (RBV), SOF/RBV, and SOF/RBV with pegylated-interferon (PEG) were analyzed in a consecutive series of 508 patients with chronic HCV infection treated at a single academic medical center. Patients with genotypes 1 through 4 were included. Rates of sustained virological response - the absence of a detectable serum HCV RNA 12 wk after the end of treatment [sustained virological response (SVR) 12] - were calculated on an intention-to-treat basis. Costs were calculated from the payer's perspective using Medicare/Medicaid fees and Redbook Wholesale Acquisition Costs. Patient-related factors associated with SVR12 were identified using multivariable logistic regression. SVR12 rates were as follows: 86% (95%CI: 80%-91%) among 178 patients on SMV/SOF ± RBV; 62% (95%CI: 55%-68%) among 234 patients on SOF/RBV; and 78% (95%CI: 68%-86%) among 96 patients on SOF/PEG/RBV. Mean costs-per-SVR12 were $174442 (standard deviation: ± $18588) for SMV/SOF ± RBV; $223003 (± $77946) for SOF/RBV; and $126496 (± $31052) for SOF/PEG/RBV. Among patients on SMV/SOF ± RBV, SVR12 was less likely in patients previously treated with a protease inhibitor [odds ratio (OR): 0.20, 95%CI: 0.06-0.56]. Higher bilirubin (OR: 0.47, 95%CI: 0.30-0.69) reduced the likelihood of SVR12 among patients on SOF/RBV, while FIB-4 score ≥ 3.25 reduced the likelihood of SVR12 (OR: 0.18, 95%CI: 0.05-0.59) among those on SOF/PEG/RBV. SVR12 rates for SMV and/or SOF-based regimens in a diverse real-world population are comparable to those in clinical trials. Treatment failure accounts for 27% of costs.

Liver Stiffness Decreases Rapidly in Response to Successful Hepatitis C Treatment and Then Plateaus.

Directory of Open Access Journals (Sweden)

Sweta Chekuri

Full Text Available To investigate the impact of a sustained virological response (SVR to hepatitis C virus (HCV treatment on liver stiffness (LS.LS, measured by transient elastography (FibroScan, demographic and laboratory data of patients treated with interferon (IFN-containing or IFN-free regimens who had an SVR24 (undetectable HCV viral load 24 weeks after the end of treatment were analyzed using two-tailed paired t-tests, Mann-Whitney Wilcoxon Signed-rank tests and linear regression. Two time intervals were investigated: pre-treatment to SVR24 and SVR24 to the end of follow-up. LS scores ≥ 12.5 kPa indicated LS-defined cirrhosis. A p-value below 0.05 was considered statistically significant.The median age of the patients (n = 100 was 60 years [IQR (interquartile range 54-64; 72% were male; 60% were Caucasian; and 42% had cirrhosis pre-treatment according to the FibroScan measurement. The median LS score dropped from 10.40 kPa (IQR: 7.25-18.60 pre-treatment to 7.60 kPa (IQR: 5.60-12.38 at SVR24, p <0.01. Among the 42 patients with LS-defined cirrhosis pre-treatment, 25 (60% of patients still had LS scores ≥ 12.5 kPa at SVR24, indicating the persistence of cirrhosis. The median change in LS was similar in patients receiving IFN-containing and IFN-free regimens: -1.95 kPa (IQR: -5.75 --0.38 versus -2.40 kPa (IQR: -7.70 --0.23, p = 0.74. Among 56 patients with a post-SVR24 LS measurement, the LS score changed by an additional -0.90 kPa (IQR: -2.98-0.5 during a median follow-up time of 1.17 (IQR: 0.88-1.63 years, which was not a statistically significant decrease (p = 0.99.LS decreased from pre-treatment to SVR24, but did not decrease significantly during additional follow-up. Earlier treatment may be needed to reduce the burden of liver disease.

Development of Predictive QSAR Models of 4-Thiazolidinones Antitrypanosomal Activity using Modern Machine Learning Algorithms.

Science.gov (United States)

Kryshchyshyn, Anna; Devinyak, Oleg; Kaminskyy, Danylo; Grellier, Philippe; Lesyk, Roman

2017-11-14

This paper presents novel QSAR models for the prediction of antitrypanosomal activity among thiazolidines and related heterocycles. The performance of four machine learning algorithms: Random Forest regression, Stochastic gradient boosting, Multivariate adaptive regression splines and Gaussian processes regression have been studied in order to reach better levels of predictivity. The results for Random Forest and Gaussian processes regression are comparable and outperform other studied methods. The preliminary descriptor selection with Boruta method improved the outcome of machine learning methods. The two novel QSAR-models developed with Random Forest and Gaussian processes regression algorithms have good predictive ability, which was proved by the external evaluation of the test set with corresponding Q 2 ext =0.812 and Q 2 ext =0.830. The obtained models can be used further for in silico screening of virtual libraries in the same chemical domain in order to find new antitrypanosomal agents. Thorough analysis of descriptors influence in the QSAR models and interpretation of their chemical meaning allows to highlight a number of structure-activity relationships. The presence of phenyl rings with electron-withdrawing atoms or groups in para-position, increased number of aromatic rings, high branching but short chains, high HOMO energy, and the introduction of 1-substituted 2-indolyl fragment into the molecular structure have been recognized as trypanocidal activity prerequisites. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

A New Approach for Mobile Advertising Click-Through Rate Estimation Based on Deep Belief Nets

Directory of Open Access Journals (Sweden)

Jie-Hao Chen

2017-01-01

Full Text Available In recent years, with the rapid development of mobile Internet and its business applications, mobile advertising Click-Through Rate (CTR estimation has become a hot research direction in the field of computational advertising, which is used to achieve accurate advertisement delivery for the best benefits in the three-side game between media, advertisers, and audiences. Current research on the estimation of CTR mainly uses the methods and models of machine learning, such as linear model or recommendation algorithms. However, most of these methods are insufficient to extract the data features and cannot reflect the nonlinear relationship between different features. In order to solve these problems, we propose a new model based on Deep Belief Nets to predict the CTR of mobile advertising, which combines together the powerful data representation and feature extraction capability of Deep Belief Nets, with the advantage of simplicity of traditional Logistic Regression models. Based on the training dataset with the information of over 40 million mobile advertisements during a period of 10 days, our experiments show that our new model has better estimation accuracy than the classic Logistic Regression (LR model by 5.57% and Support Vector Regression (SVR model by 5.80%.

Machine learning to predict the occurrence of bisphosphonate-related osteonecrosis of the jaw associated with dental extraction: A preliminary report.

Science.gov (United States)

Kim, Dong Wook; Kim, Hwiyoung; Nam, Woong; Kim, Hyung Jun; Cha, In-Ho

2018-04-23

The aim of this study was to build and validate five types of machine learning models that can predict the occurrence of BRONJ associated with dental extraction in patients taking bisphosphonates for the management of osteoporosis. A retrospective review of the medical records was conducted to obtain cases and controls for the study. Total 125 patients consisting of 41 cases and 84 controls were selected for the study. Five machine learning prediction algorithms including multivariable logistic regression model, decision tree, support vector machine, artificial neural network, and random forest were implemented. The outputs of these models were compared with each other and also with conventional methods, such as serum CTX level. Area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the results. The performance of machine learning models was significantly superior to conventional statistical methods and single predictors. The random forest model yielded the best performance (AUC = 0.973), followed by artificial neural network (AUC = 0.915), support vector machine (AUC = 0.882), logistic regression (AUC = 0.844), decision tree (AUC = 0.821), drug holiday alone (AUC = 0.810), and CTX level alone (AUC = 0.630). Machine learning methods showed superior performance in predicting BRONJ associated with dental extraction compared to conventional statistical methods using drug holiday and serum CTX level. Machine learning can thus be applied in a wide range of clinical studies. Copyright © 2017. Published by Elsevier Inc.

Classification of Listeria monocytogenes persistence in retail delicatessen environments using expert elicitation and machine learning.

Science.gov (United States)

Vangay, P; Steingrimsson, J; Wiedmann, M; Stasiewicz, M J

2014-10-01

Increasing evidence suggests that persistence of Listeria monocytogenes in food processing plants has been the underlying cause of a number of human listeriosis outbreaks. This study extracts criteria used by food safety experts in determining bacterial persistence in the environment, using retail delicatessen operations as a model. Using the Delphi method, we conducted an expert elicitation with 10 food safety experts from academia, industry, and government to classify L. monocytogenes persistence based on environmental sampling results collected over six months for 30 retail delicatessen stores. The results were modeled using variations of random forest, support vector machine, logistic regression, and linear regression; variable importance values of random forest and support vector machine models were consolidated to rank important variables in the experts' classifications. The duration of subtype isolation ranked most important across all expert categories. Sampling site category also ranked high in importance and validation errors doubled when this covariate was removed. Support vector machine and random forest models successfully classified the data with average validation errors of 3.1% and 2.2% (n = 144), respectively. Our findings indicate that (i) the frequency of isolations over time and sampling site information are critical factors for experts determining subtype persistence, (ii) food safety experts from different sectors may not use the same criteria in determining persistence, and (iii) machine learning models have potential for future use in environmental surveillance and risk management programs. Future work is necessary to validate the accuracy of expert and machine classification against biological measurement of L. monocytogenes persistence. © 2014 Society for Risk Analysis.

Comparison of naïve Bayes and logistic regression for computer-aided diagnosis of breast masses using ultrasound imaging

Science.gov (United States)

Cary, Theodore W.; Cwanger, Alyssa; Venkatesh, Santosh S.; Conant, Emily F.; Sehgal, Chandra M.

2012-03-01

This study compares the performance of two proven but very different machine learners, Naïve Bayes and logistic regression, for differentiating malignant and benign breast masses using ultrasound imaging. Ultrasound images of 266 masses were analyzed quantitatively for shape, echogenicity, margin characteristics, and texture features. These features along with patient age, race, and mammographic BI-RADS category were used to train Naïve Bayes and logistic regression classifiers to diagnose lesions as malignant or benign. ROC analysis was performed using all of the features and using only a subset that maximized information gain. Performance was determined by the area under the ROC curve, Az, obtained from leave-one-out cross validation. Naïve Bayes showed significant variation (Az 0.733 +/- 0.035 to 0.840 +/- 0.029, P machine learning models for characterizing solid breast masses on ultrasound.

Classification of older adults with/without a fall history using machine learning methods.

Science.gov (United States)

Lin Zhang; Ou Ma; Fabre, Jennifer M; Wood, Robert H; Garcia, Stephanie U; Ivey, Kayla M; McCann, Evan D

2015-01-01

Falling is a serious problem in an aged society such that assessment of the risk of falls for individuals is imperative for the research and practice of falls prevention. This paper introduces an application of several machine learning methods for training a classifier which is capable of classifying individual older adults into a high risk group and a low risk group (distinguished by whether or not the members of the group have a recent history of falls). Using a 3D motion capture system, significant gait features related to falls risk are extracted. By training these features, classification hypotheses are obtained based on machine learning techniques (K Nearest-neighbour, Naive Bayes, Logistic Regression, Neural Network, and Support Vector Machine). Training and test accuracies with sensitivity and specificity of each of these techniques are assessed. The feature adjustment and tuning of the machine learning algorithms are discussed. The outcome of the study will benefit the prediction and prevention of falls.

Machine terms dictionary

Energy Technology Data Exchange (ETDEWEB)

NONE

1979-04-15

This book gives descriptions of machine terms which includes machine design, drawing, the method of machine, machine tools, machine materials, automobile, measuring and controlling, electricity, basic of electron, information technology, quality assurance, Auto CAD and FA terms and important formula of mechanical engineering.

A unified and comprehensible view of parametric and kernel methods for genomic prediction with application to rice

Directory of Open Access Journals (Sweden)

Laval Jacquin

2016-08-01

Full Text Available One objective of this study was to provide readers with a clear and unified understanding ofparametric statistical and kernel methods, used for genomic prediction, and to compare some ofthese in the context of rice breeding for quantitative traits. Furthermore, another objective wasto provide a simple and user-friendly R package, named KRMM, which allows users to performRKHS regression with several kernels. After introducing the concept of regularized empiricalrisk minimization, the connections between well-known parametric and kernel methods suchas Ridge regression (i.e. genomic best linear unbiased predictor (GBLUP and reproducingkernel Hilbert space (RKHS regression were reviewed. Ridge regression was then reformulatedso as to show and emphasize the advantage of the kernel trick concept, exploited by kernelmethods in the context of epistatic genetic architectures, over parametric frameworks used byconventional methods. Some parametric and kernel methods; least absolute shrinkage andselection operator (LASSO, GBLUP, support vector machine regression (SVR and RKHSregression were thereupon compared for their genomic predictive ability in the context of ricebreeding using three real data sets. Among the compared methods, RKHS regression and SVRwere often the most accurate methods for prediction followed by GBLUP and LASSO. An Rfunction which allows users to perform RR-BLUP of marker effects, GBLUP and RKHS regression,with a Gaussian, Laplacian, polynomial or ANOVA kernel, in a reasonable computation time hasbeen developed. Moreover, a modified version of this function, which allows users to tune kernelsfor RKHS regression, has also been developed and parallelized for HPC Linux clusters. The corresponding KRMM package and all scripts have been made publicly available.

ATLS Hypovolemic Shock Classification by Prediction of Blood Loss in Rats Using Regression Models.

Science.gov (United States)

Choi, Soo Beom; Choi, Joon Yul; Park, Jee Soo; Kim, Deok Won

2016-07-01

In our previous study, our input data set consisted of 78 rats, the blood loss in percent as a dependent variable, and 11 independent variables (heart rate, systolic blood pressure, diastolic blood pressure, mean arterial pressure, pulse pressure, respiration rate, temperature, perfusion index, lactate concentration, shock index, and new index (lactate concentration/perfusion)). The machine learning methods for multicategory classification were applied to a rat model in acute hemorrhage to predict the four Advanced Trauma Life Support (ATLS) hypovolemic shock classes for triage in our previous study. However, multicategory classification is much more difficult and complicated than binary classification. We introduce a simple approach for classifying ATLS hypovolaemic shock class by predicting blood loss in percent using support vector regression and multivariate linear regression (MLR). We also compared the performance of the classification models using absolute and relative vital signs. The accuracies of support vector regression and MLR models with relative values by predicting blood loss in percent were 88.5% and 84.6%, respectively. These were better than the best accuracy of 80.8% of the direct multicategory classification using the support vector machine one-versus-one model in our previous study for the same validation data set. Moreover, the simple MLR models with both absolute and relative values could provide possibility of the future clinical decision support system for ATLS classification. The perfusion index and new index were more appropriate with relative changes than absolute values.

A methodology for the design of experiments in computational intelligence with multiple regression models.

Science.gov (United States)

Fernandez-Lozano, Carlos; Gestal, Marcos; Munteanu, Cristian R; Dorado, Julian; Pazos, Alejandro

2016-01-01

The design of experiments and the validation of the results achieved with them are vital in any research study. This paper focuses on the use of different Machine Learning approaches for regression tasks in the field of Computational Intelligence and especially on a correct comparison between the different results provided for different methods, as those techniques are complex systems that require further study to be fully understood. A methodology commonly accepted in Computational intelligence is implemented in an R package called RRegrs. This package includes ten simple and complex regression models to carry out predictive modeling using Machine Learning and well-known regression algorithms. The framework for experimental design presented herein is evaluated and validated against RRegrs. Our results are different for three out of five state-of-the-art simple datasets and it can be stated that the selection of the best model according to our proposal is statistically significant and relevant. It is of relevance to use a statistical approach to indicate whether the differences are statistically significant using this kind of algorithms. Furthermore, our results with three real complex datasets report different best models than with the previously published methodology. Our final goal is to provide a complete methodology for the use of different steps in order to compare the results obtained in Computational Intelligence problems, as well as from other fields, such as for bioinformatics, cheminformatics, etc., given that our proposal is open and modifiable.

A methodology for the design of experiments in computational intelligence with multiple regression models

Directory of Open Access Journals (Sweden)

Carlos Fernandez-Lozano

2016-12-01

Full Text Available The design of experiments and the validation of the results achieved with them are vital in any research study. This paper focuses on the use of different Machine Learning approaches for regression tasks in the field of Computational Intelligence and especially on a correct comparison between the different results provided for different methods, as those techniques are complex systems that require further study to be fully understood. A methodology commonly accepted in Computational intelligence is implemented in an R package called RRegrs. This package includes ten simple and complex regression models to carry out predictive modeling using Machine Learning and well-known regression algorithms. The framework for experimental design presented herein is evaluated and validated against RRegrs. Our results are different for three out of five state-of-the-art simple datasets and it can be stated that the selection of the best model according to our proposal is statistically significant and relevant. It is of relevance to use a statistical approach to indicate whether the differences are statistically significant using this kind of algorithms. Furthermore, our results with three real complex datasets report different best models than with the previously published methodology. Our final goal is to provide a complete methodology for the use of different steps in order to compare the results obtained in Computational Intelligence problems, as well as from other fields, such as for bioinformatics, cheminformatics, etc., given that our proposal is open and modifiable.

Some relations between quantum Turing machines and Turing machines

OpenAIRE

Sicard, Andrés; Vélez, Mario

1999-01-01

For quantum Turing machines we present three elements: Its components, its time evolution operator and its local transition function. The components are related with the components of deterministic Turing machines, the time evolution operator is related with the evolution of reversible Turing machines and the local transition function is related with the transition function of probabilistic and reversible Turing machines.

Prediction of Baseflow Index of Catchments using Machine Learning Algorithms

Science.gov (United States)

Yadav, B.; Hatfield, K.

2017-12-01

We present the results of eight machine learning techniques for predicting the baseflow index (BFI) of ungauged basins using a surrogate of catchment scale climate and physiographic data. The tested algorithms include ordinary least squares, ridge regression, least absolute shrinkage and selection operator (lasso), elasticnet, support vector machine, gradient boosted regression trees, random forests, and extremely randomized trees. Our work seeks to identify the dominant controls of BFI that can be readily obtained from ancillary geospatial databases and remote sensing measurements, such that the developed techniques can be extended to ungauged catchments. More than 800 gauged catchments spanning the continental United States were selected to develop the general methodology. The BFI calculation was based on the baseflow separated from daily streamflow hydrograph using HYSEP filter. The surrogate catchment attributes were compiled from multiple sources including digital elevation model, soil, landuse, climate data, other publicly available ancillary and geospatial data. 80% catchments were used to train the ML algorithms, and the remaining 20% of the catchments were used as an independent test set to measure the generalization performance of fitted models. A k-fold cross-validation using exhaustive grid search was used to fit the hyperparameters of each model. Initial model development was based on 19 independent variables, but after variable selection and feature ranking, we generated revised sparse models of BFI prediction that are based on only six catchment attributes. These key predictive variables selected after the careful evaluation of bias-variance tradeoff include average catchment elevation, slope, fraction of sand, permeability, temperature, and precipitation. The most promising algorithms exceeding an accuracy score (r-square) of 0.7 on test data include support vector machine, gradient boosted regression trees, random forests, and extremely randomized

Wire Electrical Discharge Machining of a Hybrid Composite: Evaluation of Kerf Width and Surface Roughness

Directory of Open Access Journals (Sweden)

Abdil KUŞ

2016-06-01

Full Text Available In this study, the machinability characteristics of Al/B4C-Gr hybrid composite were investigated using wire electrical discharge machining (WEDM. In the experiments, the machining parameters of wire speed, pulse-on time and pulse-off time were varied in order to explaiın their effects on machining performance, including the width of slit (kerf and surface roughness values (Rz and Rt. According to the Taguchi quality design concept, a L18 (21×32 orthogonal array was used to determine the S/N ratio, and analysis of variance (ANOVA and the F-test were used to indicate the significant machining parameters affecting the machining performance. From the ANOVA and F-test results, the significant factors were determined for each of the machining performance criteria of kerf, Rz and Rt. The variations of kerf, Rz and Rt with the machining parameters were statistically modeled via the regression analysis method. The optimum levels of the control factors for kerf, Rz and Rt were specified as A1B1C1, A1B1C2 and A1B1C2, respectively. The correlation coefficients of the predictive equations developed for kerf, Rz and Rt were calculated as 0.98, 0.828 and 0.855, respectively.

Contemporary machine learning: techniques for practitioners in the physical sciences

Science.gov (United States)

Spears, Brian

2017-10-01

Machine learning is the science of using computers to find relationships in data without explicitly knowing or programming those relationships in advance. Often without realizing it, we employ machine learning every day as we use our phones or drive our cars. Over the last few years, machine learning has found increasingly broad application in the physical sciences. This most often involves building a model relationship between a dependent, measurable output and an associated set of controllable, but complicated, independent inputs. The methods are applicable both to experimental observations and to databases of simulated output from large, detailed numerical simulations. In this tutorial, we will present an overview of current tools and techniques in machine learning - a jumping-off point for researchers interested in using machine learning to advance their work. We will discuss supervised learning techniques for modeling complicated functions, beginning with familiar regression schemes, then advancing to more sophisticated decision trees, modern neural networks, and deep learning methods. Next, we will cover unsupervised learning and techniques for reducing the dimensionality of input spaces and for clustering data. We'll show example applications from both magnetic and inertial confinement fusion. Along the way, we will describe methods for practitioners to help ensure that their models generalize from their training data to as-yet-unseen test data. We will finally point out some limitations to modern machine learning and speculate on some ways that practitioners from the physical sciences may be particularly suited to help. This work was performed by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.

Support vector machine in machine condition monitoring and fault diagnosis

Science.gov (United States)

Widodo, Achmad; Yang, Bo-Suk

2007-08-01

Recently, the issue of machine condition monitoring and fault diagnosis as a part of maintenance system became global due to the potential advantages to be gained from reduced maintenance costs, improved productivity and increased machine availability. This paper presents a survey of machine condition monitoring and fault diagnosis using support vector machine (SVM). It attempts to summarize and review the recent research and developments of SVM in machine condition monitoring and diagnosis. Numerous methods have been developed based on intelligent systems such as artificial neural network, fuzzy expert system, condition-based reasoning, random forest, etc. However, the use of SVM for machine condition monitoring and fault diagnosis is still rare. SVM has excellent performance in generalization so it can produce high accuracy in classification for machine condition monitoring and diagnosis. Until 2006, the use of SVM in machine condition monitoring and fault diagnosis is tending to develop towards expertise orientation and problem-oriented domain. Finally, the ability to continually change and obtain a novel idea for machine condition monitoring and fault diagnosis using SVM will be future works.

Machine-learning scoring functions to improve structure-based binding affinity prediction and virtual screening.

Science.gov (United States)

Ain, Qurrat Ul; Aleksandrova, Antoniya; Roessler, Florian D; Ballester, Pedro J

2015-01-01

Docking tools to predict whether and how a small molecule binds to a target can be applied if a structural model of such target is available. The reliability of docking depends, however, on the accuracy of the adopted scoring function (SF). Despite intense research over the years, improving the accuracy of SFs for structure-based binding affinity prediction or virtual screening has proven to be a challenging task for any class of method. New SFs based on modern machine-learning regression models, which do not impose a predetermined functional form and thus are able to exploit effectively much larger amounts of experimental data, have recently been introduced. These machine-learning SFs have been shown to outperform a wide range of classical SFs at both binding affinity prediction and virtual screening. The emerging picture from these studies is that the classical approach of using linear regression with a small number of expert-selected structural features can be strongly improved by a machine-learning approach based on nonlinear regression allied with comprehensive data-driven feature selection. Furthermore, the performance of classical SFs does not grow with larger training datasets and hence this performance gap is expected to widen as more training data becomes available in the future. Other topics covered in this review include predicting the reliability of a SF on a particular target class, generating synthetic data to improve predictive performance and modeling guidelines for SF development. WIREs Comput Mol Sci 2015, 5:405-424. doi: 10.1002/wcms.1225 For further resources related to this article, please visit the WIREs website.

Retro-regression--another important multivariate regression improvement.

Science.gov (United States)

Randić, M

2001-01-01

We review the serious problem associated with instabilities of the coefficients of regression equations, referred to as the MRA (multivariate regression analysis) "nightmare of the first kind". This is manifested when in a stepwise regression a descriptor is included or excluded from a regression. The consequence is an unpredictable change of the coefficients of the descriptors that remain in the regression equation. We follow with consideration of an even more serious problem, referred to as the MRA "nightmare of the second kind", arising when optimal descriptors are selected from a large pool of descriptors. This process typically causes at different steps of the stepwise regression a replacement of several previously used descriptors by new ones. We describe a procedure that resolves these difficulties. The approach is illustrated on boiling points of nonanes which are considered (1) by using an ordered connectivity basis; (2) by using an ordering resulting from application of greedy algorithm; and (3) by using an ordering derived from an exhaustive search for optimal descriptors. A novel variant of multiple regression analysis, called retro-regression (RR), is outlined showing how it resolves the ambiguities associated with both "nightmares" of the first and the second kind of MRA.

Modified Regression Correlation Coefficient for Poisson Regression Model

Science.gov (United States)

Kaengthong, Nattacha; Domthong, Uthumporn

2017-09-01

This study gives attention to indicators in predictive power of the Generalized Linear Model (GLM) which are widely used; however, often having some restrictions. We are interested in regression correlation coefficient for a Poisson regression model. This is a measure of predictive power, and defined by the relationship between the dependent variable (Y) and the expected value of the dependent variable given the independent variables [E(Y|X)] for the Poisson regression model. The dependent variable is distributed as Poisson. The purpose of this research was modifying regression correlation coefficient for Poisson regression model. We also compare the proposed modified regression correlation coefficient with the traditional regression correlation coefficient in the case of two or more independent variables, and having multicollinearity in independent variables. The result shows that the proposed regression correlation coefficient is better than the traditional regression correlation coefficient based on Bias and the Root Mean Square Error (RMSE).

Application of machine learning for the evaluation of turfgrass plots using aerial images

Science.gov (United States)

Ding, Ke; Raheja, Amar; Bhandari, Subodh; Green, Robert L.

2016-05-01

Historically, investigation of turfgrass characteristics have been limited to visual ratings. Although relevant information may result from such evaluations, final inferences may be questionable because of the subjective nature in which the data is collected. Recent advances in computer vision techniques allow researchers to objectively measure turfgrass characteristics such as percent ground cover, turf color, and turf quality from the digital images. This paper focuses on developing a methodology for automated assessment of turfgrass quality from aerial images. Images of several turfgrass plots of varying quality were gathered using a camera mounted on an unmanned aerial vehicle. The quality of these plots were also evaluated based on visual ratings. The goal was to use the aerial images to generate quality evaluations on a regular basis for the optimization of water treatment. Aerial images are used to train a neural network so that appropriate features such as intensity, color, and texture of the turfgrass are extracted from these images. Neural network is a nonlinear classifier commonly used in machine learning. The output of the neural network trained model is the ratings of the grass, which is compared to the visual ratings. Currently, the quality and the color of turfgrass, measured as the greenness of the grass, are evaluated. The textures are calculated using the Gabor filter and co-occurrence matrix. Other classifiers such as support vector machines and simpler linear regression models such as Ridge regression and LARS regression are also used. The performance of each model is compared. The results show encouraging potential for using machine learning techniques for the evaluation of turfgrass quality and color.

EEG machine learning with Higuchi fractal dimension and Sample Entropy as features for successful detection of depression

OpenAIRE

Cukic, Milena; Pokrajac, David; Stokic, Miodrag; Simic, slobodan; Radivojevic, Vlada; Ljubisavljevic, Milos

2018-01-01

Reliable diagnosis of depressive disorder is essential for both optimal treatment and prevention of fatal outcomes. In this study, we aimed to elucidate the effectiveness of two non-linear measures, Higuchi Fractal Dimension (HFD) and Sample Entropy (SampEn), in detecting depressive disorders when applied on EEG. HFD and SampEn of EEG signals were used as features for seven machine learning algorithms including Multilayer Perceptron, Logistic Regression, Support Vector Machines with the linea...

Hybrid genetic algorithm tuned support vector machine regression for wave transmission prediction of horizontally interlaced multilayer moored floating pipe breakwater

Digital Repository Service at National Institute of Oceanography (India)

Patil, S.G.; Mandal, S.; Hegde, A.V.; Muruganandam, A.

Support Vector Machine (SVM) works on structural risk minimization principle that has greater generalization ability and is superior to the empirical risk minimization principle as adopted in conventional neural network models. However...

The Neural-fuzzy Thermal Error Compensation Controller on CNC Machining Center

Science.gov (United States)

Tseng, Pai-Chung; Chen, Shen-Len

The geometric errors and structural thermal deformation are factors that influence the machining accuracy of Computer Numerical Control (CNC) machining center. Therefore, researchers pay attention to thermal error compensation technologies on CNC machine tools. Some real-time error compensation techniques have been successfully demonstrated in both laboratories and industrial sites. The compensation results still need to be enhanced. In this research, the neural-fuzzy theory has been conducted to derive a thermal prediction model. An IC-type thermometer has been used to detect the heat sources temperature variation. The thermal drifts are online measured by a touch-triggered probe with a standard bar. A thermal prediction model is then derived by neural-fuzzy theory based on the temperature variation and the thermal drifts. A Graphic User Interface (GUI) system is also built to conduct the user friendly operation interface with Insprise C++ Builder. The experimental results show that the thermal prediction model developed by neural-fuzzy theory methodology can improve machining accuracy from 80µm to 3µm. Comparison with the multi-variable linear regression analysis the compensation accuracy is increased from ±10µm to ±3µm.

Identification of immune correlates of protection in Shigella infection by application of machine learning.

Science.gov (United States)

Arevalillo, Jorge M; Sztein, Marcelo B; Kotloff, Karen L; Levine, Myron M; Simon, Jakub K

2017-10-01

Immunologic correlates of protection are important in vaccine development because they give insight into mechanisms of protection, assist in the identification of promising vaccine candidates, and serve as endpoints in bridging clinical vaccine studies. Our goal is the development of a methodology to identify immunologic correlates of protection using the Shigella challenge as a model. The proposed methodology utilizes the Random Forests (RF) machine learning algorithm as well as Classification and Regression Trees (CART) to detect immune markers that predict protection, identify interactions between variables, and define optimal cutoffs. Logistic regression modeling is applied to estimate the probability of protection and the confidence interval (CI) for such a probability is computed by bootstrapping the logistic regression models. The results demonstrate that the combination of Classification and Regression Trees and Random Forests complements the standard logistic regression and uncovers subtle immune interactions. Specific levels of immunoglobulin IgG antibody in blood on the day of challenge predicted protection in 75% (95% CI 67-86). Of those subjects that did not have blood IgG at or above a defined threshold, 100% were protected if they had IgA antibody secreting cells above a defined threshold. Comparison with the results obtained by applying only logistic regression modeling with standard Akaike Information Criterion for model selection shows the usefulness of the proposed method. Given the complexity of the immune system, the use of machine learning methods may enhance traditional statistical approaches. When applied together, they offer a novel way to quantify important immune correlates of protection that may help the development of vaccines. Copyright © 2017 Elsevier Inc. All rights reserved.

Simulations of Quantum Turing Machines by Quantum Multi-Stack Machines

OpenAIRE

Qiu, Daowen

2005-01-01

As was well known, in classical computation, Turing machines, circuits, multi-stack machines, and multi-counter machines are equivalent, that is, they can simulate each other in polynomial time. In quantum computation, Yao [11] first proved that for any quantum Turing machines $M$, there exists quantum Boolean circuit $(n,t)$-simulating $M$, where $n$ denotes the length of input strings, and $t$ is the number of move steps before machine stopping. However, the simulations of quantum Turing ma...

Machine learning methods without tears: a primer for ecologists.

Science.gov (United States)

Olden, Julian D; Lawler, Joshua J; Poff, N LeRoy

2008-06-01

Machine learning methods, a family of statistical techniques with origins in the field of artificial intelligence, are recognized as holding great promise for the advancement of understanding and prediction about ecological phenomena. These modeling techniques are flexible enough to handle complex problems with multiple interacting elements and typically outcompete traditional approaches (e.g., generalized linear models), making them ideal for modeling ecological systems. Despite their inherent advantages, a review of the literature reveals only a modest use of these approaches in ecology as compared to other disciplines. One potential explanation for this lack of interest is that machine learning techniques do not fall neatly into the class of statistical modeling approaches with which most ecologists are familiar. In this paper, we provide an introduction to three machine learning approaches that can be broadly used by ecologists: classification and regression trees, artificial neural networks, and evolutionary computation. For each approach, we provide a brief background to the methodology, give examples of its application in ecology, describe model development and implementation, discuss strengths and weaknesses, explore the availability of statistical software, and provide an illustrative example. Although the ecological application of machine learning approaches has increased, there remains considerable skepticism with respect to the role of these techniques in ecology. Our review encourages a greater understanding of machin learning approaches and promotes their future application and utilization, while also providing a basis from which ecologists can make informed decisions about whether to select or avoid these approaches in their future modeling endeavors.

Impact of Total Vending Machine Restrictions on US Young Adult Smoking

Science.gov (United States)

Kelly, Brian C.; Kadowaki, Joy

2016-01-01

Introduction: In an analysis of smoking using a longitudinal sample of US young adults, we extend research on tobacco vending machine restrictions beyond its prior focus on minors by examining the influence of total vending machine restrictions, which apply to adult-only facilities and represents the only remaining vending machine exemption since the enactment of the Family Smoking Prevention and Tobacco Control Act. We identify whether the passage of a restriction influences an individual’s smoking on repeated observations, and if the propensity is lower among those who live in locations with a restriction. Methods: Combining a repository of US tobacco policies at all geographic levels with the nationally-representative geocoded National Longitudinal Survey of Youth 1997 and Census data, we use multilevel logistic regression to examine the impact of total vending machine restrictions on any past 30-day smoking and past 30-day smoking of one pack per day among young adults (ages 19–31), while accounting for other tobacco control policy, community, and individual covariates. Results: We find that total vending machine restrictions decrease any recent smoking (OR = 0.451; p vending machine restrictions on smoking a pack daily. Conclusions: Total vending machine restrictions appear to be an effective, yet highly underutilized, means of tobacco control. Implications: Past scientific inquiries examining vending machine restrictions have focused upon minor access, adolescent perceptions of availability, and subsequent smoking. The potential for total vending machine restrictions, which extend to adult-only facilities, to influence patterns of smoking among those of legal age, remains significant. Those who are subject to total vending machine restrictions for longer periods are less likely to have recently smoked, but individuals do not change their smoking behavior in response to the passage of a restriction. These restrictions do not affect heavy smokers. Such

Displacement prediction of Baijiabao landslide based on empirical mode decomposition and long short-term memory neural network in Three Gorges area, China

Science.gov (United States)

Xu, Shiluo; Niu, Ruiqing

2018-02-01

Every year, landslides pose huge threats to thousands of people in China, especially those in the Three Gorges area. It is thus necessary to establish an early warning system to help prevent property damage and save peoples' lives. Most of the landslide displacement prediction models that have been proposed are static models. However, landslides are dynamic systems. In this paper, the total accumulative displacement of the Baijiabao landslide is divided into trend and periodic components using empirical mode decomposition. The trend component is predicted using an S-curve estimation, and the total periodic component is predicted using a long short-term memory neural network (LSTM). LSTM is a dynamic model that can remember historical information and apply it to the current output. Six triggering factors are chosen to predict the periodic term using the Pearson cross-correlation coefficient and mutual information. These factors include the cumulative precipitation during the previous month, the cumulative precipitation during a two-month period, the reservoir level during the current month, the change in the reservoir level during the previous month, the cumulative increment of the reservoir level during the current month, and the cumulative displacement during the previous month. When using one-step-ahead prediction, LSTM yields a root mean squared error (RMSE) value of 6.112 mm, while the support vector machine for regression (SVR) and the back-propagation neural network (BP) yield values of 10.686 mm and 8.237 mm, respectively. Meanwhile, the Elman network (Elman) yields an RMSE value of 6.579 mm. In addition, when using multi-step-ahead prediction, LSTM obtains an RMSE value of 8.648 mm, while SVR, BP and the Elman network obtains RSME values of 13.418 mm, 13.014 mm, and 13.370 mm. The predicted results indicate that, to some extent, the dynamic model (LSTM) achieves results that are more accurate than those of the static models (i.e., SVR and BP). LSTM even

Support Vector Hazards Machine: A Counting Process Framework for Learning Risk Scores for Censored Outcomes.

Science.gov (United States)

Wang, Yuanjia; Chen, Tianle; Zeng, Donglin

2016-01-01

Learning risk scores to predict dichotomous or continuous outcomes using machine learning approaches has been studied extensively. However, how to learn risk scores for time-to-event outcomes subject to right censoring has received little attention until recently. Existing approaches rely on inverse probability weighting or rank-based regression, which may be inefficient. In this paper, we develop a new support vector hazards machine (SVHM) approach to predict censored outcomes. Our method is based on predicting the counting process associated with the time-to-event outcomes among subjects at risk via a series of support vector machines. Introducing counting processes to represent time-to-event data leads to a connection between support vector machines in supervised learning and hazards regression in standard survival analysis. To account for different at risk populations at observed event times, a time-varying offset is used in estimating risk scores. The resulting optimization is a convex quadratic programming problem that can easily incorporate non-linearity using kernel trick. We demonstrate an interesting link from the profiled empirical risk function of SVHM to the Cox partial likelihood. We then formally show that SVHM is optimal in discriminating covariate-specific hazard function from population average hazard function, and establish the consistency and learning rate of the predicted risk using the estimated risk scores. Simulation studies show improved prediction accuracy of the event times using SVHM compared to existing machine learning methods and standard conventional approaches. Finally, we analyze two real world biomedical study data where we use clinical markers and neuroimaging biomarkers to predict age-at-onset of a disease, and demonstrate superiority of SVHM in distinguishing high risk versus low risk subjects.

Piece-wise quadratic approximations of arbitrary error functions for fast and robust machine learning.

Science.gov (United States)

Gorban, A N; Mirkes, E M; Zinovyev, A

2016-12-01

Most of machine learning approaches have stemmed from the application of minimizing the mean squared distance principle, based on the computationally efficient quadratic optimization methods. However, when faced with high-dimensional and noisy data, the quadratic error functionals demonstrated many weaknesses including high sensitivity to contaminating factors and dimensionality curse. Therefore, a lot of recent applications in machine learning exploited properties of non-quadratic error functionals based on L 1 norm or even sub-linear potentials corresponding to quasinorms L p (0application of min-plus algebra. The approach can be applied in most of existing machine learning methods, including methods of data approximation and regularized and sparse regression, leading to the improvement in the computational cost/accuracy trade-off. We demonstrate that on synthetic and real-life datasets PQSQ-based machine learning methods achieve orders of magnitude faster computational performance than the corresponding state-of-the-art methods, having similar or better approximation accuracy. Copyright © 2016 Elsevier Ltd. All rights reserved.

Machine tool structures

CERN Document Server

Koenigsberger, F

1970-01-01

Machine Tool Structures, Volume 1 deals with fundamental theories and calculation methods for machine tool structures. Experimental investigations into stiffness are discussed, along with the application of the results to the design of machine tool structures. Topics covered range from static and dynamic stiffness to chatter in metal cutting, stability in machine tools, and deformations of machine tool structures. This volume is divided into three sections and opens with a discussion on stiffness specifications and the effect of stiffness on the behavior of the machine under forced vibration c

Valid Probabilistic Predictions for Ginseng with Venn Machines Using Electronic Nose

Directory of Open Access Journals (Sweden)

You Wang

2016-07-01

Full Text Available In the application of electronic noses (E-noses, probabilistic prediction is a good way to estimate how confident we are about our prediction. In this work, a homemade E-nose system embedded with 16 metal-oxide semi-conductive gas sensors was used to discriminate nine kinds of ginsengs of different species or production places. A flexible machine learning framework, Venn machine (VM was introduced to make probabilistic predictions for each prediction. Three Venn predictors were developed based on three classical probabilistic prediction methods (Platt’s method, Softmax regression and Naive Bayes. Three Venn predictors and three classical probabilistic prediction methods were compared in aspect of classification rate and especially the validity of estimated probability. A best classification rate of 88.57% was achieved with Platt’s method in offline mode, and the classification rate of VM-SVM (Venn machine based on Support Vector Machine was 86.35%, just 2.22% lower. The validity of Venn predictors performed better than that of corresponding classical probabilistic prediction methods. The validity of VM-SVM was superior to the other methods. The results demonstrated that Venn machine is a flexible tool to make precise and valid probabilistic prediction in the application of E-nose, and VM-SVM achieved the best performance for the probabilistic prediction of ginseng samples.

Statistical learning from a regression perspective

CERN Document Server

Berk, Richard A

2016-01-01

This textbook considers statistical learning applications when interest centers on the conditional distribution of the response variable, given a set of predictors, and when it is important to characterize how the predictors are related to the response. As a first approximation, this can be seen as an extension of nonparametric regression. This fully revised new edition includes important developments over the past 8 years. Consistent with modern data analytics, it emphasizes that a proper statistical learning data analysis derives from sound data collection, intelligent data management, appropriate statistical procedures, and an accessible interpretation of results. A continued emphasis on the implications for practice runs through the text. Among the statistical learning procedures examined are bagging, random forests, boosting, support vector machines and neural networks. Response variables may be quantitative or categorical. As in the first edition, a unifying theme is supervised learning that can be trea...

T-wave end detection using neural networks and Support Vector Machines.

Science.gov (United States)

Suárez-León, Alexander Alexeis; Varon, Carolina; Willems, Rik; Van Huffel, Sabine; Vázquez-Seisdedos, Carlos Román

2018-05-01

In this paper we propose a new approach for detecting the end of the T-wave in the electrocardiogram (ECG) using Neural Networks and Support Vector Machines. Both, Multilayer Perceptron (MLP) neural networks and Fixed-Size Least-Squares Support Vector Machines (FS-LSSVM) were used as regression algorithms to determine the end of the T-wave. Different strategies for selecting the training set such as random selection, k-means, robust clustering and maximum quadratic (Rényi) entropy were evaluated. Individual parameters were tuned for each method during training and the results are given for the evaluation set. A comparison between MLP and FS-LSSVM approaches was performed. Finally, a fair comparison of the FS-LSSVM method with other state-of-the-art algorithms for detecting the end of the T-wave was included. The experimental results show that FS-LSSVM approaches are more suitable as regression algorithms than MLP neural networks. Despite the small training sets used, the FS-LSSVM methods outperformed the state-of-the-art techniques. FS-LSSVM can be successfully used as a T-wave end detection algorithm in ECG even with small training set sizes. Copyright © 2018 Elsevier Ltd. All rights reserved.

Estimating atmospheric visibility using synergy of MODIS data and ground-based observations

Science.gov (United States)

Komeilian, H.; Mohyeddin Bateni, S.; Xu, T.; Nielson, J.

2015-05-01

Dust events are intricate climatic processes, which can have adverse effects on human health, safety, and the environment. In this study, two data mining approaches, namely, back-propagation artificial neural network (BP ANN) and supporting vector regression (SVR), were used to estimate atmospheric visibility through the synergistic use of Moderate Resolution Imaging Spectroradiometer (MODIS) Level 1B (L1B) data and ground-based observations at fourteen stations in the province of Khuzestan (southwestern Iran), during 2009-2010. Reflectance and brightness temperature in different bands (from MODIS) along with in situ meteorological data were input to the models to estimate atmospheric visibility. The results show that both models can accurately estimate atmospheric visibility. The visibility estimates from the BP ANN network had a root-mean-square error (RMSE) and Pearson's correlation coefficient (R) of 0.67 and 0.69, respectively. The corresponding RMSE and R from the SVR model were 0.59 and 0.71, implying that the SVR approach outperforms the BP ANN.

Determination of relationship between sensory viscosity rating and instrumental flow behaviour of soluble dietary fibers.

Science.gov (United States)

Arora, Simran Kaur; Patel, A A; Kumar, Naveen; Chauhan, O P

2016-04-01

The shear-thinning low, medium and high-viscosity fiber preparations (0.15-1.05 % psyllium husk, 0.07-0.6 % guar gum, 0.15-1.20 % gum tragacanth, 0.1-0.8 % gum karaya, 0.15-1.05 % high-viscosity Carboxy Methyl Cellulose and 0.1-0.7 % xanthan gum) showed that the consistency coefficient (k) was a function of concentration, the relationship being exponential (R(2), 0.87-0.96; P flow behaviour index (n) (except for gum karaya and CMC) was exponentially related to concentration (R(2), 0.61-0.98). The relationship between k and sensory viscosity rating (SVR) was essentially linear in nearly all cases. The SVR could be predicted from the consistency coefficient using the regression equations developed. Also, the relationship of k with fiber concentration would make it possible to identify the concentration of a particular gum required to have desired consistency in terms of SVR.

Electricity of machine tool

International Nuclear Information System (INIS)

Gijeon media editorial department

1977-10-01

This book is divided into three parts. The first part deals with electricity machine, which can taints from generator to motor, motor a power source of machine tool, electricity machine for machine tool such as switch in main circuit, automatic machine, a knife switch and pushing button, snap switch, protection device, timer, solenoid, and rectifier. The second part handles wiring diagram. This concludes basic electricity circuit of machine tool, electricity wiring diagram in your machine like milling machine, planer and grinding machine. The third part introduces fault diagnosis of machine, which gives the practical solution according to fault diagnosis and the diagnostic method with voltage and resistance measurement by tester.

Machine medical ethics

CERN Document Server

Pontier, Matthijs

2015-01-01

The essays in this book, written by researchers from both humanities and sciences, describe various theoretical and experimental approaches to adding medical ethics to a machine in medical settings. Medical machines are in close proximity with human beings, and getting closer: with patients who are in vulnerable states of health, who have disabilities of various kinds, with the very young or very old, and with medical professionals. In such contexts, machines are undertaking important medical tasks that require emotional sensitivity, knowledge of medical codes, human dignity, and privacy. As machine technology advances, ethical concerns become more urgent: should medical machines be programmed to follow a code of medical ethics? What theory or theories should constrain medical machine conduct? What design features are required? Should machines share responsibility with humans for the ethical consequences of medical actions? How ought clinical relationships involving machines to be modeled? Is a capacity for e...

Humanizing machines: Anthropomorphization of slot machines increases gambling.

Science.gov (United States)

Riva, Paolo; Sacchi, Simona; Brambilla, Marco

2015-12-01

Do people gamble more on slot machines if they think that they are playing against humanlike minds rather than mathematical algorithms? Research has shown that people have a strong cognitive tendency to imbue humanlike mental states to nonhuman entities (i.e., anthropomorphism). The present research tested whether anthropomorphizing slot machines would increase gambling. Four studies manipulated slot machine anthropomorphization and found that exposing people to an anthropomorphized description of a slot machine increased gambling behavior and reduced gambling outcomes. Such findings emerged using tasks that focused on gambling behavior (Studies 1 to 3) as well as in experimental paradigms that included gambling outcomes (Studies 2 to 4). We found that gambling outcomes decrease because participants primed with the anthropomorphic slot machine gambled more (Study 4). Furthermore, we found that high-arousal positive emotions (e.g., feeling excited) played a role in the effect of anthropomorphism on gambling behavior (Studies 3 and 4). Our research indicates that the psychological process of gambling-machine anthropomorphism can be advantageous for the gaming industry; however, this may come at great expense for gamblers' (and their families') economic resources and psychological well-being. (c) 2015 APA, all rights reserved).

Machine Learning Techniques for Stellar Light Curve Classification

Science.gov (United States)

Hinners, Trisha A.; Tat, Kevin; Thorp, Rachel

2018-07-01

We apply machine learning techniques in an attempt to predict and classify stellar properties from noisy and sparse time-series data. We preprocessed over 94 GB of Kepler light curves from the Mikulski Archive for Space Telescopes (MAST) to classify according to 10 distinct physical properties using both representation learning and feature engineering approaches. Studies using machine learning in the field have been primarily done on simulated data, making our study one of the first to use real light-curve data for machine learning approaches. We tuned our data using previous work with simulated data as a template and achieved mixed results between the two approaches. Representation learning using a long short-term memory recurrent neural network produced no successful predictions, but our work with feature engineering was successful for both classification and regression. In particular, we were able to achieve values for stellar density, stellar radius, and effective temperature with low error (∼2%–4%) and good accuracy (∼75%) for classifying the number of transits for a given star. The results show promise for improvement for both approaches upon using larger data sets with a larger minority class. This work has the potential to provide a foundation for future tools and techniques to aid in the analysis of astrophysical data.

Determination of total iron-reactive phenolics, anthocyanins and tannins in wine grapes of skins and seeds based on near-infrared hyperspectral imaging.

Science.gov (United States)

Zhang, Ni; Liu, Xu; Jin, Xiaoduo; Li, Chen; Wu, Xuan; Yang, Shuqin; Ning, Jifeng; Yanne, Paul

2017-12-15

Phenolics contents in wine grapes are key indicators for assessing ripeness. Near-infrared hyperspectral images during ripening have been explored to achieve an effective method for predicting phenolics contents. Principal component regression (PCR), partial least squares regression (PLSR) and support vector regression (SVR) models were built, respectively. The results show that SVR behaves globally better than PLSR and PCR, except in predicting tannins content of seeds. For the best prediction results, the squared correlation coefficient and root mean square error reached 0.8960 and 0.1069g/L (+)-catechin equivalents (CE), respectively, for tannins in skins, 0.9065 and 0.1776 (g/L CE) for total iron-reactive phenolics (TIRP) in skins, 0.8789 and 0.1442 (g/L M3G) for anthocyanins in skins, 0.9243 and 0.2401 (g/L CE) for tannins in seeds, and 0.8790 and 0.5190 (g/L CE) for TIRP in seeds. Our results indicated that NIR hyperspectral imaging has good prospects for evaluation of phenolics in wine grapes. Copyright © 2017 Elsevier Ltd. All rights reserved.

Water cut measurement of oil–water flow in vertical well by combining total flow rate and the response of a conductance probe

International Nuclear Information System (INIS)

Chen, Jianjun; Xu, Lijun; Cao, Zhang; Zhang, Wen; Liu, Xingbin; Hu, Jinhai

2015-01-01

In this paper, a conductance probe-based well logging instrument was developed and the total flow rate is combined with the response of the conductance probe to estimate the water cut of the oil–water flow in a vertical well. The conductance probe records the time-varying electrical characteristics of the oil–water flow. Linear least squares regression (LSR) and nonlinear support vector regression (SVR) were used to establish models to map the total flow rate and features extracted from the probe response onto the water cut, respectively. Principal component analysis (PCA) and partial least squares analysis (PLSA) techniques were employed to reduce data redundancy within the extracted features. An experiment was carried out in a vertical pipe with an inner diameter of 125 mm and a height of 24 m in an experimental multi-phase flow setup, Daqing Oilfield, China. In the experiment, oil–water flow was used and the total flow rate varied from 10 to 200 m 3 per day and the water cut varied from 0% to 100%. As a direct comparison, the cases were also studied when the total flow rate was not used as an independent input to the models. The results obtained demonstrate that: (1) the addition of the total flow rate as an input to the regression models can greatly improve the accuracy of water cut prediction, (2) the nonlinear SVR model performs much better than the linear LSR model, and (3) for the SVR model with the total flow rate as an input, the adoption of PCA or PLSA not only decreases the dimensions of inputs, but also increases prediction accuracy. The SVR model with five PCA-treated features plus the total flow rate achieves the best performance in water cut prediction, with a coefficient of determination (R 2 ) as high as 0.9970. The corresponding root mean squared error (RMSE) and mean quoted error (MQE) are 0.0312% and 1.99%, respectively. (paper)

Supporting Regularized Logistic Regression Privately and Efficiently

Science.gov (United States)

Li, Wenfa; Liu, Hongzhe; Yang, Peng; Xie, Wei

2016-01-01

As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Concerns over data privacy make it increasingly difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used statistical model while at the same time has not been investigated from a data security and privacy perspective. We consider a common use scenario of multi-institution collaborative studies, such as in the form of research consortia or networks as widely seen in genetics, epidemiology, social sciences, etc. To make our privacy-enhancing solution practical, we demonstrate a non-conventional and computationally efficient method leveraging distributing computing and strong cryptography to provide comprehensive protection over individual-level and summary data. Extensive empirical evaluations on several studies validate the privacy guarantee, efficiency and scalability of our proposal. We also discuss the practical implications of our solution for large-scale studies and applications from various disciplines, including genetic and biomedical studies, smart grid, network analysis, etc. PMID:27271738

Supporting Regularized Logistic Regression Privately and Efficiently.

Science.gov (United States)

Li, Wenfa; Liu, Hongzhe; Yang, Peng; Xie, Wei

2016-01-01

As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Concerns over data privacy make it increasingly difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used statistical model while at the same time has not been investigated from a data security and privacy perspective. We consider a common use scenario of multi-institution collaborative studies, such as in the form of research consortia or networks as widely seen in genetics, epidemiology, social sciences, etc. To make our privacy-enhancing solution practical, we demonstrate a non-conventional and computationally efficient method leveraging distributing computing and strong cryptography to provide comprehensive protection over individual-level and summary data. Extensive empirical evaluations on several studies validate the privacy guarantee, efficiency and scalability of our proposal. We also discuss the practical implications of our solution for large-scale studies and applications from various disciplines, including genetic and biomedical studies, smart grid, network analysis, etc.

Supporting Regularized Logistic Regression Privately and Efficiently.

Directory of Open Access Journals (Sweden)

Wenfa Li

Full Text Available As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Concerns over data privacy make it increasingly difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used statistical model while at the same time has not been investigated from a data security and privacy perspective. We consider a common use scenario of multi-institution collaborative studies, such as in the form of research consortia or networks as widely seen in genetics, epidemiology, social sciences, etc. To make our privacy-enhancing solution practical, we demonstrate a non-conventional and computationally efficient method leveraging distributing computing and strong cryptography to provide comprehensive protection over individual-level and summary data. Extensive empirical evaluations on several studies validate the privacy guarantee, efficiency and scalability of our proposal. We also discuss the practical implications of our solution for large-scale studies and applications from various disciplines, including genetic and biomedical studies, smart grid, network analysis, etc.

A Comparison of a Machine Learning Model with EuroSCORE II in Predicting Mortality after Elective Cardiac Surgery: A Decision Curve Analysis.

Science.gov (United States)

Allyn, Jérôme; Allou, Nicolas; Augustin, Pascal; Philip, Ivan; Martinet, Olivier; Belghiti, Myriem; Provenchere, Sophie; Montravers, Philippe; Ferdynus, Cyril

2017-01-01

The benefits of cardiac surgery are sometimes difficult to predict and the decision to operate on a given individual is complex. Machine Learning and Decision Curve Analysis (DCA) are recent methods developed to create and evaluate prediction models. We conducted a retrospective cohort study using a prospective collected database from December 2005 to December 2012, from a cardiac surgical center at University Hospital. The different models of prediction of mortality in-hospital after elective cardiac surgery, including EuroSCORE II, a logistic regression model and a machine learning model, were compared by ROC and DCA. Of the 6,520 patients having elective cardiac surgery with cardiopulmonary bypass, 6.3% died. Mean age was 63.4 years old (standard deviation 14.4), and mean EuroSCORE II was 3.7 (4.8) %. The area under ROC curve (IC95%) for the machine learning model (0.795 (0.755-0.834)) was significantly higher than EuroSCORE II or the logistic regression model (respectively, 0.737 (0.691-0.783) and 0.742 (0.698-0.785), p machine learning model, in this monocentric study, has a greater benefit whatever the probability threshold. According to ROC and DCA, machine learning model is more accurate in predicting mortality after elective cardiac surgery than EuroSCORE II. These results confirm the use of machine learning methods in the field of medical prediction.

Modeling Music Emotion Judgments Using Machine Learning Methods

Directory of Open Access Journals (Sweden)

Naresh N. Vempala

2018-01-01

Full Text Available Emotion judgments and five channels of physiological data were obtained from 60 participants listening to 60 music excerpts. Various machine learning (ML methods were used to model the emotion judgments inclusive of neural networks, linear regression, and random forests. Input for models of perceived emotion consisted of audio features extracted from the music recordings. Input for models of felt emotion consisted of physiological features extracted from the physiological recordings. Models were trained and interpreted with consideration of the classic debate in music emotion between cognitivists and emotivists. Our models supported a hybrid position wherein emotion judgments were influenced by a combination of perceived and felt emotions. In comparing the different ML approaches that were used for modeling, we conclude that neural networks were optimal, yielding models that were flexible as well as interpretable. Inspection of a committee machine, encompassing an ensemble of networks, revealed that arousal judgments were predominantly influenced by felt emotion, whereas valence judgments were predominantly influenced by perceived emotion.

Code-expanded radio access protocol for machine-to-machine communications

DEFF Research Database (Denmark)

Thomsen, Henning; Kiilerich Pratas, Nuno; Stefanovic, Cedomir

2013-01-01

The random access methods used for support of machine-to-machine, also referred to as Machine-Type Communications, in current cellular standards are derivatives of traditional framed slotted ALOHA and therefore do not support high user loads efficiently. We propose an approach that is motivated b...... subframes and orthogonal preambles, the amount of available contention resources is drastically increased, enabling the massive support of Machine-Type Communication users that is beyond the reach of current systems.......The random access methods used for support of machine-to-machine, also referred to as Machine-Type Communications, in current cellular standards are derivatives of traditional framed slotted ALOHA and therefore do not support high user loads efficiently. We propose an approach that is motivated...... by the random access method employed in LTE, which significantly increases the amount of contention resources without increasing the system resources, such as contention subframes and preambles. This is accomplished by a logical, rather than physical, extension of the access method in which the available system...

Using support vector machines to identify literacy skills: Evidence from eye movements.

Science.gov (United States)

Lou, Ya; Liu, Yanping; Kaakinen, Johanna K; Li, Xingshan

2017-06-01

Is inferring readers' literacy skills possible by analyzing their eye movements during text reading? This study used Support Vector Machines (SVM) to analyze eye movement data from 61 undergraduate students who read a multiple-paragraph, multiple-topic expository text. Forward fixation time, first-pass rereading time, second-pass fixation time, and regression path reading time on different regions of the text were provided as features. The SVM classification algorithm assisted in distinguishing high-literacy-skilled readers from low-literacy-skilled readers with 80.3 % accuracy. Results demonstrate the effectiveness of combining eye tracking and machine learning techniques to detect readers with low literacy skills, and suggest that such approaches can be potentially used in predicting other cognitive abilities.

Prediction of drug synergy in cancer using ensemble-based machine learning techniques

Science.gov (United States)

Singh, Harpreet; Rana, Prashant Singh; Singh, Urvinder

2018-04-01

Drug synergy prediction plays a significant role in the medical field for inhibiting specific cancer agents. It can be developed as a pre-processing tool for therapeutic successes. Examination of different drug-drug interaction can be done by drug synergy score. It needs efficient regression-based machine learning approaches to minimize the prediction errors. Numerous machine learning techniques such as neural networks, support vector machines, random forests, LASSO, Elastic Nets, etc., have been used in the past to realize requirement as mentioned above. However, these techniques individually do not provide significant accuracy in drug synergy score. Therefore, the primary objective of this paper is to design a neuro-fuzzy-based ensembling approach. To achieve this, nine well-known machine learning techniques have been implemented by considering the drug synergy data. Based on the accuracy of each model, four techniques with high accuracy are selected to develop ensemble-based machine learning model. These models are Random forest, Fuzzy Rules Using Genetic Cooperative-Competitive Learning method (GFS.GCCL), Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Dynamic Evolving Neural-Fuzzy Inference System method (DENFIS). Ensembling is achieved by evaluating the biased weighted aggregation (i.e. adding more weights to the model with a higher prediction score) of predicted data by selected models. The proposed and existing machine learning techniques have been evaluated on drug synergy score data. The comparative analysis reveals that the proposed method outperforms others in terms of accuracy, root mean square error and coefficient of correlation.

A robust combination approach for short-term wind speed forecasting and analysis – Combination of the ARIMA (Autoregressive Integrated Moving Average), ELM (Extreme Learning Machine), SVM (Support Vector Machine) and LSSVM (Least Square SVM) forecasts using a GPR (Gaussian Process Regression) model

International Nuclear Information System (INIS)

Wang, Jianzhou; Hu, Jianming

2015-01-01

With the increasing importance of wind power as a component of power systems, the problems induced by the stochastic and intermittent nature of wind speed have compelled system operators and researchers to search for more reliable techniques to forecast wind speed. This paper proposes a combination model for probabilistic short-term wind speed forecasting. In this proposed hybrid approach, EWT (Empirical Wavelet Transform) is employed to extract meaningful information from a wind speed series by designing an appropriate wavelet filter bank. The GPR (Gaussian Process Regression) model is utilized to combine independent forecasts generated by various forecasting engines (ARIMA (Autoregressive Integrated Moving Average), ELM (Extreme Learning Machine), SVM (Support Vector Machine) and LSSVM (Least Square SVM)) in a nonlinear way rather than the commonly used linear way. The proposed approach provides more probabilistic information for wind speed predictions besides improving the forecasting accuracy for single-value predictions. The effectiveness of the proposed approach is demonstrated with wind speed data from two wind farms in China. The results indicate that the individual forecasting engines do not consistently forecast short-term wind speed for the two sites, and the proposed combination method can generate a more reliable and accurate forecast. - Highlights: • The proposed approach can make probabilistic modeling for wind speed series. • The proposed approach adapts to the time-varying characteristic of the wind speed. • The hybrid approach can extract the meaningful components from the wind speed series. • The proposed method can generate adaptive, reliable and more accurate forecasting results. • The proposed model combines four independent forecasting engines in a nonlinear way.

Machine learning strategies for systems with invariance properties

Science.gov (United States)

Ling, Julia; Jones, Reese; Templeton, Jeremy

2016-08-01

In many scientific fields, empirical models are employed to facilitate computational simulations of engineering systems. For example, in fluid mechanics, empirical Reynolds stress closures enable computationally-efficient Reynolds Averaged Navier Stokes simulations. Likewise, in solid mechanics, constitutive relations between the stress and strain in a material are required in deformation analysis. Traditional methods for developing and tuning empirical models usually combine physical intuition with simple regression techniques on limited data sets. The rise of high performance computing has led to a growing availability of high fidelity simulation data. These data open up the possibility of using machine learning algorithms, such as random forests or neural networks, to develop more accurate and general empirical models. A key question when using data-driven algorithms to develop these empirical models is how domain knowledge should be incorporated into the machine learning process. This paper will specifically address physical systems that possess symmetry or invariance properties. Two different methods for teaching a machine learning model an invariance property are compared. In the first method, a basis of invariant inputs is constructed, and the machine learning model is trained upon this basis, thereby embedding the invariance into the model. In the second method, the algorithm is trained on multiple transformations of the raw input data until the model learns invariance to that transformation. Results are discussed for two case studies: one in turbulence modeling and one in crystal elasticity. It is shown that in both cases embedding the invariance property into the input features yields higher performance at significantly reduced computational training costs.

Simple machines

CERN Document Server

Graybill, George

2007-01-01

Just how simple are simple machines? With our ready-to-use resource, they are simple to teach and easy to learn! Chocked full of information and activities, we begin with a look at force, motion and work, and examples of simple machines in daily life are given. With this background, we move on to different kinds of simple machines including: Levers, Inclined Planes, Wedges, Screws, Pulleys, and Wheels and Axles. An exploration of some compound machines follows, such as the can opener. Our resource is a real time-saver as all the reading passages, student activities are provided. Presented in s

Influence of Heartwood on Wood Density and Pulp Properties Explained by Machine Learning Techniques

Directory of Open Access Journals (Sweden)

Carla Iglesias

2017-01-01

Full Text Available The aim of this work is to develop a tool to predict some pulp properties e.g., pulp yield, Kappa number, ISO brightness (ISO 2470:2008, fiber length and fiber width, using the sapwood and heartwood proportion in the raw-material. For this purpose, Acacia melanoxylon trees were collected from four sites in Portugal. Percentage of sapwood and heartwood, area and the stem eccentricity (in N-S and E-W directions were measured on transversal stem sections of A. melanoxylon R. Br. The relative position of the samples with respect to the total tree height was also considered as an input variable. Different configurations were tested until the maximum correlation coefficient was achieved. A classical mathematical technique (multiple linear regression and machine learning methods (classification and regression trees, multi-layer perceptron and support vector machines were tested. Classification and regression trees (CART was the most accurate model for the prediction of pulp ISO brightness (R = 0.85. The other parameters could be predicted with fair results (R = 0.64–0.75 by CART. Hence, the proportion of heartwood and sapwood is a relevant parameter for pulping and pulp properties, and should be taken as a quality trait when assessing a pulpwood resource.

Machine performance assessment and enhancement for a hexapod machine

Energy Technology Data Exchange (ETDEWEB)

Mou, J.I. [Arizona State Univ., Tempe, AZ (United States); King, C. [Sandia National Labs., Livermore, CA (United States). Integrated Manufacturing Systems Center

1998-03-19

The focus of this study is to develop a sensor fused process modeling and control methodology to model, assess, and then enhance the performance of a hexapod machine for precision product realization. Deterministic modeling technique was used to derive models for machine performance assessment and enhancement. Sensor fusion methodology was adopted to identify the parameters of the derived models. Empirical models and computational algorithms were also derived and implemented to model, assess, and then enhance the machine performance. The developed sensor fusion algorithms can be implemented on a PC-based open architecture controller to receive information from various sensors, assess the status of the process, determine the proper action, and deliver the command to actuators for task execution. This will enhance a hexapod machine`s capability to produce workpieces within the imposed dimensional tolerances.

Machine health prognostics using the Bayesian-inference-based probabilistic indication and high-order particle filtering framework

Science.gov (United States)

Yu, Jianbo

2015-12-01

Prognostics is much efficient to achieve zero-downtime performance, maximum productivity and proactive maintenance of machines. Prognostics intends to assess and predict the time evolution of machine health degradation so that machine failures can be predicted and prevented. A novel prognostics system is developed based on the data-model-fusion scheme using the Bayesian inference-based self-organizing map (SOM) and an integration of logistic regression (LR) and high-order particle filtering (HOPF). In this prognostics system, a baseline SOM is constructed to model the data distribution space of healthy machine under an assumption that predictable fault patterns are not available. Bayesian inference-based probability (BIP) derived from the baseline SOM is developed as a quantification indication of machine health degradation. BIP is capable of offering failure probability for the monitored machine, which has intuitionist explanation related to health degradation state. Based on those historic BIPs, the constructed LR and its modeling noise constitute a high-order Markov process (HOMP) to describe machine health propagation. HOPF is used to solve the HOMP estimation to predict the evolution of the machine health in the form of a probability density function (PDF). An on-line model update scheme is developed to adapt the Markov process changes to machine health dynamics quickly. The experimental results on a bearing test-bed illustrate the potential applications of the proposed system as an effective and simple tool for machine health prognostics.