Prediction of Parametric Roll Resonance by Multilayer Perceptron Neural Network
DEFF Research Database (Denmark)
Míguez González, M; López Peña, F.
2011-01-01
Parametric roll resonance is a ship stability related phenomenon that generates sudden large amplitude oscillations up to 30-40 degrees of roll. This can cause severe damage, and it can put the crew in serious danger. The need for a parametric rolling real time prediction system has been acknowledged in the last few years. This work proposes a prediction system based on a multilayer perceptron (MP) neural network. The training and testing of the MP network is accomplished by feeding it with simulated data of a three degrees-of-freedom nonlinear model of a fishing vessel. The neural network is shown to be capable of forecasting the ship’s roll motion in realistic scenarios.
DEFF Research Database (Denmark)
Proud, Simon Richard
2015-01-01
A multilayer perceptron neural network cloud mask for Meteosat Second Generation SEVIRI (Spinning Enhanced Visible and Infrared Imager) images is introduced and evaluated. The model is trained for cloud detection on MSG SEVIRI daytime data. It consists of a multi-layer perceptron with one hidden sigmoid layer, trained with the error back-propagation algorithm. The model is fed by six bands of MSG data (0.6, 0.8, 1.6, 3.9, 6.2 and 10.8 ?m) with 10 hidden nodes. The multiple-layer perceptrons lead to a cloud detection accuracy of 88.96%, when trained to map two predefined values that classify cloud and clear sky. The network was further evaluated using sixty MSG images taken at different dates. The network detected not only bright thick clouds but also thin or less bright clouds. The analysis demonstrated the feasibility of using machine learning models of cloud detection in MSG SEVIRI imagery.
Directory of Open Access Journals (Sweden)
Flávio Clésio Silva de Souza
2014-06-01
Full Text Available The purpose of the present research is to apply a Multilayer Perceptron (MLP neural network technique to create classification models from a portfolio of Non-Performing Loans (NPLs to classify this type of credit derivative. These credit derivatives are characterized as the amount of loans that were not paid and are already overdue more than 90 days. Since these titles are, because of legislative motives, moved by losses, Credit Rights Investment Funds (FDIC performs the purchase of these debts and the recovery of the credits. Using the Multilayer Perceptron (MLP architecture of Artificial Neural Network (ANN, classification models regarding the posterior recovery of these debts were created. To evaluate the performance of the models, evaluation metrics of classification relating to the neural networks with different architectures were presented. The results of the classifications were satisfactory, given the classification models were successful in the presented economics costs structure.
Directory of Open Access Journals (Sweden)
Alireza Taravat
2015-02-01
Full Text Available A multilayer perceptron neural network cloud mask for Meteosat Second Generation SEVIRI (Spinning Enhanced Visible and Infrared Imager images is introduced and evaluated. The model is trained for cloud detection on MSG SEVIRI daytime data. It consists of a multi-layer perceptron with one hidden sigmoid layer, trained with the error back-propagation algorithm. The model is fed by six bands of MSG data (0.6, 0.8, 1.6, 3.9, 6.2 and 10.8 ?m with 10 hidden nodes. The multiple-layer perceptrons lead to a cloud detection accuracy of 88.96%, when trained to map two predefined values that classify cloud and clear sky. The network was further evaluated using sixty MSG images taken at different dates. The network detected not only bright thick clouds but also thin or less bright clouds. The analysis demonstrated the feasibility of using machine learning models of cloud detection in MSG SEVIRI imagery.
Classification of fuels using multilayer perceptron neural networks
International Nuclear Information System (INIS)
Electrical impedance data obtained with an array of conducting polymer chemical sensors was used by a neural network (ANN) to classify fuel adulteration. Real samples were classified with accuracy greater than 90% in two groups: approved and adulterated.
Highly Accurate Multi-layer Perceptron Neural Network for Air Data System
Directory of Open Access Journals (Sweden)
H. S. Krishna
2009-11-01
Full Text Available The error backpropagation multi-layer perceptron algorithm is revisited. This algorithm is used to train and validate two models of three-layer neural networks that can be used to calibrate a 5-hole pressure probe. This paper addresses Occam's Razor problem as it describes the adhoc training methodology applied to improve accuracy and sensitivity. The trained outputs from 5-4-3 feed-forward network architecture with jump connection are comparable to second decimal digit (~0.05 accuracy, hitherto unreported in literature.Defence Science Journal, 2009, 59(6, pp.670-674, DOI:http://dx.doi.org/10.14429/dsj.59.1574
LALIT KUMAR BEHERA; MAYA NAYAK; SAREETA MOHANTY
2011-01-01
This paper presents discrete wavelet transform and the S-transform based neural classifier scheme used for time series data mining of power quality events occurring due to power signal disturbances. The DWT and the S –transform are used for feature extraction and then the extracted features are classified with neural classifiers such as multilayered perceptron network (MLP) for pattern classification, data mining and subsequent knowledge discovery.
Geomagnetic Dst index forecast using a multilayer perceptrons artificial neural network
International Nuclear Information System (INIS)
Complete text of publication follows. The best known manifestations of the impact of solar wind on the magnetosphere are the geomagnetic storms. The prediction of geomagnetic field behavior allows the alert of geomagnetic storms occurrence, as those phenomena can cause many damages in the planet. The Artificial Intelligence tools have been applied in many multidisciplinary studies, covering several areas of knowledge, as a choice of approach to the solution of problems with characteristics like non-linearity, imprecision, and other features that can not be easily solved with conventional computational models. Techniques such as Artificial Neural Networks, Expert Systems and Decision Trees have been used in the Space Weather studies to perform tasks such as forecasting geomagnetic storms and the investigation of rules and parameters related on its occurrence. The main focus of this work is on forecasting the geomagnetic field behavior, represented this time by the Dst index, using for that task, mainly, the interplanetary magnetic field components and solar wind data. The tool chosen here to solve the non-linear problem was a Multi-layer Perceptrons Artificial Neural Network, trained with the backpropagation algorithm. Unlike what was done in other studies, we chose to predict calm and disturbed periods like, for example, a full month of data, for application in a real time forecasting system. It was possible to predict the geomagnetic Dst index one or two hours before with great percentage efficiency.
Indian Academy of Sciences (India)
Kamal Ahmed; Shamsuddin Shahid; Sobri Bin Haroon; Wang Xiao-Jun
2015-08-01
Downscaling rainfall in an arid region is much challenging compared to wet region due to erratic and infrequent behaviour of rainfall in the arid region. The complexity is further aggregated due to scarcity of data in such regions. A multilayer perceptron (MLP) neural network has been proposed in the present study for the downscaling of rainfall in the data scarce arid region of Baluchistan province of Pakistan, which is considered as one of the most vulnerable areas of Pakistan to climate change. The National Center for Environmental Prediction (NCEP) reanalysis datasets from 20 grid points surrounding the study area were used to select the predictors using principal component analysis. Monthly rainfall data for the time periods 1961–1990 and 1991–2001 were used for the calibration and validation of the MLP model, respectively. The performance of the model was assessed using various statistics including mean, variance, quartiles, root mean square error (RMSE), mean bias error (MBE), coefficient of determination (R2) and Nash–Sutcliffe efficiency (NSE). Comparisons of mean monthly time series of observed and downscaled rainfall showed good agreement during both calibration and validation periods, while the downscaling model was found to underpredict rainfall variance in both periods. Other statistical parameters also revealed good agreement between observed and downscaled rainfall during both calibration and validation periods in most of the stations.
Experiments with Evolutionary and Hybrid Learning of Multi-layer Perceptron Neural Networks.
Czech Academy of Sciences Publication Activity Database
Neruda, Roman; Slušný, Stanislav
Ostrava : VŠB Technická univerzita, 2007 - (Mikulecký, P.; Dvorský, J.; Krátký, M.), s. 75-84 ISBN 978-80-248-1279-3. [Znalosti 2007. Ostrava (CZ), 21.02.2007-23.02.2007] R&D Projects: GA AV ?R 1ET100300414 Institutional research plan: CEZ:AV0Z10300504 Keywords : multilayer perceptron * evolutionary learning * hybrid algorithms Subject RIV: IN - Informatics, Computer Science
DEFF Research Database (Denmark)
Kucuk, Nil; Manohara, S.R.; Hanagodimath, S.M.; Gerward, L.
2013-01-01
In this work, multilayered perceptron neural networks (MLPNNs) were presented for the computation of the gamma-ray energy absorption buildup factors (BA) of seven thermoluminescent dosimetric (TLD) materials [LiF, BeO, Na2B4O7, CaSO4, Li2B4O7, KMgF3, Ca3(PO4)2] in the energy region 0.015–15MeV, and for penetration depths up to 10 mfp (mean-free-path). The MLPNNs have been trained by a Levenberg–Marquardt learning algorithm. The developed model is in 99% agreement with the ANSI/ANS-6.4.3 standard...
Quaternionic Multilayer Perceptron with Local Analyticity
Directory of Open Access Journals (Sweden)
Nobuyuki Matsui
2012-11-01
Full Text Available A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons’ states in order to construct learning algorithm for this network. An error back-propagation algorithm is introduced for modifying the connection weights of the network.
International Nuclear Information System (INIS)
Critical heat flux (CHF) is an important parameter for the design of nuclear reactors. Although many experimental and theoretical researches have been performed, there is not a single correlation to predict CHF because it is influenced by many parameters. These parameters are based on fixed inlet, local and fixed outlet conditions. Artificial neural networks (ANNs) have been applied to a wide variety of different areas such as prediction, approximation, modeling and classification. In this study, two types of neural networks, radial basis function (RBF) and multilayer perceptron (MLP), are trained with the experimental CHF data and their performances are compared. RBF predicts CHF with root mean square (RMS) errors of 0.24%, 7.9%, 0.16% and MLP predicts CHF with RMS errors of 1.29%, 8.31% and 2.71%, in fixed inlet conditions, local conditions and fixed outlet conditions, respectively. The results show that neural networks with RBF structure have superior performance in CHF data prediction over MLP neural networks. The parametric trends of CHF obtained by the trained ANNs are also evaluated and results reported
Directory of Open Access Journals (Sweden)
Alireza Taravat
2014-12-01
Full Text Available Oil spills represent a major threat to ocean ecosystems and their environmental status. Previous studies have shown that Synthetic Aperture Radar (SAR, as its recording is independent of clouds and weather, can be effectively used for the detection and classification of oil spills. Dark formation detection is the first and critical stage in oil-spill detection procedures. In this paper, a novel approach for automated dark-spot detection in SAR imagery is presented. A new approach from the combination of adaptive Weibull Multiplicative Model (WMM and MultiLayer Perceptron (MLP neural networks is proposed to differentiate between dark spots and the background. The results have been compared with the results of a model combining non-adaptive WMM and pulse coupled neural networks. The presented approach overcomes the non-adaptive WMM filter setting parameters by developing an adaptive WMM model which is a step ahead towards a full automatic dark spot detection. The proposed approach was tested on 60 ENVISAT and ERS2 images which contained dark spots. For the overall dataset, an average accuracy of 94.65% was obtained. Our experimental results demonstrate that the proposed approach is very robust and effective where the non-adaptive WMM & pulse coupled neural network (PCNN model generates poor accuracies.
Directory of Open Access Journals (Sweden)
A. Piotrowski
2007-08-01
Full Text Available The prediction of temporal concentration profiles of a transported pollutant in a river is still a subject of ongoing research efforts worldwide. The present paper is aimed at studying the possibility of using Multi-Layer Perceptron Neural Networks to evaluate the whole concentration versus time profile at several cross-sections of a river under various flow conditions, using as little information about the river system as possible. In contrast with the earlier neural networks based work on longitudinal dispersion coefficients, this new approach relies more heavily on measurements of concentration collected during tracer tests over a range of flow conditions, but fewer hydraulic and morphological data are needed. The study is based upon 26 tracer experiments performed in a small river in Edinburgh, UK (Murray Burn at various flow rates in a 540 m long reach. The only data used in this study were concentration measurements collected at 4 cross-sections, distances between the cross-sections and the injection site, time, as well as flow rate and water velocity, obtained according to the data measured at the 1st and 2nd cross-sections.
The four main features of concentration versus time profiles at a particular cross-section, namely the peak concentration, the arrival time of the peak at the cross-section, and the shapes of the rising and falling limbs of the profile are modeled, and for each of them a separately designed neural network was used. There was also a variant investigated in which the conservation of the injected mass was assured by adjusting the predicted peak concentration. The neural network methods were compared with the unit peak attenuation curve concept.
In general the neural networks predicted the main features of the concentration profiles satisfactorily. The predicted peak concentrations were generally better than those obtained using the unit peak attenuation method, and the method with mass-conservation assured generally performed better than the method that did not account for mass-conservation. Predictions of peak travel time were also better using the neural networks than the unit peak attenuation method. Including more data into the neural network training set clearly improved the prediction of the shapes of the concentration profiles. Similar improvements in peak concentration were less significant and the travel time prediction appeared to be largely unaffected.
Directory of Open Access Journals (Sweden)
A. Piotrowski
2007-12-01
Full Text Available The prediction of temporal concentration profiles of a transported pollutant in a river is still a subject of ongoing research efforts worldwide. The present paper is aimed at studying the possibility of using Multi-Layer Perceptron Neural Networks to evaluate the whole concentration versus time profile at several cross-sections of a river under various flow conditions, using as little information about the river system as possible. In contrast with the earlier neural networks based work on longitudinal dispersion coefficients, this new approach relies more heavily on measurements of concentration collected during tracer tests over a range of flow conditions, but fewer hydraulic and morphological data are needed. The study is based upon 26 tracer experiments performed in a small river in Edinburgh, UK (Murray Burn at various flow rates in a 540 m long reach. The only data used in this study were concentration measurements collected at 4 cross-sections, distances between the cross-sections and the injection site, time, as well as flow rate and water velocity, obtained according to the data measured at the 1st and 2nd cross-sections.
The four main features of concentration versus time profiles at a particular cross-section, namely the peak concentration, the arrival time of the peak at the cross-section, and the shapes of the rising and falling limbs of the profile are modeled, and for each of them a separately designed neural network was used. There was also a variant investigated in which the conservation of the injected mass was assured by adjusting the predicted peak concentration. The neural network methods were compared with the unit peak attenuation curve concept.
In general the neural networks predicted the main features of the concentration profiles satisfactorily. The predicted peak concentrations were generally better than those obtained using the unit peak attenuation method, and the method with mass-conservation assured generally performed better than the method that did not account for mass-conservation. Predictions of peak travel time were also better using the neural networks than the unit peak attenuation method. Including more data into the neural network training set clearly improved the prediction of the shapes of the concentration profiles. Similar improvements in peak concentration were less significant and the travel time prediction appeared to be largely unaffected.
Wind speed estimation using multilayer perceptron
International Nuclear Information System (INIS)
Highlights: • We present a method for determining the average wind speed using neural networks. • We use data from that site in the short term and data from other nearby stations. • The inputs used in the ANN were wind speed and direction data from a station. • The method allows knowing the wind speed without topographical data. - Abstract: Wind speed knowledge is prerequisite in the siting of wind turbines. In consequence the wind energy use requires meticulous and specified knowledge of the wind characteristics at a location. This paper presents a method for determining the annual average wind speed at a complex terrain site by using neural networks, when only short term data are available for that site. This information is useful for preliminary calculations of the wind resource at a remote area having only a short time period of wind measurements measurement in a site. Artificial neural networks are useful for implementing non-linear process variables over time, and therefore are a useful tool for estimating the wind speed. The neural network used is multilayer perceptron with three layers and the supervised learning algorithm used is backpropagation. The inputs used in the neural network were wind speed and direction data from a single station, and the training patterns used correspond to sixty days data. The results obtained by simulating the annual average wind speed at the selected site based on data from nearby stations with correlation coefficients above 0.5 were satisfactory, compared with actual values. Reliable estimations were obtained, with errors below 6%
Sarakhs branch; Sarakhs, Iran.
2012-01-01
This paper presents a multi-layered perceptronneural network (MLPNN) method to solve the combinedeconomic and emission dispatch (CEED) problem. The harmfulecological effects caused by the emission of particulate andgaseous pollutants like sulfur dioxide (SO2) and oxides ofnitrogen ( NOx ) can be reduced by adequate distribution ofload between the plants of a power system. However, this leadsto a noticeable increase in the operating cost of the plants. Thispaper presents the (MLPNN) method app...
Auto-kernel using multilayer perceptron
Directory of Open Access Journals (Sweden)
Wei-Chen Cheng
2012-06-01
Full Text Available This work presents a constructive method to train the multilayer perceptron layer after layer successively and to accomplish the kernel used in the support vector machine. Data in different classes will be trained to map to distant points in each layer. This will ease the mapping of the next layer. A perfect mapping kernel can be accomplished successively. Those distant mapped points can be discriminated easily by a single perceptron.
Multi-Layer Perceptrons and Symbolic Data
Rossi, Fabrice
2008-01-01
In some real world situations, linear models are not sufficient to represent accurately complex relations between input variables and output variables of a studied system. Multilayer Perceptrons are one of the most successful non-linear regression tool but they are unfortunately restricted to inputs and outputs that belong to a normed vector space. In this chapter, we propose a general recoding method that allows to use symbolic data both as inputs and outputs to Multilayer Perceptrons. The recoding is quite simple to implement and yet provides a flexible framework that allows to deal with almost all practical cases. The proposed method is illustrated on a real world data set.
Multi-Layer Perceptrons and Symbolic Data
Rossi, Fabrice; Conan-Guez, Brieuc
2008-01-01
In some real world situations, linear models are not sufficient to represent accurately complex relations between input variables and output variables of a studied system. Multilayer Perceptrons are one of the most successful non-linear regression tool but they are unfortunately restricted to inputs and outputs that belong to a normed vector space. In this chapter, we propose a general recoding method that allows to use symbolic data both as inputs and outputs to Multilayer ...
A Parallel Framework for Multilayer Perceptron for Human Face Recognition
Mita Nasipuri; Mahantapas Kundu; Dipak Kumar Basu; Debotosh Bhattacharjee; Mrinal Kanti Bhowmik
2010-01-01
Artificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is that it is extremely slow during training for larger classes and hence not suitable for real-time complex problems such as pattern recognition. This is an attempt to develop a parallel framework for the training algorithm of a perceptron. In this paper, two general architectures for a Multilayer Perce...
DEFF Research Database (Denmark)
Kucuk, Nil; Manohara, S.R.
2013-01-01
In this work, multilayered perceptron neural networks (MLPNNs) were presented for the computation of the gamma-ray energy absorption buildup factors (BA) of seven thermoluminescent dosimetric (TLD) materials [LiF, BeO, Na2B4O7, CaSO4, Li2B4O7, KMgF3, Ca3(PO4)2] in the energy region 0.015–15MeV, and for penetration depths up to 10 mfp (mean-free-path). The MLPNNs have been trained by a Levenberg–Marquardt learning algorithm. The developed model is in 99% agreement with the ANSI/ANS-6.4.3 standard data set. Furthermore, the model is fast and does not require tremendous computational efforts. The estimated BA data for TLD materials have been given with penetration depth and incident photon energy as comparative to the results of the interpolation method using the Geometrical Progression (G-P) fitting formula.
KLASIFIKASI WEBSITE MENGGUNAKAN ALGORITMA MULTILAYER PERCEPTRON
Directory of Open Access Journals (Sweden)
Nyoman Purnama
2014-08-01
Full Text Available Sistem klasifikasi merupakan proses temu balik informasi yang sangat bergantung dari elemen-elemen penyusunnya.Sistem ini banyak digunakan untuk mengatasi permasalahan segmentasi data. Klasifikasi dapat digunakan pada website sebagaimetode untuk mengelompokkan website. Website merupakan salah satu data yang memiliki informasi yang beraneka-ragam,sehingga pengelompokan data ini penting untuk diteliti. Sistem klasifikasi dimulai dengan melakukan proses pengumpulaninformasi dari halaman website (parsing dan untuk setiap hasil parsing dilakukan proses penghapusan kata henti, stemming,feature selection dengan tf-idf. Hasil dari proses ini berupa fitur yang menjadi inputan algoritma Multilayer Perceptron. Dalamalgoritma ini terjadi proses pembelajaran terhadap pola input masukan dan pembuatan bobot pelatihan. Bobot ini akandigunakan pada proses klasifikasi. Hasil dari penelitian menunjukkan bahwa algoritma Multilayer Perceptron dapatmenghasilkan klasifikasi website dengan akurasi yang bagus. Hal ini dibuktikan dengan beberapa tahapan penelitian yangberbeda dan didapatkan nilai akurasi rata-rata diatas 70%.
Multilayer perceptron-based DFE with lattice structure.
Zerguine, A; Shafi, A; Bettayeb, M
2001-01-01
The severely distorting channels limit the use of linear equalizers and the use of the nonlinear equalizers then becomes justifiable. Neural-network-based equalizers, especially the multilayer perceptron (MLP)-based equalizers, are computationally efficient alternative to currently used nonlinear filter realizations, e.g., the Volterra type. The drawback of the MLP-based equalizers is, however, their slow rate of convergence, which limit their use in practical systems. In this work, the effect of whitening the input data in a multilayer perceptron-based decision feedback equalizer (DFE) is evaluated. It is shown from computer simulations that whitening the received data employing adaptive lattice channel equalization algorithms improves the convergence rate and bit error rate performances of multilayer perceptron-based DFE. The adaptive lattice algorithm is a modification to the one developed by Ling and Proakis (1985). The consistency in performance is observed in both time-invariant and time-varying channels. Finally, it is found in this work that, for time-invariant channels, the MLP DFE outperforms the least mean squares (LMS)-based DFE. However, for time-varying channels comparable performance is obtained for the two configurations. PMID:18249886
Learning of Multilayer Perceptrons with Piecewise-Linear Activation Functions.
Czech Academy of Sciences Publication Activity Database
Kozub, P.; Hole?a, Martin
Praha : Matfyzpress, 2008 - (Obdržálek, D.; Štanclová, J.; Plátek, M.), s. 27-46 ISBN 978-80-7378-076-0. [MIS 2008. Malý informatický seminá? /25./. Josef?v d?l (CZ), 12.01.2008-19.01.2008] R&D Projects: GA ?R GA201/08/0802; GA ?R GA201/08/1744 Institutional research plan: CEZ:AV0Z10300504 Keywords : artificial neural networks * multilayer perceptrons * activation functions * function approximation * constrained optimization Subject RIV: IN - Informatics, Computer Science
Mandal, Uttam; Gowda, Veeran; Ghosh, Animesh; Bose, Anirbandeep; Bhaumik, Uttam; Chatterjee, Bappaditya; Pal, Tapan Kumar
2008-02-01
The aim of the present study was to apply the simultaneous optimization method incorporating Artificial Neural Network (ANN) using Multi-layer Perceptron (MLP) model to the development of a metformin HCl 500 mg sustained release matrix tablets with an optimized in vitro release profile. The amounts of HPMC K15M and PVP K30 at three levels (-1, 0, +1) for each were selected as casual factors. In vitro dissolution time profiles at four different sampling times (1 h, 2 h, 4 h and 8 h) were chosen as output variables. 13 kinds of metformin matrix tablets were prepared according to a 2(3) factorial design (central composite) with five extra center points, and their dissolution tests were performed. Commercially available STATISTICA Neural Network software (Stat Soft, Inc., Tulsa, OK, U.S.A.) was used throughout the study. The training process of MLP was completed until a satisfactory value of root square mean (RSM) for the test data was obtained using feed forward back propagation method. The root mean square value for the trained network was 0.000097, which indicated that the optimal MLP model was reached. The optimal tablet formulation based on some predetermined release criteria predicted by MLP was 336 mg of HPMC K15M and 130 mg of PVP K30. Calculated difference (f(1) 2.19) and similarity (f(2) 89.79) factors indicated that there was no difference between predicted and experimentally observed drug release profiles for the optimal formulation. This work illustrates the potential for an artificial neural network with MLP, to assist in development of sustained release dosage forms. PMID:18239298
International Nuclear Information System (INIS)
In this work, multilayered perceptron neural networks (MLPNNs) were presented for the computation of the gamma-ray energy absorption buildup factors (BA) of seven thermoluminescent dosimetric (TLD) materials [LiF, BeO, Na2B4O7, CaSO4, Li2B4O7, KMgF3, Ca3(PO4)2] in the energy region 0.015–15 MeV, and for penetration depths up to 10 mfp (mean-free-path). The MLPNNs have been trained by a Levenberg–Marquardt learning algorithm. The developed model is in 99% agreement with the ANSI/ANS-6.4.3 standard data set. Furthermore, the model is fast and does not require tremendous computational efforts. The estimated BA data for TLD materials have been given with penetration depth and incident photon energy as comparative to the results of the interpolation method using the Geometrical Progression (G-P) fitting formula. - Highlights: ? Gamma-ray energy absorption buildup factors estimation in TLD materials. ? The ANN approach can be alternative to G-P fitting method for BA calculations. ? The applied model is not time-consuming and easily predicted
Scientific Electronic Library Online (English)
Héctor, Tabares; John, Branch; Jaime, Valencia.
2006-09-01
Full Text Available En este trabajo se aplica un método constructivo aproximado para encontrar arquitecturas de redes neuronales artificiales (RNA) de tipo perceptrón multicapa (PMC). El método se complementa con la técnica de la búsqueda forzada de mejores mínimos locales. El entrenamiento de la red se lleva a cabo a [...] través del algoritmo gradiente descendente básico (GDB); se aplican técnicas como la repetición del entrenamiento y la detención temprana (validación cruzada), para mejorar los resultados. El criterio de evaluación se basa en las habilidades de aprendizaje y de generalización de las arquitecturas generadas específicas de un dominio. Se presentan resultados experimentales con los cuales se demuestra la efectividad del método propuesto y comparan con las arquitecturas halladas por otros métodos. Abstract in english This paper deals with an approximate constructive method to find architectures of artificial neuronal network (ANN) of the type MultiLayer Percetron (MLP) which solves a particular problem. This method is supplemented with the technique of the Forced search of better local minima. The training of th [...] e net uses an algorithm basic descending gradient (BDG). Techniques such as repetition of the training and the early stopping (cross validation) are used to improve the results. The evaluation approach is based not only on the learning abilities but also on the generalization of the specific generated architectures of a domain. Experimental results are presented in order to prove the effectiveness of the proposed method. These are compared with architectures found by other methods.
Online learning dynamics of multilayer perceptrons with unidentifiable parameters
International Nuclear Information System (INIS)
In the over-realizable learning scenario of multilayer perceptrons, in which the student network has a larger number of hidden units than the true or optimal network, some of the weight parameters are unidentifiable. In this case, the teacher network consists of a union of optimal subspaces included in the parameter space. The optimal subspaces, which lead to singularities, are known to affect the estimation performance of neural networks. Using statistical mechanics, we investigate the online learning dynamics of two-layer neural networks in the over-realizable scenario with unidentifiable parameters. We show that the convergence speed strongly depends on the initial parameter conditions. We also show that there is a quasi-plateau around the optimal subspace, which differs from the well-known plateaus caused by permutation symmetry. In addition, we discuss the property of the final learning state, relating this to the singular structures
Directory of Open Access Journals (Sweden)
Rodrigo Martins da Silva
2011-12-01
Full Text Available There are several neural network implementations using either software, hardware-based or a hardware/software co-design. This work proposes a hardware architecture to implement an artificial neural network (ANN, whose topology is the multilayer perceptron (MLP. In this paper, we explore the parallelism of neural networks and allow on-thefly changes of the number of inputs, number of layers and number of neurons per layer of the net. This reconfigurability characteristic permits that any application of ANNs may be implemented using the proposed hardware. In order to reduce the processing time that is spent in arithmetic computation, a real number is represented using a fraction of integers. In this way, the arithmetics is limited to integer operations, performed by fast combinational circuits. A simple state machine is required to control sums and products of fractions. Sigmoid is used as the activation function in the proposed implementation. It is approximated by polynomials, whose underlying computation requires only sums and products. A theorem is introduced and proven so as to cover the arithmetic strategy of the computation of the activation function. Thus, the arithmetic circuitry used to implement the neuron weighted sum is reused for computing the sigmoid. this resource sharing decreased drastically the total area of the system. After modeling and simulation for functionality validation, the proposed architecture synthesized using reconfigurable hardware. The results are promising.Em termos computacionais, uma rede neural artificial (RNA pode ser implementada em software ou em hardware, ou ainda de maneira híbrida, combinando ambos os recursos. O presente trabalho propõe uma arquitetura de hardware para a computação de uma rede neural do tipo perceptron com múltiplas camadas (MLP. Soluções em hardware tendem a ser mais eficientes do que soluções em software. O projeto em questão, além de explorar fortemente o paralelismo das redes neurais, permite alterações do número de entradas, número de camadas e de neurônios por camada, de modo que diversas aplicações de RNAs possam ser executadas no hardware proposto. Visando a uma redução de tempo do processamento aritmético, um número real é aproximado por uma fração de inteiros. Dessa forma, as operações aritméticas limitam-se a operações inteiras, executadas por circuitos combinacionais. Uma simples máquina de estados é demandada para controlar somas e produtos de frações. A função de ativação usada neste projeto é a sigmóide. Essa função é aproximada mediante o uso de polinômios, cujas operações são regidas por somas e produtos. Um teorema é introduzido e provado, permitindo a fundamentação da estratégia de cálculo da função de ativação. Dessa forma, reaproveita-se o circuito aritmético da soma ponderada para também computar a sigmóide. Essa re-utilização dos recursos levou a uma redução drástica de área total de circuito. Após modelagem e simulação para validação do bom funcionamento, a arquitetura proposta foi sintetizada utilizando recursos reconfiguráveis, do tipo FPGA. Os resultados são promissores.
Scientific Electronic Library Online (English)
Rodrigo Martins da, Silva; Luiza de Macedo, Mourelle; Nadia, Nedjah.
2011-12-01
Full Text Available Em termos computacionais, uma rede neural artificial (RNA) pode ser implementada em software ou em hardware, ou ainda de maneira híbrida, combinando ambos os recursos. O presente trabalho propõe uma arquitetura de hardware para a computação de uma rede neural do tipo perceptron com múltiplas camadas [...] (MLP). Soluções em hardware tendem a ser mais eficientes do que soluções em software. O projeto em questão, além de explorar fortemente o paralelismo das redes neurais, permite alterações do número de entradas, número de camadas e de neurônios por camada, de modo que diversas aplicações de RNAs possam ser executadas no hardware proposto. Visando a uma redução de tempo do processamento aritmético, um número real é aproximado por uma fração de inteiros. Dessa forma, as operações aritméticas limitam-se a operações inteiras, executadas por circuitos combinacionais. Uma simples máquina de estados é demandada para controlar somas e produtos de frações. A função de ativação usada neste projeto é a sigmóide. Essa função é aproximada mediante o uso de polinômios, cujas operações são regidas por somas e produtos. Um teorema é introduzido e provado, permitindo a fundamentação da estratégia de cálculo da função de ativação. Dessa forma, reaproveita-se o circuito aritmético da soma ponderada para também computar a sigmóide. Essa re-utilização dos recursos levou a uma redução drástica de área total de circuito. Após modelagem e simulação para validação do bom funcionamento, a arquitetura proposta foi sintetizada utilizando recursos reconfiguráveis, do tipo FPGA. Os resultados são promissores. Abstract in english There are several neural network implementations using either software, hardware-based or a hardware/software co-design. This work proposes a hardware architecture to implement an artificial neural network (ANN), whose topology is the multilayer perceptron (MLP). In this paper, we explore the parall [...] elism of neural networks and allow on-thefly changes of the number of inputs, number of layers and number of neurons per layer of the net. This reconfigurability characteristic permits that any application of ANNs may be implemented using the proposed hardware. In order to reduce the processing time that is spent in arithmetic computation, a real number is represented using a fraction of integers. In this way, the arithmetics is limited to integer operations, performed by fast combinational circuits. A simple state machine is required to control sums and products of fractions. Sigmoid is used as the activation function in the proposed implementation. It is approximated by polynomials, whose underlying computation requires only sums and products. A theorem is introduced and proven so as to cover the arithmetic strategy of the computation of the activation function. Thus, the arithmetic circuitry used to implement the neuron weighted sum is reused for computing the sigmoid. this resource sharing decreased drastically the total area of the system. After modeling and simulation for functionality validation, the proposed architecture synthesized using reconfigurable hardware. The results are promising.
A Parallel Framework for Multilayer Perceptron for Human Face Recognition
Directory of Open Access Journals (Sweden)
Mita Nasipuri
2010-01-01
Full Text Available Artificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is that it is extremely slow during training for larger classes and hence not suitable for real-time complex problems such as pattern recognition. This is an attempt to develop a parallel framework for the training algorithm of a perceptron. In this paper, two general architectures for a Multilayer Perceptron (MLP have been demonstrated. The first architecture is All-Class-in-One-Network (ACON where all the classes are placed in a single network and the second one is One-Class-in-One-Network (OCON where an individual single network is responsible for each and every class. Capabilities of these two architectures were compared and verified in solving human face recognition, which is a complex pattern recognition task where several factors affect the recognition performance like pose variations, facial expression changes, occlusions, and most importantly illumination changes. Experimental results show that the proposed OCON structure performs better than the conventional ACON in terms of network training convergence speed and which can be easily exercised in a parallel environment.
Multilayer perceptron in damage detection of bridge structures
Pandey, P. C.; Barai, S. V.
1995-02-01
Recent developments in artificial neural networks (ANN) have opened up new possibilities in the domain of structural engineering. For inverse problems like structural identification of large civil engineerlng structures such as bridges and buildings where the in situ measured data are expected to be imprecise and often incomplete, the ANN holds greater promise. The detection of structural damage and identification of damaged element in a large complex structure is a challenging task indeed. This paper presents an application of multilayer perceptron in the damage detection of steel bridge structures. The ssues relating to the design of network and learning paradigm are addressed and network architectures have been developed with reference to trussed bridge structures. The training patterns are generated for multiple damaged zones in a structure and performance of the networks with one and two hidden layers are examined. It has been observed that the performance of the network with two hidden layers was better than that of a single-layer architecture in general. The engineering importance of the whole exercise is demonstrated from the fact that measured input at only a few locations in the structure is needed in the identification process using the ANN.
Validation of Infinite Impulse Response Multilayer Perceptron for Modelling Nuclear Dynamics
Directory of Open Access Journals (Sweden)
N. Pedroni
2008-03-01
Full Text Available Artificial neural networks are powerful algorithms for constructing nonlinear empirical models from operational data. Their use is becoming increasingly popular in the complex modeling tasks required by diagnostic, safety, and control applications in complex technologies such as those employed in the nuclear industry. In this paper, the nonlinear modeling capabilities of an infinite impulse response multilayer perceptron (IIR-MLP for nuclear dynamics are considered in comparison to static modeling by a finite impulse response multilayer perceptron (FIR-MLP and a conventional static MLP. The comparison is made with respect to the nonlinear dynamics of a nuclear reactor as investigated by IIR-MLP in a previous paper. The superior performance of the locally recurrent scheme is demonstrated.
Classification of Log-Polar-Visual Eigenfaces using Multilayer Perceptron
Bhowmik, Mrinal Kanti; Bhattacharjee, Debotosh; Nasipuri, Mita; Kundu, Mahantapas; Basu, Dipak kumar
2010-01-01
In this paper we present a simple novel approach to tackle the challenges of scaling and rotation of face images in face recognition. The proposed approach registers the training and testing visual face images by log-polar transformation, which is capable to handle complicacies introduced by scaling and rotation. Log-polar images are projected into eigenspace and finally classified using an improved multi-layer perceptron. In the experiments we have used ORL face database an...
Sartori, Michael A.; Passino, Kevin M.; Antsaklis, Panos J.
1992-01-01
In rule-based AI planning, expert, and learning systems, it is often the case that the left-hand-sides of the rules must be repeatedly compared to the contents of some 'working memory'. The traditional approach to solve such a 'match phase problem' for production systems is to use the Rete Match Algorithm. Here, a new technique using a multilayer perceptron, a particular artificial neural network model, is presented to solve the match phase problem for rule-based AI systems. A syntax for premise formulas (i.e., the left-hand-sides of the rules) is defined, and working memory is specified. From this, it is shown how to construct a multilayer perceptron that finds all of the rules which can be executed for the current situation in working memory. The complexity of the constructed multilayer perceptron is derived in terms of the maximum number of nodes and the required number of layers. A method for reducing the number of layers to at most three is also presented.
Efficient training of multilayer perceptrons using principal component analysis
International Nuclear Information System (INIS)
A training algorithm for multilayer perceptrons is discussed and studied in detail, which relates to the technique of principal component analysis. The latter is performed with respect to a correlation matrix computed from the example inputs and their target outputs. Typical properties of the training procedure are investigated by means of a statistical physics analysis in models of learning regression and classification tasks. We demonstrate that the procedure requires by far fewer examples for good generalization than traditional online training. For networks with a large number of hidden units we derive the training prescription which achieves, within our model, the optimal generalization behavior
Theoretical Properties of Projection Based Multilayer Perceptrons with Functional Inputs
Rossi, F; Rossi, Fabrice; Conan-Guez, Brieuc
2006-01-01
Many real world data are sampled functions. As shown by Functional Data Analysis (FDA) methods, spectra, time series, images, gesture recognition data, etc. can be processed more efficiently if their functional nature is taken into account during the data analysis process. This is done by extending standard data analysis methods so that they can apply to functional inputs. A general way to achieve this goal is to compute projections of the functional data onto a finite dimensional sub-space of the functional space. The coordinates of the data on a basis of this sub-space provide standard vector representations of the functions. The obtained vectors can be processed by any standard method. In our previous work, this general approach has been used to define projection based Multilayer Perceptrons (MLPs) with functional inputs. We study in this paper important theoretical properties of the proposed model. We show in particular that MLPs with functional inputs are universal approximators: they can approximate to ...
Scientific Electronic Library Online (English)
José C, Cúrvelo Santana; Sidnei A, de Araújo; Joana P, M. Biazus; Roberto R, de Souza.
2015-04-01
Full Text Available En este trabajo se propone utilizar una Red Neuronal Artificial (RNA) Perceptrón Multicapa (PMC) para simular la variación de la concentración de proteína de acuerdo con el tiempo y también para determinar la hora final del procedimiento, además de los parámetros óptimos del proceso de biodegradació [...] n de las proteínas de un efluente de matadero. Para eso, han sido utilizadas las papaínas, presentes en el látex de la papaya (Carica papaya) con el objetivo de disminuir la concentración de proteínas de un efluente de matadero a pH (5 y 7) con una temperatura de (25 y 30° C) controlada. Los resultados mostraron que las papaínas redujeron de 82% a 91% la concentración de proteína en 30 y 40 h de proceso. Las simulaciones con la RNA apuntaron que las condiciones perfectas fueron obtenidas a pH 5, con 30 °C y en 35 h, en el cual se ha alcanzado una reducción de 91% de la concentración de proteínas. Abstract in english In this paper, the use of a multilayer perceptron (MLP) artificial neural network (ANN) is proposed to simulate the variation of protein concentration according to the time and also to determine the end and optimal conditions of the biodegradation process of wastewater from meat industry. To reduce [...] the protein concentration, papains from Carica papaya latex have been used at controlled condition of pH (5 and 7) and temperature (25 and 30 °C). Results showed that a reduction of 82 to 91% of protein concentration by the action of papains for 30 to 40 h of process time. Simulations showed that the best condition of the process occurred at pH 5, 30 °C and 35 h, in which a maximum biodegradation of 91% was obtained.
Mozumder, Chitrini; Tripathi, Nitin K.
2014-10-01
In recent decades, the world has experienced unprecedented urban growth which endangers the green environment in and around urban areas. In this work, an artificial neural network (ANN) based model is developed to predict future impacts of urban and agricultural expansion on the uplands of Deepor Beel, a Ramsar wetland in the city area of Guwahati, Assam, India, by 2025 and 2035 respectively. Simulations were carried out for three different transition rates as determined from the changes during 2001-2011, namely simple extrapolation, Markov Chain (MC), and system dynamic (SD) modelling, using projected population growth, which were further investigated based on three different zoning policies. The first zoning policy employed no restriction while the second conversion restriction zoning policy restricted urban-agricultural expansion in the Guwahati Municipal Development Authority (GMDA) proposed green belt, extending to a third zoning policy providing wetland restoration in the proposed green belt. The prediction maps were found to be greatly influenced by the transition rates and the allowed transitions from one class to another within each sub-model. The model outputs were compared with GMDA land demand as proposed for 2025 whereby the land demand as produced by MC was found to best match the projected demand. Regarding the conservation of Deepor Beel, the Landscape Development Intensity (LDI) Index revealed that wetland restoration zoning policies may reduce the impact of urban growth on a local scale, but none of the zoning policies was found to minimize the impact on a broader base. The results from this study may assist the planning and reviewing of land use allocation within Guwahati city to secure ecological sustainability of the wetlands.
An application of the multilayer perceptron: Solar radiation maps in Spain
Energy Technology Data Exchange (ETDEWEB)
Hontoria, L.; Aguilera, J. [Grupo Investigacion y Desarrollo en Energia Solar y Automatica, Dpto. de Ingenieria Electronica, de Telecomunicaciones y Automatica, Escuela Politecnica Superior de Jaen, Campus de las Lagunillas, Universidad de Jaen, 23071 Jaen (Spain); Zufiria, P. [Grupo de Redes Neuronales, Dpto. de Matematica Aplicada a las Tecnologias de la Informacion, ETSI Telecomunicaciones, UPM Ciudad Universitaria s/n, 28040 Madrid (Spain)
2005-11-01
In this work an application of a methodology to obtain solar radiation maps is presented. This methodology is based on a neural network system [Lippmann, R.P., 1987. An introduction to computing with neural nets. IEEE ASSP Magazine, 4-22] called Multi-Layer Perceptron (MLP) [Haykin, S., 1994. Neural Networks. A Comprehensive Foundation. Macmillan Publishing Company; Hornik, K., Stinchcombe, M., White, H., 1989. Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359-366]. To obtain a solar radiation map it is necessary to know the solar radiation of many points spread wide across the zone of the map where it is going to be drawn. For most of the locations all over the world the records of these data (solar radiation in whatever scale, daily or hourly values) are non-existent. Only very few locations have the privilege of having good meteorological stations where records of solar radiation have being registered. But even in those locations with historical records of solar data, the quality of these solar series is not as good as it should be for most purposes. In addition, to draw solar radiation maps the number of points on the maps (real sites) that it is necessary to work with makes this problem difficult to solve. Nevertheless, with the application of the methodology proposed in this paper, this problem has been solved and solar radiation maps have been obtained for a small region of Spain: Jaen province, a southern province of Spain between parallels 38{sup o}25' N and 37{sup o}25' N, and meridians 4{sup o}10' W and 2{sup o}10' W, and for a larger region: Andalucia, the most southern region of Spain situated between parallels 38{sup o}40' N and 36{sup o}00' N, and meridians 7{sup o}30' W and 1{sup o}40' W. (author)
International Nuclear Information System (INIS)
The problem of pion-electron identification based on their energy losses in the TRD is considered in the frame of the CBM experiment. For particles identification an artificial neural network (ANN) was used, a multilayer perceptron realized in JETNET and ROOT packages. It is demonstrated that, in order to get correct and comparable results, it is important to define the network structure correctly. The recommendations for such a selection are given. In order to achieve an acceptable level of pions suppression, the energy losses need to be transformed to more 'effective' variables. The dependency of ANN output threshold for a fixed portion of electron loss on the particle momentum is presented
Using multilayer perceptron and a satellite image for the estimation of soil salinity
International Nuclear Information System (INIS)
Applying the model of the Perceptron multilayer with momentum of an artificial neural network particularly and a multispectral image of high resolution spatial and radiometric, for the first time estimated the salinity of the soil cultivated with sugar cane. The study area is the UBPC 'Lazaro Romero' of the sugar company 'Hector Molina' of the locality San Nicolas de Bari, Havana province, located at 22° 44' North latitude and 81 ° 56' longitude West. The experiments were made in the framework of the El-479 project funded by the Inter universities Council of Flanders, Belgium. 36 samples geo referenced of soils were taken at 3 depths in each of the 4 sugar cane selected blocks, which determined the electrical conductivity of the saturation extract; half of that amount of data was used for the training of the network and the other half for control in a computer program of the artificial neural network created to that effect, together with the reflectance of vegetation indexes for the image, which were maps of electrical conductivity of each block and bands. They were compared with those obtained by simple linear regression between the normalized difference vegetation index and electrical conductivity, Ndv with the approach of the neuronal network, the correlation coefficient was 0.78 to 0.83, while the linear regression was between 0.65 to 0.75
Face Recognition through Multilayer Perceptron (MLP and Learning Vector Quantization (LVQ
Directory of Open Access Journals (Sweden)
Dr. Ikvinderpal Singh
2012-12-01
Full Text Available Face recognition is challenging problems and there is still a lot of work that needs to be done in this area. Over the past ten years, face recognition has received substantial attention from researchers in biometrics, pattern recognition, computer vision, and cognitive psychology communities. This common interest in facial recognition technology among researchers working in diverse fields is motivated both by the remarkable ability to recognize people and by the increased attention being devoted to security applications. Applications of face recognition can be found in security, tracking, multimedia, and entertainment domains.This paper presents a face recognition system using artificial neural network. Here, we have designed a neural network with some own set network parameters. The results presented here have been obtained using two basic methods: multilayer perceptron (MLP, and learning vector quantization (LVQ. In both cases, two kinds of data have been fed to the classifiers: reduced resolution images (gray level or segmented, and feature vectors. The experimental results also show that, for the approaches considered here, analyzing gray level images produced better results than analyzing geometrical features, either because of the errors introduced during their extraction or because the original images have a richer information content. Furthermore, training times were much shorter for LVQ than for MLP. On the other hand, MLP achieved lower error rates when dealing with geometrical features.
Directory of Open Access Journals (Sweden)
Lenniet Coello
2015-01-01
Full Text Available The most widely used neural network model is Multilayer Perceptron (MLP, in which training of the connection weights is normally completed by a Back Propagation learning algorithm. G ood initial values of weights bear a fast convergence and a better generalization capability even with simple gradient - based error minimization techniques. This work presen ts a method to calculate the initial weights in order to train the Multilayer Perceptron Model. The method named PSO+RST+FUZZY is based on the similarity quality measure proposed within the framework of the extended Rough Set Theory that employs fuzzy sets to characterize the domain of similarity thresholds. Sensitivity of BP to initial weights with PSO+RST+FUZZY was studied experimentally, showing better performance than other methods used to calculate feature weights .
Dines, John; Vepa, Jithendra
2007-01-01
We propose an alternative means of training a multilayer perceptron for the task of speech activity detection based on a criterion to minimise the error in the estimation of mean and variance statistics for speech cepstrum based features using the Kullback-Leibler divergence. We present our baseline and proposed speech activity detection approaches for multi-channel meeting room recordings and demonstrate the effectiveness of the new criterion by comparing the two approaches when used to carr...
Hybrid Evolutionary Algorithm for Multilayer Perceptron Networks with Competetive Performance.
Czech Academy of Sciences Publication Activity Database
Neruda, Roman
Los Alamitos : IEEE, 2007, s. 1620-1627. ISBN 978-1-4244-1339-3. [CEC 2007. Congress on Evolutionary Computation. Singapore (SG), 25.09.2007-28.09.2007] R&D Projects: GA AV ?R 1ET100300419 Institutional research plan: CEZ:AV0Z10300504 Keywords : hybrid algorithms * evolutionary learning * neural networks Subject RIV: IN - Informatics, Computer Science
FPGA Implementation of Multilayer Perceptron for Modeling of Photovoltaic panel
International Nuclear Information System (INIS)
The Number of electronic applications using artificial neural network-based solutions has increased considerably in the last few years. However, their applications in photovoltaic systems are very limited. This paper introduces the preliminary result of the modeling and simulation of photovoltaic panel based on neural network and VHDL-language. In fact, an experimental database of meteorological data (irradiation, temperature) and output electrical generation signals of the PV-panel (current and voltage) has been used in this study. The inputs of the ANN-PV-panel are the daily total irradiation and mean average temperature while the outputs are the current and voltage generated from the panel. Firstly, a dataset of 4x364 have been used for training the network. Subsequently, the neural network (MLP) corresponding to PV-panel is simulated using VHDL language based on the saved weights and bias of the network. Simulation results of the trained MLP-PV panel based on Matlab and VHDL are presented. The proposed PV-panel model based ANN and VHDL permit to evaluate the performance PV-panel using only the environmental factors and involves less computational efforts, and it can be used for predicting the output electrical energy from the PV-panel
International Nuclear Information System (INIS)
Highlights: • Multilayer perceptrons are used to simulate the I–V curve of thin-film PV modules. • APE from the spectral irradiance was added as an input variable to the network. • A self-organised map is used to select the curves used for training the network. • Curve error and maximum power error decrease when using this technique. • This method could provide accurate estimation of the output of a PV plant. - Abstract: In this paper, we propose the use of a methodology to characterise the electrical parameters of several thin-film photovoltaic module technologies. This methodology allows us to use not only solar irradiance and module temperature as classical models do, but also spectral distribution of solar radiation. The methodology is based on the use of neural network models. From all measured I–V curves of a module, a previous selection of them has been used in order to train the neural network model. This selection is performed using a Kohonen self-organising map fed with spectral data. This spectral information has been added as an input to the neural network itself. The results show that the incorporation of spectral measurements to simulate thin-film modules improves significantly both the fitting of the predicted I–V curve to the measured one and the peak power point estimation
Sleep snoring detection using multi-layer neural networks.
Nguyen, Tan Loc; Won, Yonggwan
2015-08-17
Snoring detection is important for diagnosing obstructive sleep apnea syndrome (OSAS) and other respiratory sleep disorders. In general, audio signal processing such as snoring sound analysis uses the frequency characteristics of the signal. Recently, a correlational filter Multilayer Perceptron neural network (f-MLP) has been proposed, which has the first hidden layer of correlational filter operations in frequency domain. It demonstrated a superior classification performance for the pattern sets; of these, frequency information is the dominant feature for classification. The first hidden layer is implemented with the correlational filter operation; its output is the power spectrum of the filter output, while the other layers are the same as the ordinary multilayer Perceptron (o-MLP). By using the back-propagation learning algorithm for the correlational filter layer, f-MLP was able to self-adapt the filter coefficients to produce its output with more discrimination power for classification in the higher layer. In this research, this f-MLP was applied for sleep snoring signal detection. As a result, the f-MLP achieved an average detection rate of 96% for the test patterns, compared to the conventional multilayer neural network that demonstrates an 82% average detection rate. PMID:26405943
A New Approach to Predicting Bankruptcy: Combining DEA and Multi-Layer Perceptron
Directory of Open Access Journals (Sweden)
Ayan Mukhopadhyay
2012-07-01
Full Text Available The question of financial health and sustenance of a firm is so intriguing that it has spanned numerous studies. For investors,stakeholders and lenders, assessing the risk associated with an enterprise is vital. Several tools have been formulated to deal with predicting the solvency of a firm. This paper attempts to combine Data Envelopment Analysis and Multi-Layer Perceptron (MLP to suggest a new method for prediction of bankruptcy that not only focusses on historical financial data of firms that filed for bankruptcy like other past studies but also takes into account the data of those firms that were likely to do so. This method thus identifies firms that have a high chance of facing bankruptcy along with those that have filed for bankruptcy. The performance of this procedure is compared with MLP. The suggested method outperforms MLP in prediction of bankruptcy.
Time series modeling with pruned multi-layer perceptron and 2-stage damped least-squares method
International Nuclear Information System (INIS)
A Multi-Layer Perceptron (MLP) defines a family of artificial neural networks often used in TS modeling and forecasting. Because of its ''black box'' aspect, many researchers refuse to use it. Moreover, the optimization (often based on the exhaustive approach where ''all'' configurations are tested) and learning phases of this artificial intelligence tool (often based on the Levenberg-Marquardt algorithm; LMA) are weaknesses of this approach (exhaustively and local minima). These two tasks must be repeated depending on the knowledge of each new problem studied, making the process, long, laborious and not systematically robust. In this paper a pruning process is proposed. This method allows, during the training phase, to carry out an inputs selecting method activating (or not) inter-nodes connections in order to verify if forecasting is improved. We propose to use iteratively the popular damped least-squares method to activate inputs and neurons. A first pass is applied to 10% of the learning sample to determine weights significantly different from 0 and delete other. Then a classical batch process based on LMA is used with the new MLP. The validation is done using 25 measured meteorological TS and cross-comparing the prediction results of the classical LMA and the 2-stage LMA
Time series modeling with pruned multi-layer perceptron and 2-stage damped least-squares method
Voyant, Cyril; Tamas, Wani; Paoli, Christophe; Balu, Aurélia; Muselli, Marc; Nivet, Marie-Laure; Notton, Gilles
2014-03-01
A Multi-Layer Perceptron (MLP) defines a family of artificial neural networks often used in TS modeling and forecasting. Because of its "black box" aspect, many researchers refuse to use it. Moreover, the optimization (often based on the exhaustive approach where "all" configurations are tested) and learning phases of this artificial intelligence tool (often based on the Levenberg-Marquardt algorithm; LMA) are weaknesses of this approach (exhaustively and local minima). These two tasks must be repeated depending on the knowledge of each new problem studied, making the process, long, laborious and not systematically robust. In this paper a pruning process is proposed. This method allows, during the training phase, to carry out an inputs selecting method activating (or not) inter-nodes connections in order to verify if forecasting is improved. We propose to use iteratively the popular damped least-squares method to activate inputs and neurons. A first pass is applied to 10% of the learning sample to determine weights significantly different from 0 and delete other. Then a classical batch process based on LMA is used with the new MLP. The validation is done using 25 measured meteorological TS and cross-comparing the prediction results of the classical LMA and the 2-stage LMA.
Stojnic, Mihailo
2013-01-01
Perceptrons have been known for a long time as a promising tool within the neural networks theory. The analytical treatment for a special class of perceptrons started in seminal work of Gardner \\cite{Gar88}. Techniques initially employed to characterize perceptrons relied on a statistical mechanics approach. Many of such predictions obtained in \\cite{Gar88} (and in a follow-up \\cite{GarDer88}) were later on established rigorously as mathematical facts (see, e.g. \\cite{Sch...
Schottky, B
1997-01-01
We extend our study of phase transitions in the generalization behaviour of multilayer perceptrons with non-overlapping receptive fields to the problem of the influence of noise, concerning e.g. the input units and/or the couplings between the input units and the hidden units of the second layer (='input noise'), or the final output unit (='output noise'). Without output noise, the output itself is given by a general, permutation-invariant Boolean function of the outputs of the hidden units. As a result we find that the phase transitions, which we found in the deterministic case, mostly persist in the presence of noise. The influence of the noise on the position of the phase transition, as well as on the behaviour in other regimes of the loading parameter $\\alpha$, can often be described by a simple rescaling of $\\alpha$ depending on strength and type of the noise. We then consider the problem of the optimal noise level for Gibbsian and Bayesian learning, looking on replica symmetry breaking as well. Finally ...
Leaf Recognition Algorithm Using MLP Neural Network Based Image Processing
Ekshinge Sandip Sambhaji*1,; Mr. D.B Andore2
2014-01-01
In this paper, we employ Multilayer Perceptron with image and data processing techniques and neuralIn this paper, we employ Multilayer Perceptron with image and data processing techniques and neuralIn this paper, we employ Multilayer Perceptron with image and data processing techniques and neuralnetwork to implement a general purpose automated leaf recognition. Sampling leaves and photoing them are low cost and convenient. One can easily transfer the leaf image to a computer and a computer ca...
Multilayer neural networks a generalized net perspective
Krawczak, Maciej
2013-01-01
The primary purpose of this book is to show that a multilayer neural network can be considered as a multistage system, and then that the learning of this class of neural networks can be treated as a special sort of the optimal control problem. In this way, the optimal control problem methodology, like dynamic programming, with modifications, can yield a new class of learning algorithms for multilayer neural networks. Another purpose of this book is to show that the generalized net theory can be successfully used as a new description of multilayer neural networks. Several generalized net descriptions of neural networks functioning processes are considered, namely: the simulation process of networks, a system of neural networks and the learning algorithms developed in this book. The generalized net approach to modelling of real systems may be used successfully for the description of a variety of technological and intellectual problems, it can be used not only for representing the parallel functioning of homogen...
Autonomous Perceptron Neural Network Inspired from Quantum computing
Zidan, M.; Sagheer, A.; Metwally, N.
2015-01-01
Recently with the rapid development of technology, there are a lot of applications require to achieve low-cost learning in order to accomplish inexpensive computation. However the known computational power of classical artificial neural networks (CANN), they are not capable to provide low-cost learning due to many reasons such as linearity, complexity of architecture, etc. In contrast, quantum neural networks (QNN) may be representing a good computational alternate to CANN, ...
Directory of Open Access Journals (Sweden)
Kuzmin Alexey Konstantinovich
2011-02-01
Full Text Available The algorithm of development of full set of tests for debugging of neural network expert systems based on threelayer perceptron is considered. The algo-rithm is based on rules extraction from neural network and using of the method of technical diagnostics PODEM. The use of algorithm for testing of expert sys-tem Glaukoma Complaint for prognosis of compliance of ophthalmologic patients is described.
Multi-Layer and Recursive Neural Networks for Metagenomic Classification.
Ditzler, Gregory; Polikar, Robi; Rosen, Gail
2015-09-01
Recent advances in machine learning, specifically in deep learning with neural networks, has made a profound impact on fields such as natural language processing, image classification, and language modeling; however, feasibility and potential benefits of the approaches to metagenomic data analysis has been largely under-explored. Deep learning exploits many layers of learning nonlinear feature representations, typically in an unsupervised fashion, and recent results have shown outstanding generalization performance on previously unseen data. Furthermore, some deep learning methods can also represent the structure in a data set. Consequently, deep learning and neural networks may prove to be an appropriate approach for metagenomic data. To determine whether such approaches are indeed appropriate for metagenomics, we experiment with two deep learning methods: i) a deep belief network, and ii) a recursive neural network, the latter of which provides a tree representing the structure of the data. We compare these approaches to the standard multi-layer perceptron, which has been well-established in the machine learning community as a powerful prediction algorithm, though its presence is largely missing in metagenomics literature. We find that traditional neural networks can be quite powerful classifiers on metagenomic data compared to baseline methods, such as random forests. On the other hand, while the deep learning approaches did not result in improvements to the classification accuracy, they do provide the ability to learn hierarchical representations of a data set that standard classification methods do not allow. Our goal in this effort is not to determine the best algorithm in terms accuracy-as that depends on the specific application-but rather to highlight the benefits and drawbacks of each of the approach we discuss and provide insight on how they can be improved for predictive metagenomic analysis. PMID:26316190
Cebrian, Manuel
2007-01-01
The random initialization of weights of a multilayer perceptron makes it possible to model its training process as a Las Vegas algorithm, i.e. a randomized algorithm which stops when some required training error is obtained, and whose execution time is a random variable. This modelling is used to perform a case study on a well-known pattern recognition benchmark: the UCI Thyroid Disease Database. Empirical evidence is presented of the training time probability distribution exhibiting a heavy tail behavior, meaning a big probability mass of long executions. This fact is exploited to reduce the training time cost by applying two simple restart strategies. The first assumes full knowledge of the distribution yielding a 40% cut down in expected time with respect to the training without restarts. The second, assumes null knowledge, yielding a reduction ranging from 9% to 23%.
Evolutionary Feature Selection for Spiking Neural Network Pattern Classifiers
Valko, Michal; Cavalheiro, Nuno; Castelani, Marco
2005-01-01
This paper presents an application of the biologically realistic JASTAP neural network model to classification tasks. The JASTAP neural network model is presented as an alternative to the basic multi-layer perceptron model. An evolutionary procedure previously applied to the simultaneous solution of feature selection and neural network training on standard multi-layer perceptrons is extended with JASTAP model. Preliminary results on IRIS standard data set give evidence that this extension all...
Gardner, J. W.; Craven, M.; Dow, C.; Hines, E. L.
1998-01-01
An investigation into the use of an electronic nose to predict the class and growth phase of two potentially pathogenic micro-organisms, Eschericha coli ( E. coli) and Staphylococcus aureus ( S. aureus), has been performed. In order to do this we have developed an automated system to sample, with a high degree of reproducibility, the head space of bacterial cultures grown in a standard nutrient medium. Head spaces have been examined by using an array of six different metal oxide semiconducting gas sensors and classified by a multi-layer perceptron (MLP) with a back-propagation (BP) learning algorithm. The performance of 36 different pre-processing algorithms has been studied on the basis of nine different sensor parameters and four different normalization techniques. The best MLP was found to classify successfully 100% of the unknown S. aureus samples and 92% of the unknown E. coli samples, on the basis of a set of 360 training vectors and 360 test vectors taken from the lag, log and stationary growth phases. The real growth phase of the bacteria was determined from optical cell counts and was predicted from the head space samples with an accuracy of 81%. We conclude that these results show considerable promise in that the correct prediction of the type and growth phase of pathogenic bacteria may help both in the more rapid treatment of bacterial infections and in the more efficient testing of new anti-biotic drugs.
Tfwala, Samkele S.; Yu-Min Wang; Yu-Chieh Lin
2013-01-01
Hydrological data are often missing due to natural disasters, improper operation, limited equipment life, and other factors, which limit hydrological analysis. Therefore, missing data recovery is an essential process in hydrology. This paper investigates the accuracy of artificial neural networks (ANN) in estimating missing flow records. The purpose is to develop and apply neural networks models to estimate missing flow records in a station when data from adjacent stations is available. Multi...
Berrar, Daniel; Dubitzky, Werner
2006-01-01
This paper presents a novel type of artificial neural network, called neural plasma, which is tailored for classification tasks involving few observations with a large number of variables. Neural plasma learns to adapt its classification confidence by generating artificial training data as a function of its confidence in previous decisions. In contrast to multilayer perceptrons and similar techniques, which are inspired by topological and operational aspects of biological neural networks, neu...
Electron/pion identification in the CBM TRD using a multilayer perceptron
International Nuclear Information System (INIS)
The problem of electron/pion identification in the CBM experiment based on the measurements of energy losses and transition radiation in the TRD detector is discussed. A possibility to solve such a problem by applying an artificial neural network (ANN) is considered. As input information for the network we used both the samples of energy losses of pions or electrons in the TRD absorbers and the 'clever' variable obtained on the basis of the original data. We show that usage of this new variable permits one to reach a reliable level of particle recognition no longer than after 10-20 training epochs; there are practically no fluctuations against the trend, and the needed level of pions suppression is obtained under the condition of a minimal loss of electrons
Advances in Artificial Neural Networks – Methodological Development and Application
Yanbo Huang
2009-01-01
Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a back...
Data assimilation: Particle filter and artificial neural networks
International Nuclear Information System (INIS)
The goal of this work is to present the performance of the Neural Network Multilayer Perceptrons trained to emulate a Particle Filter in the context of data assimilation. Techniques for data assimilation are applied for the Lorenz system, which presents a strong nonlinearity and chaotic nature. The cross validation method was used for training the network. Good results were obtained applying the multilayer perceptrons neural network.
Evolutionary Learning Algorithm for Multi-layer Morphological Neural Networks
He Chunmei
2013-01-01
Morphological Neural Network (MNN) is a novel and important neural network and it has many applications such as image processing and pattern recognition. It makes sense to research the learning algorithm of MNN and its application. A method based on genetic algorithm is presented to train and implement multi-layer morphological neural network in this study. The algorithm calculates the weights and biases of morphological neural network and the genetic algorithm automatically acquire the learn...
Schwindling Jerome
1995-01-01
This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in par...
Scientific Electronic Library Online (English)
Yuleidys, Mejías César; Ramón, Carrasco Velar; Isbel, Ochoa Izquierdo; Edel, Moreno Lemus.
2013-12-01
Full Text Available El perceptrón multicapa (PMC) figura dentro de los tipos de redes neuronales artificiales (RNA) con resultados útiles en los estudios de relación estructura-actividad. Dado que los volúmenes de datos en proyectos de Bioinformática son eventualmente grandes, se propuso evaluar algoritmos para acortar [...] el tiempo de entrenamiento de la red sin afectar su eficiencia. Se desarrolló un algoritmo para el entrenamiento local y distribuido del PMC con la posibilidad de variar las funciones de transferencias para lo cual se utilizaron el Weka y la Plataforma de Tareas Distribuidas Tarenal para distribuir el entrenamiento del perceptrón multicapa. Se demostró que en dependencia de la muestra de entrenamiento, la variación de las funciones de transferencia pueden reportar resultados mucho más eficientes que los obtenidos con la clásica función Sigmoidal, con incremento de la g-media entre el 4.5 y el 17 %. Se encontró además que en los entrenamientos distribuidos es posible alcanzar eventualmente mejores resultados que los logrados en ambiente local. Abstract in english The multilayer perceptron (PMC) ranks among the types of artificial neural networks (ANN), which has provided better results in studies of structure-activity relationship. As the data volumes in Bioinformatics' projects are eventually big, it was proposed to evaluate algorithms to shorten the traini [...] ng time of the network without affecting its efficiency. There were evaluated different tools that work with ANN and were selected Weka algorithm for extracting the network and the Platform for Distributed Task Tarenal to distribute the training of multilayer perceptron. Finally, it was developed a training algorithm for local and distributed the MLP with the possibility of varying transfer functions. It was shown that depending on the training sample, the change of transfer functions can yield results much more efficient than those obtained with the classic sigmoid function with increased g-media between 4.5 and 17 %. Moreover, it was found that with distributed training can be achieved eventually, better results than those achieved in the local environment.
The Normalized Radial Basis Function Neural Network and its Relation to the Perceptron
Grabec, I.
2007-01-01
The normalized radial basis function neural network emerges in the statistical modeling of natural laws that relate components of multivariate data. The modeling is based on the kernel estimator of the joint probability density function pertaining to given data. From this function a governing law is extracted by the conditional average estimator. The corresponding nonparametric regression represents a normalized radial basis function neural network and can be related with th...
The synaptic morphological perceptron
Myers, Daniel S.
2006-08-01
In recent years, several researchers have constructed novel neural network models based on lattice algebra. Because of computational similarities to operations in the system of image morphology, these models are often called morphological neural networks. One neural model that has been successfully applied to many pattern recognition problems is the single-layer morphological perceptron with dendritic structure (SLMP). In this model, the fundamental computations are performed at dendrites connected to the body of a single neuron. Current training algorithms for the SLMP work by enclosing the target patterns in a set of hyperboxes orthogonal to the axes of the data space. This work introduces an alternate model of the SLMP, dubbed the synaptic morphological perceptron (SMP). In this model, each dendrite has one or more synapses that receive connections from inputs. The SMP can learn any region of space determined by an arbitrary configuration of hyperplanes, and is not restricted to forming hyperboxes during training. Thus, it represents a more general form of the morphological perceptron than previous architectures.
An Automated MR Image Segmentation System Using Multi-layer Perceptron Neural Network
Amiri, S; Movahedi, M M; K Kazemi; Parsaei, H
2013-01-01
Background: Brain tissue segmentation for delineation of 3D anatomical structures from magnetic resonance (MR) images can be used for neuro-degenerative disorders, characterizing morphological differences between subjects based on volumetric analysis of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF), but only if the obtained segmentation results are correct. Due to image artifacts such as noise, low contrast and intensity non-uniformity, there are some classification errors...
Directory of Open Access Journals (Sweden)
Schwindling Jerome
2010-04-01
Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.
Building a Chaotic Proved Neural Network
Bahi, Jacques M; Salomon, Michel
2011-01-01
Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.
Building a Chaotic Proved Neural Network
Bahi, Jacques M.; Guyeux, Christophe; Salomon, Michel
2011-01-01
Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different arc...
Phase Transitions of Neural Networks
Kinzel, W
1997-01-01
The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.
Advances in Artificial Neural Networks - Methodological Development and Application
Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...
Neural-estimator for the surface emission rate of atmospheric gases
Paes, F. F.; Velho, H. F. Campos
2009-01-01
The emission rate of minority atmospheric gases is inferred by a new approach based on neural networks. The neural network applied is the multi-layer perceptron with backpropagation algorithm for learning. The identification of these surface fluxes is an inverse problem. A comparison between the new neural-inversion and regularized inverse solution id performed. The results obtained from the neural networks are significantly better. In addition, the inversion with the neural...
Directory of Open Access Journals (Sweden)
Haydeé Elena Musso
2013-01-01
Full Text Available En este trabajo se realizó un estudio estadístico de variables físico químicas asociadas al fenómeno de contaminación ambiental, en particular concentración media mensual de SO2 , medidas en la ciudad Salta Capital, Argentina, simultáneamente a concentraciones de NO2 y O3 . Las series bajo estudio presentaban comportamientos dinámicos no lineales, datos atípicos y cambios estructurales, lo que hizo imposible modelarlas con tipologías econométricas tradiciones (AR, MA, ARMA, ARIMA, entre otras. Una solución eficiente que se encontró, hace uso de la teoría de los perceptrones multicapa. Mediante el modelo estructural de series de tiempo, esta solución se presenta como un proceso matemático iterativo que permite obtener un modelado final el cual tiene una muy alta confiabilidad (95%, para realizar pronoósticos a futuro sobre el comportamiento de la variable estudiada.In this paper a statistical study of phisical-chemistry variables connected with enviroment pollution, specifically SO2 monthly average concentration, measured in Salta Capital city, Argentina, together with NO2 and O3 concentrations, was made. Time series under study shown non linear dinamic behaviour, outliers and structural changes. Due to these it was impossible to use typical econometric typologies (AR, MA, ARMA, ARIMA, among others. An effective solution which uses multistep perceptrons theory was found. By using structural time series modelling, this solution is presented by an iterative mathematical process that allows us to obtain a final model with a high confidence level (95% in order to do the forecasting step on the studied variable.
Scientific Electronic Library Online (English)
Haydeé Elena, Musso; Orlando José, Ávila Blas.
2013-01-01
Full Text Available En este trabajo se realizó un estudio estadístico de variables físico químicas asociadas al fenómeno de contaminación ambiental, en particular concentración media mensual de SO2 , medidas en la ciudad Salta Capital, Argentina, simultáneamente a concentraciones de NO2 y O3 . Las series bajo estudio p [...] resentaban comportamientos dinámicos no lineales, datos atípicos y cambios estructurales, lo que hizo imposible modelarlas con tipologías econométricas tradiciones (AR, MA, ARMA, ARIMA, entre otras). Una solución eficiente que se encontró, hace uso de la teoría de los perceptrones multicapa. Mediante el modelo estructural de series de tiempo, esta solución se presenta como un proceso matemático iterativo que permite obtener un modelado final el cual tiene una muy alta confiabilidad (95%), para realizar pronoósticos a futuro sobre el comportamiento de la variable estudiada. Abstract in english In this paper a statistical study of phisical-chemistry variables connected with enviroment pollution, specifically SO2 monthly average concentration, measured in Salta Capital city, Argentina, together with NO2 and O3 concentrations, was made. Time series under study shown non linear dinamic behavi [...] our, outliers and structural changes. Due to these it was impossible to use typical econometric typologies (AR, MA, ARMA, ARIMA, among others). An effective solution which uses multistep perceptrons theory was found. By using structural time series modelling, this solution is presented by an iterative mathematical process that allows us to obtain a final model with a high confidence level (95%) in order to do the forecasting step on the studied variable.
Scientific Electronic Library Online (English)
Carlos A., de Luna-Ortega; Miguel, Mora-González; Julio C., Martínez-Romo; Francisco J., Luna-Rosas; Jesús, Muñoz-Maciel.
Full Text Available En el presente artículo se da a conocer una alternativa algorítimica a los sistemas actuales de reconocimiento automático del habla (ASR), mediante una propuesta en la forma de realizar la caracterización de las palabras basada en una aproximación que usa la extracción de coeficientes de la codifica [...] ción de predicción lineal (LPC) y la correlación cruzada. La implementación consiste en extraer las características fonéticas mediante los coeficientes LPC, después se forman vectores de patrones de la pronunciación conformados por el promedio de los coeficientes LPC de las muestras de las palabras obteniendo un vector característico de cada pronunciación mediante la autocorrelación de las secuencias de coeficientes LPC; estos vectores se utilizan para entrenar un clasificador de tipo perceptrón multicapa (MLP). Se realizaron pruebas de desempeño previo entrenamiento con los diferentes patrones de las palabras a reconocer. Se utilizó la fonética de los dígitos del cero al nueve como vocabulario objetivo, debido a su amplia aplicación, y para estimar el desempeño de este método se utilizaron dos corpus de pronunciaciones: el corpus UPA, que contempla en su base de datos la pronuncación de la región occidente de México, y el corpus Tlatoa, que hace lo propio para la región centro de México. Las señales en ambos corpus fueron adquiridas en el lenguaje español, y a una frecuencia de muestreo de 8kHz. Los porcentajes de reconocimiento obtenidos fueron del 96.7 y 93.3% para las modalidades de mono-locutor para el corpus UPA y múltiple-locutor para el corpus Tlatoa, respectivamente. Asimismo, se realizó una comparación contra dos métodos clásicos del reconocimiento de voz y del habla, Dynamic Time Warping (DTW) y Hidden Markov Models (HMM). Abstract in english It this paper we present an algorithmic alternative to the current Automatic Speech Recognition (ASR) systems by proposing a way to characterize words based on approximations that use an extracted coefficient from Linear Predictive Coding (LPC). The method consists in extracting phonetic characteris [...] tics through the use of LPC coefficients, after which pattern vectors are formed from the LPC coefficient averages taken from the word sampling, thus creating a unique vector for each pronunciation through the auto correlation of the LPC coefficient sequences. These vectors are used to train a Multilayer Perceptron (MLP) classifier. After training performance trials were executed. The sounds from the digits zero through nine where used as a target vocabulary, given its general use, and to estimate the performance of this method two corpus where used: the UPA corpus, which in its vocabulary uses a pronunciation familiar to the western part of Mexico, and the Tlatoa corpus, who's vocabulary presents a pronunciation typical of the central region of Mexico. The signals from both corpus where sampled in the Spanish language, and at a sampling frequency of 8kHz. The recognition rate for the mono-speaker from the UPA corpus and the multiple-speaker from the Tlatoa corpus were 96.7% and 93.3% respectively. Additionally, there where comparisons done against two classic methods used for speech recognition, Dynamic Time Warping (DTW) and Hidden Markov Models (HMM).
Discrete Orthogonal Transforms and Neural Networks for Image Interpolation
Directory of Open Access Journals (Sweden)
J. Polec
1999-09-01
Full Text Available In this contribution we present transform and neural network approaches to the interpolation of images. From transform point of view, the principles from [1] are modified for 1st and 2nd order interpolation. We present several new interpolation discrete orthogonal transforms. From neural network point of view, we present interpolation possibilities of multilayer perceptrons. We use various configurations of neural networks for 1st and 2nd order interpolation. The results are compared by means of tables.
Artificial Neural Networks in Catalyst Development. Chapter 10.
Czech Academy of Sciences Publication Activity Database
Hole?a, Martin; Baerns, M.
New Jersey : John Wiley and Sons, 2003 - (Cawse, J.), s. 163-202 ISBN 0-471-20343-2 Source of funding: V - iné verejné zdroje Keywords : artificial neural networks * multilayer perceptrons * nonlinear dependency * approximation * network training * knowledge extraction Subject RIV: IN - Informatics, Computer Science
Applying Backpropagation Neural Networks to Bankruptcy Prediction
Yi-Chung Hu; Fang-Mei Tseng
2005-01-01
Bankruptcy prediction is an important classification problem for a business, and has become a major concern of managers. In this paper, two well-known backpropagation neural network models serving as data mining tools for classification problems are employed to perform bankruptcy forecasting: one is the backpropagation multi-layer perceptron, and the other is the radial basis function network. In particular, the radial basis function network can be treated as a fuzzy neural network. Through e...
International Nuclear Information System (INIS)
A nonlinear multivariable empirical model is developed for a U-tube steam generator using the recurrent multilayer perceptron network as the underlying model structure. The recurrent multilayer perceptron is a dynamic neural network, very effective in the input-output modeling of complex process systems. A dynamic gradient descent learning algorithm is used to train the recurrent multilayer perceptron, resulting in an order of magnitude improvement in convergence speed over static learning algorithms. In developing the U-tube steam generator empirical model, the effects of actuator, process,and sensor noise on the training and testing sets are investigated. Learning and prediction both appear very effective, despite the presence of training and testing set noise, respectively. The recurrent multilayer perceptron appears to learn the deterministic part of a stochastic training set, and it predicts approximately a moving average response. Extensive model validation studies indicate that the empirical model can substantially generalize (extrapolate), though online learning becomes necessary for tracking transients significantly different than the ones included in the training set and slowly varying U-tube steam generator dynamics. In view of the satisfactory modeling accuracy and the associated short development time, neural networks based empirical models in some cases appear to provide a serious alternative to first principles models. Caution, however, must be exercised because extensive on-line validation of these models is still warranted
Aphasia Classification Using Neural Networks
DEFF Research Database (Denmark)
Axer, H.; Jantzen, Jan; Berks, G.; Keyserlingk, Diedrich Graf von
2000-01-01
A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests of the Aachen Aphasia Test (AAT). First a coarse classification was achieved by using an assessment of spontaneous speech of the patient. This classifier produced correct results in 87% of the test cases. For ...
ESTIMATION OF INPUT IMPEDANCE OF MICROSTRIP PATCH ANTENNA USING FUZZY NEURAL NETWORK
VANDANA VIKAS THAKARE; PRAMOD KUMAR SINGHAL
2010-01-01
The paper presents the use of fuzzy neural network (FNN) as a fast and better technique for the determination of input impedance of coaxial feed rectangular microstrip antenna. The fuzzy parameter ensures better performance as compared to three layer multilayered perceptron feed forward back propagation artificial neural network (MLPFFBP ANN) and radial basis function artificial neural network (RBF ANN) in the determination of input impedance of the coaxial feed microstrip antenna.
ESTIMATION OF INPUT IMPEDANCE OF MICROSTRIP PATCH ANTENNA USING FUZZY NEURAL NETWORK
Directory of Open Access Journals (Sweden)
VANDANA VIKAS THAKARE
2010-10-01
Full Text Available The paper presents the use of fuzzy neural network (FNN as a fast and better technique for the determination of input impedance of coaxial feed rectangular microstrip antenna. The fuzzy parameter ensures better performance as compared to three layer multilayered perceptron feed forward back propagation artificial neural network (MLPFFBP ANN and radial basis function artificial neural network (RBF ANN in the determination of input impedance of the coaxial feed microstrip antenna.
Neural Network Revisited: Perception on Modified Poincare Map of Financial Time Series Data
Situngkir, H; Situngkir, Hokky; Surya, Yohanes
2004-01-01
Artificial Neural Network Model for prediction of time-series data is revisited on analysis of the Indonesian stock-exchange data. We introduce the use of Multi-Layer Perceptron to percept the modified Poincare-map of the given financial time-series data. The modified Poincare-map is believed to become the pattern of the data that transforms the data in time-t versus the data in time-t+1 graphically. We built the Multi-Layer Perceptron to percept and demonstrate predicting the data on specific stock-exchange in Indonesia.
The Use of Neural Network Technology to Model Swimming Performance
António José Silva; Aldo Manuel Costa; Paulo Moura Oliveira; Victor Machado Reis; José Saavedra; Jurgen Perl; Abel Rouboa; Daniel Almeida Marinho
2007-01-01
The aims of the present study were: to identify the factors which are able to explain the performance in the 200 meters individual medley and 400 meters front crawl events in young swimmers, to model the performance in those events using non-linear mathematic methods through artificial neural networks (multi-layer perceptrons) and to assess the neural network models precision to predict the performance. A sample of 138 young swimmers (65 males and 73 females) of national level was submitted t...
Methodological Issues in Building, Training, and Testing Artificial Neural Networks
Ozesmi, Stacy L.; Ozesmi, Uygar; Tan, Can Ozan
2005-01-01
We review the use of artificial neural networks, particularly the feedforward multilayer perceptron with back-propagation for training (MLP), in ecological modelling. Overtraining on data or giving vague references to how it was avoided is the major problem. Various methods can be used to determine when to stop training in artificial neural networks: 1) early stopping based on cross-validation, 2) stopping after a analyst defined error is reached or after the error levels of...
Intelligent neural network classifier for automatic testing
Bai, Baoxing; Yu, Heping
1996-10-01
This paper is concerned with an application of a multilayer feedforward neural network for the vision detection of industrial pictures, and introduces a high characteristics image processing and recognizing system which can be used for real-time testing blemishes, streaks and cracks, etc. on the inner walls of high-accuracy pipes. To take full advantage of the functions of the artificial neural network, such as the information distributed memory, large scale self-adapting parallel processing, high fault-tolerance ability, this system uses a multilayer perceptron as a regular detector to extract features of the images to be inspected and classify them.
Handwritten Digit Recognition with Binary Optical Perceptron
Saxena, Indu; Moerland, Perry; Fiesler, Emile; Pourzand, A. R.
1997-01-01
Binary weights are favored in electronic and optical hardware implementations of neural networks as they lead to improved system speeds. Optical neural networks based on fast ferroelectric liquid crystal binary level devices can benefit from the many orders of magnitudes improved liquid crystal response times. An optimized learning algorithm for all-positive perceptrons is simulated on a limited data set of hand-written digits and the resultant network implemented optically. First, gray-scale...
Forecasting Runoff with Artificial Neural Networks.
Czech Academy of Sciences Publication Activity Database
Neruda, M.; Neruda, Roman; Kudová, Petra
Paris : UNESCO, 2005 - (Maraga, F.), s. 65-69 [ERB 2004. Euromediterranean Network of Experimental and Representative Basins /10./. Turin (IT), 13.10.2004-17.10.2004] R&D Projects: GA ?R(CZ) GA201/02/0428 Institutional research plan: CEZ:AV0Z10300504 Keywords : artificial neural networks * rainfall-runoff modelling * multilayer perceptron * Radial Basis Function s (RBF) Subject RIV: BA - General Mathematics
A fast identification of insufficiency of nutrients using spectral features would be a useful instrument in farming and in other nutrient demanding agricultural systems such as those proposed for long period space missions. A Multilayer Perceptron (MLP) neural network and backpropagation algorithm w...
Vibration Based Damage Assessment of a Civil Engineering Structures using a Neural Networks
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
1994-01-01
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorith as a non-destructive damage assessment technique to locate and quantify a damage in Civil Engineering structures is investigated. Since artificial neural networks are proving to be an effective tool for pattern recognition, the basic idea is to train a neural network with simulated values of modal parameters in order to recognize the behaviour of the damaged as well as the undam...
A Comparison between Neural Networks and Wavelet Networks in Nonlinear System Identification
S. Ehsan Razavi; Hamed Khodadadi; Hossein Ahmadi-Noubari
2012-01-01
In this study, identification of a nonlinear function will be presented by neural network and wavelet network methods. Behavior of a nonlinear system can be identified by intelligent methods. Two groups of the most common and at the same time the most effective of neural networks methods are multilayer perceptron and radial basis function that will be used for nonlinear system identification. The selected structure is series - parallel method that after network training by a series of trainin...
Vibration Based Damage Assessment of a Civil Engineering Structures using a Neural Networks
Kirkegaard, Poul Henning; Rytter, A.
1994-01-01
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorith as a non-destructive damage assessment technique to locate and quantify a damage in Civil Engineering structures is investigated. Since artificial neural networks are proving to be an effective tool for pattern recognition, the basic idea is to train a neural network with simulated values of modal parameters in order to recognize the behaviour of the damaged as well as the un...
Directory of Open Access Journals (Sweden)
A. Piotrowski
2006-01-01
Full Text Available In this paper, Multi-Layer Perceptron and Radial-Basis Function Neural Networks, along with the Nearest Neighbour approach and linear regression are utilized for flash-flood forecasting in the mountainous Nysa Klodzka river catchment. It turned out that the Radial-Basis Function Neural Network is the best model for 3- and 6-h lead time prediction and the only reliable one for 9-h lead time forecasting for the largest flood used as a test case.
Artificial Neural Network Employed To Design Annular Ring Microstrip Antenna
Directory of Open Access Journals (Sweden)
Anil Kumar
2012-04-01
Full Text Available Neural network computational modules have recently gained as an unconventional and useful tool for RF and microwave modeling and design. Neural network is trained to learn the behavior of Annular Ring Microstrip Antenna’s equivalent circuit parameters. A trained neural network is used for designing fast and less error answers to the task that has to be learned. In this paper, structure of Annular Ring Microstrip Antenna (ARMSA is studied and sets of datum are collected for the training of the Multilayer Perceptron (MLP Neural Network.
Modeling of an industrial drying process by artificial neural networks
Scientific Electronic Library Online (English)
E., Assidjo; B., Yao; K., Kisselmina; D., Amané.
2008-09-01
Full Text Available A suitable method is needed to solve the nonquality problem in the grated coconut industry due to the poor control of product humidity during the process. In this study the possibility of using an artificial neural network (ANN), precisely a Multilayer Perceptron, for modeling the drying step of the [...] production of grated coconut process is highlighted. Drying must confer to the product a final moisture of 3%. Unfortunately, under industrial conditions, this moisture varies from 1.9 to 4.8 %. In order to control this parameter and consequently reduce the proportion of the product that does not meet the humidity specification, a 9-4-1 neural network architecture was established using data gathered from an industrial plant. This Multilayer Perceptron can satisfactorily model the process with less bias, ranging from -0.35 to 0.34%, and can reduce the rate of rejected products from 92% to 3% during the first cycle of drying.
Handwritten Farsi Character Recognition using Artificial Neural Network
Reza Gharoie Ahangar; Mohammad Farajpoor Ahangar
2009-01-01
Neural Networks are being used for character recognition from last many years but most of the work was confined to English character recognition. Till date, a very little work has been reported for Handwritten Farsi Character recognition. In this paper, we have made an attempt to recognize handwritten Farsi characters by using a multilayer perceptron with one hidden layer. The error backpropagation algorithm has been used to train the MLP network. In addition, an analysis ha...
AN EFFICIENT NEURAL NETWORK FOR RECOGNIZING GESTURAL HINDI DIGITS
Nidal Fawzi Shilbayeh; Mohammad Mahmmoud Alwakeel; Maisa Mohy Naser
2013-01-01
Handwritten Hindi digit recognition plays an important role in eastern Arab countries especially in the courtesy amounts of Arab bank checks, recognizing numbers in car plates, or in postal code for mail sorting. In our study, we proposed an efficient Hindi Digit Recognition System drawn by the mouse and developed using Multilayer Perceptron Neural Network (MLP) with backpropagation. The system has been designed, implemented and tested successfully. Analysis has been carried out to determine ...
Artificial Neural Network to predict mean monthly total ozone in Arosa, Switzerland
Chattopadhyay, S; Chattopadhyay, Surajit; Bandyopadhyay, Goutami
2006-01-01
Present study deals with the mean monthly total ozone time series over Arosa, Switzerland. The study period is 1932-1971. First of all, the total ozone time series has been identified as a complex system and then Artificial Neural Networks models in the form of Multilayer Perceptron with back propagation learning have been developed. The models are Single-hidden-layer and Two-hidden-layer Perceptrons with sigmoid activation function. After sequential learning with learning rate 0.9 the peak total ozone period (February-May) concentrations of mean monthly total ozone have been predicted by the two neural net models. After training and validation, both of the models are found skillful. But, Two-hidden-layer Perceptron is found to be more adroit in predicting the mean monthly total ozone concentrations over the aforesaid period.
Scientific Electronic Library Online (English)
Alejandro J., Orozco-Naranjo; Pablo A., Muñoz-Gutiérrez.
2013-12-30
Full Text Available Este artículo presenta los resultados obtenidos al desarrollar una metodología para la detección de 5 tipos de latidos cardiacos (Normal (N), Bloqueo de Rama Derecha (RBBB), Bloqueo de Rama Izquierda (LBBB), Contracción Auricular Prematura (APC) y Contracción Ventricular Prematura (PVC)) utilizando [...] la transformada por paquetes Wavelet de manera no adaptativa en la extracción de características de las señales cardiacas, empleando la función Shanon para cálculo de la entropía y adicionando una fase de identificación de nodos por cada tipo de señal cardiaca en el árbol Wavelet. La utilización de la transformada por paquetes Wavelet permite acceder a información obtenida de la descomposición tanto de baja como de alta frecuencia proporcionando un análisis más integral que el logrado con la transformada Wavelet discreta. Se evaluaron Wavelets madre de las familias Daubechies, Symlet 5 y Biortogonal inversa; que fueron resultado de una investigación previa en que se identificaron las Wavelet madre que mayor entropía presentaban con las señales cardiacas. Con la modalidad no adaptativa se reduce el costo computacional al utilizar los paquetes Wavelet, coste que representa la mayor desventaja de esta transformada, dando validez a la investigación realizada. Para la clasificación de los patrones cardiacos se emplearon las máquinas de soporte vectorial y el perceptrón multicapa. Con las máquinas de soporte vectorial empleando kernel de función de base radial, se logró un error de clasificación del 2,57 %. Abstract in english This paper presents the results obtained by developing a methodology to detect 5 types of heartbeats (Normal (N), Right bundle branch block (RBBB), Left bundle branch block (LBBB), Premature atrial contraction (APC) and Premature ventricular contraction (PVC)), using Wavelet transform packets with n [...] on-adaptative mode applied on features extraction from heartbeats. It was used the Shannon function to calculate the entropy and It was added an identification nodes stage per every type of cardiac signal in the Wavelet tree. The using of Wavelet packets transform allows the access to information which results of decomposition of low and high frecuency, giving providing a more integral analysis than achieved by the discrete Wavelet transform. Three families of mother Wavelet were evaluated on transformation: Daubechies, Symlet and Reverse Biorthogonal, which were results from a previous research in that were identified the mother Wavelet that had higher entropy with the cardiac signals. With non-adaptive mode, the computational cost is reduced when Wavelet packets are used; this cost represents the most marked disadvantage from the transform. To classify the heartbeats were used Support Vector Machines and Multilayer Perceptron. The best classification error was achieved employing Support Vector Machine and a radial basis function; it was 2.57 %.
Sankalia, Mayur G.; Mashru, Rajshree C.; Sankalia, Jolly M.; Sutariya, Vijay B.
2005-01-01
This work examines the influence of various process parameters (like sodium alginate concentration, calcium chloride concentration, and hardening time) on papain entrapped in ionotropically cross-linked alginate beads for stability improvement and site-specific delivery to the small intestine using neural network modeling. A 33 full-factorial design and feed-forward neural network with multilayer perceptron was used to investigate the effect of process variables on percentage of entrapment, t...
Dutot, A; Steiner, F; Rude, J
2008-01-01
A neural network combined to a neural classifier is used in a real time forecasting of hourly maximum ozone in the centre of France, in an urban atmosphere. This neural model is based on the MultiLayer Perceptron (MLP) structure. The inputs of the statistical network are model output statistics of the weather predictions from the French National Weather Service. With this neural classifier, the Success Index of forecasting is 78% whereas it is from 65% to 72% with the classical MLPs. During the validation phase, in the Summer of 2003, six ozone peaks above the threshold were detected. They actually were seven.
International Nuclear Information System (INIS)
In this paper, an automatic system is presented for word recognition using real Turkish word signals. This paper especially deals with combination of the feature extraction and classification from real Turkish word signals. A Discrete Wavelet Neural Network (DWNN) model is used, which consists of two layers: discrete wavelet layer and multi-layer perceptron. The discrete wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of Discrete Wavelet Transform (DWT) and wavelet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the used system is evaluated by using noisy Turkish word signals. Test results showing the effectiveness of the proposed automatic system are presented in this paper. The rate of correct recognition is about 92.5% for the sample speech signals. (author)
Scientific Electronic Library Online (English)
Eduardo O. de, Cerqueira; João C. de, Andrade; Ronei J., Poppi; Cesar, Mello.
2001-12-01
Full Text Available [...] Abstract in english Neural Networks are a set of mathematical methods and computer programs designed to simulate the information process and the knowledge acquisition of the human brain. In last years its application in chemistry is increasing significantly, due the special characteristics for model complex systems. Th [...] e basic principles of two types of neural networks, the multi-layer perceptrons and radial basis functions, are introduced, as well as, a pruning approach to architecture optimization. Two analytical applications based on near infrared spectroscopy are presented, the first one for determination of nitrogen content in wheat leaves using multi-layer perceptrons networks and second one for determination of BRIX in sugar cane juices using radial basis functions networks.
Directory of Open Access Journals (Sweden)
Eduardo O. de Cerqueira
2001-12-01
Full Text Available Neural Networks are a set of mathematical methods and computer programs designed to simulate the information process and the knowledge acquisition of the human brain. In last years its application in chemistry is increasing significantly, due the special characteristics for model complex systems. The basic principles of two types of neural networks, the multi-layer perceptrons and radial basis functions, are introduced, as well as, a pruning approach to architecture optimization. Two analytical applications based on near infrared spectroscopy are presented, the first one for determination of nitrogen content in wheat leaves using multi-layer perceptrons networks and second one for determination of BRIX in sugar cane juices using radial basis functions networks.
Design and FPGA-implementation of multilayer neural networks with on-chip learning
International Nuclear Information System (INIS)
Artificial Neural Networks (ANN) is used in many applications in the industry because of their parallel structure, high speed, and their ability to give easy solution to complicated problems. For example identifying the orange and apple in the sorting machine with neural network is easier than using image processing techniques to do the same thing. There are different software for designing, training, and testing the ANN, but in order to use the ANN in the industry, it should be implemented on hardware outside the computer. Neural networks are artificial systems inspired on the brain's cognitive behavior, which can learn tasks with some degree of complexity, such as signal processing, diagnosis, robotics, image processing, and pattern recognition. Many applications demand a high computing power and the traditional software implementation are not sufficient.This thesis presents design and FPGA implementation of Multilayer Neural Networks with On-chip learning in re-configurable hardware. Hardware implementation of neural network algorithm is very interesting due their high performance and they can easily be made parallel. The architecture proposed herein takes advantage of distinct data paths for the forward and backward propagation stages and a pipelined adaptation of the on- line backpropagation algorithm to significantly improve the performance of the learning phase. The architecture is easily scalable and able to cope with arbitrary network sizes with the same hardware. The implementation is targeted diagnosis of the Research Reactor accidents to avoid the risk of occurrence of a nuclear accident. The proposed designed circuits are implemented using Xilinx FPGA Chip XC40150xv and occupied 73% of Chip CLBs. It achieved 10.8 ?s to take decision in the forward propagation compared with current software implemented of RPS which take 24 ms. The results show that the proposed architecture leads to significant speed up comparing to high end software solutions. On-chip learning allows on line reconstruction of ANN. Re-configure ability and parallel structure of FPGA makes it possible to accomplish this task.
Scientific Electronic Library Online (English)
F., Dall Cortivo; E. S., Chalhoub; H. F., Campos Velho.
2012-12-01
Full Text Available Estimativa do perfil de concentração de clorofila, em águas naturais, a partir da radiação emergente na superfície de um corpo d'agua, com o uso de rede neural artificial do tipo Perceptron de Múltiplas Camadas. A concentração de clorofila está relacionada com os coeficientes de absorção e espalhame [...] nto via modelos bio-ópticos. O treinamento da rede é formulado como um problema de otimização, no qual a atualização das variáveis livres da rede (pesos, viés e parâmetros de cada função de ativação) é feita através do método quasi-Newton. Abstract in english In this work the average profile of chlorophyll concentration is estimated from the emitted radiation at the surface of natural waters. This is performed through the use an Artificial Neural Network of Multilayer Perceptron type to act as the inverse operator. Bio-optical models are used to correlat [...] e the chlorophyll concentration with the absorption and scattering coefficients. The network training is formulated as an optimization problem, in which the update of the free variables of network (weights, viéses and each slope of the activation functions) is performed through the quasi-Newton method.
How deals with discrete data for the reduction of simulation models using neural network
Thomas, Philippe; Thomas, André
2009-01-01
Simulation is useful for the evaluation of a Master Production/distribution Schedule (MPS). Also, the goal of this paper is the study of the design of a simulation model by reducing its complexity. According to theory of constraints, we want to build reduced models composed exclusively by bottlenecks and a neural network. Particularly a multilayer perceptron, is used. The structure of the network is determined by using a pruning procedure. This work focuses on the impact of ...
Extraction of Rules from Data using Piecewise-Linear Neural Networks.
Czech Academy of Sciences Publication Activity Database
Hole?a, Martin
Istanbul : ITU Management Science Fakulty, 2002, s. 1-8. ISBN 975-97963-0-9. [FSSCTIMIE'02. Istanbul (TR), 29.05.2002-31.05.2002] R&D Projects: GA AV ?R IAB2030007 Institutional research plan: AV0Z1030915 Keywords : knowledge extraction with artificial neural networks * Boolean rules * fuzzy rules * multilayer perceptron * piecewise-linear activation function * polyhedra and pseudopolyhedra * Lukasiewicz predicate calculus * rational McNaughton function Subject RIV: BA - General Mathematics
Ali Abroudi; Mohammad Shokouhifar; Fardad Farokhi
2013-01-01
This paper presents a hybrid approach with two phases for improving the performance of training artificial neural networks (ANNs) by selection of the most important instances for training, and then reduction the dimensionality of features. The ANNs which are applied in this paper for validation, are included Multi-Layer Perceptron (MLP) and Neuro-Fuzzy Network (NFN). In the first phase, the Modified Fast Condensed Nearest Neighbor (MFCNN) algorithm is used to construct the subset with instanc...
Use of Neural Networks for Damage Assessment in a Steel Mast
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
1995-01-01
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorithm for detecting location and size of a damage in a civil engineering structure is investigated. The structure considered is a 20 m high steel lattice mast subjected to wind excitation. The basic idea is to train a neural network with simulated patterns of the relative changes in natural frequencies and corresponding sizes and locations of damages in order to recognize the behavio...
Hossein Naderi; Mojtaba Moradpour; Mehdi Zangeneh; Farzad Khani
2012-01-01
Stock market prediction is one of the most important interesting areas of research in business. Stock markets prediction is normally assumed as tedious task since there are many factors influencing the market. The primary objective of this paper is to forecast trend closing price movement of Tehran Stock Exchange (TSE) using financial accounting ratios from year 2003 to year 2008. The proposed study of this paper uses two approaches namely Artificial Neural Networks and multi-layer perceptron...
Neural networks for modelling and control of a non-linear dynamic system
Murray-Smith, R; Neumerkel, D.; Sbarbaro-Hofer, D.
1992-01-01
The authors describe the use of neural nets to model and control a nonlinear second-order electromechanical model of a drive system with varying time constants and saturation effects. A model predictive control structure is used. This is compared with a proportional-integral (PI) controller with regard to performance and robustness against disturbances. Two feedforward network types, the multilayer perceptron and radial-basis-function nets, are used to model the system. The problems involved ...
Automatic Analysis of Radio Meteor Events Using Neural Networks
Roman, Victor ?tefan; Buiu, C?t?lin
2015-07-01
Meteor Scanning Algorithms (MESCAL) is a software application for automatic meteor detection from radio recordings, which uses self-organizing maps and feedforward multi-layered perceptrons. This paper aims to present the theoretical concepts behind this application and the main features of MESCAL, showcasing how radio recordings are handled, prepared for analysis, and used to train the aforementioned neural networks. The neural networks trained using MESCAL allow for valuable detection results, such as high correct detection rates and low false-positive rates, and at the same time offer new possibilities for improving the results.
A design philosophy for multi-layer neural networks with applications to robot control
Vadiee, Nader; Jamshidi, MO
1989-01-01
A system is proposed which receives input information from many sensors that may have diverse scaling, dimension, and data representations. The proposed system tolerates sensory information with faults. The proposed self-adaptive processing technique has great promise in integrating the techniques of artificial intelligence and neural networks in an attempt to build a more intelligent computing environment. The proposed architecture can provide a detailed decision tree based on the input information, information stored in a long-term memory, and the adapted rule-based knowledge. A mathematical model for analysis will be obtained to validate the cited hypotheses. An extensive software program will be developed to simulate a typical example of pattern recognition problem. It is shown that the proposed model displays attention, expectation, spatio-temporal, and predictory behavior which are specific to the human brain. The anticipated results of this research project are: (1) creation of a new dynamic neural network structure, and (2) applications to and comparison with conventional multi-layer neural network structures. The anticipated benefits from this research are vast. The model can be used in a neuro-computer architecture as a building block which can perform complicated, nonlinear, time-varying mapping from a multitude of input excitory classes to an output or decision environment. It can be used for coordinating different sensory inputs and past experience of a dynamic system and actuating signals. The commercial applications of this project can be the creation of a special-purpose neuro-computer hardware which can be used in spatio-temporal pattern recognitions in such areas as air defense systems, e.g., target tracking, and recognition. Potential robotics-related applications are trajectory planning, inverse dynamics computations, hierarchical control, task-oriented control, and collision avoidance.
Neural networks and statistical learning
Du, Ke-Lin
2014-01-01
Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...
A Novel Technique to Image Annotation using Neural Network
Directory of Open Access Journals (Sweden)
Pankaj Savita
2013-03-01
Full Text Available : Automatic annotation of digital pictures is a key technology for managing and retrieving images from large image collection. Traditional image semantics extraction and representation schemes were commonly divided into two categories, namely visual features and text annotations. However, visual feature scheme are difficult to extract and are often semantically inconsistent. On the other hand, the image semantics can be well represented by text annotations. It is also easier to retrieve images according to their annotations. Traditional image annotation techniques are time-consuming and requiring lots of human effort. In this paper we propose Neural Network based a novel approach to the problem of image annotation. These approaches are applied to the Image data set. Our main work is focused on the image annotation by using multilayer perceptron, which exhibits a clear-cut idea on application of multilayer perceptron with special features. MLP Algorithm helps us to discover the concealed relations between image data and annotation data, and annotate image according to such relations. By using this algorithm we can save more memory space, and in case of web applications, transferring of images and download should be fast. This paper reviews 50 image annotation systems using supervised machine learning Techniques to annotate images for image retrieval. Results obtained show that the multi layer perceptron Neural Network classifier outperforms conventional DST Technique.
Comparative study of different wavelet based neural network models for rainfall-runoff modeling
Shoaib, Muhammad; Shamseldin, Asaad Y.; Melville, Bruce W.
2014-07-01
The use of wavelet transformation in rainfall-runoff modeling has become popular because of its ability to simultaneously deal with both the spectral and the temporal information contained within time series data. The selection of an appropriate wavelet function plays a crucial role for successful implementation of the wavelet based rainfall-runoff artificial neural network models as it can lead to further enhancement in the model performance. The present study is therefore conducted to evaluate the effects of 23 mother wavelet functions on the performance of the hybrid wavelet based artificial neural network rainfall-runoff models. The hybrid Multilayer Perceptron Neural Network (MLPNN) and the Radial Basis Function Neural Network (RBFNN) models are developed in this study using both the continuous wavelet and the discrete wavelet transformation types. The performances of the 92 developed wavelet based neural network models with all the 23 mother wavelet functions are compared with the neural network models developed without wavelet transformations. It is found that among all the models tested, the discrete wavelet transform multilayer perceptron neural network (DWTMLPNN) and the discrete wavelet transform radial basis function (DWTRBFNN) models at decomposition level nine with the db8 wavelet function has the best performance. The result also shows that the pre-processing of input rainfall data by the wavelet transformation can significantly increases performance of the MLPNN and the RBFNN rainfall-runoff models.
Tomas Ayala-Silva; Beyl, Caula A.; Heath, Robert R.
2006-01-01
A fast identification of insufficiency of nutrients using spectral features would be a useful instrument in farming and in other nutrient demanding agricultural systems such as those proposed for long period space missions. A Multilayer Perceptron (MLP) neural network and backpropagation algorithm was used to differentiate between normal leaves of wheat (Triticum aestivum L.) and those deficient in nitrogen, phosphorus, (K) and (Ca) using hyperspectral data. The network consisted of three lay...
Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training.
Soudry, Daniel; Di Castro, Dotan; Gal, Asaf; Kolodny, Avinoam; Kvatinsky, Shahar
2015-10-01
Learning in multilayer neural networks (MNNs) relies on continuous updating of large matrices of synaptic weights by local rules. Such locality can be exploited for massive parallelism when implementing MNNs in hardware. However, these update rules require a multiply and accumulate operation for each synaptic weight, which is challenging to implement compactly using CMOS. In this paper, a method for performing these update operations simultaneously (incremental outer products) using memristor-based arrays is proposed. The method is based on the fact that, approximately, given a voltage pulse, the conductivity of a memristor will increment proportionally to the pulse duration multiplied by the pulse magnitude if the increment is sufficiently small. The proposed method uses a synaptic circuit composed of a small number of components per synapse: one memristor and two CMOS transistors. This circuit is expected to consume between 2% and 8% of the area and static power of previous CMOS-only hardware alternatives. Such a circuit can compactly implement hardware MNNs trainable by scalable algorithms based on online gradient descent (e.g., backpropagation). The utility and robustness of the proposed memristor-based circuit are demonstrated on standard supervised learning tasks. PMID:25594981
Directory of Open Access Journals (Sweden)
Manjula Devi Ramasamy
2014-01-01
Full Text Available Multilayer Feed Forward Neural Network (MFNN has been successfully administered architectures for solving a wide range of supervised pattern recognition tasks. The most problematic task of MFNN is training phase which consumes very long training time on very huge training datasets. An enhanced linear adaptive skipping training algorithm for MFNN called Half of Threshold (HOT is proposed in this research paper. The core idea of this study is to reduce the training time through random presentation of training input samples without affecting the network’s accuracy. The random presentation is done by partitioning the training dataset into two distinct classes, classified and misclassified class, based on the comparison result of the calculated error measure with half of threshold value. Only the input samples in the misclassified class are presented to the next epoch for training, whereas the correctly classified class is skipped linearly which dynamically reducing the number of input samples exhibited at every single epoch without affecting the network’s accuracy. Thus decreasing the size of the training dataset linearly can reduce the total training time, thereby speeding up the training process. This HOT algorithm can be implemented with any training algorithm used for supervised pattern classification and its implementation is very simple and easy. Simulation study results proved that HOT training algorithm achieves faster training than the other standard training algorithm.
Thomas, Philippe; Thomas, André
2008-01-01
Simulation is often used to evaluate the relevance of a Directing Program of Production (PDP) or to evaluate its impact on detailed sc\\'enarii of scheduling. Within this framework, we propose to reduce the complexity of a model of simulation by exploiting a multilayer perceptron. A main phase of the modeling of one system using a multilayer perceptron remains the determination of the structure of the network. We propose to compare and use various pruning algorithms in order ...
Perceptron-like computation based on biologically-inspired neurons with heterosynaptic mechanisms
Kaluza, Pablo; Urdapilleta, Eugenio
2014-10-01
Perceptrons are one of the fundamental paradigms in artificial neural networks and a key processing scheme in supervised classification tasks. However, the algorithm they provide is given in terms of unrealistically simple processing units and connections and therefore, its implementation in real neural networks is hard to be fulfilled. In this work, we present a neural circuit able to perform perceptron's computation based on realistic models of neurons and synapses. The model uses Wang-Buzsáki neurons with coupling provided by axodendritic and axoaxonic synapses (heterosynapsis). The main characteristics of the feedforward perceptron operation are conserved, which allows to combine both approaches: whereas the classical artificial system can be used to learn a particular problem, its solution can be directly implemented in this neural circuit. As a result, we propose a biologically-inspired system able to work appropriately in a wide range of frequencies and system parameters, while keeping robust to noise and error.
Extraction of Logical Rules from Data by Means of Piecewise-Linear Neural Networks.
Czech Academy of Sciences Publication Activity Database
Hole?a, Martin
Berlin : Springer, 2002 - (Lange, S.; Satoh, K.; Smith, C.), s. 193-205 ISBN 3-540-00188-3. ISSN 0302-9743. - (Lecture Notes in Computer Science.. 2534). [International Conference on Algorithm ic Learning Theory /13./, International Conference on Discovery Science /5./. Lübeck (DE), 24.11.2002-26.11.2002] R&D Projects: GA ?R GA201/00/1489; GA AV ?R IAB2030007 Institutional research plan: AV0Z1030915 Keywords : data mining * knowledge discovery * artificial neural networks * multilayer perceptrons * rule extraction * piecewise-linear neural networks Subject RIV: BA - General Mathematics
Using neural networks for prediction of nuclear parameters
Energy Technology Data Exchange (ETDEWEB)
Pereira Filho, Leonidas; Souto, Kelling Cabral, E-mail: leonidasmilenium@hotmail.com, E-mail: kcsouto@bol.com.br [Instituto Federal de Educacao, Ciencia e Tecnologia do Rio de Janeiro (IFRJ), Rio de Janeiro, RJ (Brazil); Machado, Marcelo Dornellas, E-mail: dornemd@eletronuclear.gov.br [Eletrobras Termonuclear S.A. (GCN.T/ELETRONUCLEAR), Rio de Janeiro, RJ (Brazil). Gerencia de Combustivel Nuclear
2013-07-01
Dating from 1943, the earliest work on artificial neural networks (ANN), when Warren Mc Cullock and Walter Pitts developed a study on the behavior of the biological neuron, with the goal of creating a mathematical model. Some other work was done until after the 80 witnessed an explosion of interest in ANNs, mainly due to advances in technology, especially microelectronics. Because ANNs are able to solve many problems such as approximation, classification, categorization, prediction and others, they have numerous applications in various areas, including nuclear. Nodal method is adopted as a tool for analyzing core parameters such as boron concentration and pin power peaks for pressurized water reactors. However, this method is extremely slow when it is necessary to perform various core evaluations, for example core reloading optimization. To overcome this difficulty, in this paper a model of Multi-layer Perceptron (MLP) artificial neural network type backpropagation will be trained to predict these values. The main objective of this work is the development of Multi-layer Perceptron (MLP) artificial neural network capable to predict, in very short time, with good accuracy, two important parameters used in the core reloading problem - Boron Concentration and Power Peaking Factor. For the training of the neural networks are provided loading patterns and nuclear data used in cycle 19 of Angra 1 nuclear power plant. Three models of networks are constructed using the same input data and providing the following outputs: 1- Boron Concentration and Power Peaking Factor, 2 - Boron Concentration and 3 - Power Peaking Factor. (author)
Empirical modeling of nuclear power plants using neural networks
International Nuclear Information System (INIS)
A summary of a procedure for nonlinear identification of process dynamics encountered in nuclear power plant components is presented in this paper using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the nonlinear structure for system identification. In the overall identification process, the feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of time-dependent system nonlinearities. The standard backpropagation learning algorithm is modified and is used to train the proposed hybrid network in a supervised manner. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The nonlinear response of a representative steam generator is predicted using a neural network and is compared to the response obtained from a sophisticated physical model during both high- and low-power operation. The transient responses compare well, though further research is warranted for training and testing of recurrent neural networks during more severe operational transients and accident scenarios
Advances in Artificial Neural Networks – Methodological Development and Application
Directory of Open Access Journals (Sweden)
Yanbo Huang
2009-08-01
Full Text Available Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a backpropagation training algorithm, have gained recognition in research and applications in various scientific and engineering areas. In order to accelerate the training process and overcome data over-fitting, research has been conducted to improve the backpropagation algorithm. Further, artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis, to enhance the ability of data interpretation and modeling and to avoid subjectivity in the operation of the training algorithm. In recent years, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers in parallel with artificial neural networks. A review on development history of artificial neural networks is presented and the standard architectures and algorithms of artificial neural networks are described. Furthermore, advanced artificial neural networks will be introduced with support vector machines, and limitations of ANNs will be identified. The future of artificial neural network development in tandem with support vector machines will be discussed in conjunction with further applications to food science and engineering, soil and water relationship for crop management, and decision support for precision agriculture. Along with the network structures and training algorithms, the applications of artificial neural networks will be reviewed as well, especially in the fields of agricultural and biological engineering.
APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION
Energy Technology Data Exchange (ETDEWEB)
Musson, John C. [JLAB; Seaton, Chad [JLAB; Spata, Mike F. [JLAB; Yan, Jianxun [JLAB
2012-11-01
Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an ?activation layer,? is responsible for the removal of saturation effects. Implementation of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.
Aphasia Classification Using Neural Networks
DEFF Research Database (Denmark)
Axer, H.; Jantzen, Jan
2000-01-01
A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests of the Aachen Aphasia Test (AAT). First a coarse classification was achieved by using an assessment of spontaneous speech of the patient. This classifier produced correct results in 87% of the test cases. For a second test, data analysis tools were used to select four features out of the 30 available test features to yield a more accurate diagnosis. This second classifier produced correct results in 92% of the test cases. This test requires four AAT scores as input for the multilayer perceptron. In practice, the second test requires hours of work on behalf of the clinician, whereas the first test can be done in about half an hour in a free interview. The results of the classifiers were analyzed regarding their accuracy dependent on the diagnosis.
Intelligent Handwritten Digit Recognition using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Saeed AL-Mansoori
2015-05-01
Full Text Available The aim of this paper is to implement a Multilayer Perceptron (MLP Neural Network to recognize and predict handwritten digits from 0 to 9. A dataset of 5000 samples were obtained from MNIST. The dataset was trained using gradient descent back-propagation algorithm and further tested using the feed-forward algorithm. The system performance is observed by varying the number of hidden units and the number of iterations. The performance was thereafter compared to obtain the network with the optimal parameters. The proposed system predicts the handwritten digits with an overall accuracy of 99.32%.
Non-linear survival analysis using neural networks
Ripley, RM; Harris, AL; Tarassenko, L.
2004-01-01
We describe models for survival analysis which are based on a multi-layer perceptron, a type of neural network. These relax the assumptions of the traditional regression models, while including them as particular cases. They allow non-linear predictors to be fitted implicitly and the effect of the covariates to vary over time. The flexibility is included in the model only when it is beneficial, as judged by cross-validation. Such models can be used to guide a search for extra regressors, by c...
Terrain Mapping and Classification in Outdoor Environments Using Neural Networks
Directory of Open Access Journals (Sweden)
Alberto Yukinobu Hata
2009-12-01
Full Text Available This paper describes a three-dimensional terrain mapping and classification technique to allow the operation of mobile robots in outdoor environments using laser range finders. We propose the use of a multi-layer perceptron neural network to classify the terrain into navigable, partially navigable, and non-navigable. The maps generated by our approach can be used for path planning, navigation, and local obstacle avoidance. Experimental tests using an outdoor robot and a laser sensor demonstrate the accuracy of the presented methods.
Energy Technology Data Exchange (ETDEWEB)
Furini, M.A.; Araujo, P.B. de; Pereira, A.L.S. [Universidade Estadual Paulista (FEIS/UNESP), Ilha Solteira, SP (Brazil). Fac. de Engenharia. Dept. Engenharia Eletrica], Emails: mafurini@aluno.feis.unesp.br, percival@dee.feis.unesp.br, andspa@gmail.com
2009-07-01
This paper aims at analyzing the main operation and design of operationally robust controllers in order to damp the electromechanics oscillations type inter area. For this we used an intelligent control technique based on artificial neural networks, where a multilayer perceptron it was implemented. We used a symmetrical test system of four generators, ten bars and nine transmission lines to verify the performance of the power system stabilizers and power oscillation damping (POD) for the FACTS devices, unified power flow controller (UPFC), designed for neural networks. The results show the superiority in the operation and control of oscillations in power systems using UPFC equipped with the POD.
International Nuclear Information System (INIS)
This paper shows that the artificial neural networks techniques could be used in PWR power plant, specially to automatically perform the control rods calibration periodic test and to predict the evolutions of the axial power distribution. In the first case we use an ordinary multilayer perceptron (MLP) and in the second case we use a time delay neural network (TDNN). In these two cases, the objectives are fulfilled (tests on a power plant model). On these basis we propose some perspectives of development; for example: the realization of a real time mock-up of the first application for tests in operational conditions. (author)
Energy Technology Data Exchange (ETDEWEB)
Bordieu, Ch.; Rebiere, D. [Bordeaux-1 Univ., Lab. IXL, UMR CNRS 5818, 33 (France); Pistre, J.; Planata, R. [Centre d' Etudes du Bouchet, 91 - Vert-le-Petit (France)
1999-07-01
The association of artificial neural networks (multilayer perceptrons) with a real time pattern recognition technique (shifting windows) allowed the development of systems for the detection and the quantification of gases. Shifting window technique is presented and offers an interesting way to improve the detection response time. The partial detector characterization with regard to its parameters was realized. Applications dealing with the detection of gas compounds using surface acoustic sensors permit to show the shifting window technique feasibility. (author)
Artificial neural network application for predicting soil distribution coefficient of nickel
International Nuclear Information System (INIS)
The distribution (or partition) coefficient (Kd) is an applicable parameter for modeling contaminant and radionuclide transport as well as risk analysis. Selection of this parameter may cause significant error in predicting the impacts of contaminant migration or site-remediation options. In this regards, various models were presented to predict Kd values for different contaminants specially heavy metals and radionuclides. In this study, artificial neural network (ANN) is used to present simplified model for predicting Kd of nickel. The main objective is to develop a more accurate model with a minimal number of parameters, which can be determined experimentally or select by review of different studies. In addition, the effects of training as well as the type of the network are considered. The Kd values of Ni is strongly dependent on pH of the soil and mathematical relationships were presented between pH and Kd of nickel recently. In this study, the same database of these presented models was used to verify that neural network may be more useful tools for predicting of Kd. Two different types of ANN, multilayer perceptron and redial basis function, were used to investigate the effect of the network geometry on the results. In addition, each network was trained by 80 and 90% of the data and tested for 20 and 10% of the rest data. Then the results of the networks compared with the results of the mathematical models. Although the networks trained by 80 and 90% of the data the results show that all the networks predict with higher accuracy relative to mathematical models which were derived by 100% of data. More training of a network increases the accuracy of the network. Multilayer perceptron network used in this study predicts better than redial basis function network. - Highlights: ? Simplified models for predicting Kd of nickel presented using artificial neural networks. ? Multilayer perceptron and redial basis function used to predict Kd of nickel in soil. ? The neural networks predict with higher accuracy relative to mathematical models.
Radial basis function neural network for power system load-flow
International Nuclear Information System (INIS)
This paper presents a method for solving the load-flow problem of the electric power systems using radial basis function (RBF) neural network with a fast hybrid training method. The main idea is that some operating conditions (values) are needed to solve the set of non-linear algebraic equations of load-flow by employing an iterative numerical technique. Therefore, we may view the outputs of a load-flow program as functions of the operating conditions. Indeed, we are faced with a function approximation problem and this can be done by an RBF neural network. The proposed approach has been successfully applied to the 10-machine and 39-bus New England test system. In addition, this method has been compared with that of a multi-layer perceptron (MLP) neural network model. The simulation results show that the RBF neural network is a simpler method to implement and requires less training time to converge than the MLP neural network. (author)
Hierarchical Neural Network Structures for Phoneme Recognition
Vasquez, Daniel; Minker, Wolfgang
2013-01-01
In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach.
Approximation of Functions by Perceptron Networks with Bounded Number of Hidden Units.
Czech Academy of Sciences Publication Activity Database
K?rková, V?ra
1995-01-01
Ro?. 8, ?. 5 (1995), s. 745-750. ISSN 0893-6080 R&D Projects: GA ?R GA201/93/0427; GA AV ?R IA23057 Keywords : approximation of function s * one-hidden-layer neural network * heaviside perceptrons * radial - basis - function units * bounded number of hidden units Impact factor: 1.262, year: 1995
Neural networks for predicting breeding values and genetic gains
Scientific Electronic Library Online (English)
Gabi Nunes, Silva; Rafael Simões, Tomaz; Isabela de Castro, Sant' Anna; Moysés, Nascimento; Leonardo Lopes, Bhering; Cosme Damião, Cruz.
2014-12-01
Full Text Available Analysis using Artificial Neural Networks has been described as an approach in the decision-making process that, although incipient, has been reported as presenting high potential for use in animal and plant breeding. In this study, we introduce the procedure of using the expanded data set for train [...] ing the network. Wealso proposed using statistical parameters to estimate the breeding value of genotypes in simulated scenarios, in addition to the mean phenotypic value in a feed-forward back propagation multilayer perceptron network. After evaluating artificial neural network configurations, our results showed its superiority to estimates based on linear models, as well as its applicability in the genetic value prediction process. The results further indicated the good generalization performance of the neural network model in several additional validation experiments.
Limitations of One-Hidden-Layer Perceptron Networks.
Czech Academy of Sciences Publication Activity Database
K?rková, V?ra
Aachen & Charleston : Technical University & CreateSpace Independent Publishing Platform, 2015 - (Yaghob, J.), s. 167-171 ISBN 978-1515120650. ISSN 1613-0073. - (CEUR Workshop Proceedings. V-1422). [ITAT 2015. Conference on Theory and Practice of Information Technologies /15./. Slovenský Raj (SK), 17.09.2015-21.09.2015] R&D Projects: GA MŠk(CZ) LD13002 Institutional support: RVO:67985807 Keywords : perceptron networks * model complexity * representations of finite mappings by neural networks Subject RIV: IN - Informatics, Computer Science
STAND-LEVEL PROGNOSIS OF EUCALYPTUS CLONES USING ARTIFICIAL NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
Mayra Luiza Marques da Silva Binoti
2015-03-01
Full Text Available The objective of this study was to train, implement and evaluate the efficiency of artificial neural networks (ANN to perform production prognosis of even-aged stands of eucalyptus clones. The data used were from plantations located in southern Bahia, totaling about 2,000 acres of forest. Numeric variables, such as age, basal area, volume and categorical variables, such as soil class texture, spacing, land relief, project and clone were used. The data were randomly divided into two groups: training (80% and generalization (20%. Three types of networks were trained: perceptron, multilayer perceptron networks and radial basis function. The RNA that showed the best performance in training and generalization were selected to perform the prognosis with data from the first forest inventory. We conclude that the RNA had satisfactory results, showing the potential and applicability of the technique in solving measurement and forest management problems.
Neural networks: a biased overview
International Nuclear Information System (INIS)
An overview of recent activity in the field of neural networks is presented. The long-range aim of this research is to understand how the brain works. First some of the problems are stated and terminology defined; then an attempt is made to explain why physicists are drawn to the field, and their main potential contribution. In particular, in recent years some interesting models have been introduced by physicists. A small subset of these models is described, with particular emphasis on those that are analytically soluble. Finally a brief review of the history and recent developments of single- and multilayer perceptrons is given, bringing the situation up to date regarding the central immediate problem of the field: search for a learning algorithm that has an associated convergence theorem
How to Improve the Generalization Ability of Multi-layer Neural Networks.
Czech Academy of Sciences Publication Activity Database
Šebesta, Václav
Vol. 6. Orlando : IIIS, 2002 - (Callaos, N.; Pisarchik, A.; Ueda, M.), s. 108-113 ISBN 980-07-8150-1. [ISAS SCI 2002. World Multiconference on Systemics, Cybernetics and Informatics /6./. Orlando (US), 14.07.2002-18.07.2002] R&D Projects: GA AV ?R IAA2030801; GA ?R GA102/02/0124 Institutional research plan: AV0Z1030915 Keywords : neural networks topology * neural networks learning * generalization ability * prediction * classification * data mining Subject RIV: BA - General Mathematics
A Novel Approach to Speech Recognition by Using Generalized Regression Neural Networks
Directory of Open Access Journals (Sweden)
Lakshmi Kanaka Venkateswarlu Revada
2011-03-01
Full Text Available Speech recognition has been a subject of active research in the last few decades. In this paper, the applicability of a special model of Generalized Regression Neural Networks as a classifier is studied. A Generalized Regression Neural Network (GRNN is often used for function approximation. It has a radial basis layer and a special linear layer. This network uses a competitive function for computing final result. The proposed network has been tested on one digit numbers dataset and produced significantly lower recognition error rate in comparison with common pattern classifiers. All of classifiers use Linear Predictive Cepstral Coefficients and Mel - Frequency Cepstral Coefficients. Results for proposed network shows that LPCC features yield better performance when compared to MFCC. It is found that the performance of Generalized Regression Neural Networks is superior to the other classifiers namely Linear and Multilayer Perceptron Neural Networks.
Neural networks in front-end processing and control
International Nuclear Information System (INIS)
Research into neural networks has gained a large following in recent years. In spite of the long term timescale of this Artificial Intelligence research, the tools which the community is developing can already find useful applications to real practical problems in experimental research. One of the main advantages of the parallel algorithms being developed in AI is the structural simplicity of the required hardware implementation, and the simple nature of the calculations involved. This makes these techniques ideal for problems in which both speed and data volume reduction are important, the case for most front-end processing tasks. In this paper we illustrate the use of a particular neural network known as the Multi-Layer Perceptron as a method for solving several different tasks, all drawn from the field of Tokamak research. We also briefly discuss the use of the Multi-Layer Perceptron as a non-linear controller in a feedback loop. We outline the type of problem which can be usefully addressed by these techniques, even before the large-scale parallel processing hardware currently under development becomes cheaply available. We also present some of the difficulties encountered in applying these networks. (author) 13 figs., 9 refs
A Study on Modeling of MIMO Channel by Using Different Neural Network Structures
Directory of Open Access Journals (Sweden)
N. Prabhakar
2012-11-01
Full Text Available Recognition of Radio Channel (channelParameters is one of Main Challenges in SignalTransformation, and has important role in cognitive radioapproach. Goal of this paper is “Channel modeling” to estimatecoefficients of transmission functions affected on data beingtransformed in the channel. We use Multilayer perceptron(MLPNeural Network with Back-propagation learning algorithm,block-structured Neural Network with Least Squares(LSmethod(cost function and a multilayer neural network withmultiple back-propagation(MBP learning algorithm for errorestimation. These networks will be trained with received signalsto be compatible with channel, then give us an estimation of thesecoefficients. Simulation will show that this MBP method is betterthan the other two method in error estimation. It has goodperformance and also consume less execution time. Then, we willuse this network for estimating coefficients of non-lineartransmission functions of actual radio channel.
Directory of Open Access Journals (Sweden)
Hossein Naderi
2012-08-01
Full Text Available Stock market prediction is one of the most important interesting areas of research in business. Stock markets prediction is normally assumed as tedious task since there are many factors influencing the market. The primary objective of this paper is to forecast trend closing price movement of Tehran Stock Exchange (TSE using financial accounting ratios from year 2003 to year 2008. The proposed study of this paper uses two approaches namely Artificial Neural Networks and multi-layer perceptron. Independent variables are accounting ratios and dependent variable of stock price , so the latter was gathered for the industry of Motor Vehicles and Auto Parts. The results of this study show that neural networks models are useful tools in forecasting stock price movements in emerging markets but multi-layer perception provides better results in term of lowering error terms.
EEG signal classification based on artificial neural networks and amplitude spectra features
Chojnowski, K.; FrÄ czek, J.
BCI (called Brain-Computer Interface) is an interface that allows direct communication between human brain and an external device. It bases on EEG signal collection, processing and classification. In this paper a complete BCI system is presented which classifies EEG signal using artificial neural networks. For this purpose we used a multi-layered perceptron architecture trained with the RProp algorithm. Furthermore a simple multi-threaded method for automatic network structure optimizing was shown. We presented the results of our system in the opening and closing eyes recognition task. We also showed how our system could be used for controlling devices basing on imaginary hand movements.
A neural method for determining electromagnetic shower positions in laterally segmented calorimeters
International Nuclear Information System (INIS)
A method based on a neural network technique is proposed to calculate the coordinates of an incident photon striking a laterally segmented calorimeter and depositing shower energies in different segments. The technique uses a multilayer perceptron trained by back-propagation implemented through standard gradient descent followed by conjugate gradient algorithms and has been demonstrated with GEANT simulations of a BAF2 detector array. The position resolution results obtained by using this method are found to be substantially better than the first moment method with logarithmic weighting. (orig.)
Using Neural and Fuzzy Software for the Classification of ECG Signals
Saad Alshaban
2010-01-01
Two approaches to classify the ECG biomedical signals are presented in this work. One is theArtificial Neural Network (ANN) with multilayer perceptron and the other is the Fuzzy Logic with FuzzyKnowledge Base Controller (FKBC). Backpropagation Learning Algorithm (BPA) has been used at preset totrain the ANN. MATLAB version 6.5 program was used. The ECG signals were classified to eleven groups,one of them is for the normal cases and the others represent ten different diseases. These ECG record...
Noise reduction technique for images using radial basis function neural networks
International Nuclear Information System (INIS)
This paper presents a NN (Neural Network) based model for reducing the noise from images. This is a RBF (Radial Basis Function) network which is used to reduce the effect of noise and blurring from the captured images. The proposed network calculates the mean MSE (Mean Square Error) and PSNR (Peak Signal to Noise Ratio) of the noisy images. The proposed network has also been successfully applied to medical images. The performance of the trained RBF network has been compared with the MLP (Multilayer Perceptron) Network and it has been demonstrated that the performance of the RBF network is better than the MLP network. (author)
International Nuclear Information System (INIS)
The artificial neural network technique was used to identify drugs and plastic explosives, from a tomography composed by a set of six neutrongraphic projections obtained in real time. Bidimensional tomographic images of samples of drugs, explosives and other materials, when digitally processed, yield the characteristic spectra of each type of material. The information contained in those spectra was then used for ANN training, the best images being obtained when the multilayer perceptron model, the back-propagation training algorithm and the Cross-validation interruption criterion were used. ANN showed to be useful in forecasting presence of drugs and explosives hitting a rate of success above 97 %. (author)
Fast non-linear extraction of plasma equilibrium parameters using a neural network mapping
International Nuclear Information System (INIS)
The shaping of non-circular plasmas requires a non-linear mapping between the measured diagnostic signals and selected equilibrium parameters. The particular configuration of Neural Network known as the multi-layer perceptron provides a powerful and general technique for formulating an arbitrary continuous non-linear multi-dimensional mapping. This technique has been successfully applied to the extraction of equilibrium parameters from measurements of single-null diverted plasmas in the DIII-D tokamak; the results are compared with a purely linear mapping. The method is promising, and hardware implementation is straightforward. (author) 15 refs., 7 figs
Energy Technology Data Exchange (ETDEWEB)
Ohlsson, M.B.O.; Roegnvaldsson, T.S.; Peterson, C.O.; Pi, H.; Soederberg, B.P.W. [Lund Univ. (Sweden). Dept. of Theoretical Physics
1994-12-31
A feed-forward artificial neural network (ANN) procedure has been devised for predicting utility loads; the resulting predictions are presented for two test problems given by ``The Great Energy Predictor Shootout-The First Building Data Analysis and Prediction Competition`` (Kreider and Haberl 1994). Key ingredients in this approach are the multilayer perceptron and a method ({delta}-test) for determining relevant inputs. These methods are briefly reviewed, together with comments on alternative schemes such as fitting to polynomials and the use of recurrent networks.
Alternative Sensor System and MLP Neural Network for Vehicle Pedal Activity Estimation
Directory of Open Access Journals (Sweden)
Ahmed M. Wefky
2010-04-01
Full Text Available It is accepted that the activity of the vehicle pedals (i.e., throttle, brake, clutch reflects the driver’s behavior, which is at least partially related to the fuel consumption and vehicle pollutant emissions. This paper presents a solution to estimate the driver activity regardless of the type, model, and year of fabrication of the vehicle. The solution is based on an alternative sensor system (regime engine, vehicle speed, frontal inclination and linear acceleration that reflects the activity of the pedals in an indirect way, to estimate that activity by means of a multilayer perceptron neural network with a single hidden layer.
Lee, I-Chi; Wu, Yu-Chieh
2014-08-27
The key factors affecting the success of neural engineering using neural stem/progenitor cells (NSPCs) are the neuron quantity, the guidance of neurite outgrowth, and the induction of neurons to form functional synapses at synaptic junctions. Herein, a biomimetic material comprising a supported lipid bilayer (SLB) with adsorbed sequential polyelectrolyte multilayer (PEM) films was fabricated to induce NSPCs to form functional neurons without the need for serum and growth factors in a short-term culture. SLBs are suitable artificial substrates for neural engineering due to their structural similarity to synaptic membranes. In addition, PEM film adsorption provides protection for the SLB as well as the ability to vary the surface properties to evaluate the effects of physical and mechanical signals on NSPC differentiation. Our results revealed that NSPCs were inducible on SLB-PEM films consisting of up to eight alternating layers. In addition, the process outgrowth length, the percentage of differentiated neurons, and the synaptic function were regulated by the number of layers and the surface charge of the outermost layer. The average process outgrowth length was greater than 500 ?m on SLB-PLL/PLGA (n = 7.5) after only 3 days of culture. Moreover, the quantity and quality of the differentiated neurons were obviously enhanced on the SLB-PEM system compared with those on the PEM-only substrates. These results suggest that the PEM films can induce NSPC adhesion and differentiation and that an SLB base may enhance neuron differentiation and trigger the formation of functional synapses. PMID:25111699
Garagnani, Max; Wennekers, Thomas; Pulvermüller, Friedemann
2009-01-01
Current cognitive theories postulate either localist representations of knowledge or fully overlapping, distributed ones. We use a connectionist model that closely replicates known anatomical properties of the cerebral cortex and neurophysiological principles to show that Hebbian learning in a multi-layer neural network leads to memory traces (cell assemblies) that are both distributed and anatomically distinct. Taking the example of word learning based on action-perception correlation, we do...
Time Series Data Mining in Rainfall Forecasting Using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Prince Gupta, S.K.Pandey
2014-01-01
Full Text Available Rainfall is very important parameter in hydrological model. Many techniques and models have been developed for rainfall time series prediction. In this study an artificial neural network (ANN based model was developed for rainfall time series forecasting. Proposed model used Multilayer perceptron (MLP network with back propagation algorithm for training. Discharge and rainfall data are took as input parameter for ANN model to predict rainfall time series. Data preprocessing and model’s sensitivity analysis were executed. Collected data is divided in three sets for optimal neural network training. The first set is the training set, used for calculate the gradient and updating the network weights and biases. The second set is the validation set. The error on the validation set is follow during the training process. The third set is test set. It is used to compare different models. Different topologies of Neural Networks were created with change in hidden layer, number of processing element and activation function. (MAE, Mean Squared error (MSE and correlation coefficient (CC are used to evaluate the model performance. On the basis of these evaluation parameter results, it is found that multilayer perceptron (MLP network predict more accurate than other traditional models.
Scientific Electronic Library Online (English)
Olívio F., Galão; Dionísio, Borsato; Jurandir P., Pinto; Jesuí V., Visentainer; Mercedes Concórdia, Carrão-Panizzi.
2011-01-01
Full Text Available Vinte variedades de soja (Glycine max), quatorze convencionais e seis variedades transgênicas (RR) foram analisadas quanto ao teor de proteína, ácido fítico, teor de óleo, fitosteróis, cinzas, minerais e ácidos graxos que foram tabelados e apresentados à rede neural do tipo perceptron de múltiplas c [...] amadas para a classificação e identificação quanto a região de plantio e quanto a variedade convencional ou transgênica. A rede neural utilizada classificou e testou corretamente 100% das amostras cultivadas por região. Para o banco de dados contendo informações sobre sojas transgênicas e convencionais foi obtido um desempenho de 94,43% no treinamento da rede, 83,30% no teste e 100% na validação. Abstract in english Twenty soybean (Glycine max) varieties, 14 conventional and 6 transgenic varieties were analyzed for protein content, phytic acid, oil content, phytosterols, ash, minerals and fatty acids. The data were tabled and presented to the multilayer perceptron neural network for classification and identific [...] ation of their planting region and whether they were a conventional or transgenic. The neural network used correctly classified and tested 100% of the samples cultivated per region. For the data bank containing information on transgenic and conventional soybean, a performance of 94.43% was obtained in the training of the neural network, 83.30% in the test and 100% in the validation.
International Nuclear Information System (INIS)
In this paper, the OTTANNO version of four -quadrant CMOS analog multiplier circuit for artificial neural networks multi layer perception operation will be proposed. The proposed multiplier can be divided into two or three parts, which will be in the input, synapse and neuron. The percentage of silicon area saving is 95% with respect to that multiplier presented in (Chible,1997). A comparison between OTANNO and OTANPS is also presented. (author)
Practical Application of Neural Networks in State Space Control
DEFF Research Database (Denmark)
Bendtsen, Jan Dimon
1999-01-01
In the present thesis we address some problems in discrete-time state space control of nonlinear dynamical systems and attempt to solve them using generic nonlinear models based on artificial neural networks. The main aim of the work is to examine how well such control algorithms perform when applied to a realistic process. The thesis therefore strives to provide a thorough treatment of two classes of neural network-based controllers, and to make a rigorous comparison between them and a classical linear controller. Thus, the thesis starts out with a short review of some relevant system theoretic notions followed by a detailed description of the topology, neuron functions and learning rules of the two types of neural networks treated in the thesis, the multilayer perceptron and the neurofuzzy networks. In both cases, a Least Squares second-order gradient method is used to train the networks, although some modifications are needed for the method to apply to the multilayer perceptron network. In connection with the multilayer perceptron networks it is also pointed out how instantaneous, sample-by-sample linearized state space models can be extracted from a trained network, thus opening up for application of linear theory at each sample instant. The case study addressed in this work is an attemporator for a high-temperature steam circuit situated in a Danish powerplant, I/S Vestkraft unit 3. The attemporator is fitted with a nonlinear and nonconstant valve, so nonlinear and adaptive control is desired to control the steam temperature tightly. A second-order nonlinear model of the attemporator based on system identification with a multilayer perceptron network is found from data collected from the actual process. It is shown to be a highly satisfying prediction and simulation model of the process. With this model in place, we turn to the control concepts. A pole placement controller based on the sample-by-sample linearizations extracted from a multilayer perceptron state observer is first derived, and it is shown how to make the control concept adaptive by continuing the training online. Then the controller is shown to work on a simulation example. We also address the potential problem of too rapidly fluctuating parameters by including regularization in the learning rule. Next we develop a direct adaptive certainty-equivalence controller based on neurofuzzy models. The control loop is proven to be stable under certain assumptions, and we address the question of how many basis functions are necessary. It is shown that basis functions with compact supports, whose supports are not entered by a system trajectory, do not need parameter updates. Therefore, a system with bounded trajectories can be controlled by a finite-dimensional model. We also introduce a modification to the algorithm which-if an upper bound on the nonlinearity growth is known-enables us to remove a sector-boundedness assumption on the nonlinearity. Finally the control concepts are applied to the nonlinear simulation model discussed above, and it is seen that the neural network -based control concepts outperform a classical linear controller.
Neural Models for the Broadside-Coupled V-Shaped Microshield Coplanar Waveguides
Guney, K.; Yildiz, C.; Kaya, S.; Turkmen, M.
2006-09-01
This article presents a new approach based on multilayered perceptron neural networks (MLPNNs) to calculate the odd-and even-mode characteristic impedances and effective permittivities of the broadside-coupled V-shaped microshield coplanar waveguides (BC-VSMCPWs). Six learning algorithms, bayesian regulation (BR), Levenberg-Marquardt (LM), quasi-Newton (QN), scaled conjugate gradient (SCG), resilient propagation (RP), and conjugate gradient of Fletcher-Powell (CGF), are used to train the MLPNNs. The neural results are in very good agreement with the results reported elsewhere. When the performances of neural models are compared with each other, the best and worst results are obtained from the MLPNNs trained by the BR and CGF algorithms, respectively.
Application of Neural Networks for unfolding neutron spectra measured by means of Bonner Spheres
International Nuclear Information System (INIS)
A Neural Network structure has been used for unfolding neutron spectra measured by means of a Bonner Sphere Spectrometer set. The present work used the 'Stuttgart Neural Network Simulator' as the interface for designing, training and validation of a MultiLayer Perceptron network. The back-propagation algorithm was applied. The Bonner Sphere set chosen has been calibrated at the National Physical Laboratory, United Kingdom, and uses gold activation foils as thermal neutron detectors. The neutron energy covered by the response functions goes from 0.0001 eV to 10 MeV. Two types of neutron spectra were numerically investigated: monoenergetic and continuous. Good results were obtained, indicating that the Neural Network can be considered an interesting alternative among the neutron spectrum unfolding methodologies
Directory of Open Access Journals (Sweden)
Therasa Chandrasekar
2015-10-01
Full Text Available This paper provides an exposition about application of neural networks in the context of research to find out the contribution of individual job satisfiers towards work commitment. The purpose of the current study is to build a predictive model to estimate the normalized importance of individual job satisfiers towards work commitment of employees working in TVS Group, an Indian automobile company. The study is based on the tool developed by Spector (1985 and Sue Hayday (2003.The input variable of the study consists of nine independent individual job satisfiers which includes Pay, Promotion, Supervision, Benefits, Rewards, Operating procedures, Co-workers, Work-itself and Communication of Spector (1985 and dependent variable as work commitment of Sue Hayday (2003.The primary data has been collected using a closed-ended questionnaire based on simple random sampling approach. This study employed the multilayer Perceptron neural network model to envisage the level of job satisfiers towards work commitment. The result from the multilayer Perceptron neural network model displayed with four hidden layer with correct classification rate of 70% and 30% for training and testing data set. The normalized importance shows high value for coworkers, superior satisfaction and communication and which acts as most significant attributes of job satisfiers that predicts the overall work commitment of employees.
Directory of Open Access Journals (Sweden)
N. Lauzon
2006-01-01
Full Text Available This work addresses the issue of better considering the heterogeneity of precipitation fields within lumped rainfall-runoff models where only areal mean precipitation is usually used as an input. A method using a Kohonen neural network is proposed for the clustering of precipitation fields. The evaluation and improvement of the performance of a lumped rainfall-runoff model for one-day ahead predictions is then established based on this clustering. Multilayer perceptron neural networks are employed as lumped rainfall-runoff models. The Bas-en-Basset watershed in France, which is equipped with 23 rain gauges with data for a 21-year period, is employed as the application case. The results demonstrate the relevance of the proposed clustering method, which produces groups of precipitation fields that are in agreement with the global climatological features affecting the region, as well as with the topographic constraints of the watershed (i.e., orography. The strengths and weaknesses of the rainfall-runoff models are highlighted by the analysis of their performance vis-à-vis the clustering of precipitation fields. The results also show the capability of multilayer perceptron neural networks to account for the heterogeneity of precipitation, even when built as lumped rainfall-runoff models.
Directory of Open Access Journals (Sweden)
N. Lauzon
2006-02-01
Full Text Available This work addresses the issue of better considering the heterogeneity of precipitation fields within lumped rainfall-runoff models where only areal mean precipitation is usually used as an input. A method using a Kohonen neural network is proposed for the classification of precipitation fields. The evaluation and improvement of the performance of a lumped rainfall-runoff model for one-day ahead predictions is then established based on this classification. Multilayer perceptron neural networks are employed as lumped rainfall-runoff models. The Bas-en-Basset watershed in France, which is equipped with 23 rain gauges with data for a 21-year period, is employed as the application case. The results demonstrate the relevance of the proposed classification method, which produces groups of precipitation fields that are in agreement with the global climatological features affecting the region, as well as with the topographic constraints of the watershed (i.e., orography. The strengths and weaknesses of the rainfall-runoff models are highlighted by the analysis of their performance vis-à-vis the classification of precipitation fields. The results also show the capability of multilayer perceptron neural networks to account for the heterogeneity of precipitation, even when built as lumped rainfall-runoff models.
International Nuclear Information System (INIS)
In multilayered Ti0.4Al0.6N/Mo coatings, a strengthening effect can be obtained by using alternate layers of materials with high and low elastic constants. This behaviour requires a multilayer periodicity below a certain value in order to reduce dislocation motion across layer interface. Below this critical period, in most cases the hardness decreases as the period decreases. The multiple interfaces have an important role on this behaviour, working as stress relaxation areas and preventing crack propagation, influencing the mechanical properties of the system. Understanding the origin of these effects requires knowledge of the interface structure, where the interfacial roughness is of prime importance. We used Rutherford backscattering to study roughness in a quantitative way, and developed an artificial neural network algorithm dedicated to the analysis of the data. The results compare very well with previous TEM and AFM data
Directory of Open Access Journals (Sweden)
Mustafa Y?ld?z
2012-08-01
Full Text Available Introduction: We aimed to develop a classification method to discriminate ventricular septal defect and atrial septal defect by using severalhemodynamic parameters.Patients and Methods: Forty three patients (30 atrial septal defect, 13 ventricular septal defect; 26 female, 17 male with documentedhemodynamic parameters via cardiac catheterization are included to study. Such parameters as blood pressure values of different areas,gender, age and Qp/Qs ratios are used for classification. Parameters, we used in classification are determined by divergence analysismethod. Those parameters are; i pulmonary artery diastolic pressure, ii Qp/Qs ratio, iii right atrium pressure, iv age, v pulmonary arterysystolic pressure, vi left ventricular sistolic pressure, vii aorta mean pressure, viii left ventricular diastolic pressure, ix aorta diastolicpressure, x aorta systolic pressure. Those parameters detected from our study population, are uploaded to multi-layered artificial neuralnetwork and the network was trained by genetic algorithm.Results: Trained cluster consists of 14 factors (7 atrial septal defect and 7 ventricular septal defect. Overall success ratio is 79.2%, andwith a proper instruction of artificial neural network this ratio increases up to 89%.Conclusion: Parameters, belonging to artificial neural network, which are needed to be detected by the investigator in classical methods,can easily be detected with the help of genetic algorithms. During the instruction of artificial neural network by genetic algorithms, boththe topology of network and factors of network can be determined. During the test stage, elements, not included in instruction cluster, areassumed as in test cluster, and as a result of this study, we observed that multi-layered artificial neural network can be instructed properly,and neural network is a successful method for aimed classification.
PREDICTION OF BOD AND COD OF A REFINERY WASTEWATER USING MULTILAYER ARTIFICIAL NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
Eldon Raj Rene
2008-06-01
Full Text Available In the recent past, artificial neural networks (ANNs have shown the ability to learn and capture non-linear static or dynamic behaviour among variables based on the given set of data. Since the knowledge of internal procedure is not necessary, the modelling can take place with minimum previous knowledge about the process through proper training of the network. In the present study, 12 ANN based models were proposed to predict the Biochemical Oxygen Demand (BOD5 and Chemical Oxygen Demand (COD concentrations of wastewater generated from the effluent treatment plant of a petrochemical industry. By employing the standard back error propagation (BEP algorithm, the network was trained with 103 data points for water quality indices such as Total Suspended Solids (TSS, Total Dissolved Solids (TDS, Phenol concentration, Ammoniacal Nitrogen (AMN, Total Organic Carbon (TOC and Kjeldahl’s Nitrogen (KJN to predict BOD and COD. After appropriate training, the network was tested with a separate test data and the best model was chosen based on the sum square error (training and percentage average relative error (% ARE for testing. The results from this study reveal that ANNs can be accurate and efficacious in predicting unknown concentrations of water quality parameters through its versatile training process.
A Novel Channel Equalizer Using Large Margin Algebraic Perceptron Network
Directory of Open Access Journals (Sweden)
Siba P. Panigrahi
2010-08-01
Full Text Available This paper proposes a novel control scheme for channel equalization for wireless communication system. The proposed scheme considers channel equalization as a classification problem. For efficient solution of the problem, this paper makes use of a neural network working on Algebraic Perceptron (AP algorithm as a classifier. Also, this paper introduces a method of performance improvement by increasing margin of AP equalizers. Novelty of the proposed scheme is evidenced by its simulation results.
A combinatorial approach to understanding perceptron capabilities.
Gibson, G J
1993-01-01
This work investigates the classification capabilities of perceptrons which incorporate a single hidden layer of nodes from a theoretical viewpoint. In particular, the question of determining whether a given set can be realized as the decision region of such a network is considered. The main theoretic result demonstrates that the realizability of a set can be determined by restricting attention to any neighborhood of its boundary. This result is then used to identify general classes of realizable sets, and an example is given which shows that even though the realizability of a set might be readily discerned, the construction of an appropriate perceptron architecture may be complicated. PMID:18276529
Aliouane, Leila; Ouadfeul, Sid-Ali; Boudella, Amar
2015-04-01
The main goal of the proposed idea is to use the artificial intelligence such as the neural network and fuzzy logic to predict the pore pressure in shale gas reservoirs. Pore pressure is a very important parameter that will be used or estimation of effective stress. This last is used to resolve well-bore stability problems, failure plan identification from Mohr-Coulomb circle and sweet spots identification. Many models have been proposed to estimate the pore pressure from well-logs data; we can cite for example the equivalent depth model, the horizontal model for undercompaction called the Eaton's model…etc. All these models require a continuous measurement of the slowness of the primary wave, some thing that is not easy during well-logs data acquisition in shale gas formtions. Here, we suggest the use the fuzzy logic and the multilayer perceptron neural network to predict the pore pressure in two horizontal wells drilled in the lower Barnett shale formation. The first horizontal well is used for the training of the fuzzy set and the multilayer perecptron, the input is the natural gamma ray, the neutron porosity, the slowness of the compression and shear wave, however the desired output is the estimated pore pressure using Eaton's model. Data of another horizontal well are used for generalization. Obtained results clearly show the power of the fuzzy logic system than the multilayer perceptron neural network machine to predict the pore pressure in shale gas reservoirs. Keywords: artificial intelligence, fuzzy logic, pore pressure, multilayer perecptron, Barnett shale.
Recursive least-squares learning algorithms for neural networks
Lewis, Paul S.; Hwang, Jenq N.
1990-11-01
This paper presents the development of a pair of recursive least squares (ItLS) algorithms for online training of multilayer perceptrons which are a class of feedforward artificial neural networks. These algorithms incorporate second order information about the training error surface in order to achieve faster learning rates than are possible using first order gradient descent algorithms such as the generalized delta rule. A least squares formulation is derived from a linearization of the training error function. Individual training pattern errors are linearized about the network parameters that were in effect when the pattern was presented. This permits the recursive solution of the least squares approximation either via conventional RLS recursions or by recursive QR decomposition-based techniques. The computational complexity of the update is 0(N2) where N is the number of network parameters. This is due to the estimation of the N x N inverse Hessian matrix. Less computationally intensive approximations of the ilLS algorithms can be easily derived by using only block diagonal elements of this matrix thereby partitioning the learning into independent sets. A simulation example is presented in which a neural network is trained to approximate a two dimensional Gaussian bump. In this example RLS training required an order of magnitude fewer iterations on average (527) than did training with the generalized delta rule (6 1 BACKGROUND Artificial neural networks (ANNs) offer an interesting and potentially useful paradigm for signal processing and pattern recognition. The majority of ANN applications employ the feed-forward multilayer perceptron (MLP) network architecture in which network parameters are " trained" by a supervised learning algorithm employing the generalized delta rule (GDIt) [1 2]. The GDR algorithm approximates a fixed step steepest descent algorithm using derivatives computed by error backpropagatiori. The GDII algorithm is sometimes referred to as the backpropagation algorithm. However in this paper we will use the term backpropagation to refer only to the process of computing error derivatives. While multilayer perceptrons provide a very powerful nonlinear modeling capability GDR training can be very slow and inefficient. In linear adaptive filtering the analog of the GDR algorithm is the leastmean- squares (LMS) algorithm. Steepest descent-based algorithms such as GDR or LMS are first order because they use only first derivative or gradient information about the training error to be minimized. To speed up the training process second order algorithms may be employed that take advantage of second derivative or Hessian matrix information. Second order information can be incorporated into MLP training in different ways. In many applications especially in the area of pattern recognition the training set is finite. In these cases block learning can be applied using standard nonlinear optimization techniques [3 4 5].
Nonlinear control structures based on embedded neural system models.
Lightbody, G; Irwin, G W
1997-01-01
This paper investigates in detail the possible application of neural networks to the modeling and adaptive control of nonlinear systems. Nonlinear neural-network-based plant modeling is first discussed, based on the approximation capabilities of the multilayer perceptron. A structure is then proposed to utilize feedforward networks within a direct model reference adaptive control strategy. The difficulties involved in training this network, embedded within the closed-loop are discussed and a novel neural-network-based sensitivity modeling approach proposed to allow for the backpropagation of errors through the plant to the neural controller. Finally, a novel nonlinear internal model control (IMC) strategy is suggested, that utilizes a nonlinear neural model of the plant to generate parameter estimates over the nonlinear operating region for an adaptive linear internal model, without the problems associated with recursive parameter identification algorithms. Unlike other neural IMC approaches the linear control law can then be readily designed. A continuous stirred tank reactor was chosen as a realistic nonlinear case study for the techniques discussed in the paper. PMID:18255659
Energy Technology Data Exchange (ETDEWEB)
ZareNezhad, B.; Aminian, A. [Semnan University, Semnan (Iran)
2010-05-15
Acidic combustion gases can cause rapid corrosion when they condense on pollution control or energy recovery equipments. Since the potential of sulfuric acid condensation from flue gases is of considerable economic significance, a multi-layer feed forward artificial neural network has been presented for accurate prediction of the flue gas sulfuric acid dew points to mitigate the corrosion problems in process and power plants. According to the network's training, validation and testing results, a three layer neural network with four neurons in the hidden layer is selected as the best architecture for accurate prediction of sulfuric acid dew points. The presented model is very accurate and reliable for predicting the acid dew points over wide ranges of sulfur trioxide and water vapor concentrations. Comparison of the suggested neural network model with the most important existing correlations shows that the proposed neuromorphic model outperforms the other alternatives both in accuracy and generality. The predicted flue gas sulfuric acid dew points are in excellent agreement with experimental data suggesting the accuracy of the proposed neural network model for predicting the sulfuric acid condensation in stacks, pollution control devices, economizers and flue gas recovery systems in process industries.
Energy Technology Data Exchange (ETDEWEB)
Guia, Jose G.C. da; Araujo, Adevid L. de [Universidade Federal de Campina Grande, PB (Brazil). Dept. de Engenharia Mecanica; Irmao, Marcos A. da Silva [Universidade Federal de Campina Grande, PB (Brazil). Dept. de Engenharia de Processos; Silva, Antonio A. [Universidade Federal de Campina Grande, PB (Brazil). Dept. de Engenharia Mecanica
2003-07-01
The condition monitoring and diagnostic of structural faults in pipelines are an important problem for the petroleum's industry, being necessary to develop supervisory systems for detection, prediction and evaluation of a fault in the pipelines to avoid environmental and financial damages. In this work, three types of Artificial Neural Networks (ANNs) are reviewed and used to detect and locate a fault in a simulated pipe. The simulated pipe was modeled through the Finite Elements Method. In Neural Networks' analysis, the first six natural frequencies of the pipe are used as networks' inputs. The used ANNs were the Multi-Layer Perceptron Network with backpropagation, the Probabilistic Neural Network and the Generalized Regression Neural Network. After the analysis, it was concluded that the ANN are a good computational tool in problems of faults detection on pipelines with a great precision. In the localization of the faults were obtained errors smaller than 5%. (author)
Prediction of slope stability using artificial neural network (case study: Noabad, Mazandaran, Iran)
International Nuclear Information System (INIS)
Investigations of failures of soil masses are subjects touching both geology and engineering. These investigations call the joint efforts of engineering geologists and geotechnical engineers. Geotechnical engineers have to pay particular attention to geology, ground water, and shear strength of soils in assessing slope stability. Artificial neural networks (ANNs) are very sophisticated modeling techniques, capable of modeling extremely complex functions. In particular, neural networks are nonlinear. In this research, with respect to the above advantages, ANN systems consisting of multilayer perceptron networks are developed to predict slope stability in a specified location, based on the available site investigation data from Noabad, Mazandaran, Iran. Several important parameters, including total stress, effective stress, angle of slope, coefficient of cohesion, internal friction angle, and horizontal coefficient of earthquake, were used as the input parameters, while the slope stability was the output parameter. The results are compared with the classical methods of limit equilibrium to check the ANN model's validity. (author)
Prediction of Force Measurements of a Microbend Sensor Based on an Artificial Neural Network
Efendioglu, Hasan S.; Yildirim, Tulay; Fidanboylu, Kemal
2009-01-01
Artificial neural network (ANN) based prediction of the response of a microbend fiber optic sensor is presented. To the best of our knowledge no similar work has been previously reported in the literature. Parallel corrugated plates with three deformation cycles, 6 mm thickness of the spacer material and 16 mm mechanical periodicity between deformations were used in the microbend sensor. Multilayer Perceptron (MLP) with different training algorithms, Radial Basis Function (RBF) network and General Regression Neural Network (GRNN) are used as ANN models in this work. All of these models can predict the sensor responses with considerable errors. RBF has the best performance with the smallest mean square error (MSE) values of training and test results. Among the MLP algorithms and GRNN the Levenberg-Marquardt algorithm has good results. These models successfully predict the sensor responses, hence ANNs can be used as useful tool in the design of more robust fiber optic sensors. PMID:22399991
Neural Network on Photodegradation of Octylphenol using Natural and Artificial UV Radiation
Directory of Open Access Journals (Sweden)
Lorentz JÄNTSCHI
2011-09-01
Full Text Available The present paper comes up with an experimental design meant to point out the factors interferingin octylphenol’s degradation in surface waters under solar radiation, underlining each factor’sinfluence on the process observable (concentration of p-octylphenol. Multiple linear regressionanalysis and artificial neural network (Multi-Layer Perceptron type were applied in order to obtaina mathematical model capable to explain the action of UV-light upon synthetic solutions of OP inultra-pure water (MilliQ type. Neural network proves to be the most efficient method in predictingthe evolution of OP concentration during photodegradation process. Thus, determination in neuralnetwork’s case has almost double value versus the regression analysis.
A Comparison between Neural Networks and Wavelet Networks in Nonlinear System Identification
Directory of Open Access Journals (Sweden)
S. Ehsan Razavi
2012-01-01
Full Text Available In this study, identification of a nonlinear function will be presented by neural network and wavelet network methods. Behavior of a nonlinear system can be identified by intelligent methods. Two groups of the most common and at the same time the most effective of neural networks methods are multilayer perceptron and radial basis function that will be used for nonlinear system identification. The selected structure is series - parallel method that after network training by a series of training random data, the output is estimated and the nonlinear function is compared to a sinusoidal input. Then, wavelet network is used for identification and we will use Orthogonal Least Squares (OLS method for wavelet selection to reduce the volume of calculations and increase the convergence speed.
Artificial neural network for modeling the extraction of aromatic hydrocarbons from lube oil cuts
Energy Technology Data Exchange (ETDEWEB)
Mehrkesh, A.H.; Hajimirzaee, S. [Islamic Azad University, Majlesi Branch, Isfahan (Iran, Islamic Republic of); Hatamipour, M.S.; Tavakoli, T. [Department of Chemical Engineering, University of Isfahan, Isfahan (Iran, Islamic Republic of)
2011-03-15
An artificial neural network (ANN) approach was used to obtain a simulation model to predict the rotating disc contactor (RDC) performance during the extraction of aromatic hydrocarbons from lube oil cuts, to produce a lubricating base oil using furfural as solvent. The field data used for training the ANN model was obtained from a lubricating oil production company. The input parameters of the ANN model were the volumetric flow rates of feed and solvent, the temperatures of feed and solvent, and the disc rotation rate. The output parameters were the volumetric flow rate of the raffinate phase and the extraction yield. In this study, a feed-forward multi-layer perceptron neural network was successfully used to demonstrate the complex relationship between the mentioned input and output parameters. (Copyright copyright 2011 WILEY-VCH Verlag GmbH and Co. KGaA, Weinheim)
Neural network model for a reactor subsystem using real time data
International Nuclear Information System (INIS)
Modern nuclear power plant is a very complex arrangement of machinery consisting of huge number of control and support systems. In real time it is possible to implement intelligent systems in the form of neural network, data mining, expert system etc. for modeling the power plant. This paper describes the development of an artificial neural network model for intermediate heat exchanger subsystem of fast breeder test reactor. Multilayer perceptron network using back propagation algorithm is implemented for training the safety critical, safety related real time data. It takes in to account the weight correction method. The results indicate a very good convergence of the algorithm. The model can be used as an operator support system for predictive measures of various parameters of the reactor subsystems. (author)
Neural network controller for Active Demand-Side Management with PV energy in the residential sector
International Nuclear Information System (INIS)
Highlights: ? We have developed a neural controller for Active Demand-Side Management. ? The controller consists of Multilayer Perceptrons evolved with a genetic algorithm. ? The architecture of the controller is distributed and modular. ? The simulations show that the electrical local behavior improves. ? Active Demand-Side Management helps users to control his energy behaviour. -- Abstract: In this paper, we describe the development of a control system for Demand-Side Management in the residential sector with Distributed Generation. The electrical system under study incorporates local PV energy generation, an electricity storage system, connection to the grid and a home automation system. The distributed control system is composed of two modules: a scheduler and a coordinator, both implemented with neural networks. The control system enhances the local energy performance, scheduling the tasks demanded by the user and maximizing the use of local generation.
DEFF Research Database (Denmark)
Farrokhzad, F.; Barari, Amin
2011-01-01
The purpose of this study was to create an empirical model for assessing the landslide risk potential at Savadkouh Azad University, which is located in the rural surroundings of Savadkouh, about 5 km from the city of Pol-Sefid in northern Iran. The soil longitudinal profile of the city of Babol, located 25 km from the Caspian Sea, also was predicted with an artificial neural network (ANN). A multilayer perceptron neural network model was applied to the landslide area and was used to analyze specific elements in the study area that contributed to previous landsliding events. The ANN models were trained with geotechnical data obtained from an investigation of the study area. The quality of the modeling was improved further by the application of some controlling techniques involved in ANN. The observed >90% overall accuracy produced by the ANN technique in both cases is promising for future studies in landslide susceptibility zonation.
Practical application of artificial neural networks in the neurosciences
Pinti, Antonio
1995-04-01
This article presents a practical application of artificial multi-layer perceptron (MLP) neural networks in neurosciences. The data that are processed are labeled data from the visual analysis of electrical signals of human sleep. The objective of this work is to automatically classify into sleep stages the electrophysiological signals recorded from electrodes placed on a sleeping patient. Two large data bases were designed by experts in order to realize this study. One data base was used to train the network and the other to test its generalization capacity. The classification results obtained with the MLP network were compared to a type K nearest neighbor Knn non-parametric classification method. The MLP network gave a better result in terms of classification than the Knn method. Both classification techniques were implemented on a transputer system. With both networks in their final configuration, the MLP network was 160 times faster than the Knn model in classifying a sleep period.
Hybrid Learning Algorithm in Neural Network System for Enzyme Classification
Directory of Open Access Journals (Sweden)
Mohd Haniff Osman
2010-07-01
Full Text Available Nucleic acid and protein sequences store a wealth of informationwhich ultimately determines their functions and characteristics.Protein sequences classification deals with the assignment ofsequences to known categories based on homology detectionproperties. In this paper, we developed a hybrid learning algorithm inneural network system called Neural Network Enzyme Classification(NNEC to classify an enzyme found in Protein Data Bank (PDB to agiven family of enzymes. NNEC was developed based on MultilayerPerceptron with hybrid learning algorithm combining the geneticalgorithm (GA and Backpropagation (BP, where one of them acts asan operator in the other. Here, BP is used as a mutation-like-operatorof the general GA search template. The proposed hybrid model wastested with different topologies of network architecture, especially indetermining the number of hidden nodes. The precision results arequite promising in classifying the enzyme accordingly.
Neural Network Aided Glitch-Burst Discrimination and Glitch Classification
Rampone, Salvatore; Troiano, Luigi; Pinto, Innocenzo M
2014-01-01
We investigate the potential of neural-network based classifiers for discriminating gravitational wave bursts (GWBs) of a given canonical family (e.g. core-collapse supernova waveforms) from typical transient instrumental artifacts (glitches), in the data of a single detector. The further classification of glitches into typical sets is explored.In order to provide a proof of concept,we use the core-collapse supernova waveform catalog produced by H. Dimmelmeier and co-Workers, and the data base of glitches observed in laser interferometer gravitational wave observatory (LIGO) data maintained by P. Saulson and co-Workers to construct datasets of (windowed) transient waveforms (glitches and bursts) in additive (Gaussian and compound-Gaussian) noise with different signal-tonoise ratios (SNR). Principal component analysis (PCA) is next implemented for reducing data dimensionality, yielding results consistent with, and extending those in the literature. Then, a multilayer perceptron is trained by a backpropagation ...
Minimization of Empirical Error over Perceptron Networks.
Czech Academy of Sciences Publication Activity Database
K?rková, V?ra
Wien : Springer-Verlag, 2005 - (Ribiero, B.; Albrecht, R.; Dobnikar, A.; Pearson, D.; Steele, N.), s. 46-49 ISBN 3-211-24934-6. [ICANNGA'2005 /7./. Coimbra (PT), 21.03.2005-23.03.2005] R&D Projects: GA ?R GA201/05/0557 Institutional research plan: CEZ:AV0Z10300504 Keywords : supervised learning * perceptron networks * approximate optimization Subject RIV: BA - General Mathematics
Landscape statistics of the binary perceptron
Fontanari, J. F.; Köberle, R.
1990-01-01
The landscape of the binary perceptron is studied by Simulated Annealing, exhaustive search and performing random walks on the landscape. We find that the number of local minima increases exponentially with the number of bonds, becoming deeper in the vicinity of a global minimum, but more and more shallow as we move away from it. The random walker detects a simple dependence on the size of the mapping, the architecture introducing a nontrivial dependence on the number of steps.
Directory of Open Access Journals (Sweden)
2009-03-01
Full Text Available An electrocardiogram (ECG beat classification scheme based on multiple signal classification (MUSIC algorithm, morphological descriptors, and neural networks is proposed for discriminating nine ECG beat types. These are normal, fusion of ventricular and normal, fusion of paced and normal, left bundle branch block, right bundle branch block, premature ventricular concentration, atrial premature contraction, paced beat, and ventricular flutter. ECG signal samples from MIT-BIH arrhythmia database are used to evaluate the scheme. MUSIC algorithm is used to calculate pseudospectrum of ECG signals. The low-frequency samples are picked to have the most valuable heartbeat information. These samples along with two morphological descriptors, which deliver the characteristics and features of all parts of the heart, form an input feature vector. This vector is used for the initial training of a classifier neural network. The neural network is designed to have nine sample outputs which constitute the nine beat types. Two neural network schemes, namely multilayered perceptron (MLP neural network and a probabilistic neural network (PNN, are employed. The experimental results achieved a promising accuracy of 99.03% for classifying the beat types using MLP neural network. In addition, our scheme recognizes NORMAL class with 100% accuracy and never misclassifies any other classes as NORMAL.
The Chebyshev-polynomials-based unified model neural networks for function approximation.
Lee, T T; Jeng, J T
1998-01-01
In this paper, we propose the approximate transformable technique, which includes the direct transformation and indirect transformation, to obtain a Chebyshev-Polynomials-Based (CPB) unified model neural networks for feedforward/recurrent neural networks via Chebyshev polynomials approximation. Based on this approximate transformable technique, we have derived the relationship between the single-layer neural networks and multilayer perceptron neural networks. It is shown that the CPB unified model neural networks can be represented as a functional link networks that are based on Chebyshev polynomials, and those networks use the recursive least square method with forgetting factor as learning algorithm. It turns out that the CPB unified model neural networks not only has the same capability of universal approximator, but also has faster learning speed than conventional feedforward/recurrent neural networks. Furthermore, we have also derived the condition such that the unified model generating by Chebyshev polynomials is optimal in the sense of error least square approximation in the single variable ease. Computer simulations show that the proposed method does have the capability of universal approximator in some functional approximation with considerable reduction in learning time. PMID:18256014
Chattopadhyay, S
2006-01-01
In the present research, possibility of predicting average summer-monsoon rainfall over India has been analyzed through Artificial Neural Network models. In formulating the Artificial Neural Network based predictive model, three layered networks have been constructed with sigmoid non-linearity. The models under study are different in the number of hidden neurons. After a thorough training and test procedure, neural net with three nodes in the hidden layer is found to be the best predictive model.
Chattopadhyay, Surajit
2006-01-01
In the present research, possibility of predicting average summer-monsoon rainfall over India has been analyzed through Artificial Neural Network models. In formulating the Artificial Neural Network based predictive model, three layered networks have been constructed with sigmoid non-linearity. The models under study are different in the number of hidden neurons. After a thorough training and test procedure, neural net with three nodes in the hidden layer is found to be the ...
Energy Technology Data Exchange (ETDEWEB)
Altran, A.B.; Lotufo, A.D.P.; Minussi, C.R. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil). Dept. de Engenharia Eletrica], Emails: lealtran@yahoo.com.br, annadiva@dee.feis.unesp.br, minussi@dee.feis.unesp.br; Lopes, M.L.M. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil). Dept. de Matematica], E-mail: mara@mat.feis.unesp.br
2009-07-01
This paper presents a methodology for electrical load forecasting, using radial base functions as activation function in artificial neural networks with the training by backpropagation algorithm. This methodology is applied to short term electrical load forecasting (24 h ahead). Therefore, results are presented analyzing the use of radial base functions substituting the sigmoid function as activation function in multilayer perceptron neural networks. However, the main contribution of this paper is the proposal of a new formulation of load forecasting dedicated to the forecasting in several points of the electrical network, as well as considering several types of users (residential, commercial, industrial). It deals with the MLF (Multimodal Load Forecasting), with the same processing time as the GLF (Global Load Forecasting). (author)
Jung, Jun-Young; Heo, Wonho; Yang, Hyundae; Park, Hyunsub
2015-01-01
An exact classification of different gait phases is essential to enable the control of exoskeleton robots and detect the intentions of users. We propose a gait phase classification method based on neural networks using sensor signals from lower limb exoskeleton robots. In such robots, foot sensors with force sensing registers are commonly used to classify gait phases. We describe classifiers that use the orientation of each lower limb segment and the angular velocities of the joints to output the current gait phase. Experiments to obtain the input signals and desired outputs for the learning and validation process are conducted, and two neural network methods (a multilayer perceptron and nonlinear autoregressive with external inputs (NARX)) are used to develop an optimal classifier. Offline and online evaluations using four criteria are used to compare the performance of the classifiers. The proposed NARX-based method exhibits sufficiently good performance to replace foot sensors as a means of classifying gait phases. PMID:26528986
Directory of Open Access Journals (Sweden)
Mahmoud Akbarian
2015-07-01
Results: Twelve features with P<0.05 and four features with P<0.1 were identified by using binary logistic regression as effective features. These sixteen features were used as input variables in artificial neural networks. The accuracy, sensitivity and specificity of the test data for the MLP network were 90.9%, 80.0%, and 94.1% respectively and for the total data were 97.3%, 93.5%, and 99.0% respectively. Conclusion: According to the results, we concluded that feed-forward Multi-Layer Perceptron (MLP neural network with scaled conjugate gradient (trainscg back propagation learning algorithm can help physicians to predict the pregnancy outcomes (spontaneous abortion and live birth among pregnant women with lupus by using identified effective variables.
Scientific Electronic Library Online (English)
Gustavo A., García; Octavio, Salcedo.
2010-06-01
Full Text Available El presente artículo describe la implementación de un sistema de predicción de fallos en redes LAN (fallos de timeout y rechazo en las conexiones), utilizando redes neuronales artificiales Perceptrón Multicapa. Se describe como se implementó el sistema, las pruebas realizadas para la selección de lo [...] s parámetros propios de la red neuronal, como del algoritmo de entrenamiento y los resultados de evaluación obtenidos. Abstract in english The paper presents the implementation of a system for predicting failures in LAN (timeout failure and rejection of connections), using neural networks (multilayer perceptron). It describes the implementation of the system, experiments conducted for the selection of specific parameters of the neural [...] network, training algorithm and evaluation results.
Directory of Open Access Journals (Sweden)
Jun-Young Jung
2015-10-01
Full Text Available An exact classification of different gait phases is essential to enable the control of exoskeleton robots and detect the intentions of users. We propose a gait phase classification method based on neural networks using sensor signals from lower limb exoskeleton robots. In such robots, foot sensors with force sensing registers are commonly used to classify gait phases. We describe classifiers that use the orientation of each lower limb segment and the angular velocities of the joints to output the current gait phase. Experiments to obtain the input signals and desired outputs for the learning and validation process are conducted, and two neural network methods (a multilayer perceptron and nonlinear autoregressive with external inputs (NARX are used to develop an optimal classifier. Offline and online evaluations using four criteria are used to compare the performance of the classifiers. The proposed NARX-based method exhibits sufficiently good performance to replace foot sensors as a means of classifying gait phases.
Garagnani, Max; Wennekers, Thomas; Pulvermüller, Friedemann
2009-06-01
Current cognitive theories postulate either localist representations of knowledge or fully overlapping, distributed ones. We use a connectionist model that closely replicates known anatomical properties of the cerebral cortex and neurophysiological principles to show that Hebbian learning in a multi-layer neural network leads to memory traces (cell assemblies) that are both distributed and anatomically distinct. Taking the example of word learning based on action-perception correlation, we document mechanisms underlying the emergence of these assemblies, especially (i) the recruitment of neurons and consolidation of connections defining the kernel of the assembly along with (ii) the pruning of the cell assembly's halo (consisting of very weakly connected cells). We found that, whereas a learning rule mapping covariance led to significant overlap and merging of assemblies, a neurobiologically grounded synaptic plasticity rule with fixed LTP/LTD thresholds produced minimal overlap and prevented merging, exhibiting competitive learning behaviour. Our results are discussed in light of current theories of language and memory. As simulations with neurobiologically realistic neural networks demonstrate here spontaneous emergence of lexical representations that are both cortically dispersed and anatomically distinct, both localist and distributed cognitive accounts receive partial support. PMID:20396612
Laboratory implementation of a neural network trajectory controller for a DC motor
Energy Technology Data Exchange (ETDEWEB)
Weerasooriya, S.; El-Sharkawi, M.A. (Univ. of Washington, Seattle (United States))
1993-03-01
The paper describes the laboratory implementation of a neural network controller for high performance dc drives. The objective is to control the rotor speed and/or position to follow an arbitrarily selected trajectory at all time. The control strategy is based on indirect Model Reference Adaptive Control(MRAC). The motor characteristics are explicitly identified through a multi-layer perceptron type neural network. The output of the trained neural network is used to drive the motor in order to achieve a desired time trajectory of the controlled variable. The main feature of the proposed controller is a neural network which captures the unknown inverse dynamics of the motor through a supervised learning algorithm. The noise rejection and knowledge generalization capabilities of the neural network are effectively used in order to achieve a robust controller design applicable in a wide range of operating conditions. Performance of the control algorithm is evaluated through a laboratory implementation. The neural network controller is assembled in a commercially available PC-based real-time control system shell, using software subroutines. An H-bridge, dc/dc voltage converter is interfaced with the computer to generate the specified terminal voltage sequence for driving the motor. All software and hardware components are off the shelf.' The versatility of the motor/controller arrangement is displayed through real-time plots of the controlled states.
Stochastic resonance in an intracellular genetic perceptron
Bates, Russell; Blyuss, Oleg; Zaikin, Alexey
2014-03-01
Intracellular genetic networks are more intelligent than was first assumed due to their ability to learn. One of the manifestations of this intelligence is the ability to learn associations of two stimuli within gene-regulating circuitry: Hebbian-type learning within the cellular life. However, gene expression is an intrinsically noisy process; hence, we investigate the effect of intrinsic and extrinsic noise on this kind of intracellular intelligence. We report a stochastic resonance in an intracellular associative genetic perceptron, a noise-induced phenomenon, which manifests itself in noise-induced increase of response in efficiency after the learning event under the conditions of optimal stochasticity.
Representations of Boolean Functions by Perceptron Networks.
Czech Academy of Sciences Publication Activity Database
K?rková, V?ra
Prague : Institute of Computer Science AS CR, 2014 - (K?rková, V.; Bajer, L.; Peška, L.; Vojtáš, R.; Hole?a, M.; Nehéz, M.), s. 68-70 ISBN 978-80-87136-19-5. [ITAT 2014. European Conference on Information Technologies - Applications and Theory /14./. Demänovská dolina (SK), 25.09.2014-29.09.2014] R&D Projects: GA MŠk(CZ) LD13002 Institutional support: RVO:67985807 Keywords : perceptron networks * model complexity * Boolean functions Subject RIV: IN - Informatics, Computer Science
Optimal Capacity of the Blume-Emery-Griffiths perceptron
Bolle, D.; Castillo, I. Perez; Shim, G. M.
2002-01-01
A Blume-Emery-Griffiths perceptron model is introduced and its optimal capacity is calculated within the replica-symmetric Gardner approach, as a function of the pattern activity and the imbedding stability parameter. The stability of the replica-symmetric approximation is studied via the analogue of the Almeida-Thouless line. A comparison is made with other three-state perceptrons.
Barron, Leon P; McEneff, Gillian L
2016-01-15
For the first time, the performance of a generalised artificial neural network (ANN) approach for the prediction of 2492 chromatographic retention times (tR) is presented for a total of 1117 chemically diverse compounds present in a range of complex matrices and across 10 gradient reversed-phase liquid chromatography-(high resolution) mass spectrometry methods. Probabilistic, generalised regression, radial basis function as well as 2- and 3-layer multilayer perceptron-type neural networks were investigated to determine the most robust and accurate model for this purpose. Multi-layer perceptrons most frequently yielded the best correlations in 8 out of 10 methods. Averaged correlations of predicted versus measured tR across all methods were R(2)=0.918, 0.924 and 0.898 for the training, verification and test sets respectively. Predictions of blind test compounds (n=8-84 cases) resulted in an average absolute accuracy of 1.02±0.54min for all methods. Within this variation, absolute accuracy was observed to marginally improve for shorter runtimes, but was found to be relatively consistent with respect to analyte retention ranges (~5%). Finally, optimised and replicated network dependency on molecular descriptor data is presented and critically discussed across all methods. Overall, ANNs were considered especially suitable for suspects screening applications and could potentially be utilised in bracketed-type analyses in combination with high resolution mass spectrometry. PMID:26592605
Neural Networks in Control Applications
DEFF Research Database (Denmark)
Sørensen, O.
1994-01-01
The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is...
Directory of Open Access Journals (Sweden)
Stefania Bonafoni
2009-01-01
Full Text Available In this study different approaches based on multilayer perceptron neural networks are proposed and evaluated with the aim to retrieve tropospheric profiles by using GPS radio occultation data. We employed a data set of 445 occultations covering the land surface within the Tropics, split into desert and vegetation zone. The neural networks were trained with refractivity profiles as input computed from geometrical occultation parameters provided by the FORMOSAT-3/COSMIC satellites, while the targets were the dry and wet refractivity profiles and the dry pressure profiles obtained from the contemporary European Centre for Medium-Range Weather Forecast data. Such a new retrieval algorithm was chosen to solve the atmospheric profiling problem without the constraint of an independent knowledge of one atmospheric parameter at each GPS occultation.
Directory of Open Access Journals (Sweden)
J. C. Ochoa-Rivera
2002-01-01
Full Text Available A model for multivariate streamflow generation is presented, based on a multilayer feedforward neural network. The structure of the model results from two components, the neural network (NN deterministic component and a random component which is assumed to be normally distributed. It is from this second component that the model achieves the ability to incorporate effectively the uncertainty associated with hydrological processes, making it valuable as a practical tool for synthetic generation of streamflow series. The NN topology and the corresponding analytical explicit formulation of the model are described in detail. The model is calibrated with a series of monthly inflows to two reservoir sites located in the Tagus River basin (Spain, while validation is performed through estimation of a set of statistics that is relevant for water resources systems planning and management. Among others, drought and storage statistics are computed and compared for both the synthetic and historical series. The performance of the NN-based model was compared to that of a standard autoregressive AR(2 model. Results show that NN represents a promising modelling alternative for simulation purposes, with interesting potential in the context of water resources systems management and optimisation. Keywords: neural networks, perceptron multilayer, error backpropagation, hydrological scenario generation, multivariate time-series..
Prediction of Atmospheric Pressure at Ground Level using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Angshuman Ray
2013-01-01
Full Text Available Prediction of Atmospheric Pressure is one important and challenging task that needs lot of attention and study for analyzing atmospheric conditions. Advent of digital computers and development of data driven artificial intelligence approaches like Artificial Neural Networks (ANN have helped in numerical prediction of pressure. However, very few works have been done till now in this area. The present study developed an ANN model based on the past observations of several meteorological parameters like temperature, humidity, air pressure and vapour pressure as an input for training the model. The novel architecture of the proposed model contains several multilayer perceptron network (MLP to realize better performance. The model is enriched by analysis of alternative hybrid model of k-means clustering and MLP. The improvement of the performance in the prediction accuracy has been demonstrated by the automatic selection of the appropriate cluster
Evaluation of Starting Current of Induction Motors Using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Iman Sadeghkhani
2014-07-01
Full Text Available Induction motors (IMs are widely used in industry including it be an electrical or not. However during starting period, their starting currents are so large that can damage equipment. Therefore, this current should be estimated accurately to prevent hazards caused by it. In this paper, the artificial neural network (ANN as an intelligent tool is used to evaluate starting current peak of IMs. Both Multilayer Perceptron (MLP and Radial Basis Function (RBF structures have been analyzed. Six learning algorithms, backpropagation (BP, delta-bar-delta (DBD, extended delta-bar-delta (EDBD, directed random search (DRS, quick propagation (QP, and levenberg marquardt (LM were used to train the MLP. The simulation results using MATLAB show that most developed ANNs can estimate the starting current peak of IMs with good accuracy. However, it is proven that LM and EDBD algorithms present better performance for starting current evaluation based on average of relative and absolute errors.
A new approach for sizing stand alone photovoltaic systems based in neural networks
Energy Technology Data Exchange (ETDEWEB)
Hontoria, L.; Aguilera, J. [Universidad de Jaen, Dept. de Electronica, Jaen (Spain); Zufiria, P. [UPM Ciudad Universitaria, Dept. de Matematica Aplicada a las Tecnologias de la Informacion, Madrid (Spain)
2005-02-01
Several methods for sizing stand alone photovoltaic (pv) systems has been developed. The more simplistic are called intuitive methods. They are a useful tool for a first approach in sizing stand alone photovoltaic systems. Nevertheless they are very inaccurate. Analytical methods use equations to describe the pv system size as a function of reliability. These ones are more accurate than the previous ones but they are also not accurate enough for sizing of high reliability. In a third group there are methods which use system simulations. These ones are called numerical methods. Many of the analytical methods employ the concept of reliability of the system or the complementary term: loss of load probability (LOLP). In this paper an improvement for obtaining LOLP curves based on the neural network called Multilayer Perceptron (MLP) is presented. A unique MLP for many locations of Spain has been trained and after the training, the MLP is able to generate LOLP curves for any value and location. (Author)
A Review of Artificial Neural Networks: How Well Do They Perform in Forecasting Time Series?
Directory of Open Access Journals (Sweden)
Elsy Gómez-Ramos
2013-12-01
Full Text Available At the beginning of the 90’s, Artificial Neural Networks (ANNs started their applications in finance. The ANNs are data-drive, self-adaptive and non-linear methods that do not require specific assumptions about the underlying model. In general, there are five groups of networks used as forecasting tools: 1 Feedforward Networks, like the Multilayer Perceptron (MLP, 2 Recurrent Networks, 3 Polynomial Networks, 4 Modular Networks, and 5 Support Vector Machine. This paper carries out a review of the specialized literature on ANNs and makes a comparative analysis according to their performance in forecasting stock indices and exchange rates. The objective is to assess the performance when applying different types of networks in relation to MLP. It is shown that the MLP is the best network in forecasting time series. However, it is shown that the MLP has important delimitations in several respects: network architecture, basic functions and initialization weights.
Static sign language recognition using 1D descriptors and neural networks
Solís, José F.; Toxqui, Carina; Padilla, Alfonso; Santiago, César
2012-10-01
A frame work for static sign language recognition using descriptors which represents 2D images in 1D data and artificial neural networks is presented in this work. The 1D descriptors were computed by two methods, first one consists in a correlation rotational operator.1 and second is based on contour analysis of hand shape. One of the main problems in sign language recognition is segmentation; most of papers report a special color in gloves or background for hand shape analysis. In order to avoid the use of gloves or special clothing, a thermal imaging camera was used to capture images. Static signs were picked up from 1 to 9 digits of American Sign Language, a multilayer perceptron reached 100% recognition with cross-validation.
Directory of Open Access Journals (Sweden)
Ali Abroudi
2013-04-01
Full Text Available This paper presents a hybrid approach with two phases for improving the performance of training artificial neural networks (ANNs by selection of the most important instances for training, and then reduction the dimensionality of features. The ANNs which are applied in this paper for validation, are included Multi-Layer Perceptron (MLP and Neuro-Fuzzy Network (NFN. In the first phase, the Modified Fast Condensed Nearest Neighbor (MFCNN algorithm is used to construct the subset with instances very close to the decision boundary. It leads to achieve the instances more useful for training the network. And in the second phase, an Ant-based approach to the supervised reduction of feature dimensionality is introduced, aims to reduce the complexity, and improve the accuracy of learning the ANN. The main purpose of this method is to enhance the classification performance by improving the quality of the training set. Experimental results illustrated the efficiency of the proposed approach.
Scott, D J; Kilner, J A; Rossiny, J C H; McAlford, N N
2007-01-01
We describe the development of artificial neural networks (ANN) for the prediction of the properties of ceramic materials. The ceramics studied here include polycrystalline, inorganic, non-metallic materials and are investigated on the basis of their dielectric and ionic properties. Dielectric materials are of interest in telecommunication applications where they are used in tuning and filtering equipment. Ionic and mixed conductors are the subjects of a concerted effort in the search for new materials that can be incorporated into efficient, clean electrochemical devices of interest in energy production and greenhouse gas reduction applications. Multi-layer perceptron ANNs are trained using the back-propagation algorithm and utilise data obtained from the literature to learn composition-property relationships between the inputs and outputs of the system. The trained networks use compositional information to predict the relative permittivity and oxygen diffusion properties of ceramic materials. The results sh...
Concept and design of the fast H1 second level trigger using artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Kolanoski, H. [Humboldt-Universitaet, Berlin (Germany). Inst. fuer Physik; Getta, H.; Goldner, D. [Dortmund Univ. (Germany). Inst. fuer Physik] [and others
1996-07-01
The experiments at the HERA ep collider have to cope with machine background rates which exceed the rates of the majority ofinteresting physics interactions by several orders of magnitude. To deal with this the H1 experiment was designed with a four staged trigger system. The second trigger level is currently being equipped with a highly parallel computing system that is specialized to run Artificial Neural Network (ANN) algorithms. The trigger is based on CNAPS neurocomputer boards, which are able to compute multilayer perceptron networks with 64 inputs, 64 hidden nodes and one output node in less than 8 {mu}s. In this contribution we present the concept and design of this system. (author)
Concept and design of the fast H1 second level trigger using artificial neural networks
International Nuclear Information System (INIS)
The experiments at the HERA ep collider have to cope with machine background rates which exceed the rates of the majority of interesting physics interactions by several orders of magnitude. To deal with this the H1 experiment was designed with a four staged trigger system. The second trigger level is currently being equipped with a highly parallel computing system that is specialized to run Artificial Neural Network (ANN) algorithms. The trigger is based on CNAPS neurocomputer boards, which are able to compute multilayer perceptron networks with 64 inputs, 64 hidden nodes and one output node in less than 8 ?s. In this contribution we present the concept and design of this system. (author)
Neural networks for emulation variational method for data assimilation in nonlinear dynamics
Energy Technology Data Exchange (ETDEWEB)
Morais Furtado, Helaine Cristina; Fraga de Campos Velho, Haroldo; Macau, Elbert E N, E-mail: helaine.furtado@lac.inpe.br, E-mail: haroldo@lac.inpe.br, E-mail: elbert@lac.inpe.br [Laboratorio Associado de Computacao e Matematica Aplicada, Sao Jose dos Campos (Brazil)
2011-03-01
Description of a physical phenomenon through differential equations has errors involved, since the mathematical model is always an approximation of reality. For an operational prediction system, one strategy to improve the prediction is to add some information from the real dynamics into mathematical model. This additional information consists of observations on the phenomenon. However, the observational data insertion should be done carefully, for avoiding a worse performance of the prediction. Technical data assimilation are tools to combine data from physical-mathematics model with observational data to obtain a better forecast. The goal of this work is to present the performance of the Neural Network Multilayer Perceptrons trained to emulate a Variational method in context of data assimilation. Techniques for data assimilation are applied for the Lorenz systems; which presents a strong nonlinearity and chaotic nature.
Dynamic model of a PEM electrolyser based on artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Chavez-Ramirez, A.U.; Munoz-Guerrero, R.; Sanchez-Huerta, V.; Ramirez-Arredondo, Juan M.; Ornelas, R.; Arriaga, L.G.; Siracusano, S.; Brunaccini, G.; Napoli, G.; Antonucci, V.; Arico, A.S.
2011-01-15
Hydrogen production by electrolysis is emerging as a promising way to meet future fuel demand, and developing models capable of simulating the operation of electrolysis devices is indispensable to efficiently design power generation systems, reduce manufacturing costs and save resources. The nonlinear nature of the Artificial Neural Network (ANN) plays a key role in developing models predicting the performance of complex systems. The behaviour of a Polymer Electrolyte Membrane (PEM) Electrolyser of three cell stack was modelled successfully using a Multilayer Perceptron Network (MLP). This dynamic model was trained to learn the internal relationships of this electrolysis device and predict its behaviour without physical equations. Electric current supply and operation temperature were used as input vector able to predict each cell voltage behaviour. An accuracy (< 2%) was reached after comparing the single cell performance of the real electrolyser versus the ANN based model. This predictive model can be used as a virtual device into a more complex energy system.
Neural networks for emulation variational method for data assimilation in nonlinear dynamics
International Nuclear Information System (INIS)
Description of a physical phenomenon through differential equations has errors involved, since the mathematical model is always an approximation of reality. For an operational prediction system, one strategy to improve the prediction is to add some information from the real dynamics into mathematical model. This additional information consists of observations on the phenomenon. However, the observational data insertion should be done carefully, for avoiding a worse performance of the prediction. Technical data assimilation are tools to combine data from physical-mathematics model with observational data to obtain a better forecast. The goal of this work is to present the performance of the Neural Network Multilayer Perceptrons trained to emulate a Variational method in context of data assimilation. Techniques for data assimilation are applied for the Lorenz systems; which presents a strong nonlinearity and chaotic nature.
Cintra, Rosangela S
2014-01-01
This paper presents an approach for employing artificial neural networks (NN) to emulate an ensemble Kalman filter (EnKF) as a method of data assimilation. The assimilation methods are tested in the Simplified Parameterizations PrimitivE-Equation Dynamics (SPEEDY) model, an atmospheric general circulation model (AGCM), using synthetic observational data simulating localization of balloon soundings. For the data assimilation scheme, the supervised NN, the multilayer perceptrons (MLP-NN), is applied. The MLP-NN are able to emulate the analysis from the local ensemble transform Kalman filter (LETKF). After the training process, the method using the MLP-NN is seen as a function of data assimilation. The NN were trained with data from first three months of 1982, 1983, and 1984. A hind-casting experiment for the 1985 data assimilation cycle using MLP-NN were performed with synthetic observations for January 1985. The numerical results demonstrate the effectiveness of the NN technique for atmospheric data assimilati...
Energy and Carbon Flux Coupling: Multi-ecosystem Comparisons Using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Assefa M. Melesse
2005-01-01
Full Text Available A multi-ecosystems carbon flux simulation from energy fluxes is presented. A new statistical learning technique based on Artificial Neural Network (ANN back propagation algorithm and multi-layer perceptron architecture was used in the CO2 simulation. Four input layers (net radiation, soil heat flux, sensible and latent heat flux were used for training (calibration and testing (verification of model outputs. The 15-days half-hourly (grassland and hourly (forest and cropland micrometeorological data from eddy covariance observations of AmeriFlux towers were divided into training (5-days and testing (10-days sets. Results show that the ANN-based technique predicts CO2 flux with testing R2 values of 0.86, 0.75 and 0.94 for forest, grassland and cropland ecosystems, respectively. The technique is reliable and efficient to estimate regional or global CO2 fluxes from point measurements and understand the spatiotemporal budget of the CO2 fluxes.
Directory of Open Access Journals (Sweden)
A. Ghaemi
2008-01-01
Full Text Available In this study, an Artificial Neural Network (ANN model has been developed for aqueous solutions of electrolyte systems. Multilayer Perceptron (MLP and Radial Basis Function (RBF networks were applied to estimate vapor-liquid equilibrium data for ternary system of NH3-CO2-H2O. Experimental data, taken from the literature were divided into three sections of training, validating and testing. Mean Absolute Errors (MAE of the networks for training set are used as network selection criterion and to find optimal design of the networks. The performance of ANN models to predict partial and total pressures of NH3-CO2-H2O system were evaluated by comparing their results with the predictions of some thermodynamic models. The criterion for this comparison was the error between models perditions and the experimental data. The comparison indicated that both MLP and RBF models predict the system better than the thermodynamic models.
A new source difference artificial neural network for enhanced positioning accuracy
International Nuclear Information System (INIS)
Integrated inertial navigation system (INS) and global positioning system (GPS) units provide reliable navigation solution compared to standalone INS or GPS. Traditional Kalman filter-based INS/GPS integration schemes have several inadequacies related to sensor error model and immunity to noise. Alternatively, multi-layer perceptron (MLP) neural networks with three layers have been implemented to improve the position accuracy of the integrated system. However, MLP neural networks show poor accuracy for low-cost INS because of the large inherent sensor errors. For the first time the paper demonstrates the use of knowledge-based source difference artificial neural network (SDANN) to improve navigation performance of low-cost sensor, with or without external aiding sources. Unlike the conventional MLP or artificial neural networks (ANN), the structure of SDANN consists of two MLP neural networks called the coarse model and the difference model. The coarse model learns the input–output data relationship whereas the difference model adds knowledge to the system and fine-tunes the coarse model output by learning the associated training or estimation error. Our proposed SDANN model illustrated a significant improvement in navigation accuracy of up to 81% over conventional MLP. The results demonstrate that the proposed SDANN method is effective for GPS/INS integration schemes using low-cost inertial sensors, with and without GPS
Evaluation of Neural Networks Performance in Active Cancellation of Acoustic Noise
Directory of Open Access Journals (Sweden)
Mehrshad Salmasi,
2014-12-01
Full Text Available Active Noise Control (ANC works on the principle of destructive interference between the primary disturbance field heard as undesired noise and the secondary field which is generated from control actuators. In the simplest system, the disturbance field can be a simple sine wave, and the secondary field is the same sine wave but 180 degrees out of phase. This research presents an investigation on the use of different types of neural networks in active noise control. Performance of the multilayer perceptron (MLP, Elman and generalized regression neural networks (GRNN in active cancellation of acoustic noise signals is investigated and compared in this paper. Acoustic noise signals are selected from a Signal Processing Information Base (SPIB database. In order to compare the networks appropriately, similar structures and similar training and test samples are deduced for neural networks. The simulation results show that MLP, GRNN, and Elman neural networks present proper performance in active cancellation of acoustic noise. It is concluded that Elman and MLP neural networks have better performance than GRNN in noise attenuation. It is demonstrated that designed ANC system achieve good noise reduction in low frequencies.
Unfolding the neutron spectrum of a NE213 scintillator using artificial neural networks
International Nuclear Information System (INIS)
Artificial neural networks technology has been applied to unfold the neutron spectra from the pulse height distribution measured with NE213 liquid scintillator. Here, both the single and multi-layer perceptron neural network models have been implemented to unfold the neutron spectrum from an Am-Be neutron source. The activation function and the connectivity of the neurons have been investigated and the results have been analyzed in terms of the network's performance. The simulation results show that the neural network that utilizes the Satlins transfer function has the best performance. In addition, omitting the bias connection of the neurons improve the performance of the network. Also, the SCINFUL code is used for generating the response functions in the training phase of the process. Finally, the results of the neural network simulation have been compared with those of the FORIST unfolding code for both 241Am-Be and 252Cf neutron sources. The results of neural network are in good agreement with FORIST code.
Offline analysis of HEP events by ''dynamic perceptron'' neural network
International Nuclear Information System (INIS)
In this paper we start from a critical analysis of the fundamental problems of the parallel calculus in linear structures and of their extension to the partial solutions obtained with non-linear architectures. Then, we present shortly a new dynamic architecture able to solve the limitations of the previous architectures through an automatic re-definition of the topology. This architecture is applied to real-time recognition of particle tracks in high-energy accelerators. (orig.)
Vassiliadis, V S
2006-01-01
A novel algorithm for tunable compression to within the precision of reproduction targets, or storage, is proposed. The new algorithm is termed the `Perceptron Algorithm', which utilises simple existing concepts in a novel way, has multiple immediate commercial application aspects as well as it opens up a multitude of fronts in computational science and technology. The aims of this paper are to present the concepts underlying the algorithm, observations by its application to some example cases, and the identification of a multitude of potential areas of applications such as: image compression by orders of magnitude, signal compression including sound as well, image analysis in a multilayered detailed analysis, pattern recognition and matching and rapid database searching (e.g. face recognition), motion analysis, biomedical applications e.g. in MRI and CAT scan image analysis and compression, as well as hints on the link of these ideas to the way how biological memory might work leading to new points of view i...
Scientific Electronic Library Online (English)
Mayra Luiza Marques da Silva, Binoti; Helio Garcia, Leite; Daniel Henrique Breda, Binoti; José Marinaldo, Gleriani.
2015-03-01
Full Text Available Objetivou-se, neste estudo, treinar, aplicar e avaliar a eficiência de redes neurais artificiais (RNA) para realizar a prognose da produção de povoamentos equiâneos de clones de eucalipto. Os dados utilizados foram provenientes de povoamentos localizados no sul da Bahia, totalizando cerca de 2.000 h [...] ectares de floresta. Foram utilizadas variáveis numéricas, como: idade, área basal, volume e variáveis categóricas, como classe de solo, textura, tipos de espaçamento, relevo, projeto e clone. Os dados foram divididos aleatoriamente em dois grupos: treinamento (80%) e generalização (20%). Foram treinadas redes de três tipos: perceptron, perceptron de múltiplas camadas e redes de função de base radial. As RNA que apresentaram os melhores desempenhos no treinamento e generalização foram selecionadas para realizar a prognose com dados, a partir do primeiro inventário florestal. Conclui-se que as RNA apresentaram resultados satisfatórios, comprovando o potencial e aplicabilidade da técnica na solução dos problemas de mensuração e manejo florestal. Abstract in english The objective of this study was to train, implement and evaluate the efficiency of artificial neural networks (ANN) to perform production prognosis of even-aged stands of eucalyptus clones. The data used were from plantations located in southern Bahia, totaling about 2,000 acres of forest. Numeric v [...] ariables, such as age, basal area, volume and categorical variables, such as soil class texture, spacing, land relief, project and clone were used. The data were randomly divided into two groups: training (80%) and generalization (20%). Three types of networks were trained: perceptron, multilayer perceptron networks and radial basis function. The RNA that showed the best performance in training and generalization were selected to perform the prognosis with data from the first forest inventory. We conclude that the RNA had satisfactory results, showing the potential and applicability of the technique in solving measurement and forest management problems.
Neural Network Based Lna Design for Mobile Satellite Receiver
Directory of Open Access Journals (Sweden)
Abhijeet Upadhya
2014-08-01
Full Text Available Paper presents a Neural Network Modelling approach to microwave LNA design. To acknowledge the specifications of the amplifier, Mobile Satellite Systems are analyzed. Scattering parameters of the LNA in the frequency range 0.5 to 18 GHz are calculated using a Multilayer Perceptron Artificial Neural Network model and corresponding smith charts and polar charts are plotted as output to the model. From these plots, the microwave scattering parameter description of the LNA are obtained. Model is efficiently trained using Agilent ATF 331M4 InGaAs/InP Low Noise pHEMT amplifier datasheet and the neural model’s output seem to follow the various device characteristic curves with high regression. Next, Maximum Allowable Gain and Noise figure of the device are modelled and plotted for the same frequency range. Finally, the optimized model is utilized as an interpolator and the resolution of the amplifying capability with noise characteristics are obtained for the L Band of MSS operation.
Chaotic diagonal recurrent neural network
International Nuclear Information System (INIS)
We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)
Prediction of the local power factor in BWR fuel cells by means of a multilayer neural network
International Nuclear Information System (INIS)
To the beginning of a new operation cycle in a BWR reactor the reactivity of this it increases by means of the introduction of fresh fuel, the one denominated reload fuel. The problem of the definition of the characteristics of this reload fuel represents a combinatory optimization problem that requires significantly a great quantity of CPU time for their determination. This situation has motivated to study the possibility to substitute the Helios code, the one which is used to generate the new cells of the reload fuel parameters, by an artificial neuronal network, with the purpose of predicting the parameters of the fuel reload cell of a BWR reactor. In this work the results of the one training of a multilayer neuronal net that can predict the local power factor (LPPF) in such fuel cells are presented. The prediction of the LPPF is carried out in those condition of beginning of the life of the cell (0.0 MWD/T, to 40% of holes in the one moderator, temperature of 793 K in the fuel and a moderator temperature of 560 K. The cells considered in the present study consist of an arrangement of 10x10 bars, of those which 92 contains U235, some of these bars also contain a concentration of Gd2O3 and 8 of them contain only water. The axial location inside the one assembles of recharge of these cells it is exactly up of the cells that contain natural uranium in the base of the reactor core. The training of the neuronal net is carried out by means of a retro-propagation algorithm that uses a space of training formed starting from previous evaluations of cells by means of the Helios code. They are also presented the results of the application of the neuronal net found for the prediction of the LPPF of some cells used in the real operation of the Unit One of the Laguna Verde Nuclear Power station. (Author)
Sun, Y.; Wendi, D.; Kim, D. E.; Liong, S.-Y.
2015-09-01
Accurate prediction of groundwater table is important for the efficient management of groundwater resources. Despite being the most widely used tools for depicting the hydrological regime, numerical models suffer from formidable constraints, such as extensive data demanding, high computational cost and inevitable parameter uncertainty. Artificial neural networks (ANNs), in contrast, can make predictions on the basis of more easily accessible variables, rather than requiring explicit characterization of the physical systems and prior knowledge of the physical parameters. This study applies ANN to predict the groundwater table in a swamp forest of Singapore. A standard multilayer perceptron (MLP) is selected, trained with the Levenberg-Marquardt (LM) algorithm. The inputs to the network are solely the surrounding reservoir levels and rainfall. The results reveal that ANN is able to produce accurate forecast with a leading time up to 7 days, whereas the performance slightly decreases when leading time increases.
Evrendilek, Fatih; Denizli, Haluk; Yetis, Hakan; Karakaya, Nusret
2013-07-01
Concentrations of outdoor radon-222 ((222)Rn) in temperate grazed peatland and deciduous forest in northwestern Turkey were measured, compared, and modeled using artificial neural networks (ANNs) and multiple nonlinear regression (MNLR) models. The best-performing multilayer perceptron model selected out of 28 ANNs considerably enhanced accuracy metrics in emulating (222)Rn concentrations relative to the MNLR model. The two ecosystems had similar diel patterns with the lowest (222)Rn concentrations in the afternoon and the highest ones near dawn. Mean level (5.1?+?2.5 Bq?m(-3) h(-1)) of (222)Rn in the forest was three times smaller than that (15.8?+?9.7 Bq?m(-3)) of (222)Rn in the peatland. Mean (222)Rn level had negative and positive relationships with air temperature and relative humidity, respectively. PMID:23096138
Integrated on-line plant monitoring system for HTTR using neural networks
International Nuclear Information System (INIS)
The neural networks have been utilized in on-line monitoring-system of High Temperature Engineering Tested Reactor (HTTR) with thermal power of 30 MW. In this system, several neural networks can independently model the plant dynamics with different architecture, input and output signals and learning algorithm. Monitoring task of each neural network is also different, respectively. Those parallel method applications require distributed architecture of computer network for performing real-time tasks. One of main task is real-time monitoring by Multi-Layer Perceptron (MLP) in auto-associative mode, which can model and estimate the whole plant dynamics by training normal operational data only. The basic principle of the anomaly detection is to monitor the difference between process signals measured from the actual plant and the corresponding values estimated by MLP. Other tasks are on-line reactivity prediction, reactivity and helium leak monitoring, respectively. From the on-line test results, each neural network shows good prediction and reliable detection performances. (author)
Integrated On-line Plant Monitoring System for HTTR with Neural Networks
Nabeshima, Kunihiko; Subekti, Muhammad; Matsuishi, Tomomi; Ohno, Tomio; Kudo, Kazuhiko; Nakagawa, Shigeaki
The neural networks have been utilized in on-line monitoring-system of High Temperature Engineering Tested Reactor (HTTR) with thermal power of 30MW. In this system, several neural networks can independently model the plant dynamics with different architecture, input and output signals and learning algorithm. Monitoring task of each neural network is also different, respectively. Those parallel method applications require distributed architecture of computer network for performing real-time tasks. One of main task is real-time plant monitoring by Multi-Layer Perceptron (MLP) in auto-associative mode, which can model and estimate the whole plant dynamics by training normal operational data only. The basic principle of the anomaly detection is to monitor the difference between process signals measured from the actual plant and the corresponding values estimated by MLP. Other tasks are on-line reactivity prediction, reactivity and helium leak monitoring, respectively. From the on-line monitoring results at the safety demonstration tests, each neural network shows good prediction and reliable detection performances.
Application of Artificial Neural Networks for Efficient High-Resolution 2D DOA Estimation
Directory of Open Access Journals (Sweden)
M. Agatonovi?
2012-12-01
Full Text Available A novel method to provide high-resolution Two-Dimensional Direction of Arrival (2D DOA estimation employing Artificial Neural Networks (ANNs is presented in this paper. The observed space is divided into azimuth and elevation sectors. Multilayer Perceptron (MLP neural networks are employed to detect the presence of a source in a sector while Radial Basis Function (RBF neural networks are utilized for DOA estimation. It is shown that a number of appropriately trained neural networks can be successfully used for the high-resolution DOA estimation of narrowband sources in both azimuth and elevation. The training time of each smaller network is significantly re¬duced as different training sets are used for networks in detection and estimation stage. By avoiding the spectral search, the proposed method is suitable for real-time ap¬plications as it provides DOA estimates in a matter of seconds. At the same time, it demonstrates the accuracy comparable to that of the super-resolution 2D MUSIC algorithm.
Multifractals and percolation in the coupling space of perceptrons
Weigt, M
1996-01-01
The coupling space of perceptrons with continuous as well as with binary weights gets partitioned into a disordered multifractal by a set of $p=\\gamma N$ random input patterns. The multifractal spectrum $f(\\alpha)$ can be calculated analytically using the replica formalism. The storage capacity and the generalization behaviour of the perceptron are shown to be related to properties of $f(\\alpha)$ which are correctly described within the replica symmetric ansatz. Replica symmetry breaking is interpreted geometrically as a transition from percolating to non-percolating cells. The existence of empty cells gives rise to singularities in the multifractal spectrum. The relation of these singularities to the Vapnik-Chervonenkis-dimension of the perceptron is discussed. The analytical results for binary couplings are corroborated by numerical studies.
Automatic localization of vertebrae based on convolutional neural networks
Shen, Wei; Yang, Feng; Mu, Wei; Yang, Caiyun; Yang, Xin; Tian, Jie
2015-03-01
Localization of the vertebrae is of importance in many medical applications. For example, the vertebrae can serve as the landmarks in image registration. They can also provide a reference coordinate system to facilitate the localization of other organs in the chest. In this paper, we propose a new vertebrae localization method using convolutional neural networks (CNN). The main advantage of the proposed method is the removal of hand-crafted features. We construct two training sets to train two CNNs that share the same architecture. One is used to distinguish the vertebrae from other tissues in the chest, and the other is aimed at detecting the centers of the vertebrae. The architecture contains two convolutional layers, both of which are followed by a max-pooling layer. Then the output feature vector from the maxpooling layer is fed into a multilayer perceptron (MLP) classifier which has one hidden layer. Experiments were performed on ten chest CT images. We used leave-one-out strategy to train and test the proposed method. Quantitative comparison between the predict centers and ground truth shows that our convolutional neural networks can achieve promising localization accuracy without hand-crafted features.
Analysis of JET charge exchange spectra using neural networks
International Nuclear Information System (INIS)
Active charge exchange spectra representing the local interaction of injected neutral beams and fully stripped impurity ions are hard to analyse due to strong blending with passive emission from the plasma edge. As a result, the deduced plasma parameters (e.g. ion temperature, rotation velocity, impurity density) cannot always be determined unambiguously. Also, the speed of the analysis is limited by the time consuming nonlinear least-squares minimization procedure. In practice, semi-manual analysis is necessary and fast, automatic analysis, based on currently used techniques, does not seem feasible. In this paper the development of a robust and accurate analysis procedure based on multi-layer perceptron (MLP) neural networks is described. This procedure is fully automatic and fast, thus enabling a real-time analysis of charge exchange spectra. Accuracy has been increased in several ways as compared to earlier straightforward neural network implementations and is comparable to a standard least-squares based analysis. Robustness is achieved by using a combination of different confidence measures. A novel technique for the creation of training data, suitable for high-dimensional inverse problems has been developed and used extensively. A new method for fast calculation of error bars directly from the hidden neurons in a MLP network is also described, and used as part of the confidence calculations. For demonstration purposes, a real-time ion temperature profile diagnostic based on this work has been implemented. (author)
Prosopagnosia in high capacity neural networks storing uncorrelated classes
Franz, S; Amit, D J; Virasoro, M.A.
1990-01-01
We display a synaptic matrix that can efficiently store, in attractor neural networks (ANN) and perceptrons, patterns organized in uncorrelated classes. We find a storage capacity limit increasing with m, the overlap of a pattern with its class ancestor, and diverging as m ? 1. The probability distribution of the local stability parameters is studied, leading to a complete analysis of the performance of a perceptron with this synaptic matrix, and to a qualitative understanding of the behavior...
Stability of the replica symmetric solution in diluted perceptron learning
International Nuclear Information System (INIS)
We study the role played by dilution in the average behavior of a perceptron model with continuous coupling with the replica method. We analyze the stability of the replica symmetric solution as a function of the dilution field for the generalization and memorization problems. Thanks to a Gardner-like stability analysis we show that at any fixed ratio ? between the number of patterns M and the dimension N of the perceptron (? = M/N), there exists a critical dilution field hc above which the replica symmetric ansatz becomes unstable. (letter)
Machine and component residual life estimation through the application of neural networks
International Nuclear Information System (INIS)
This paper concerns the use of neural networks for predicting the residual life of machines and components. In addition, the advantage of using condition-monitoring data to enhance the predictive capability of these neural networks was also investigated. A number of neural network variations were trained and tested with the data of two different reliability-related datasets. The first dataset represents the renewal case where the failed unit is repaired and restored to a good-as-new condition. Data were collected in the laboratory by subjecting a series of similar test pieces to fatigue loading with a hydraulic actuator. The average prediction error of the various neural networks being compared varied from 431 to 841 s on this dataset, where test pieces had a characteristic life of 8971 s. The second dataset were collected from a group of pumps used to circulate a water and magnetite solution within a plant. The data therefore originated from a repaired system affected by reliability degradation. When optimized, the multi-layer perceptron neural networks trained with the Levenberg-Marquardt algorithm and the general regression neural network produced a sum-of-squares error within 11.1% of each other for the renewal dataset. The small number of inputs and poorly mapped input space on the second dataset meant that much larger errors were recorded on some of the test data. The potential for using neural networks for residual life prediction and the advantage of incorporating condition-based data into the model was nevertheless proven for both examples
Torrecilla, José S; García, Julián; Rojo, Ester; Rodríguez, Francisco
2009-05-15
Multiple linear regression (MLR), radial basis network (RB), and multilayer perceptron (MLP) neural network (NN) models have been explored for the estimation of toxicity of ammonium, imidazolium, morpholinium, phosphonium, piperidinium, pyridinium, pyrrolidinium and quinolinium ionic liquid salts in the Leukemia Rat Cell Line (IPC-81) and Acetylcholinesterase (AChE) using only their empirical formulas (elemental composition) and molecular weights. The toxicity values were estimated by means of decadic logarithms of the half maximal effective concentration (EC(50)) in microM (log(10)EC(50)). The model's performances were analyzed by statistical parameters, analysis of residuals and central tendency and statistical dispersion tests. The MLP model estimates the log(10)EC(50) in IPC-81 and AchE with a mean prediction error less than 2.2 and 3.8%, respectively. PMID:18805639
Directory of Open Access Journals (Sweden)
Bednyakov Dmitriy Andreevich
2012-11-01
Full Text Available The article is devoted to the simulation of the influence of environmental osmotic pressure on the changes of the level of ?-amylase activity of mucous tunic of the intestine of Russian sturgeon (Acipenser güldenstädtii Brandt. For the solving of this problem the apparatus of neural networks is used. The designed model can be classified as multilayer perceptrone and has rather transparent structure. The conformities of this influence are examined and the model with high approximating and generalizing properties is created. The conclusion about high availability of application of the approach in the studies of adaptations of the digestive system of aquatic organisms to the influence of environmental factors with some qualifications about used rate of exactness of the simulation is made.
A Neural Network Based Real Time Controller for Turning Process
Bahaa Ibraheem Kazem; Nihad F. H. Zangana
2007-01-01
In this paper, the design and implementation of an effective neural network model for turning process identification as well as a neural network controller to track a desired vibration level of the turning machine is as an example of using the neural network for manufacturing process control. Multi – Layer Perceptron (MLP) neural network architecture with Levenberg Marquardt (LM) algorithm has been utilized to train the turning process identifier. Two different strategies have been used for t...
Tagging b quark events in ALEPH with neural networks
International Nuclear Information System (INIS)
Comparison of different methods to tag b quark events are presented: multilayered perceptron (MLP), Learning Vector Quantization (LVQ), discriminant analysis, combination of any two of the above methods. The sample events come from the ALEPH Monte Carlo and data, from the 1990 ALEPH runs. (authors) 12 refs., 16 figs., 5 tabs
Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
Ciresan, Dan Claudiu; Meier, Ueli; Gambardella, Luca Maria; Schmidhuber, Juergen
2010-01-01
Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0.35% error rate on the famous MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images, and graphics cards to greatly speed up learning.
Deep, big, simple neural nets for handwritten digit recognition.
Cire?an, Dan Claudiu; Meier, Ueli; Gambardella, Luca Maria; Schmidhuber, Jürgen
2010-12-01
Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. PMID:20858131
Modeling soil temperatures at different depths by using three different neural computing techniques
Kisi, Ozgur; Tombul, Mustafa; Kermani, Mohammad Zounemat
2015-07-01
This study compares the accuracy of three different neural computing techniques, multi-layer perceptron (MLP), radial basis neural networks (RBNN), and generalized regression neural networks (GRNN), in modeling soil temperatures (ST) at different depths. Climatic data of air temperature, wind speed, solar radiation, and relative humidity from Mersin Station, Turkey, were used as inputs to the models to estimate monthly ST values. In the first part of the study, the effect of each climatic variable on ST was investigated by using GRNN models. Air temperature was found to be the most effective variable in modeling monthly ST. In the second part of the study, the accuracy of GRNN models was compared with MLP, RBNN, and multiple linear regression (MLR) models. RBNN models were found to be better than the GRNN, MLP, and MLR models in estimating monthly ST at the depths of 5 and 10 cm while the MLR and GRNN models gave the best accuracy in the case of 50- and 100-cm depths, respectively. In the third part of the study, the effect of periodicity on the training, validation, and test accuracy of the applied models was investigated. The results indicated that the adding periodicity component significantly increase models' accuracies in estimating monthly ST at different depths. Root mean square errors of the GRNN, MLP, RBNN, and MLR models were decreased by 19, 15, 19, and 15 % using periodicity in estimating monthly ST at 5-cm depth.
Artificial neural network as the tool in prediction rheological features of raw minced meat
Directory of Open Access Journals (Sweden)
Edyta Balejko
2012-09-01
Full Text Available Background. The aim of the study was to elaborate a method of modelling and forecasting rheological features which could be applied to raw minced meat at the stage of mixture preparation with a given ingredient composition. Material and methods. The investigated material contained pork and beef meat, pork fat, fat substitutes, ice and curing mixture in various proportions. Seven texture parameters were measured for each sample of raw minced meat. The data obtained were processed using the artificial neural network module in Statistica 9.0 software. Results. The model that reached the lowest training error was a multi-layer perceptron MLP with three neural layers and architecture 7:7-11-7:7. Correlation coefficients between the experimental and calculated values in training, verification and testing subsets were similar and rather high (around 0.65 which indicated good network performance. Conclusion. High percentage of the total variance explained in PCA analysis (73.5% indicated that the percentage composition of raw minced meat can be successfully used in the prediction of its rheological features. Statistical analysis of the results revealed, that artificial neural network model is able to predict rheological parameters and thus a complete texture profile of raw minced meat.
A research about breast cancer detection using different neural networks and K-MICA algorithm
Directory of Open Access Journals (Sweden)
A A Kalteh
2013-01-01
Full Text Available Breast cancer is the second leading cause of death for women all over the world. The correct diagnosis of breast cancer is one of the major problems in the medical field. From the literature it has been found that different pattern recognition techniques can help them to improve in this domain. This paper presents a novel hybrid intelligent method for detection of breast cancer. The proposed method includes two main modules: Clustering module and the classifier module. In the clustering module, first the input data will be clustered by a new technique. This technique is a suitable combination of the modified imperialist competitive algorithm (MICA and K-means algorithm. Then the Euclidean distance of each pattern is computed from the determined clusters. The classifier module determines the membership of the patterns using the computed distance. In this module, several neural networks, such as the multilayer perceptron, probabilistic neural networks and the radial basis function neural networks are investigated. Using the experimental study, we choose the best classifier in order to recognize the breast cancer. The proposed system is tested on Wisconsin Breast Cancer (WBC database and the simulation results show that the recommended system has high accuracy.
Identification and control of plasma vertical position using neural network in Damavand tokamak
Energy Technology Data Exchange (ETDEWEB)
Rasouli, H. [School of Plasma Physics and Nuclear Fusion, Institute of Nuclear Science and Technology, AEOI, P.O. Box 14155-1339, Tehran (Iran, Islamic Republic of); Advanced Process Automation and Control (APAC) Research Group, Faculty of Electrical Engineering, K.N. Toosi University of Technology, P.O. Box 16315-1355, Tehran (Iran, Islamic Republic of); Rasouli, C.; Koohi, A. [School of Plasma Physics and Nuclear Fusion, Institute of Nuclear Science and Technology, AEOI, P.O. Box 14155-1339, Tehran (Iran, Islamic Republic of)
2013-02-15
In this work, a nonlinear model is introduced to determine the vertical position of the plasma column in Damavand tokamak. Using this model as a simulator, a nonlinear neural network controller has been designed. In the first stage, the electronic drive and sensory circuits of Damavand tokamak are modified. These circuits can control the vertical position of the plasma column inside the vacuum vessel. Since the vertical position of plasma is an unstable parameter, a direct closed loop system identification algorithm is performed. In the second stage, a nonlinear model is identified for plasma vertical position, based on the multilayer perceptron (MLP) neural network (NN) structure. Estimation of simulator parameters has been performed by back-propagation error algorithm using Levenberg-Marquardt gradient descent optimization technique. The model is verified through simulation of the whole closed loop system using both simulator and actual plant in similar conditions. As the final stage, a MLP neural network controller is designed for simulator model. In the last step, online training is performed to tune the controller parameters. Simulation results justify using of the NN controller for the actual plant.
Identification and control of plasma vertical position using neural network in Damavand tokamak
International Nuclear Information System (INIS)
In this work, a nonlinear model is introduced to determine the vertical position of the plasma column in Damavand tokamak. Using this model as a simulator, a nonlinear neural network controller has been designed. In the first stage, the electronic drive and sensory circuits of Damavand tokamak are modified. These circuits can control the vertical position of the plasma column inside the vacuum vessel. Since the vertical position of plasma is an unstable parameter, a direct closed loop system identification algorithm is performed. In the second stage, a nonlinear model is identified for plasma vertical position, based on the multilayer perceptron (MLP) neural network (NN) structure. Estimation of simulator parameters has been performed by back-propagation error algorithm using Levenberg–Marquardt gradient descent optimization technique. The model is verified through simulation of the whole closed loop system using both simulator and actual plant in similar conditions. As the final stage, a MLP neural network controller is designed for simulator model. In the last step, online training is performed to tune the controller parameters. Simulation results justify using of the NN controller for the actual plant.
Identification and control of plasma vertical position using neural network in Damavand tokamak
Rasouli, H.; Rasouli, C.; Koohi, A.
2013-02-01
In this work, a nonlinear model is introduced to determine the vertical position of the plasma column in Damavand tokamak. Using this model as a simulator, a nonlinear neural network controller has been designed. In the first stage, the electronic drive and sensory circuits of Damavand tokamak are modified. These circuits can control the vertical position of the plasma column inside the vacuum vessel. Since the vertical position of plasma is an unstable parameter, a direct closed loop system identification algorithm is performed. In the second stage, a nonlinear model is identified for plasma vertical position, based on the multilayer perceptron (MLP) neural network (NN) structure. Estimation of simulator parameters has been performed by back-propagation error algorithm using Levenberg-Marquardt gradient descent optimization technique. The model is verified through simulation of the whole closed loop system using both simulator and actual plant in similar conditions. As the final stage, a MLP neural network controller is designed for simulator model. In the last step, online training is performed to tune the controller parameters. Simulation results justify using of the NN controller for the actual plant.
Directory of Open Access Journals (Sweden)
Epping W. J. M.
2006-11-01
Full Text Available Neural networks with the multi-layered perceptron architecture were trained on an autoassociation task to compress 2D seismic data. Networks with linear transfer functions outperformed nonlinear neural nets with single or multiple hidden layers. This indicates that the correlational structure of the seismic data is predominantly linear. A compression factor of 5 to 7 can be achieved if a reconstruction error of 10% is allowed. The performance on new test data was similar to that achieved with the training data. The hidden units developed feature-detecting properties that resemble oriented line, edge and more complex feature detectors. The feature detectors of linear neural nets are near-orthogonal rotations of the principal eigenvectors of the Karhunen-Loève transformation. Des réseaux neuronaux à architecture de perceptron multicouches ont été expérimentés en auto-association pour permettre la compression de données sismiques bidimensionnelles. Les réseaux neuronaux à fonctions de transfert linéaires s'avèrent plus performants que les réseaux neuronaux non linéaires, à une ou plusieurs couches cachées. Ceci indique que la structure corrélative des données sismiques est à prédominance linéaire. Un facteur de compression de 5 à 7 peut être obtenu si une erreur de reconstruction de 10 % est admise. La performance sur les données de test est très proche de celle obtenue sur les données d'apprentissage. Les unités cachées développent des propriétés de détection de caractéristiques ressemblant à des détecteurs de lignes orientées, de bords et de figures plus complexes. Les détecteurs de caractéristique des réseaux neuronaux linéaires sont des rotations quasi orthogonales des vecteurs propres principaux de la transformation de Karhunen-Loève.
Neural network based method for conversion of solar radiation data
International Nuclear Information System (INIS)
Highlights: ? Generalized regression neural network is used to predict the solar radiation on tilted surfaces. ? The above network, amongst many such as multilayer perceptron, is the most successful one. ? The present neural network returns a relative mean absolute error value of 9.1%. ? The present model leads to a mean absolute error value of estimate of 14.9 Wh/m2. - Abstract: The receiving ends of the solar energy conversion systems that generate heat or electricity from radiation is usually tilted at an optimum angle to increase the solar incident on the surface. Solar irradiation data measured on horizontal surfaces is readily available for many locations where such solar energy conversion systems are installed. Various equations have been developed to convert solar irradiation data measured on horizontal surface to that on tilted one. These equations constitute the conventional approach. In this article, an alternative approach, generalized regression type of neural network, is used to predict the solar irradiation on tilted surfaces, using the minimum number of variables involved in the physical process, namely the global solar irradiation on horizontal surface, declination and hour angles. Artificial neural networks have been successfully used in recent years for optimization, prediction and modeling in energy systems as alternative to conventional modeling approaches. To show the merit of the presently developed neural network, the solar irradiation data predicted from the novel model was compared to that from the conventional approach (isotropic and anisotropic models), with strict reference to the irradiation data measured in the same location. The present neural network model was found to provide closer solar irradiation values to the measured than the conventional approach, with a mean absolute error value of 14.9 Wh/m2. The other statistical values of coefficient of determination and relative mean absolute error also indicate the advantage of the neural network approach over the conventional one. In terms of the coefficient of determination, the neural network model results in a value of 0.987 whereas the isotropic and anisotropic approaches result in values of 0.959 and 0.966, respectively. On the other hand, the isotropic and anisotropic approaches give relative mean absolute error values of 11.4% and 11.5%, respectively, while that of the neural network model is 9.1%
Akhbardeh, Alireza; Junnila, Sakari; Koivistoinen, Teemu; Värri, Alpo
2007-02-01
This paper presents a comparative analysis of novel supervised fuzzy adaptive resonance theory (SF-ART), multilayer perceptron (MLP) and Multi Layer Perceptrons (MLP) neural networks over Ballistocardiogram (BCG) signal recognition. To extract essential features of the BCG signal, we applied Biorthogonal wavelets. SF-ART performs classification on two levels. At first level, pre-classifier which is self-organized fuzzy ART tuned for fast learning classifies the input data roughly to arbitrary (M) classes. At the second level, post-classification level, a special array called Affine Look-up Table (ALT) with M elements stores the labels of corresponding input samples in the address equal to the index of fuzzy ART winner. However, in running (testing) mode, the content of an ALT cell with address equal to the index of fuzzy ART winner output will be read. The read value declares the final class that input data belongs to. In this paper, we used two well-known patterns (IRIS and Vowel data) and a medical application (Ballistocardiogram data) to evaluate and check SF-ART stability, reliability, learning speed and computational load. Initial tests with BCG from six subjects (both healthy and unhealthy people) indicate that the SF-ART is capable to perform with a high classification performance, high learning speed (elapsed time for learning around half second), and very low computational load compared to the well-known neural networks such as MLP which needs minutes to learn the training material. Moreover, to extract essential features of the BCG signal, we applied Biorthogonal wavelets. The applied wavelet transform requires no prior knowledge of the statistical distribution of data samples. PMID:17283924
Some Properties of the Assembly Neural Networks.
Czech Academy of Sciences Publication Activity Database
Húsek, Dušan; Goltsev, A.
2002-01-01
Ro?. 12, ?. 1 (2002), s. 15-32. ISSN 1210-0552 R&D Projects: GA MŠk LN00B096 Keywords : neuron * neural assembly * neuural column subnetwork * generalization * recognition * perceptron * the nearest-neighbor method Subject RIV: BA - General Mathematics
Neural Network Methods for Boundary Value Problems Defined in Arbitrarily Shaped Domains
Lagaris, I E; Papageorgiou, D G
1998-01-01
Partial differential equations (PDEs) with Dirichlet boundary conditions defined on boundaries with simple geomerty have been succesfuly treated using sigmoidal multilayer perceptrons in previous works. This article deals with the case of complex boundary geometry, where the boundary is determined by a number of points that belong to it and are closely located, so as to offer a reasonable representation. Two networks are employed: a multilayer perceptron and a radial basis function network. The later is used to account for the satisfaction of the boundary conditions. The method has been succesfuly tested on two-dimensional and three-dimensional PDEs and has yielded accurate solutions.
Directory of Open Access Journals (Sweden)
hojat moayedi rad
2012-02-01
Full Text Available Due to simplicity and low cost, induction motors are more useful than direct current motors. Hence the control of these motors is important. The pervious methods are fitted normally for a limited speed range and could not be used for high, low and very low speeds. The voltage model is suitable for high speed because the voltage drop of stator resistance is not small in low speed. The current model is suitable for low speed because of the problems of flux saturation at high speed. This research presents a new method of PWM pulse generating in induction motors based on artificial neural networks in which, the switching pulses are generated by a multilayer feed-forward neural network that is trained by the voltage and current references. Also, for the estimation of required torque and flux information a multilayer perceptron is used. By application of this new method, there is no problem of stability at low and high speeds. The simulation results by matlab-simulink verify the proposed method in transient and steady-state operating modes.
Time series forecasting using cascade correlation networks
Juan David Velásquez; Fernán Alonso Villa; REINALDO C. SOUZA
2010-01-01
Artificial neural networks, especially multilayer perceptrons, have been recognised as being a powerful technique for forecasting nonlinear time series; however, cascade-correlation architecture is a strong competitor in this task due to it incorporating several advantages related to the statistical identification of multilayer perceptrons. This paper compares the accuracy of a cascade-co- rrelation neural network to the linear approach, multilayer perceptrons and dynamic architecture...
International Nuclear Information System (INIS)
A neural network structure has been used for unfolding neutron spectra measured by means of a Bonner Sphere Spectrometer set and a foil activation set using several neutron induced reactions. The present work used the SNNS (Stuttgart Neural Network Simulator) as the interface for designing, training and validation of the Multilayer Perceptron network. The back-propagation algorithm was applied. The Bonner Sphere set chosen has been calibrated at the National Physical Laboratory, United Kingdom, and uses gold activation foils as thermal neutron detectors. The neutron energy covered by the response functions goes from 0.0001 eV to 14 MeV. The foil activation set chosen has been irradiated at the IEA-R1 research reactor and measured at the Nuclear Metrology Laboratory of IPEN-CNEN/SP. Two types of neutron spectra were numerically investigated: monoenergetic and continuous The unfolded spectra were compared to a conventional method using code SAND-II as part of the neutron dosimetry system SAIPS. Good results were obtained, indicating that the Neural Network can be considered an interesting alternative among the neutron spectrum unfolding methodologies. (author)
A MLP neural network as an investigator of TEC time series to detect seismo-ionospheric anomalies
Akhoondzadeh, M.
2013-06-01
Anomaly detection is extremely important for earthquake parameters estimation. In this paper, an application of Artificial Neural Networks (ANNs) in the earthquake precursor's domain has been developed. This study is concerned with investigating the Total Electron Content (TEC) time series by using a Multi-Layer Perceptron (MLP) neural network to detect seismo-ionospheric anomalous variations induced by the powerful Tohoku earthquake of March 11, 2011.The duration of TEC time series dataset is 120 days at time resolution of 2 h. The results show that the MLP presents anomalies better than referenced and conventional methods such as Auto-Regressive Integrated Moving Average (ARIMA) technique. In this study, also the detected TEC anomalies using the proposed method, are compared to the previous results (Akhoondzadeh, 2012) dealing with the observed TEC anomalies by applying the mean, median, wavelet and Kalman filter methods. The MLP detected anomalies are similar to those detected using the previous methods applied on the same case study. The results indicate that a MLP feed-forward neural network can be a suitable non-parametric method to detect changes of a non linear time series such as variations of earthquake precursors.
International Nuclear Information System (INIS)
In computational physics proton transfer phenomena could be viewed as pattern classification problems based on a set of input features allowing classification of the proton motion into two categories: transfer ‘occurred’ and transfer ‘not occurred’. The goal of this paper is to evaluate the use of artificial neural networks in the classification of proton transfer events, based on the feed-forward back propagation neural network, used as a classifier to distinguish between the two transfer cases. In this paper, we use a new developed data mining and pattern recognition tool for automating, controlling, and drawing charts of the output data of an Empirical Valence Bond existing code. The study analyzes the need for pattern recognition in aqueous proton transfer processes and how the learning approach in error back propagation (multilayer perceptron algorithms) could be satisfactorily employed in the present case. We present a tool for pattern recognition and validate the code including a real physical case study. The results of applying the artificial neural networks methodology to crowd patterns based upon selected physical properties (e.g., temperature, density) show the abilities of the network to learn proton transfer patterns corresponding to properties of the aqueous environments, which is in turn proved to be fully compatible with previous proton transfer studies. (condensed matter: structural, mechanical, and thermal properties)
Hariharan, M; Sindhu, R; Yaacob, Sazali
2012-11-01
Crying is the most noticeable behavior of infancy. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. General Regression Neural Network (GRNN) is employed as a classifier for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals from deaf infants. To prove the reliability of the proposed features, two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm are also used as classifiers. The experimental results show that the GRNN classifier gives very promising classification accuracy compared to MLP and TDNN and the proposed method can effectively classify normal and pathological infant cries. PMID:21824676
A coherent perceptron for all-optical learning
Energy Technology Data Exchange (ETDEWEB)
Tezak, Nikolas; Mabuchi, Hideo [Stanford University, Edward L. Ginzton Laboratory, Stanford, CA (United States)
2015-12-15
We present nonlinear photonic circuit models for constructing programmable linear transformations and use these to realize a coherent perceptron, i.e., an all-optical linear classifier capable of learning the classification boundary iteratively from training data through a coherent feedback rule. Through extensive semi-classical stochastic simulations we demonstrate that the device nearly attains the theoretical error bound for a model classification problem. (orig.)
A coherent perceptron for all-optical learning
International Nuclear Information System (INIS)
We present nonlinear photonic circuit models for constructing programmable linear transformations and use these to realize a coherent perceptron, i.e., an all-optical linear classifier capable of learning the classification boundary iteratively from training data through a coherent feedback rule. Through extensive semi-classical stochastic simulations we demonstrate that the device nearly attains the theoretical error bound for a model classification problem. (orig.)
VoIP attacks detection engine based on neural network
Safarik, Jakub; Slachta, Jiri
2015-05-01
The security is crucial for any system nowadays, especially communications. One of the most successful protocols in the field of communication over IP networks is Session Initiation Protocol. It is an open-source project used by different kinds of applications, both open-source and proprietary. High penetration and text-based principle made SIP number one target in IP telephony infrastructure, so security of SIP server is essential. To keep up with hackers and to detect potential malicious attacks, security administrator needs to monitor and evaluate SIP traffic in the network. But monitoring and following evaluation could easily overwhelm the security administrator in networks, typically in networks with a number of SIP servers, users and logically or geographically separated networks. The proposed solution lies in automatic attack detection systems. The article covers detection of VoIP attacks through a distributed network of nodes. Then the gathered data analyze aggregation server with artificial neural network. Artificial neural network means multilayer perceptron network trained with a set of collected attacks. Attack data could also be preprocessed and verified with a self-organizing map. The source data is detected by distributed network of detection nodes. Each node contains a honeypot application and traffic monitoring mechanism. Aggregation of data from each node creates an input for neural networks. The automatic classification on a centralized server with low false positive detection reduce the cost of attack detection resources. The detection system uses modular design for easy deployment in final infrastructure. The centralized server collects and process detected traffic. It also maintains all detection nodes.
Energy demand estimation of South Korea using artificial neural network
International Nuclear Information System (INIS)
Because South Korea's industries depend heavily on imported energy sources (fifth largest importer of oil and second largest importer of liquefied natural gas in the world), the accurate estimating of its energy demand is critical in energy policy-making. This research proposes an artificial neural network model (a structure with feed-forward multilayer perceptron, error back-propagation algorithm, momentum process, and scaled data) to efficiently estimate the energy demand for South Korea. The model has four independent variables, such as gross domestic product (GDP), population, import, and export amounts. The data are obtained from diverse local and international sources. The proposed model better estimated energy demand than a linear regression model (a structure with multiple linear variables and least square method) or an exponential model (a structure with mixed integer variables, branch and bound method, and Broyden-Fletcher-Goldfarb-Shanno (BFGS) method) in terms of root mean squared error (RMSE). The model also forecasted better than the other two models in terms of RMSE without any over-fitting problem. Further testing with four scenarios based upon reliable source data showed unanticipated results. Instead of growing permanently, the energy demands peaked at certain points, and then decreased gradually. This trend is quite different from the results by regression or exponential model.
Monthly monsoon rainfall forecasting using artificial neural networks
Ganti, Ravikumar
2014-10-01
Indian agriculture sector heavily depends on monsoon rainfall for successful harvesting. In the past, prediction of rainfall was mainly performed using regression models, which provide reasonable accuracy in the modelling and forecasting of complex physical systems. Recently, Artificial Neural Networks (ANNs) have been proposed as efficient tools for modelling and forecasting. A feed-forward multi-layer perceptron type of ANN architecture trained using the popular back-propagation algorithm was employed in this study. Other techniques investigated for modeling monthly monsoon rainfall include linear and non-linear regression models for comparison purposes. The data employed in this study include monthly rainfall and monthly average of the daily maximum temperature in the North Central region in India. Specifically, four regression models and two ANN model's were developed. The performance of various models was evaluated using a wide variety of standard statistical parameters and scatter plots. The results obtained in this study for forecasting monsoon rainfalls using ANNs have been encouraging. India's economy and agricultural activities can be effectively managed with the help of the availability of the accurate monsoon rainfall forecasts.
AN APPLICATION OF SPEAKER RECOGNITION USING ARTIFICIAL NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
Murat CANER
2006-02-01
Full Text Available In this study an artificial neural network (ANN is implemented, which has been used frequently as an implementation model in recent years, to recognize speaker identification. Generally, recognition is consist of three stages that, processing of signal, obtaining attributes and comparing them. Speech samples are transformed into digital data according to voice card of PC. In the analysis of voice stage, recurrent periods and white noise of voice data are trimmed by hamming window method and voice attribute part of the digital data is obtained. For obtaining attribute of voice data LPC (linear predictive coding and DFT (discrete fourier transform methods are used. Of those 28 coefficents, that is used for speaker recognition, 16 were obtained by the analysis of DFT and 12 were obtained by the analysis of LPC. The parameters that represent speaker voice, is used for training and test of ANN. Multilayer perceptron model is used as an architecture of ANN and backpropagation algorithm is used for training method. Voices of "a" is taken from 7 different person and their attributes are found. ANN is trained with these features to find the speaker who is the owner of the sample voice. And then using the test data that is not used for training part, recognition achievement of ANN is tested. As a result, good results were obtained with low failure rate.
AN EFFICIENT NEURAL NETWORK FOR RECOGNIZING GESTURAL HINDI DIGITS
Directory of Open Access Journals (Sweden)
Nidal Fawzi Shilbayeh
2013-01-01
Full Text Available Handwritten Hindi digit recognition plays an important role in eastern Arab countries especially in the courtesy amounts of Arab bank checks, recognizing numbers in car plates, or in postal code for mail sorting. In our study, we proposed an efficient Hindi Digit Recognition System drawn by the mouse and developed using Multilayer Perceptron Neural Network (MLP with backpropagation. The system has been designed, implemented and tested successfully. Analysis has been carried out to determine the number of hidden nodes that achieves high performance. The proposed system has been trained on samples of 800 images and tested on samples of 300 images written by different users selected from different ages. An experimental result shows high accuracy of about 91% on the testing samples and very close to 100% on the training samples. Experiments showed that our result is high in comparison with other Hindi digit recognition systems especially if we consider the way of writing (mouse and children in our trained and tested results.
Energy demand estimation of South Korea using artificial neural network
Energy Technology Data Exchange (ETDEWEB)
Geem, Zong Woo [Environmental Planning and Management Program, Johns Hopkins University, Clarksburg, Maryland 20871 (United States); Roper, William E. [Department of Geography and Geo-information Science, George Mason University, Fairfax, Virginia 22030 (United States)
2009-10-15
Because South Korea's industries depend heavily on imported energy sources (fifth largest importer of oil and second largest importer of liquefied natural gas in the world), the accurate estimating of its energy demand is critical in energy policy-making. This research proposes an artificial neural network model (a structure with feed-forward multilayer perceptron, error back-propagation algorithm, momentum process, and scaled data) to efficiently estimate the energy demand for South Korea. The model has four independent variables, such as gross domestic product (GDP), population, import, and export amounts. The data are obtained from diverse local and international sources. The proposed model better estimated energy demand than a linear regression model (a structure with multiple linear variables and least square method) or an exponential model (a structure with mixed integer variables, branch and bound method, and Broyden-Fletcher-Goldfarb-Shanno (BFGS) method) in terms of root mean squared error (RMSE). The model also forecasted better than the other two models in terms of RMSE without any over-fitting problem. Further testing with four scenarios based upon reliable source data showed unanticipated results. Instead of growing permanently, the energy demands peaked at certain points, and then decreased gradually. This trend is quite different from the results by regression or exponential model. (author)
Effect of Heat Fluxes on Ammonia Emission from Swine Waste Lagoon Based on Neural Network Analyses
Directory of Open Access Journals (Sweden)
N. Lovanh
2014-01-01
Full Text Available Understanding factors that affect ammonia emissions from swine waste lagoons or any animal waste receptacles is a necessary first step in deploying potential remediation options. In this study, we examined the various meteorological factors (i.e., air temperatures, solar radiation and heat fluxes that potentially affect ammonia emissions from swine waste lagoon. Ammonia concentrations were monitored using a photoacoustic gas analyzer. The ammonia emissions from the lagoon were monitored continuously for a 24 h cycle, twice a week during a winter month at a height of 50 cm above the lagoon surface. Meteorological data were also monitored simultaneously. Heat fluxes were tabulated and correlated to the averaged ammonia concentrations (range of zero to 8.0 ppmv. Multi-layer Perceptron (MLP neural network predictive model was built based on the most important meteorological parameters. The results from MLP neural networks analysis show that ammonia emissions from the swine waste lagoon were affected by heat fluxes such as net solar radiation, sensible heat and latent heat of vaporization. Thus it is important to consider environmental conditions (i.e., meteorological parameters such as solar radiation, latent heat and etc. in formulating management or abatement strategies for reducing ammonia emissions from swine waste lagoons or any other air pollutant emissions from livestock waste receptacles.
Delogu, P; Kasae, P; Retico, A
2008-01-01
The computer-aided diagnosis system we developed for the mass characterization is mainly based on a segmentation algorithm and on the neural classification of several features computed on the segmented mass. Mass segmentation plays a key role in most computerized systems. Our technique is a gradient-based one, showing the main characteristic that no free parameters have been evaluated on the dataset used in this analysis, thus it can directly be applied to datasets acquired in different conditions without any ad-hoc modification. A dataset of 226 masses (109 malignant and 117 benign) has been used in this study. The segmentation algorithm works with a comparable efficiency both on malignant and benign masses. Sixteen features based on shape, size and intensity of the segmented masses are analyzed by a multi-layered perceptron neural network. A feature selection procedure has been carried out on the basis of the feature discriminating power and of the linear correlations interplaying among them. The comparison...
Directory of Open Access Journals (Sweden)
Chakraborty Prithviraj
2015-01-01
Full Text Available This study aimed to apply the simultaneous optimization method incorporating artificial neural network (ANN using multi-layer perceptron (MLP model to develop buccoadhesive pharmaceutical wafers containing loratadine with an optimized physicochemical property and drug release. The amount of sodium carboxymethyl cellulose and lactose monohydrate at three levels (?1, 0, +1 for each was selected as casual factors. Bioadhesive strength, disintegration time, percent swelling index and t 70% as wafer properties were selected as output variables. Nine buccoadhesive wafers were prepared according to a 3 2 factorial design and their physicochemical property and dissolution tests were performed. Commercially available Statistica Neural Network Software (Stat Soft, Inc., Tulsa, OK, USA was used throughout the study. The training process of MLP was completed until a satisfactory value of root mean square for the test data was obtained using back propagation, conjugate gradient descent method. This work exemplifies the probability for an ANN with MLP, to support in development of buccoadhesive wafers with enviable characteristics.
On-line control of the COMPASS-D tokamak using a neural network
International Nuclear Information System (INIS)
Multi-layer perceptron (MLP) networks are particularly appropriate for performing rapid non-linear mapping. In the application discussed in this Paper the position and shape of the plasma within the experimental fusion research tokamak COMPASS-D at UKAEA's Culham Laboratory is determined from a series of magnetic sensors placed around the vacuum vessel, close to the plasma boundary. By using a real-time analogue neural network it is possible to achieve control within a sub-millisecond time-scale. In this application the neural network is needed to solve an inverse problem. Numerical codes exist that are able to calculate the signals expected on the magnetic sensors for a given plasma position and profile. The problem is well defined from the solution of the Grad-Shafranov equation. However, no easy analytical formalism exists to reverse the problem - to calculate the plasma parameters given the magnetic signals. It is this mapping, from the set of magnetic diagnostic input signals to the parameters of the plasma, that an MLP network can be trained to solve. The training data are some 2000 example plasma equilibria, covering the likely possible configurations of the plasma, solved by numerical methods. The desired aim, to control the plasma boundary position to within a few millimetres, has now been achieved. (author)
International Nuclear Information System (INIS)
A nuclear power plant's (NPP's) status is usually monitored by a human operator. Any classifier system used to enhance the operator's capability to diagnose a safety-critical system like an NPP should classify a novel transient as ''don't-know'' if it is not contained within its accumulated knowledge base. In particular, the classifier needs some kind of proximity measure between the new data and its training set. Artificial neural networks have been proposed as NPP classifiers, the most popular ones being the multilayered perceptron (MLP) type. However, MLPs do not have a proximity measure, while learning vector quantization, probabilistic neural networks (PNNs), and some others do. This proximity measure may also serve as an explanation to the classifier's decision in the way that case-based-reasoning expert systems do. The capability of a PNN network as a classifier is demonstrated using simulator data for the three-loop 436-MW(electric) Westinghouse San Onofre unit 1 pressurized water reactor. A transient's classification history is used in an ''evidence accumulation'' technique to enhance a classifier's accuracy as well as its consistency
Energy Technology Data Exchange (ETDEWEB)
Dashtbayazi, M.R. [Faculty of Mechanical Engineering, K. N. Toosi University of Technology, P.O. Box 16765-3381, Tehran (Iran, Islamic Republic of)], E-mail: dashtbayazi@me.kntu.ac.ir; Shokuhfar, A. [Faculty of Mechanical Engineering, K. N. Toosi University of Technology, P.O. Box 16765-3381, Tehran (Iran, Islamic Republic of); Simchi, A. [Department of Materials Science and Engineering, Institute for Nanoscience and Nanotechnology, Sharif University of Technology, P.O. Box 11365-9466, Azadi Avenue, 14588 Tehran (Iran, Islamic Republic of)
2007-09-25
An artificial neural network model was developed for modeling of the effects of mechanical alloying parameters including milling time, milling speed and ball to powder weight ratio on the characteristics of Al-8 vol%SiC nanocomposite powders. The crystallite size and lattice strain of the aluminum matrix were considered for modeling. This nanostructured nanocomposite powder was synthesized by utilizing planetary high energy ball mill and the required data for training were collected from the experimental results. The characteristics of the particles were determined by X-ray diffraction, scanning and transmission electron microscopy. Two types of neural network architecture, i.e. multi-layer perceptron (MLP) and radial basis function (RBF), were used. The steepest descent along with variable learning rate back-propagation algorithm known as a heuristic technique was utilized for training the MLP network. It was found that MLP network yields better results compared to RBF network, giving an acceptable mapping between the network responses and the target data with a high correlation coefficients. The response surfaces between the response variables, i.e. crystallite size, lattice strain of the aluminum matrix and the processing parameters are presented. The procedure modeling can be used for optimization of the MA process for synthesizing of nanostructured metal matrix nanocomposites.
International Nuclear Information System (INIS)
An artificial neural network model was developed for modeling of the effects of mechanical alloying parameters including milling time, milling speed and ball to powder weight ratio on the characteristics of Al-8 vol%SiC nanocomposite powders. The crystallite size and lattice strain of the aluminum matrix were considered for modeling. This nanostructured nanocomposite powder was synthesized by utilizing planetary high energy ball mill and the required data for training were collected from the experimental results. The characteristics of the particles were determined by X-ray diffraction, scanning and transmission electron microscopy. Two types of neural network architecture, i.e. multi-layer perceptron (MLP) and radial basis function (RBF), were used. The steepest descent along with variable learning rate back-propagation algorithm known as a heuristic technique was utilized for training the MLP network. It was found that MLP network yields better results compared to RBF network, giving an acceptable mapping between the network responses and the target data with a high correlation coefficients. The response surfaces between the response variables, i.e. crystallite size, lattice strain of the aluminum matrix and the processing parameters are presented. The procedure modeling can be used for optimization of the MA process for synthesizing of nanostructured metal matrix nanocomposites
Artificial neural networks for simulating wind effects on sprinkler distribution patterns
Energy Technology Data Exchange (ETDEWEB)
Sayyadi, H.; Sadraddini, A. A.; Farsadi Zadeh, D.; Montero, J.
2012-07-01
A new approach based on Artificial Neural Networks (ANNs) is presented to simulate the effects of wind on the distribution pattern of a single sprinkler under a center pivot or block irrigation system. Field experiments were performed under various wind conditions (speed and direction). An experimental data from different distribution patterns using a Nelson R3000 Rotator sprinkler have been split into three and used for model training, validation and testing. Parameters affecting the distribution pattern were defined. To find an optimal structure, various networks with different architectures have been trained using an Early Stopping method. The selected structure produced R2 0.929 and RMSE = 6.69 mL for the test subset, consisting of a Multi-Layer Perceptron (MLP) neural network with a backpropagation training algorithm; two hidden layers (twenty neurons in the first hidden layer and six neurons in the second hidden layer) and a tangent-sigmoid transfer function. This optimal network was implemented in MATLAB to develop a model termed ISSP (Intelligent Simulator of Sprinkler Pattern). ISSP uses wind speed and direction as input variables and is able to simulate the distorted distribution pattern from a R3000 Rotator sprinkler with reasonable accuracy (R{sup 2} > 0.935). Results of model evaluation confirm the accuracy and robustness of ANNs for simulation of a single sprinkler distribution pattern under real field conditions. (Author) 41 refs.
Presenting an Appropriate Neural Network for Optimal Mix Design of Roller Compacted Concrete Dams
Directory of Open Access Journals (Sweden)
Taha Mehmannavaz
2014-03-01
Full Text Available In general, one of the main targets to achieve the optimal mix design of concrete dams is to reduce the amount of cement, heat of hydration, increasing the size of aggregate (coarse and reduced the permeability. Thus, one of the methods which is used in construction of concrete and soil dams as a suitable replacement is construction of dams in roller compacted concrete method. Spending fewer budgets, using road building machinery, short time of construction and continuation of construction all are the specifications of this construction method, which have caused priority of these two methods and finally this method has been known as a suitable replacement for constructing dams in different parts of the world. On the other hand, expansion of the materials used in this type of concrete, complexity of its mix design, effect of different parameters on its mix design and also finding relations between different parameters of its mix design have necessitated the presentation of a model for roller compacted concretemix design. Artificial neural networks are one of the modeling methods which have shown very high power for adjustment to engineering problems. A kind of these networks, called Multi-Layer Perceptron (MLP neural networks, was used as the main core of modeling in this study along with error-back propagation training algorithm, which is mostly applied in modeling mapping behaviors.
Scientific Electronic Library Online (English)
Juan David, Velásquez Henao; Mario Alberto, Aldana Dumar.
2007-12-01
Full Text Available En este artículo, se modela el precio promedio mensual del café colombiano en la Bolsa de Nueva York, usando varios modelos alternativos. El modelo final seleccionado está compuesto por una componente lineal autorregresiva más una red neuronal artificial tipo perceptron multicapa con dos neuronas en [...] la capa oculta, que permite representar la dinámica que sigue el valor esperado de la serie de precios; mientras que la dinámica de los residuales es especificada usando un proceso heterocedástico condicional autoregresivo de primer orden. Los residuales normalizados del modelo son incorrelacionados y homocedásticos, y siguen aproximadamente una distribución normal. Los resultados indican que el precio actual depende de los precios ocurridos en los últimos cuatro meses. Abstract in english In this paper, the monthly average price of the Colombian coffee in the New York Stock Exchange, is modelling by means of several alternative models. The preferred model is composed by a lineal autoregressive component plus a multilayer perceptron neural network with two neurons in the hidden layer, [...] that allow us to representing the dynamic following by the expected value of the price time series; while, the dynamic of the residuals is specified by an autoregressive conditional heterocedastic model of first order. The normalized residuals of the preferred model are uncorrelated, homocedastic and are distributed following a normal distribution. The results indicate that the current price depend of the prices in the previous four months.
Scientific Electronic Library Online (English)
JUAN DAVID, VELÁSQUEZ HENAO; SANTIAGO FERNANDO, MONTOYA MORENO.
2005-11-01
Full Text Available Un nuevo modelo híbrido es propuesto para pronosticar el índice colombiano de precios al consumidor. Este es basado en una descomposición estructural de la serie temporal con el objetivo de remover cualquier patrón fácilmente detectable en los datos, y en el uso de un perceptron multicapa para model [...] ar las relaciones ocultas en la serie de tiempo. Los resultados superan las aproximaciones clásicas basadas en la aproximación de Box y Jenkins, y los modelos convencionales de Redes Neuronales, e incentivan el estudio de este tipo de aproximación híbrida para modelar otras series temporales. Abstract in english A new hybrid model is proposed to forecasting the Colombian Consumer Price Index. It’s based on the structural decomposition of the original time series with the aim of remove any easily detected pattern in the data, and in the use of multilayer perceptron to model hidden relationships in the studie [...] d time series. The results overcome classical approaches based on Box-Jenkins methodology and conventional neural networks methodology, and encourage the study of this hybrid approach to modelling other time series.
Parinet, Julien; Julien, Maxime; Nun, Pierrick; Robins, Richard J; Remaud, Gerald; Höhener, Patrick
2015-09-01
We aim at predicting the effect of structure and isotopic substitutions on the equilibrium vapour pressure isotope effect of various organic compounds (alcohols, acids, alkanes, alkenes and aromatics) at intermediate temperatures. We attempt to explore quantitative structure property relationships by using artificial neural networks (ANN); the multi-layer perceptron (MLP) and compare the performances of it with multi-linear regression (MLR). These approaches are based on the relationship between the molecular structure (organic chain, polar functions, type of functions, type of isotope involved) of the organic compounds, and their equilibrium vapour pressure. A data set of 130 equilibrium vapour pressure isotope effects was used: 112 were used in the training set and the remaining 18 were used for the test/validation dataset. Two sets of descriptors were tested, a set with all the descriptors: number of(12)C, (13)C, (16)O, (18)O, (1)H, (2)H, OH functions, OD functions, CO functions, Connolly Solvent Accessible Surface Area (CSA) and temperature and a reduced set of descriptors. The dependent variable (the output) is the natural logarithm of the ratios of vapour pressures (ln R), expressed as light/heavy as in classical literature. Since the database is rather small, the leave-one-out procedure was used to validate both models. Considering higher determination coefficients and lower error values, it is concluded that the multi-layer perceptron provided better results compared to multi-linear regression. The stepwise regression procedure is a useful tool to reduce the number of descriptors. To our knowledge, a Quantitative Structure Property Relationship (QSPR) approach for isotopic studies is novel. PMID:25559176
Directory of Open Access Journals (Sweden)
Luciana C. Bucene
2004-12-01
Full Text Available Objetivando classificar terras para irrigação, faz-se necessário analisar e determinar alguns parâmetros, entre eles a produtividade do solo. A classificação de produtividade (comumente chamada fertilidade aparente é delimitada em cinco classes: muito alta, alta, média, baixa e muito baixa, e em cada classe é preciso avaliar certos atributos do solo, como pH, CTC (capacidade de troca de cátions, V% (índice de saturação por bases, P (fósforo, Mg (magnésio e K (potássio. Neste trabalho, objetivou-se identificar a produtividade na qual atributos do solo, da parte inicial da microbacia hidrográfica do Rio Pardo, localizada em Pardinho, SP, foram analisados e classificados nas classes que a delimitam, através de Redes Neurais Artificiais (RNAs utilizandose Perceptron Múltiplas Camadas (Multilayers Perceptrons - MLP com o algoritmo de treinamento "backpropagation"- classificador de padrões, obtendo-se um número ótimo de camadas intermediárias e de neurônios; resultando na classificação de produtividade, a situação ótima da rede obteve 78% dos resultados iguais aos desejados, com duas camadas de neurônios, uma das quais intermediária, com 5 neurônios, e uma camada de saída.Productivity data (commonly known as apparent fertility of the initial part of the river Pardo-SP watershed was analyzed and classified with Artificial Neural Networks (ANNs, in order to classify lands for irrigation. Soil attributes as pH, CEC (cation exchange capacity, V% (base saturation index, P (phosphorus, Mg (magnesium and K (potassium were defined in five classes: very high, high, medium, low and very low. Apparent fertility classification taking into account the five classes was performed by using Multiple Layers Perceptron (MLP. Backpropagation algorithm was performed with the training set. One hidden layer with 5 neurons was the situation that best performed.
Multilayer perceptron for simulation models reduction: application to a sawmill workshop
Thomas, Philippe; Thomas, André
2011-01-01
Simulation is often used to evaluate supply chain or workshop management. This simulation task needs models, which are difficult to construct. The aim of this work is to reduce the complexity of a simulation model design. The proposed approach combines discrete and continuous approaches in order to construct speeder and simpler reduced model. The simulation model focuses on bottlenecks with a discrete approach according to the theory of constraints. The remaining of the workshop must be taken...
The reactor safety study with help of artificial neuron networks (multilayer perceptrons)
International Nuclear Information System (INIS)
One deals with deposition of insulation large amounts on settling tank components that may result in malfunction of residual heat removal systems. Paper describes briefly simulation of pressure drops in confinement systems by means of an artificial neuron nets and compares the simulation data with the experiment ones
Modeling of gamma-ray energy absorption buildup factors using neural network
International Nuclear Information System (INIS)
This paper presents a new approach based on multilayered perceptrons (MLPs) to compute energy absorption buildup factors. The MLP has been trained by a Levenberg-Marquardt learning algorithm. The model is fast and does not require tremendous computational efforts. The results obtained by using the proposed model are in good agreement with the ANSI/ANS-6.4.3 standard data set
Representations of highly-varying functions by perceptron networks.
Czech Academy of Sciences Publication Activity Database
K?rková, V?ra
North Charleston : CreateSpace Independent Publishing Platform, 2013 - (Vina?, T.; Hole?a, M.; Lexa, M.; Peška, L.; Vojtáš, P.), s. 73-76 ISBN 978-1-4909-5208-6. [ITAT 2013. Conference on Theory and Practice of Information Technologies. Donovaly (SK), 11.09.2013-15.09.2013] R&D Projects: GA ?R GAP202/11/1368 Institutional support: RVO:67985807 Keywords : one-hidden-layer networks * perceptrons * Boolean functions * network complexity Subject RIV: IN - Informatics, Computer Science
Directory of Open Access Journals (Sweden)
Chennai Salim
2011-09-01
Full Text Available The increased use of nonlinear devices in the industry has resulted in the direct increase of harmonic distortion in power systems during these last years. Active filter systems are proposed to mitigate current harmonics generated by nonlinear loads. The conventional scheme based on a two-level voltage source inverter controlled by a hysteresis controller has several disadvantages and cannot be used for medium or high-power applications. To overcome these drawbacks and improve the APF performance, there’s a great tendency to use multilevel inverters controlled by intelligent controllers. Three level (NPC inverter is one of the most widely used topologies in various industrial applications such as machine drives and power factor compensators. On the other hand, artificial neural networks are under study and investigation in other power electronics applications. In order to gain the advantages of the three-level inverter and artificial neural networks and to reduce the complexity of classical control schemes, a new active power filter configuration controlled by two MLPNN (Multi-Layer Perceptron Neural Network is proposed in this paper. The first ANN is used to replace the PWM current controller, and the second one to maintain a constant dc link voltage across the capacitors and compensate the inverter power losses. The performance of the global system, including power and control circuits is evaluated by Matlab-Simulink and SimPowerSystem Toolbox simulation. The obtained results confirm the effectiveness of the proposed control scheme.
Directory of Open Access Journals (Sweden)
Luiz Henry Monken e Silva
2005-01-01
Full Text Available Neste artigo a habilidade das redes neurais perceptron multicamada eminterpolar foi utilizada para analisar duas classes de problemas de contorno. A primeira classe é formada por equações diferenciais em que a solução pode apresentar gradientes elevados e a segunda classe é formada de equações diferenciais definidas em domínios arbitrários. As metodologias propostas por Lagaris et al. (1998 foram estendidas para casos de equações diferenciais sujeitas às condições de Cauchy e condições de contorno mistas. Os resultados fornecidos pelo método da rede neural se apresentam precisos quando comparados com os resultados analíticos ou por métodos numéricos de resolução deequações diferenciais. A precisão alcançada nos resultados e a facilidade no manuseio do método para resolver estes problemas de contorno encorajaram a continuidade da pesquisa, particularmente no tocante à convergência e estabilidade numérica.In this paper, the ability of the multilayer perceptron neural network (MLP in interpolation was used to analyze two classes of boundary value problems. The first class is formed by differential equations, with solutions which can have high gradients and the second are partial differential equations, defined on arbitrary shaped domain. Also, the methodologies proposed by Lagaris et al. (1998 were enlarged for differential equations subjected to Cauchy and mix boundary conditions type. The results of the artificial neural network method are very precise when comparison to the analytical ones or those of classical numerical methods to solve differential equations. The precision achieved in the results and the ability to handle the method, to solve those boundary value problems, were encouraging to keep the research, particularly on an important direction, concerning convergence and numerical stability.
Implementation of a spike-based perceptron learning rule using TiO2-x memristors.
Mostafa, Hesham; Khiat, Ali; Serb, Alexander; Mayr, Christian G; Indiveri, Giacomo; Prodromakis, Themis
2015-01-01
Synaptic plasticity plays a crucial role in allowing neural networks to learn and adapt to various input environments. Neuromorphic systems need to implement plastic synapses to obtain basic "cognitive" capabilities such as learning. One promising and scalable approach for implementing neuromorphic synapses is to use nano-scale memristors as synaptic elements. In this paper we propose a hybrid CMOS-memristor system comprising CMOS neurons interconnected through TiO2-x memristors, and spike-based learning circuits that modulate the conductance of the memristive synapse elements according to a spike-based Perceptron plasticity rule. We highlight a number of advantages for using this spike-based plasticity rule as compared to other forms of spike timing dependent plasticity (STDP) rules. We provide experimental proof-of-concept results with two silicon neurons connected through a memristive synapse that show how the CMOS plasticity circuits can induce stable changes in memristor conductances, giving rise to increased synaptic strength after a potentiation episode and to decreased strength after a depression episode. PMID:26483629
Implementation of a spike-based perceptron learning rule using TiO2?x memristors
Mostafa, Hesham; Khiat, Ali; Serb, Alexander; Mayr, Christian G.; Indiveri, Giacomo; Prodromakis, Themis
2015-01-01
Synaptic plasticity plays a crucial role in allowing neural networks to learn and adapt to various input environments. Neuromorphic systems need to implement plastic synapses to obtain basic “cognitive” capabilities such as learning. One promising and scalable approach for implementing neuromorphic synapses is to use nano-scale memristors as synaptic elements. In this paper we propose a hybrid CMOS-memristor system comprising CMOS neurons interconnected through TiO2?x memristors, and spike-based learning circuits that modulate the conductance of the memristive synapse elements according to a spike-based Perceptron plasticity rule. We highlight a number of advantages for using this spike-based plasticity rule as compared to other forms of spike timing dependent plasticity (STDP) rules. We provide experimental proof-of-concept results with two silicon neurons connected through a memristive synapse that show how the CMOS plasticity circuits can induce stable changes in memristor conductances, giving rise to increased synaptic strength after a potentiation episode and to decreased strength after a depression episode. PMID:26483629
Scientific Electronic Library Online (English)
Jesús D., Villalba; Ivan D., Gómez; José E., Laier.
2012-06-01
Full Text Available En este trabajo se presenta una red neuronal perceptron multicapa combinada con el método Nelder-Mead Simplex para detectar daño en vigas. Los parámetros de entrada a la red se basan en frecuencias naturales y flexibilidad modal. Se considera que solo una cantidad específica de modos fueron identifi [...] cados y que se dispone de mediciones en grados de libertad verticales. La confiabilidad de la metodología propuesta se evalúa a partir de escenarios de daño aleatorios y de la definición de 3 tipos de error que la red puede cometer durante el proceso de detección del daño. Los resultados muestran que la metodología puede determinar confiablemente los escenarios de daño buscados. Sin embargo, su aplicación a vigas de gran tamaño puede verse limitada por el elevado costo computacional asociado al entrenamiento de la red. Abstract in english In this paper is presented a multilayer perceptron neural network combined with the Nelder-Mead Simplex method to detect damage in multiple support beams. The input parameters are based on natural frequencies and modal flexibility. It was considered that only a number of modes were available and tha [...] t only vertical degrees of freedom were measured. The reliability of the proposed methodology is assessed from the generation of random damages scenarios and the definition of three types of errors, which can be found during the damage identification process. Results show that the methodology can reliably determine the damage scenarios. However, its application to large beams may be limited by the high computational cost of training the neural network.
Braga, C C
2001-01-01
A neural network structure has been used for unfolding neutron spectra measured by means of a Bonner Sphere Spectrometer set and a foil activation set using several neutron induced reactions. The present work used the SNNS (Stuttgart Neural Network Simulator) as the interface for designing, training and validation of the Multilayer Perceptron network. The back-propagation algorithm was applied. The Bonner Sphere set chosen has been calibrated at the National Physical Laboratory, United Kingdom, and uses gold activation foils as thermal neutron detectors. The neutron energy covered by the response functions goes from 0.0001 eV to 14 MeV. The foil activation set chosen has been irradiated at the IEA-R1 research reactor and measured at the Nuclear Metrology Laboratory of IPEN-CNEN/SP. Two types of neutron spectra were numerically investigated: monoenergetic and continuous The unfolded spectra were compared to a conventional method using code SAND-II as part of the neutron dosimetry system SAIPS. Good results wer...
Rai, H. M.; Trivedi, A.; Chatterjee, K.; Shukla, S.
2014-01-01
This paper employed the Daubechies wavelet transform (WT) for R-peak detection and radial basis function neural network (RBFNN) to classify the electrocardiogram (ECG) signals. Five types of ECG beats: normal beat, paced beat, left bundle branch block (LBBB) beat, right bundle branch block (RBBB) beat and premature ventricular contraction (PVC) were classified. 500 QRS complexes were arbitrarily extracted from 26 records in Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database, which are available on Physionet website. Each and every QRS complex was represented by 21 points from p1 to p21 and these QRS complexes of each record were categorized according to types of beats. The system performance was computed using four types of parameter evaluation metrics: sensitivity, positive predictivity, specificity and classification error rate. The experimental result shows that the average values of sensitivity, positive predictivity, specificity and classification error rate are 99.8%, 99.60%, 99.90% and 0.12%, respectively with RBFNN classifier. The overall accuracy achieved for back propagation neural network (BPNN), multilayered perceptron (MLP), support vector machine (SVM) and RBFNN classifiers are 97.2%, 98.8%, 99% and 99.6%, respectively. The accuracy levels and processing time of RBFNN is higher than or comparable with BPNN, MLP and SVM classifiers.
Directory of Open Access Journals (Sweden)
M. Aquilino
2014-01-01
The historical archive of LANDSAT imagery dating back to the launch of ERTS in 1972 provides a comprehensive and permanent data source for tracking change on the planet?s land surface. In this study case the imagery acquisition dates of 1987, 2002 and 2011 were selected to cover a time trend of 24 years. Land cover categories were based on classes outlined by the Curve Number method with the aim of characterizing land use according to the level of surface imperviousness. After comparing two land use classification methods, i.e. Maximum Likelihood Classifier (MLC and Multi-Layer Perceptron (MLP neural network, the Artificial Neural Networks (ANN approach was found the best reliable and efficient method in the absence of ground reference data. The ANN approach has a distinct advantage over statistical classification methods in that it is non-parametric and requires little or no a priori knowledge on the distribution model of input data. The results quantify land cover change patterns in the river basin area under study and demonstrate the potential of multitemporal LANDSAT data to provide an accurate and cost-effective means to map and analyse land cover changes over time that can be used as input in land management and policy decision-making.
Scientific Electronic Library Online (English)
Sandra P, Mateus; Natalia, González; John W, Branch.
Full Text Available En este trabajo se presenta la creación de dos Entornos Virtuales Inteligentes (EVI) con Redes Neuronales Artificiales (RNA). En un EVI se realiza el diagnóstico de problemas visuales como astigmatismo, miopía e hipermetropía. El otro se enfoca, en la percepción y el razonamiento de señales de adver [...] tencia en un entorno laboral. En el desarrollo del trabajo, se hace primero una caracterización de las Redes Neuronales Artificiales y luego se hace una simulación de ellas; de acuerdo a los resultados obtenidos, se selecciona una arquitectura de red (Perceptrón Multicapa) y ésa es la que se implementa en los EVI. Finalmente se abordan las limitantes del tiempo en el aprendizaje de la RNA y en el costo computacional aplicados a los EVI. Abstract in english In this paper, the creation and application of two Intelligent Virtual Environments (IVE) with Artificial Neural Networks (ANN) are presented. In one EVI, the diagnosis of vision problems like astigmatism, myopia and hyperopia is studied. The other one focuses to the perception and reasoning of warn [...] ing signals in a work environment. For the development of this paper, the characterization of Artificial Neural Networks is done, followed by the simulation; according to the results one network architecture is selected (Multilayer Perceptron) and then implemented in the IVE. Finally the time constraints in ANN learning and in computational cost applied to IVE are discussed.
Scientific Electronic Library Online (English)
Rodrigo Mikosz, Gonçalves; Leandro dos Santos, Coelho; Claudia Pereira, Krueger; Bernhard, Heck.
2010-09-01
Full Text Available Estudar modelagens através de dados geodésicos temporais com a possibilidade de predizer a posição de linha de costa é uma tarefa importante e pode auxiliar significativamente na gestão costeira. A área de estudo neste trabalho se refere ao município de Matinhos no estado do Paraná, Brasil. As linha [...] s de costa temporais utilizadas para testar a modelagem preditiva são provenientes respectivamente da fotogrametria analógica para anos 1954, 1963, 1980, 1991 e 1997 e de levantamentos geodésicos utilizando GPS (Global Position System) para 2001, 2002, 2005 e 2008 (como controle). Dois testes com as redes neurais artificiais foram organizados mudando alguns parâmetros como: arquitetura, número de neurônios nas camadas ocultas e algoritmos de treinamentos. Quando comparados o valor dos resíduos entre a predição e a linha de costa de controle, os melhores resultados estatísticos indicam que o MAPE (mean absolute percentage error) são 0,28% utilizando a rede neural parcialmente recorrente de Elman com o algoritmo de treinamento quase-Newton e 0,46% para o caso da rede neural perceptron multicamadas com o algoritmo de treinamento utilizando o método Bayesiano com regularização. Abstract in english The study of models using geodetic temporal data which can possibly predict the shoreline position is an important task and can significantly contribute to coastal management. The studied area is located at municipality of Matinhos in the Paraná State, Brazil. The temporal shoreline used to test the [...] prediction model is respectively from analog photogrammetric data, related to the years 1954, 1963, 1980, 1991 and 1997, and GPS (Global Position System) geodetic surveys for 2001, 2002, 2005 and 2008 (as control). Two different tests with artificial neural network were organized setting the parameters like: architecture, number of neuron in hidden layers and the training algorithms. Comparing the residuals between the prediction to the shoreline of control, the best statistical results show the MAPE (Mean Absolute Percentage Error) is 0,28% using the Elman partially recurrent network with quasi-Newton training function and 0,46% using the neural network multilayer perceptron with Bayesian regulation training function.
Directory of Open Access Journals (Sweden)
Teodorico Alves Sobrinho
2011-06-01
Full Text Available A estimativa da evapotranspiração por métodos indiretos propicia, de modo facilitado, a geração de dados para o planejamento de sistemas de irrigação e aplicação de modelos meteorológicos e hidrológicos, ambos, úteis na gestão de bacias hidrográficas. O objetivo deste trabalho foi elaborar uma Rede Neural Artificial (RNA para estimar a evapotranspiração de referência (Eto em função de dados diários de temperatura do ar. A RNA, do tipo FeedForward Multilayer Perceptron, foi treinada tomando-se por referência a Eto diária obtida pelo método de Penman-Monteith. Nas camadas intermediárias e de saída foram utilizadas funções de ativação do tipo tan-sigmóide e lineares, respectivamente. Os valores de Eto gerados pela RNA foram comparados com os obtidos pelos métodos de Blanney-Criddle e Hargreaves considerando meses referentes às quatro estações do ano. Em relação aos outros métodos analisados, os resultados obtidos a partir da RNA foram mais próximos ao método padrão Penman-Monteith. Assim, o desempenho da RNA desenvolvida foi satisfatório, podendo-se considerá-la como integrante do conjunto de métodos indiretos para estimativa da evapotranspiração, além de representar uma diminuição dos custos de aquisição de dados para estimativa desta variável.The estimation of evapotranspiration by indirect methods provides synthetic data for planning irrigation systems and application on meteorological and hydrological models, both useful in watershed management. The objective of this study was to develop an Artificial Neural Network (ANN to estimate the reference evapotranspiration (Eto based on daily air temperature data. The ANN model of Feedforward Multilayer Perceptron type, was trained using as a reference the daily Eto obtained by the Penman-Monteith method. In the intermediate and output layers were used activation functions like tan-sigmoid and linear, respectively. Eto values generated by ANN were compared with those obtained by the methods of Blanney-Criddle and Hargreaves considering the months of the four seasons. Comparing to the other analyzed methods, the results obtained from the ANN were closer to the standard Penman-Monteith method. Thus, the performance of the developed ANN was satisfactory, and the ANN model can be considered as one indirect method for estimating evapotranspiration and allows a cost reduction on data acquisition to estimate this variable.
Scientific Electronic Library Online (English)
Teodorico, Alves Sobrinho; Dulce Buchala Bicca, Rodrigues; Paulo Tarso Sanches de, Oliveira; Lais Cristina Soares, Rebucci; Caroline Alvarenga, Pertussatti.
2011-06-01
Full Text Available A estimativa da evapotranspiração por métodos indiretos propicia, de modo facilitado, a geração de dados para o planejamento de sistemas de irrigação e aplicação de modelos meteorológicos e hidrológicos, ambos, úteis na gestão de bacias hidrográficas. O objetivo deste trabalho foi elaborar uma Rede [...] Neural Artificial (RNA) para estimar a evapotranspiração de referência (Eto) em função de dados diários de temperatura do ar. A RNA, do tipo FeedForward Multilayer Perceptron, foi treinada tomando-se por referência a Eto diária obtida pelo método de Penman-Monteith. Nas camadas intermediárias e de saída foram utilizadas funções de ativação do tipo tan-sigmóide e lineares, respectivamente. Os valores de Eto gerados pela RNA foram comparados com os obtidos pelos métodos de Blanney-Criddle e Hargreaves considerando meses referentes às quatro estações do ano. Em relação aos outros métodos analisados, os resultados obtidos a partir da RNA foram mais próximos ao método padrão Penman-Monteith. Assim, o desempenho da RNA desenvolvida foi satisfatório, podendo-se considerá-la como integrante do conjunto de métodos indiretos para estimativa da evapotranspiração, além de representar uma diminuição dos custos de aquisição de dados para estimativa desta variável. Abstract in english The estimation of evapotranspiration by indirect methods provides synthetic data for planning irrigation systems and application on meteorological and hydrological models, both useful in watershed management. The objective of this study was to develop an Artificial Neural Network (ANN) to estimate t [...] he reference evapotranspiration (Eto) based on daily air temperature data. The ANN model of Feedforward Multilayer Perceptron type, was trained using as a reference the daily Eto obtained by the Penman-Monteith method. In the intermediate and output layers were used activation functions like tan-sigmoid and linear, respectively. Eto values generated by ANN were compared with those obtained by the methods of Blanney-Criddle and Hargreaves considering the months of the four seasons. Comparing to the other analyzed methods, the results obtained from the ANN were closer to the standard Penman-Monteith method. Thus, the performance of the developed ANN was satisfactory, and the ANN model can be considered as one indirect method for estimating evapotranspiration and allows a cost reduction on data acquisition to estimate this variable.
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.
Land, Walker H., Jr.; Masters, Timothy D.; Lo, Joseph Y.; McKee, Dan
2001-07-01
A new neural network technology was developed for improving the benign/malignant diagnosis of breast cancer using mammogram findings. A new paradigm, Adaptive Boosting (AB), uses a markedly different theory in solutioning Computational Intelligence (CI) problems. AB, a new machine learning paradigm, focuses on finding weak learning algorithm(s) that initially need to provide slightly better than random performance (i.e., approximately 55%) when processing a mammogram training set. Then, by successive development of additional architectures (using the mammogram training set), the adaptive boosting process improves the performance of the basic Evolutionary Programming derived neural network architectures. The results of these several EP-derived hybrid architectures are then intelligently combined and tested using a similar validation mammogram data set. Optimization focused on improving specificity and positive predictive value at very high sensitivities, where an analysis of the performance of the hybrid would be most meaningful. Using the DUKE mammogram database of 500 biopsy proven samples, on average this hybrid was able to achieve (under statistical 5-fold cross-validation) a specificity of 48.3% and a positive predictive value (PPV) of 51.8% while maintaining 100% sensitivity. At 97% sensitivity, a specificity of 56.6% and a PPV of 55.8% were obtained.
Prediction of Rainfall in India using Artificial Neural Network (ANN) Models
Santosh Kumar Nanda; Debi Prasad Tripathy; Simanta Kumar Nayak; Subhasis Mohapatra
2013-01-01
In this paper, ARIMA(1,1,1) model and Artificial Neural Network (ANN) models like Multi Layer Perceptron (MLP), Functional-link Artificial Neural Network (FLANN) and Legendre Polynomial Equation ( LPE) were used to predict the time series data. MLP, FLANN and LPE gave very accurate results for complex time series model. All the Artificial Neural Network model results matched closely with the ARIMA(1,1,1) model with minimum Absolute Average Percentage Error(AAPE). Comparing the different ANN ...
Intellect Sensing of Neural Network that Trained to Classify Complex Signals
Reznik, A.; Galinskaya, A.
2003-01-01
An experimental comparison of information features used by neural network is performed. The sensing method was used. Suboptimal classifier agreeable to the gaussian model of the training data was used as a probe. Neural nets with architectures of perceptron and feedforward net with one hidden layer were used. The experiments were carried out with spatial ultrasonic data, which are used for car’s passenger safety system neural controller learning. In this paper we show that a n...
Lu, W Z; Wang, W J; Wang, X K; Xu, Z B; Leung, A Y T
2003-09-01
As the health impact of air pollutants existing in ambient addresses much attention in recent years, forecasting of air pollutant parameters becomes an important and popular topic in environmental science. Airborne pollution is a serious, and will be a major problem in Hong Kong within the next few years. In Hong Kong, Respirable Suspended Particulate (RSP) and Nitrogen Oxides NOx and NO2 are major air pollutants due to the dominant diesel fuel usage by public transportation and heavy vehicles. Hence, the investigation and prediction of the influence and the tendency of these pollutants are of significance to public and the city image. The multi-layer perceptron (MLP) neural network is regarded as a reliable and cost-effective method to achieve such tasks. The works presented here involve developing an improved neural network model, which combines the principal component analysis (PCA) technique and the radial basis function (RBF) network, and forecasting the pollutant levels and tendencies based in the recorded data. In the study, the PCA is firstly used to reduce and orthogonalize the original input variables (data), these treated variables are then used as new input vectors in RBF neural network model established for forecasting the pollutant tendencies. Comparing with the general neural network models, the proposed model possesses simpler network architecture, faster training speed, and more satisfactory predicting performance. This improved model is evaluated by using hourly time series of RSP, NOx and NO2 concentrations collected at Mong Kok Roadside Gaseous Monitory Station in Hong Kong during the year 2000. By comparing the predicted RSP. NOx and NO2 concentrations with the actual data of these pollutants recorded at the monitory station, the effectiveness of the proposed model has been proven. Therefore, in authors' opinion, the model presented in the paper is a potential tool in forecasting air quality parameters and has advantages over the traditional neural network methods. PMID:12952354
Modeling of Soft sensor based on Artificial Neural Network for Galactic Cosmic Rays Application
International Nuclear Information System (INIS)
For successful designing of space radiation Galactic Cosmic Rays (GCRs) model, we develop a soft sensor based on the Artificial Neural Network (ANN) model. At the first step, the soft sensor based ANN was constructed as an alternative to model space radiation environment. The structure of ANN in this model is using Multilayer Perceptron (MLP) and Levenberg Marquardt algorithms with 3 inputs and 2 outputs. In the input variable, we use 12 years data (Corr, Uncorr and Press) of GCR particles obtained from Neutron Monitor of Bartol University (Fort Smith area) and the target output is (Corr and Press) from the same source but for Inuvik area in the Polar Regions. In the validation step, we obtained the Root Mean Square Error (RMSE) value of Corr 3.8670e-004 and Press 1.3414e-004 and Variance Accounted For (VAF) of Corr 99.9839 % and Press 99.9831% during the training section. After all the results obtained, then we applied into a Matlab GUI simulation (soft sensor simulation). This simulation will display the estimation of output value from input (Corr and Press). Testing results showed an error of 0.133% and 0.014% for Corr and Press, respectively
Greek long-term energy consumption prediction using artificial neural networks
International Nuclear Information System (INIS)
In this paper artificial neural networks (ANN) are addressed in order the Greek long-term energy consumption to be predicted. The multilayer perceptron model (MLP) has been used for this purpose by testing several possible architectures in order to be selected the one with the best generalizing ability. Actual recorded input and output data that influence long-term energy consumption were used in the training, validation and testing process. The developed ANN model is used for the prediction of 2005-2008, 2010, 2012 and 2015 Greek energy consumption. The produced ANN results for years 2005-2008 were compared with the results produced by a linear regression method, a support vector machine method and with real energy consumption records showing a great accuracy. The proposed approach can be useful in the effective implementation of energy policies, since accurate predictions of energy consumption affect the capital investment, the environmental quality, the revenue analysis, the market research management, while conserve at the same time the supply security. Furthermore it constitutes an accurate tool for the Greek long-term energy consumption prediction problem, which up today has not been faced effectively.
An Efficient Weather Forecasting System using a Hybrid Neural Network SOFM–MLP
Directory of Open Access Journals (Sweden)
I.Kadar Shereef
2010-12-01
Full Text Available Weather prediction is a challenging task for researchers and has drawn a lot of research interest in the recent years. Literature studies have shown that machine learning techniques achieved better performance than traditional statistical methods. Presently multilayer perceptron networks (MLPs are used for prediction of the maximum and the minimum temperatures based on past observations on various atmospheric parameters. To capture the seasonality of atmospheric data, with a view to improving the prediction accuracy, a novel weather forecasting system is presented in this paper. The proposed system is based on a neural architecture that combines a selforganizing feature map (SOFM and MLPs to realize a hybrid network named SOFM–MLP. It is also demonstrated that the use of appropriate features such as temperature gradient can not only reduce the number of features drastically, but also can improve the prediction accuracy. These observations motivated us to use a feature selection MLP (FSMLP instead of MLP, which can select good features online while learning the prediction task. FSMLP is used as a preprocessor to select good features. The combined use of FSMLP and SOFM–MLP provides better result in a network system that uses only very few inputs but can produce good prediction. The proposed system is experimented using the real time data observations and from which it is found that the proposed system predict the temperature with minimum error.
Aspects of artificial neural networks - with applications in high energy physics
International Nuclear Information System (INIS)
Different aspects of artificial neural networks are studied and discussed. They are demonstrated to be powerful general purpose algorithms, applicable to many different problem areas like pattern recognition, function fitting and prediction. Multi-layer perceptron (MPL) models are shown to out perform previous standard approaches on both off-line and on-line analysis tasks in high energy physics, like quark flavour tagging and mass reconstruction, as well as being powerful tools for prediction tasks. It is also demonstrated how a self-organizing network can be employed to extract information from data, for instance to track down origins of unexpected model discrepancies. Furthermore, it is proved that the MPL is more efficient than the learning vector quantization technique on classification problems, by producing smoother discrimination surfaces, and that an MPL network should be trained with a noisy updating schedule if the Hessian is ill-conditioned - A result that is especially important for MPL network with more than just one hidden layer. 81 refs, 6 figs
{\\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
Auld, T; Hobson, M P
2007-01-01
We present a further development of a method for accelerating the calculation of CMB power spectra, matter power spectra and likelihood functions for use in cosmological Bayesian inference. The algorithm, called {\\sc CosmoNet}, is based on training a multilayer perceptron neural network. We compute CMB power spectra (up to $\\ell=2000$) and matter transfer functions over a hypercube in parameter space encompassing the $4\\sigma$ confidence region of a selection of CMB (WMAP + high resolution experiments) and large scale structure surveys (2dF and SDSS). We work in the framework of a generic 7 parameter non-flat cosmology. Additionally we use {\\sc CosmoNet} to compute the WMAP 3-year, 2dF and SDSS likelihoods over the same region. We find that the average error in the power spectra is typically well below cosmic variance for spectra, and experimental likelihoods calculated to within a fraction of a log unit. We demonstrate that marginalised posteriors generated with {\\sc CosmoNet} spectra agree to within a few p...
Improving Neural Network Prediction Accuracy for PM10 Individual Air Quality Index Pollution Levels.
Feng, Qi; Wu, Shengjun; Du, Yun; Xue, Huaiping; Xiao, Fei; Ban, Xuan; Li, Xiaodong
2013-12-01
Fugitive dust deriving from construction sites is a serious local source of particulate matter (PM) that leads to air pollution in cities undergoing rapid urbanization in China. In spite of this fact, no study has yet been published relating to prediction of high levels of PM with diameters neural network models (multilayer perceptron, Elman, and support vector machine) in predicting daily PM10 IAQI one day in advance. To obtain acceptable forecasting accuracy, measured time series data were decomposed into wavelet representations and wavelet coefficients were predicted. Effectiveness of these forecasters were tested using a time series recorded between January 1, 2005, and December 31, 2011, at six monitoring stations situated within the urban area of the city of Wuhan, China. Experimental trials showed that the improved models provided low root mean square error values and mean absolute error values in comparison to the original models. In addition, these improved models resulted in higher values of coefficients of determination and AHPC (the accuracy rate of high PM10 IAQI caused by nearby construction activity) compared to the original models when predicting high PM10 IAQI levels attributable to fugitive dust from nearby construction sites. PMID:24381481
Determining the appropriate amount of anesthetic gas using DWT and EMD combined with neural network.
Co?kun, Mustafa; Gürüler, Hüseyin; Istanbullu, Ayhan; Peker, Musa
2015-01-01
The spectrum of EEG has been studied to predict the depth of anesthesia using variety of signal processing methods up to date. Those standard models have used the full spectrum of EEG signals together with the systolic-diastolic pressure and pulse values. As it is generally agreed today that the brain is in stable state and the delta-theta bands of the EEG spectrum remain active during anesthesia. Considering this background, two questions that motivates this paper. First, determining the amount of gas to be administered is whether feasable from the spectrum of EEG during the maintenance stage of surgical operations. Second, more specifically, the delta-theta bands of the EEG spectrum are whether sufficient alone for this aim. This research aims to answer these two questions together. Discrete wavelet transformation (DWT) and empirical mode decomposition (EMD) were applied to the EEG signals to extract delta-theta bands. The power density spectrum (PSD) values of target bands were presented as inputs to multi-layer perceptron (MLP) neural network (NN), which predicted the gas level. The present study has practical implications in terms of using less data, in an effective way and also saves time as well. PMID:25472730
Artificial Neural Network Based Equation to Estimate Head Loss Along Drip Irrigation Laterals
Directory of Open Access Journals (Sweden)
Acácio Perboni
2014-04-01
Full Text Available This work proposes an equation based on Artificial Neural Network (ANN to estimate head loss along emitting pipes accounting for cylindrical in-line emitters. The following input variables were used to fit the model: total head loss between two consecutive emitters; emitter spacing; internal diameter of the pipe; mean water velocity at uniform pipe sections; and, kinematic viscosity of water. The input data was obtained by experimental means and standardized from 0 to 1. Five replications and six distinct structures of ANNs multilayer perceptron (MLP were used during the training stage performed using the package neuralnet of the software R. A MLP structure consisting of six neurons at input layer, six neurons at hidden layer, and one neuron at output layer was applied for fitting the model. Estimated values by the ANN’s equation were compared to the estimated values by an equation based on dimensional analysis. The ANN’s equation and the equation based on dimensional analysis presented maximum deviations between measured and estimated values of 0.324 kPa and 1.647 kPa, respectively. Therefore the ANN’s equation presented better results than the equation based on dimensional analysis.
Scientific Electronic Library Online (English)
Olanrewaju A, Oludolapo; Adisa A, Jimoh; Pule A, Kholopane.
Full Text Available In view of the close association between energy and economic growth, South Africa's aspirations for higher growth, more energy is required; formulating a long-term economic development plan and implementing an energy strategy for a country /industry necessitates establishing the correct relationship [...] between energy and the economy. As insufficient energy or a lack thereof is reported to be a major cause of social and economic poverty, it is very important to select a model to forecast the consumption of energy reasonably accurately. This study presents techniques based on the development of multilayer perceptron (MLP) and radial basis function (RBF) of artificial neural network (ANN) models, for calculating the energy consumption of South Africa's industrial sector between 1993 and 2000. The approach examines the energy consumption in relation to the gross domestic product. The results indicate a strong agreement between model predictions and observed values, since the mean absolute percentage error is below 5%. When performance indices are compared, the RBF-based model is a more accurate predictor than the MLP model.
Artificial Neural Network applied as a methodology of mosquito species identification.
Lorenz, Camila; Ferraudo, Antonio Sergio; Suesdek, Lincoln
2015-12-01
There are about 200 species of mosquitoes (Culicidae) known to be vectors of pathogens that cause diseases in humans. Correct identification of mosquito species is an essential step in the development of effective control strategies for these diseases; recognizing the vectors of pathogens is integral to understanding transmission. Unfortunately, taxonomic identification of mosquitoes is a laborious task, which requires trained experts, and it is jeopardized by the high variability of morphological and molecular characters found within the Culicidae family. In this context, the development of an automatized species identification method would be a valuable and more accessible resource to non-taxonomist and health professionals. In this work, an artificial neural network (ANN) technique was proposed for the identification and classification of 17 species of the genera Anopheles, Aedes, and Culex, based on wing shape characters. We tested the hypothesis that classification using ANN is better than traditional classification by discriminant analysis (DA). Thirty-two wing shape principal components were used as input to a Multilayer Perceptron Classification ANN. The obtained ANN correctly identified species with accuracy rates ranging from 85.70% to 100%, and classified species more efficiently than did the traditional method of multivariate discriminant analysis. The results highlight the power of ANNs to diagnose mosquito species and to partly automatize taxonomic identification. These findings also support the hypothesis that wing venation patterns are species-specific, and thus should be included in taxonomic keys. PMID:26394186
Spatial Disaggregation of Areal Rainfall Using Two Different Artificial Neural Networks Models
Directory of Open Access Journals (Sweden)
Sungwon Kim
2015-06-01
Full Text Available The objective of this study is to develop artificial neural network (ANN models, including multilayer perceptron (MLP and Kohonen self-organizing feature map (KSOFM, for spatial disaggregation of areal rainfall in the Wi-stream catchment, an International Hydrological Program (IHP representative catchment, in South Korea. A three-layer MLP model, using three training algorithms, was used to estimate areal rainfall. The Levenberg–Marquardt training algorithm was found to be more sensitive to the number of hidden nodes than were the conjugate gradient and quickprop training algorithms using the MLP model. Results showed that the networks structures of 11-5-1 (conjugate gradient and quickprop and 11-3-1 (Levenberg-Marquardt were the best for estimating areal rainfall using the MLP model. The networks structures of 1-5-11 (conjugate gradient and quickprop and 1-3-11 (Levenberg–Marquardt, which are the inverse networks for estimating areal rainfall using the best MLP model, were identified for spatial disaggregation of areal rainfall using the MLP model. The KSOFM model was compared with the MLP model for spatial disaggregation of areal rainfall. The MLP and KSOFM models could disaggregate areal rainfall into individual point rainfall with spatial concepts.
Artificial neural networks for analysis of process states in fluidized bed combustion
Energy Technology Data Exchange (ETDEWEB)
Liukkonen, M.; Heikkinen, M.; Hiltunen, T.; Halikka, E.; Kuivalainen, R.; Hiltunen, Y. [University of Eastern Finland, Kuopio (Finland). Dept. of Environmental Science
2011-01-15
There are several challenges confronting energy production nowadays, such as increasing the efficiency of combustion processes and at the same time reducing harmful emissions. The latter, however, often necessitates process improvement, which requires knowledge of the behavior of the process. It is therefore important to develop and implement novel methods for process diagnostics that can respond to the challenges of modern-day energy plants. In this study the formation of nitrogen oxides (NOx) in a circulating fluidized bed (CFB) boiler is modeled by using artificial neural networks (ANN). In the approach used, the process data are first arranged using self-organizing maps (SOM) and k-means clustering to create subsets representing the separate process states in the boiler, including load increase and load decrease situations and conditions of high or low boiler load. After the determination of these process states, variable selection based on multilayer perceptrons (MLP) is performed to obtain information on the factors affecting the formation of NOx in those states. The results show that this approach provides a useful way of monitoring a combustion process.
/ Artificial neural networks (ANN): prediction of sensory measurements from instrumental data
Scientific Electronic Library Online (English)
Naiara Barbosa, Carvalho; Valéria Paula Rodrigues, Minim; Rita de Cássia dos Santos Navarro, Silva; Suzana Maria, Della Lucia; Luis Aantonio, Minim.
2013-12-01
Full Text Available [...] Abstract in english The objective of this study was to predict by means of Artificial Neural Network (ANN), multilayer perceptrons, the texture attributes of light cheesecurds perceived by trained judges based on instrumental texture measurements. Inputs to the network were the instrumental texture measurements of ligh [...] t cheesecurd (imitative and fundamental parameters). Output variables were the sensory attributes consistency and spreadability. Nine light cheesecurd formulations composed of different combinations of fat and water were evaluated. The measurements obtained by the instrumental and sensory analyses of these formulations constituted the data set used for training and validation of the network. Network training was performed using a back-propagation algorithm. The network architecture selected was composed of 8-3-9-2 neurons in its layers, which quickly and accurately predicted the sensory texture attributes studied, showing a high correlation between the predicted and experimental values for the validation data set and excellent generalization ability, with a validation RMSE of 0.0506.
NEURAL NETWORKS FOR THE SIMULATION OF MICROCLIMATIC PARAMETERS IN DAIRY HOUSES
Directory of Open Access Journals (Sweden)
Alessandro D'Emilio
2009-06-01
Full Text Available The aim of the present paper is to study natural ventilation in a dairy house by means of a parametric analysis relating wind speed and direction to the air flows through the ridge vent of the building. This analysis was carried out by means of an artificial neural network (ANN which capability in modelling and simulating some climatic parameters inside a dairy house has been validated using the data collected in a trial carried out during summer 2005. The results show that modelling a Generalized feed-forward Multi-Layer Perceptron ANN allowed to obtain satisfactory results in the simulation of air speed and direction and air temperature and humidity inside a dairy house, using as input the values of wind speed and direction and outdoor air temperature and humidity. The adequate accuracy in the simulation of the air motion across the ridge vent allowed to perform a parametric analysis of the ventilation, which provided the values of air speed and direction in function of a fixed range of values of wind speed and direction.
Use of artificial neural networks and geographic objects for classifying remote sensing imagery
Directory of Open Access Journals (Sweden)
Pedro Resende Silva
2014-06-01
Full Text Available The aim of this study was to develop a methodology for mapping land use and land cover in the northern region of Minas Gerais state, where, in addition to agricultural land, the landscape is dominated by native cerrado, deciduous forests, and extensive areas of vereda. Using forest inventory data, as well as RapidEye, Landsat TM and MODIS imagery, three specific objectives were defined: 1 to test use of image segmentation techniques for an object-based classification encompassing spectral, spatial and temporal information, 2 to test use of high spatial resolution RapidEye imagery combined with Landsat TM time series imagery for capturing the effects of seasonality, and 3 to classify data using Artificial Neural Networks. Using MODIS time series and forest inventory data, time signatures were extracted from the dominant vegetation formations, enabling selection of the best periods of the year to be represented in the classification process. Objects created with the segmentation of RapidEye images, along with the Landsat TM time series images, were classified by ten different Multilayer Perceptron network architectures. Results showed that the methodology in question meets both the purposes of this study and the characteristics of the local plant life. With excellent accuracy values for native classes, the study showed the importance of a well-structured database for classification and the importance of suitable image segmentation to meet specific purposes.
Comparative Study of Artificial Neural Network and ARIMA Models in Predicting Exchange Rate
Directory of Open Access Journals (Sweden)
karamollah Bagherifard
2012-11-01
Full Text Available Capital market as an organized market has an effective role in mobilizing financial resources due to have growth and economic development of countries and many countries now in the finance firms is responsible for the required credits. In the stock market, shareholders are always seeking the highest efficiency, so the stock price prediction is important for them. Since the stock market is a nonlinear system under conditions of political, economic and psychological, it is difficult to predict the correct stock price. Thus, in the present study artificial intelligence and ARIMA method has been used to predict stock prices. Multilayer Perceptron neural network and radial basis functions are two methods used in this research. Evaluation methods, selection methods and exponential smoothing methods are compared to random walk. The results showed that AI-based methods used in predicting stock performance are more accurate. Between two methods used in artificial intelligence, a method based on radial basis functions is capable to estimate stock prices in the future with higher accuracy.
International Nuclear Information System (INIS)
A new analysis technique, called multi-level interval estimation method, is developed for locating damage in structures. In this method, the artificial neural networks (ANN) analysis method is combined with the statistics theory to estimate the range of damage location. The ANN is multilayer perceptron trained by back-propagation. Natural frequencies and modal shape at a few selected points are used as input to identify the location and severity of damage. Considering the large-scale structures which have lots of elements, multi-level interval estimation method is developed to reduce the estimation range of damage location step-by-step. Every step, estimation range of damage location is obtained from the output of ANN by using the method of interval estimation. The next ANN training cases are selected from the estimation range after linear transform, and the output of new ANN estimation range of damage location will gained a reduced estimation range. Two numerical example analyses on 10-bar truss and 100-bar truss are presented to demonstrate the effectiveness of the proposed method.
Determination of number of check dams by artificial neural networks in arid regions of Iran.
Hashemi, Seyed Ali Asghar; Kashi, Hamed
2015-09-01
An artificial neural network (ANN) model with six hydrological factors including time of concentration (TC), curve number, slope, imperviousness, area and input discharge as input parameters and number of check dams (NCD) as output parameters was developed and created using GIS and field surveys. The performance of this model was assessed by the coefficient of determination R(2), root mean square error (RMSE), values account and mean absolute error (MAE). The results showed that the computed values of NCD using ANN with a multi-layer perceptron (MLP) model regarding RMSE, MAE, values adjustment factor (VAF), and R(2) (1.75, 1.25, 90.74, and 0.97) for training, (1.34, 0.89, 97.52, and 0.99) for validation and (0.53, 0.8, 98.32, and 0.99) for test stage, respectively, were in close agreement with their respective values in the watershed. Finally, the sensitivity analysis showed that the area, TC and curve number were the most effective parameters in estimating the number of check dams. PMID:26360755
Czech Academy of Sciences Publication Activity Database
Šíma, Ji?í
1995-01-01
Ro?. 8, ?. 2 (1995), s. 261-271. ISSN 0893-6080 R&D Projects: GA ?R GA201/95/0976 Keywords : expert system * knowledge representation * multilayered neural network * back propagation * interval neuron function * incomplete information * explanation Impact factor: 1.262, year: 1995
On-line learning of non-monotonic rules by simple perceptron
Inoue, J; Kabashima, Yoshiyuki; Inoue, Jun-ichi; Nishimori, Hidetoshi; Kabashima, Yoshiyuki
1997-01-01
We study the generalization ability of a simple perceptron which learns unlearnable rules. The rules are presented by a teacher perceptron with a non-monotonic transfer function. The student is trained in the on-line mode. The asymptotic behaviour of the generalization error is estimated under various conditions. Several learning strategies are proposed and improved to obtain the theoretical lower bound of the generalization error.
Using Probabilistic Neural Networks for Handwritten Digit Recognition
Abdelkader Benyettou; Abdelhadi Lotfi
2011-01-01
Artificial neural networks are well known in the field of pattern recognition and machine learning. Multi-layer neural networks are usually used as universal neural classifiers even though probabilistic neural networks represent a special type of artificial neural networks and have been designed to be used mainly in classification problems. In this article a study has been conducted to train a probabilistic neural network to recognize handwritten digits taken from the MINST database for handw...
Directory of Open Access Journals (Sweden)
Rajesh Rai
2010-11-01
Full Text Available In this paper, an attempt is made to apply the principles of artificial neural networks (ANN towards developing a prediction model for surface roughness during the machining of high chromium steel through face milling process. Now a days, hot chromium steel is prominently used in die and mould industry as well as in press tools, helicopter rotor blades, etc... Initially, Taguchi design of experiments was applied while conducting the experiments to reduce the time and cost of experiment. Multilayer perceptron (MLP network using Feed Forward Error Back propagation was chosen as the Neural Network architecture to describe the process model. The experiments were conducted on a C.N.C milling machine using carbide cutters. Pearson correlation coefficient was also calculated to analyze the correlation between the system inputs and selected system output i.e. surface roughness. The results of ANN modeling were substantiated by testing and validation of the resulting surface roughness values and the results have been encouraging. The outputs of Pearson correlation coefficient also showed a strong correlation between the feed per tooth and surface roughness, followed by cutting speed.
Cámara, Montaña; Torrecilla, José S; Caceres, Jorge O; Sánchez Mata, M Cortes; Fernández-Ruiz, Virginia
2010-01-13
In this study a neural network (NN) model was designed to predict lycopene and beta-carotene concentrations in food samples, combined with a simple and fast technique, such as UV-vis spectroscopy. The measurement of the absorbance at 446 and 502 nm of different beta-carotene and lycopene standard mixtures was used to optimize a neural network based on a multilayer perceptron (MLP) (learning and verification process). Then, for validation purposes, the optimized NN has been applied to determine the concentration of both compounds in food samples (fresh tomato, tomato concentrate, tomato sauce, ketchup, tomato juice, watermelon, medlar, green pepper, and carrots), comparing the NN results with the known values of these compounds obtained by analytical techniques (UV-vis and HPLC). It was concluded that when the MLP-NN is used within the range studied, the optimized NN is able to estimate the beta-carotene and lycopene concentrations in food samples with an adequate accuracy, solving the UV-vis interference of beta-carotene and lycopene. PMID:19919099
Hosseini-Golgoo, S. M.; Bozorgi, H.; Saberkari, A.
2015-06-01
Performances of three neural networks, consisting of a multi-layer perceptron, a radial basis function, and a neuro-fuzzy network with local linear model tree training algorithm, in modeling and extracting discriminative features from the response patterns of a temperature-modulated resistive gas sensor are quantitatively compared. For response pattern recording, a voltage staircase containing five steps each with a 20?s plateau is applied to the micro-heater of the sensor, when 12 different target gases, each at 11 concentration levels, are present. In each test, the hidden layer neuron weights are taken as the discriminatory feature vector of the target gas. These vectors are then mapped to a 3D feature space using linear discriminant analysis. The discriminative information content of the feature vectors are determined by the calculation of the Fisher’s discriminant ratio, affording quantitative comparison among the success rates achieved by the different neural network structures. The results demonstrate a superior discrimination ratio for features extracted from local linear neuro-fuzzy and radial-basis-function networks with recognition rates of 96.27% and 90.74%, respectively.
Scientific Electronic Library Online (English)
Hamid Reza, Tavakoli; Omid Lotfi, Omran; Saman Soleimani, Kutanaei; Masoud Falahtabar, shiade.
2014-11-01
Full Text Available The main objective of the present work is to utilize feedforward multi-layer perceptron (MLP) type of artificial neural networks (ANN) to find the combined effect of nano-silica and different fibers (steel, polypropylene, glass) on the toughness, flexural strength and fracture energy of concrete is [...] evaluated.For this purpose, 40 mix plot including 4 series A and B and C and D, which contain, respectively, 0, 2, 4 and 6% weight of cement, nano-silica particles were used as a substitute for cement. Each of series includes three types of fibers (metal: 0.2, 0.3 and 0.5% volume and polypropylene: 0.1, 0.15 and 0.2 % volume and glass 0.15 and 0.2 and 0.3% by volume) were tested. The obtained results from the experimental data are used to train the MLP type artificial neural network. The Results of this study show that fibers conjugate presence and optimal percent of nano-silica improved toughness, flexural strength and fracture energy of concrete of Self-compacting concrete (SCC). Results of this study show that fibers conjugate presence and optimal per-cent of nano-silica improved toughness, toughness, fracture ener-gy and flexural strength of SCC.
Computationally efficient model predictive control algorithms a neural network approach
?awry?czuk, Maciej
2014-01-01
This book thoroughly discusses computationally efficient (suboptimal) Model Predictive Control (MPC) techniques based on neural models. The subjects treated include: · A few types of suboptimal MPC algorithms in which a linear approximation of the model or of the predicted trajectory is successively calculated on-line and used for prediction. · Implementation details of the MPC algorithms for feedforward perceptron neural models, neural Hammerstein models, neural Wiener models and state-space neural models. · The MPC algorithms based on neural multi-models (inspired by the idea of predictive control). · The MPC algorithms with neural approximation with no on-line linearization. · The MPC algorithms with guaranteed stability and robustness. · Cooperation between the MPC algorithms and set-point optimization. Thanks to linearization (or neural approximation), the presented suboptimal algorithms do not require d...
International Nuclear Information System (INIS)
This paper describes a practical introduction to the use of Artificial Neural Networks. Artificial Neural Nets are often used as an alternative to the traditional symbolic manipulation and first order logic used in Artificial Intelligence, due the high degree of difficulty to solve problems that can not be handled by programmers using algorithmic strategies. As a particular case of Neural Net a Multilayer Perception developed by programming in C language on OS9 real time operating system is presented. A detailed description about the program structure and practical use are included. Finally, several application examples that have been treated with the tool are presented, and some suggestions about hardware implementations. (Author) 15 refs
Energy Technology Data Exchange (ETDEWEB)
Labrador, I.; Carrasco, R.; Martinez, L.
1996-07-01
This paper describes a practical introduction to the use of Artificial Neural Networks. Artificial Neural Nets are often used as an alternative to the traditional symbolic manipulation and first order logic used in Artificial Intelligence, due the high degree of difficulty to solve problems that can not be handled by programmers using algorithmic strategies. As a particular case of Neural Net a Multilayer Perception developed by programming in C language on OS9 real time operating system is presented. A detailed description about the program structure and practical use are included. Finally, several application examples that have been treated with the tool are presented, and some suggestions about hardware implementations. (Author) 15 refs.
International Conference on Artificial Neural Networks (ICANN)
Mladenov, Valeri; Kasabov, Nikola; Artificial Neural Networks : Methods and Applications in Bio-/Neuroinformatics
2015-01-01
The book reports on the latest theories on artificial neural networks, with a special emphasis on bio-neuroinformatics methods. It includes twenty-three papers selected from among the best contributions on bio-neuroinformatics-related issues, which were presented at the International Conference on Artificial Neural Networks, held in Sofia, Bulgaria, on September 10-13, 2013 (ICANN 2013). The book covers a broad range of topics concerning the theory and applications of artificial neural networks, including recurrent neural networks, super-Turing computation and reservoir computing, double-layer vector perceptrons, nonnegative matrix factorization, bio-inspired models of cell communities, Gestalt laws, embodied theory of language understanding, saccadic gaze shifts and memory formation, and new training algorithms for Deep Boltzmann Machines, as well as dynamic neural networks and kernel machines. It also reports on new approaches to reinforcement learning, optimal control of discrete time-delay systems, new al...
Artificial Neural Nets with Interaction of Afferents
Blasio, Gabriel de; Moreno Díaz, Arminda; Moreno Díaz, Roberto
2011-01-01
The aim is to obtain computationally more powerful, neuro physiologically founded, arti?cial neurons and neural nets. Arti?cial Neural Nets (ANN) of the Perceptron type evolved from the original proposal by McCulloch an Pitts classical paper [1]. Essentially, they keep the computing structure of a linear machine followed by a non linear operation. The McCulloch-Pitts formal neuron (which was never considered by the author’s to be models of real neurons) consists of the simplest case of a lin...
Scientific Electronic Library Online (English)
Vitor Hugo, Ferreira; Alexandre Pinto Alves da, Silva.
2011-12-01
Full Text Available Após 1991, a literatura sobre previsão de carga passou a ser dominada por propostas baseadas em modelos neurais. Entretanto, um empecilho na aplicação destes modelos reside na possibilidade do ajuste excessivo dos dados, i.e, overfitting. O excesso de não-linearidade disponibilizado pelos modelos ne [...] urais de previsão de carga, que depende da representação do espaço de entrada, vem sendo ajustado de maneira heurística. Modelos autônomos incluindo técnicas automáticas e acopladas para seleção de entradas e controle de complexidade dos modelos foram propostos recentemente para previsão de carga em curto prazo. Entretanto, estas técnicas necessitam da especificação do conjunto inicial de entradas que será processado pelo modelo visando determinar aquelas mais relevantes. Este trabalho explora a teoria do caos como ferramenta de análise não-linear de séries temporais na definição automática do conjunto de atrasos de uma dada série de carga a serem utilizados como entradas de modelos neurais autônomos. Neste trabalho, inferência Bayesiana aplicada a perceptrons de múltiplas camadas e máquinas de vetores relevantes são utilizadas no desenvolvimento de modelos neurais autônomos. Abstract in english After 1991, the literature on load forecasting has been dominated by neural network based proposals. However, one major risk in using neural models is the possibility of excessive training, i.e., data overfitting. The extent of nonlinearity provided by neural network based load forecasters, which de [...] pends on the input space representation, has been adjusted using heuristic procedures. The empirical nature of these procedures makes their application cumbersome and time consuming. Autonomous modeling including automatic input selection and model complexity control has been proposed recently for short-term load forecasting. However, these techniques require the specification of an initial input set that will be processed by the model in order to select the most relevant variables. This paper explores chaos theory as a tool from non-linear time series analysis to automatic select the lags of the load series data that will be used by the neural models. In this paper, Bayesian inference applied to multi-layered perceptrons and relevance vector machines are used in the development of autonomous neural models.
Directory of Open Access Journals (Sweden)
Vitor Hugo Ferreira
2011-12-01
Full Text Available After 1991, the literature on load forecasting has been dominated by neural network based proposals. However, one major risk in using neural models is the possibility of excessive training, i.e., data overfitting. The extent of nonlinearity provided by neural network based load forecasters, which depends on the input space representation, has been adjusted using heuristic procedures. The empirical nature of these procedures makes their application cumbersome and time consuming. Autonomous modeling including automatic input selection and model complexity control has been proposed recently for short-term load forecasting. However, these techniques require the specification of an initial input set that will be processed by the model in order to select the most relevant variables. This paper explores chaos theory as a tool from non-linear time series analysis to automatic select the lags of the load series data that will be used by the neural models. In this paper, Bayesian inference applied to multi-layered perceptrons and relevance vector machines are used in the development of autonomous neural models.Após 1991, a literatura sobre previsão de carga passou a ser dominada por propostas baseadas em modelos neurais. Entretanto, um empecilho na aplicação destes modelos reside na possibilidade do ajuste excessivo dos dados, i.e, overfitting. O excesso de não-linearidade disponibilizado pelos modelos neurais de previsão de carga, que depende da representação do espaço de entrada, vem sendo ajustado de maneira heurística. Modelos autônomos incluindo técnicas automáticas e acopladas para seleção de entradas e controle de complexidade dos modelos foram propostos recentemente para previsão de carga em curto prazo. Entretanto, estas técnicas necessitam da especificação do conjunto inicial de entradas que será processado pelo modelo visando determinar aquelas mais relevantes. Este trabalho explora a teoria do caos como ferramenta de análise não-linear de séries temporais na definição automática do conjunto de atrasos de uma dada série de carga a serem utilizados como entradas de modelos neurais autônomos. Neste trabalho, inferência Bayesiana aplicada a perceptrons de múltiplas camadas e máquinas de vetores relevantes são utilizadas no desenvolvimento de modelos neurais autônomos.
Munro, Kelly; Miller, Thomas H; Martins, Claudia P B; Edge, Anthony M; Cowan, David A; Barron, Leon P
2015-05-29
The modelling and prediction of reversed-phase chromatographic retention time (tR) under gradient elution conditions for 166 pharmaceuticals in wastewater extracts is presented using artificial neural networks for the first time. Radial basis function, multilayer perceptron and generalised regression neural networks were investigated and a comparison of their predictive ability for model solutions discussed. For real world application, the effect of matrix complexity on tR measurements is presented. Measured tR for some compounds in influent wastewater varied by >1min in comparison to tR in model solutions. Similarly, matrix impact on artificial neural network predictive ability was addressed towards developing a more robust approach for routine screening applications. Overall, the best neural network had a predictive accuracy of <1.3min at the 75th percentile of all measured tR data in wastewater samples (<10% of the total runtime). Coefficients of determination for 30 blind test compounds in wastewater matrices lay at or above R(2)=0.92. Finally, the model was evaluated for application to the semi-targeted identification of pharmaceutical residues during a weeklong wastewater sampling campaign. The model successfully identified native compounds at a rate of 83±4% and 73±5% in influent and effluent extracts, respectively. The use of an HRMS database and the optimised ANN model was also applied to shortlisting of 37 additional compounds in wastewater. Ultimately, this research will potentially enable faster identification of emerging contaminants in the environment through more efficient post-acquisition data mining. PMID:25892634
Introduction to neural networks
International Nuclear Information System (INIS)
This lecture is a presentation of today's research in neural computation. Neural computation is inspired by knowledge from neuro-science. It draws its methods in large degree from statistical physics and its potential applications lie mainly in computer science and engineering. Neural networks models are algorithms for cognitive tasks, such as learning and optimization, which are based on concepts derived from research into the nature of the brain. The lecture first gives an historical presentation of neural networks development and interest in performing complex tasks. Then, an exhaustive overview of data management and networks computation methods is given: the supervised learning and the associative memory problem, the capacity of networks, the Perceptron networks, the functional link networks, the Madaline (Multiple Adalines) networks, the back-propagation networks, the reduced coulomb energy (RCE) networks, the unsupervised learning and the competitive learning and vector quantization. An example of application in high energy physics is given with the trigger systems and track recognition system (track parametrization, event selection and particle identification) developed for the CPLEAR experiment detectors from the LEAR at CERN. (J.S.). 56 refs., 20 figs., 1 tab., 1 appendix
A neural network construction method for surrogate modeling of physics-based analysis
Sung, Woong Je
In this thesis existing methodologies related to the developmental methods of neural networks have been surveyed and their approaches to network sizing and structuring are carefully observed. This literature review covers the constructive methods, the pruning methods, and the evolutionary methods and questions about the basic assumption intrinsic to the conventional neural network learning paradigm, which is primarily devoted to optimization of connection weights (or synaptic strengths) for the pre-determined connection structure of the network. The main research hypothesis governing this thesis is that, without breaking a prevailing dichotomy between weights and connectivity of the network during learning phase, the efficient design of a task-specific neural network is hard to achieve because, as long as connectivity and weights are searched by separate means, a structural optimization of the neural network requires either repetitive re-training procedures or computationally expensive topological meta-search cycles. The main contribution of this thesis is designing and testing a novel learning mechanism which efficiently learns not only weight parameters but also connection structure from a given training data set, and positioning this learning mechanism within the surrogate modeling practice. In this work, a simple and straightforward extension to the conventional error Back-Propagation (BP) algorithm has been formulated to enable a simultaneous learning for both connectivity and weights of the Generalized Multilayer Perceptron (GMLP) in supervised learning tasks. A particular objective is to achieve a task-specific network having reasonable generalization performance with a minimal training time. The dichotomy between architectural design and weight optimization is reconciled by a mechanism establishing a new connection for a neuron pair which has potentially higher error-gradient than one of the existing connections. Interpreting an instance of the absence of connection as a zero-weight connection, the potential contribution to training error reduction of any present or absent connection can readily be evaluated using the BP algorithm. Instead of being broken, the connections that contribute less remain frozen with constant weight values optimized to that point but they are excluded from further weight optimization until reselected. In this way, a selective weight optimization is executed only for the dynamically maintained pool of high gradient connections. By searching the rapidly changing weights and concentrating optimization resources on them, the learning process is accelerated without either a significant increase in computational cost or a need for re-training. This results in a more task-adapted network connection structure. Combined with another important criterion for the division of a neuron which adds a new computational unit to a network, a highly fitted network can be grown out of the minimal random structure. This particular learning strategy can belong to a more broad class of the variable connectivity learning scheme and the devised algorithm has been named Optimal Brain Growth (OBG). The OBG algorithm has been tested on two canonical problems; a regression analysis using the Complicated Interaction Regression Function and a classification of the Two-Spiral Problem. A comparative study with conventional Multilayer Perceptrons (MLPs) consisting of single- and double-hidden layers shows that OBG is less sensitive to random initial conditions and generalizes better with only a minimal increase in computational time. This partially proves that a variable connectivity learning scheme has great potential to enhance computational efficiency and reduce efforts to select proper network architecture. To investigate the applicability of the OBG to more practical surrogate modeling tasks, the geometry-to-pressure mapping of a particular class of airfoils in the transonic flow regime has been sought using both the conventional MLP networks with pre-defined architecture and the OBG-developed networks started from
Anderson, R. B.; Morris, Richard V.; Clegg, S. M.; Humphries, S. D.; Wiens, R. C.; Bell, J. F., III; Mertzman, S. A.
2010-01-01
The ChemCam instrument [1] on the Mars Science Laboratory (MSL) rover will be used to obtain the chemical composition of surface targets within 7 m of the rover using Laser Induced Breakdown Spectroscopy (LIBS). ChemCam analyzes atomic emission spectra (240-800 nm) from a plasma created by a pulsed Nd:KGW 1067 nm laser. The LIBS spectra can be used in a semiquantitative way to rapidly classify targets (e.g., basalt, andesite, carbonate, sulfate, etc.) and in a quantitative way to estimate their major and minor element chemical compositions. Quantitative chemical analysis from LIBS spectra is complicated by a number of factors, including chemical matrix effects [2]. Recent work has shown promising results using multivariate techniques such as partial least squares (PLS) regression and artificial neural networks (ANN) to predict elemental abundances in samples [e.g. 2-6]. To develop, refine, and evaluate analysis schemes for LIBS spectra of geologic materials, we collected spectra of a diverse set of well-characterized natural geologic samples and are comparing the predictive abilities of PLS, cascade correlation ANN (CC-ANN) and multilayer perceptron ANN (MLP-ANN) analysis procedures.
DEFF Research Database (Denmark)
S. Nadimi, Esmaeil; Nyholm JØrgensen, Rasmus
2012-01-01
Animal welfare is an issue of great importance in modern food production systems. Because animal behavior provides reliable information about animal health and welfare, recent research has aimed at designing monitoring systems capable of measuring behavioral parameters and transforming them into their corresponding behavioral modes. However, network unreliability and high-energy consumption have limited the applicability of those systems. In this study, a 2.4-GHz ZigBee-based mobile ad hoc wireless sensor network (MANET) that is able to overcome those problems is presented. The designed MANET showed high communication reliability, low energy consumption and low packet loss rate (14.8%) due to the deployment of modern communication protocols (e.g. multi-hop communication and handshaking protocol). The measured behavioral parameters were transformed into the corresponding behavioral modes using a multilayer perceptron (MLP)-based artificial neural network (ANN). The best performance of the ANN in terms of the mean squared error (MSE) and the convergence speed was achieved when it was initialized and trained using the Nguyen–Widrow and Levenberg–Marquardt back-propagation algorithms, respectively. The success rate of behavior classification into five classes (i.e. grazing, lying down, walking, standing and others) was 76.2% (?mean=1.06)(?mean=1.06) on average. The results of this study showed an important improvement regarding the performance of the designed MANET and behavior classification compared to the results of other similar studies.
International Nuclear Information System (INIS)
A technique for level measurement in pressure vessels was developed using thermal probes with internal cooling and artificial neural networks (ANN's). This new concept of thermal probes was experimentally tested in an experimental facility (BETSNI) with two test sections, ST1 and ST2. Two different thermal probes were designed and constructed: concentric tubes probe and U tube probe. A data acquisition system (DAS) was assembled to record the experimental data during the tests. Steady state and transient level tests were carried out and the experimental data obtained were used as learning and recall data sets in the ANN's program RETRO-05 that simulate a multilayer perceptron with backpropagation. The results of the analysis show that the technique can be applied for level measurements in pressure vessel. The technique is applied for a less input temperature data than the initially designed to the probes. The technique is robust and can be used in case of lack of some temperature data. Experimental data available in literature from electrically heated thermal probe were also used in the ANN's analysis producing good results. The results of the ANN's analysis show that the technique can be improved and applied to level measurements in pressure vessels. (author)
Li, Wei; Zhang, Yan; Cui, Lijuan; Zhang, Manyin; Wang, Yifei
2015-08-01
A horizontal subsurface flow constructed wetland (HSSF-CW) was designed to improve the water quality of an artificial lake in Beijing Wildlife Rescue and Rehabilitation Center, Beijing, China. Artificial neural networks (ANNs), including multilayer perceptron (MLP) and radial basis function (RBF), were used to model the removal of total phosphorus (TP). Four variables were selected as the input parameters based on the principal component analysis: the influent TP concentration, water temperature, flow rate, and porosity. In order to improve model accuracy, alternative ANNs were developed by incorporating meteorological variables, including precipitation, air humidity, evapotranspiration, solar heat flux, and barometric pressure. A genetic algorithm and cross-validation were used to find the optimal network architectures for the ANNs. Comparison of the observed data and the model predictions indicated that, with careful variable selection, ANNs appeared to be an efficient and robust tool for predicting TP removal in the HSSF-CW. Comparison of the accuracy and efficiency of MLP and RBF for predicting TP removal showed that the RBF with additional meteorological variables produced the most accurate results, indicating a high potentiality for modeling TP removal in the HSSF-CW. PMID:25903184
Directory of Open Access Journals (Sweden)
Zhe Dong
2014-02-01
Full Text Available Small modular reactors (SMRs could be beneficial in providing electricity power safely and also be viable for applications such as seawater desalination and heat production. Due to its inherent safety features, the modular high temperature gas-cooled reactor (MHTGR has been seen as one of the best candidates for building SMR-based nuclear power plants. Since the MHTGR dynamics display high nonlinearity and parameter uncertainty, it is necessary to develop a nonlinear adaptive power-level control law which is not only beneficial to the safe, stable, efficient and autonomous operation of the MHTGR, but also easy to implement practically. In this paper, based on the concept of shifted-ectropy and the physically-based control design approach, it is proved theoretically that the simple proportional-differential (PD output-feedback power-level control can provide asymptotic closed-loop stability. Then, based on the strong approximation capability of the multi-layer perceptron (MLP artificial neural network (ANN, a compensator is established to suppress the negative influence caused by system parameter uncertainty. It is also proved that the MLP-compensated PD power-level control law constituted by an experientially-tuned PD regulator and this MLP-based compensator can guarantee bounded closed-loop stability. Numerical simulation results not only verify the theoretical results, but also illustrate the high performance of this MLP-compensated PD power-level controller in suppressing the oscillation of process variables caused by system parameter uncertainty.
Directory of Open Access Journals (Sweden)
Pablo García
2013-06-01
Full Text Available Thanks to the built in intelligence (deployment of new intelligent devices and sensors in places where historically they were not present, the Smart Grid and Microgrid paradigms are able to take advantage from aggregated load forecasting, which opens the door for the implementation of new algorithms to seize this information for optimization and advanced planning. Therefore, accuracy in load forecasts will potentially have a big impact on key operation factors for the future Smart Grid/Microgrid-based energy network like user satisfaction and resource saving, and new methods to achieve an efficient prediction in future energy landscapes (very different from the centralized, big area networks studied so far. This paper proposes different improved models to forecast next day’s aggregated load using artificial neural networks, taking into account the variables that are most relevant for the aggregated. In particular, seven models based on the multilayer perceptron will be proposed, progressively adding input variables after analyzing the influence of climate factors on aggregated load. The results section presents the forecast from the proposed models, obtained from real data.
Scientific Electronic Library Online (English)
Eduardo Costa da, Silva; Marley M. B. R., Vellasco; Carlos R. Hall, Barbosa; Elisabeth Costa, Monteiro; Luiz A. P. de, Gusmão.
2012-10-01
Full Text Available Ao longo dos últimos anos, diversos trabalhos têm sido desenvolvidos a fim de se modelar quantitativamente o efeito GMI (Magnetoimpedância Gigante). No entanto, esses modelos adotam simplificações que afetam significativamente seu desempenho teórico-experimental e sua generalidade, e ainda são raros [...] os modelos quantitativos que incorporam parâmetros geradores de assimetria - AGMI (GMI assimétrica) - como, por exemplo, o nível CC da corrente de excitação das amostras GMI. Este trabalho objetiva o desenvolvimento de um novo modelo, suficientemente geral, que incorpore inclusive a assimetria induzida pelo nível CC da corrente de excitação, capaz de guiar os procedimentos experimentais de caracterização das amostras GMI. Assim, este artigo propõe, apresenta e discute a utilização de um modelo computacional baseado em Redes Neurais feedforward Multilayer Perceptron na modelagem da sensibilidade de módulo e fase da impedância do efeito GMI em função do campo magnético, para ligas ferromagnéticas amorfas de composição Co70Fe5Si15B10. O modelo proposto permite a obtenção da sensibilidade a partir de alguns dos principais parâmetros que a afetam: comprimento das amostras, nível CC e frequência da corrente de excitação e campo magnético externo. Abstract in english Over the past few years, several studies have been developed in order to quantitatively model the GMI effect (Giant Magnetoimpedance). However, these models adopt simplifications that significantly affect its theoretical-experimental performance and its generalization capability, and models that inc [...] orporate parameters that generate asymmetry - AGMI (asymmetric GMI) - such as the DC level of the excitation current of the GMI samples are still rare. This work aims to develop a new model, sufficiently general, which also incorporates the asymmetry induced by the DC level of the excitation current, capable of guiding the experimental procedures of characterization of the GMI samples. Thus, this paper proposes, presents and discusses the use of a computational model based on feedforward Multilayer Perceptron Neural Networks to model the impedance magnitude sensitivity and impedance phase sensitivity, of the GMI effect, as functions of the magnetic field, for Co70Fe5Si15B10 ferromagnetic amorphous alloys. The proposed model allows obtaining these sensitivities based on some of the main parameters that affect it: length of the samples, DC level and frequency of the excitation current and the external magnetic field.
Isomorphisms in Multilayer Networks
Kivelä, Mikko
2015-01-01
We extend the concept of graph isomorphisms to multilayer networks, and we identify multiple types of isomorphisms. For example, in multilayer networks with a single "aspect" (i.e., type of layering), permuting vertex labels, layer labels, and both of types of layers each yield a different type of isomorphism. We discuss how multilayer network isomorphisms naturally lead to defining isomorphisms in any type of network that can be represented as a multilayer network. This thereby yields isomorphisms for multiplex networks, temporal networks, networks with both such features, and more. We reduce each of the multilayer network isomorphism problems to a graph isomorphism problem, and we use this reduction to prove that the multilayer network isomorphism problem is computationally equally hard as the graph isomorphism problem. One can thus use software that has been developed to solve graph isomorphism problems as a practical means for solving multilayer network isomorphism problems.
Monthly evaporation forecasting using artificial neural networks and support vector machines
Tezel, Gulay; Buyukyildiz, Meral
2015-02-01
Evaporation is one of the most important components of the hydrological cycle, but is relatively difficult to estimate, due to its complexity, as it can be influenced by numerous factors. Estimation of evaporation is important for the design of reservoirs, especially in arid and semi-arid areas. Artificial neural network methods and support vector machines (SVM) are frequently utilized to estimate evaporation and other hydrological variables. In this study, usability of artificial neural networks (ANNs) (multilayer perceptron (MLP) and radial basis function network (RBFN)) and ?-support vector regression (SVR) artificial intelligence methods was investigated to estimate monthly pan evaporation. For this aim, temperature, relative humidity, wind speed, and precipitation data for the period 1972 to 2005 from Beysehir meteorology station were used as input variables while pan evaporation values were used as output. The Romanenko and Meyer method was also considered for the comparison. The results were compared with observed class A pan evaporation data. In MLP method, four different training algorithms, gradient descent with momentum and adaptive learning rule backpropagation (GDX), Levenberg-Marquardt (LVM), scaled conjugate gradient (SCG), and resilient backpropagation (RBP), were used. Also, ?-SVR model was used as SVR model. The models were designed via 10-fold cross-validation (CV); algorithm performance was assessed via mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R 2). According to the performance criteria, the ANN algorithms and ?-SVR had similar results. The ANNs and ?-SVR methods were found to perform better than the Romanenko and Meyer methods. Consequently, the best performance using the test data was obtained using SCG(4,2,2,1) with R 2 = 0.905.
ANNAM. An artificial neural net attraction model to analyze market shares.
Hruschka, Harald
1999-01-01
The marketing literature so far only considers attraction models with strict functional forms. Greater exibility can be achieved by the neural net based approach introduced which assesses brands' attraction values by means of a perceptron with one hidden layer. Using log-ratio transformed market shares as dependent variables stochastic gradient descent followed by a quasi-Newton method estimates parameters. For store-level data the neural net model performs better and implies a price response...
Transformation of Neural State Space Models into LFT Models for Robust Control Design
DEFF Research Database (Denmark)
Bendtsen, Jan Dimon; Trangbæk, Klaus
2000-01-01
This paper considers the extraction of linear state space models and uncertainty models from neural networks trained as state estimators with direct application to robust control. A new method for writing a neural state space model in a linear fractional transformation form in a non-conservative way is proposed, and it is demonstrated how a standard robust control law can be designed for a system described by means of a multi layer perceptron.
An Efficient Weather Forecasting System using a Hybrid Neural Network SOFM–MLP
I. Kadar Shereef; S Santhosh Baboo
2010-01-01
Weather prediction is a challenging task for researchers and has drawn a lot of research interest in the recent years. Literature studies have shown that machine learning techniques achieved better performance than traditional statistical methods. Presently multilayer perceptron networks (MLPs) are used for prediction of the maximum and the minimum temperatures based on past observations on various atmospheric parameters. To capture the seasonality of atmospheric data, with a view to improvin...
Neural network analysis of W UMa eclipsing binaries
Zeraatgari, F. Z.; Abedi, A.; Farshad, M.; Ebadian, M.; Riazi, N.
2015-04-01
We try five different artificial neural models, four models based on PNN (Perceptron Neural Network), and one using GRNN (Generalized Regression Neural Network) as tools for the automated light curve analysis of W UMa-type eclipsing binary systems. These algorithms, which are inspired by the Rucinski method, are designed and trained using MATLAB 7.6. A total of 17,820 generated contact binary light curves are first analyzed using a truncated cosine series with 11 coefficients and the most significant coefficients are applied as inputs of the neural models. The required sample light curves are systematically generated, using the WD2007 program (Wilson and Devinney 2007). The trained neural models are then applied to estimate the geometrical parameters of seven W UMa-type systems. The efficiency of different neural network models are then evaluated and compared to find the most efficient one.
Variants of Memetic and Hybrid Learning of Perceptron Networks.
Czech Academy of Sciences Publication Activity Database
Neruda, Roman; Slušný, Stanislav
Los Alamitos : IEEE, 2007 - (Tjoa, A.; Wagner, R.), s. 158-162 ISBN 978-0-7695-2932-5. [ETID '07. International Workshop on Evolutionary Techniques /1./, DEXA 2007 International Conference /18./. Regensburg (DE), 03.09.2007-07.09.2007] R&D Projects: GA AV ?R 1ET100300414 Institutional research plan: CEZ:AV0Z10300504 Keywords : memetic learning * evolutionary learning * neural networks Subject RIV: IN - Informatics, Computer Science
Abnormal Control Chart Pattern Classification Optimisation Using Multi Layered Perceptron
Mitra Mahdiani; Hairulliza Mohd. Judi; Noraidah Sahari Ashaari
2014-01-01
In today's industry, control charts are widely used to monitor production process. The abnormal patterns of a quality control chart could reveal problems that occur in the process. In the recent years, as an alternative of the traditional process quality management methods, such as Shewhart Statistical Process Control (SPC), Artificial Neural Networks (ANN) have been widely used to recognize the abnormal pattern of control charts. Various types of patterns are observed in control charts. Iden...
Directory of Open Access Journals (Sweden)
M. Hayatzadeh
2015-08-01
Full Text Available Since the development of surface water control needs accurate access to flow behavior of sediment rates, the lack of sediment measurement stations, the novelty of most stations and the lack of statistics on the deposit make it difficult to properly evaluate and simulate the flow behavior and their sediments. In a watershed, the morphological characteristics and sediment load of flow affect each other. It is, thus, important to know about the extent of this relationship to manage and control the flow in downstream areas. In the present study, using artificial neural networks and sediment rating regression methods based on the data from 136 events and also morphological parameters, we have attempted to predict the sediment load of Bagh Abbas basin. In the first step, we used flow data to predict the sediment load of both methods, and then basin morphological characteristics such as the compactness factor and form factor were added to the models. The results of this study showed that by using neural networks of Multilayer Perceptron (MLP type with Levenberg – Marquardt algorithm and the stimulation function of tangent Sigmoid with two hidden layers and four neurons in each layer, we can predict suspended sediment discharge rate with a sufficient accuracy. Accuracy of the results obtained from the ANN method was higher than the accuracy of rating curve method. In the evaluation of NGANN & GANN network methods and SRC & MARS regression methods, correlation coefficients were respectively calculated as 0.94, 0.93, 0.767, 0.766, and root mean square errors (RMSE, 0.45, 0.49, 2.3 and 2.3. Nash coefficient (NS was calculated respectively as 0.71, 0.58, 0.27 and 0.23. Therefore, the most efficient method among the four models is artificial neural network combined with morphological data (GANN. Furthermore, the findings of the study show that adding geomorphological parameters to sediment rating has little effect on the model performance.
Kumari, Amrita; Das, Suchandan Kumar; Srivastava, Prem Kumar
2015-07-01
Application of computational intelligence for predicting industrial processes has been in extensive use in various industrial sectors including power sector industry. An ANN model using multi-layer perceptron philosophy has been proposed in this paper to predict the deposition behaviors of oxide scale on waterwall tubes of a coal fired boiler. The input parameters comprises of boiler water chemistry and associated operating parameters, such as, pH, alkalinity, total dissolved solids, specific conductivity, iron and dissolved oxygen concentration of the feed water and local heat flux on boiler tube. An efficient gradient based network optimization algorithm has been employed to minimize neural predictions errors. Effects of heat flux, iron content, pH and the concentrations of total dissolved solids in feed water and other operating variables on the scale deposition behavior have been studied. It has been observed that heat flux, iron content and pH of the feed water have a relatively prime influence on the rate of oxide scale deposition in water walls of an Indian boiler. Reasonably good agreement between ANN model predictions and the measured values of oxide scale deposition rate has been observed which is corroborated by the regression fit between these values.
Atila, U.; Karas, I. R.; Turan, M. K.; Rahman, A. A.
2013-09-01
One of the most dangerous disaster threatening the high rise and complex buildings of today's world including thousands of occupants inside is fire with no doubt. When we consider high population and the complexity of such buildings it is clear to see that performing a rapid and safe evacuation seems hard and human being does not have good memories in case of such disasters like world trade center 9/11. Therefore, it is very important to design knowledge based realtime interactive evacuation methods instead of classical strategies which lack of flexibility. This paper presents a 3D-GIS implementation which simulates the behaviour of an intelligent indoor pedestrian navigation model proposed for a self -evacuation of a person in case of fire. The model is based on Multilayer Perceptron (MLP) which is one of the most preferred artificial neural network architecture in classification and prediction problems. A sample fire scenario following through predefined instructions has been performed on 3D model of the Corporation Complex in Putrajaya (Malaysia) and the intelligent evacuation process has been realized within a proposed 3D-GIS based simulation.
Directory of Open Access Journals (Sweden)
Behniafar Ali
2013-01-01
Full Text Available The electric marine instruments are newly inserted in the trade and industry, for which the existence of an equipped and reliable power system is necessitated. One of the features of such a power system is that it cannot have an earth system causing the protection relays not to be able to detect the single line to ground short circuit fault. While on the other hand, the occurrence of another similar fault at the same time can lead to the double line fault and thereby the tripping of relays and shortening of vital loads. This in turn endangers the personals' security and causes the loss of military plans. From the above considerations, it is inferred that detecting the single line to ground fault in the marine instruments is of a special importance. In this way, this paper intends to detect the single line to ground fault in the power systems of the marine instruments using the wavelet transform and Multi-Layer Perceptron (MLP neural network. In the numerical analysis, several different types of short circuit faults are simulated on several marine power systems and the proposed approach is applied to detect the single line to ground fault. The results are of a high quality and preciseness and perfectly demonstrate the effectiveness of the proposed approach.
International Nuclear Information System (INIS)
Highlights: ? Solar radiation estimation based on Gene Expression Programming is unexplored. ? This approach is evaluated for the first time in this study. ? Other artificial intelligence models (ANN and ANFIS) are also included in the study. ? New alternatives for solar radiation estimation based on temperatures are provided. - Abstract: Surface incoming solar radiation is a key variable for many agricultural, meteorological and solar energy conversion related applications. In absence of the required meteorological sensors for the detection of global solar radiation it is necessary to estimate this variable. Temperature based modeling procedures are reported in this study for estimating daily incoming solar radiation by using Gene Expression Programming (GEP) for the first time, and other artificial intelligence models such as Artificial Neural Networks (ANNs), and Adaptive Neuro-Fuzzy Inference System (ANFIS). A comparison was also made among these techniques and traditional temperature based global solar radiation estimation equations. Root mean square error (RMSE), mean absolute error (MAE) RMSE-based skill score (SSRMSE), MAE-based skill score (SSMAE) and r2 criterion of Nash and Sutcliffe criteria were used to assess the models’ performances. An ANN (a four-input multilayer perceptron with 10 neurons in the hidden layer) presented the best performance among the studied models (2.93 MJ m?2 d?1 of RMSE). The ability of GEP approach to model global solar radiation based on daily atmospheric variables was found to be satisfactory.
International Nuclear Information System (INIS)
Fall prevention lacks easy, quantitative and wearable methods for the classification of fall-risk (FR). Efforts must be thus devoted to the choice of an ad hoc classifier both to reduce the size of the sample used to train the classifier and to improve performances. A new methodology that uses a neural network (NN) and a wearable device are hereby proposed for this purpose. The NN uses kinematic parameters assessed by a wearable device with accelerometers and rate gyroscopes during a posturography protocol. The training of the NN was based on the Mahalanobis distance and was carried out on two groups of 30 elderly subjects with varying fall-risk Tinetti scores. The validation was done on two groups of 100 subjects with different fall-risk Tinetti scores and showed that, both in terms of specificity and sensitivity, the NN performed better than other classifiers (naive Bayes, Bayes net, multilayer perceptron, support vector machines, statistical classifiers). In particular, (i) the proposed NN methodology improved the specificity and sensitivity by a mean of 3% when compared to the statistical classifier based on the Mahalanobis distance (SCMD) described in Giansanti (2006 Physiol. Meas. 27 1081–90); (ii) the assessed specificity was 97%, the assessed sensitivity was 98% and the area under receiver operator characteristics was 0.965. (note)
Torrecilla, José S; Tortuero, César; Cancilla, John C; Díaz-Rodríguez, Pablo
2013-09-15
A multilayer perceptron neural network (NN) model has been created for the estimation of the water content present in the following ionic liquids (ILs): 1-butyl-3-methylimidazolium tetrafluoroborate, 1-butyl-3-methylimidazolium methylsulfate, 1,3-dimethylimidazolium methylsulfate and 1-ethyl-3-methylimidazolium ethylsulfate. To achieve this goal, their density and viscosity values were used. The experimental values of these physicochemical properties, employed to design the NN model, were measured and registered at 298.15K. They were determined at different relative humidity values ranging from 11.1 to 84.3%. The estimated results were then compared with the experimental measurements of the water content, which were carried out by the Karl Fischer technique, and the difference between the real and estimated values was less than 0.05 and 3.1% in the verification and validation processes, respectively. In addition, an external validation process was developed using four bibliographical references. In this case, the mean prediction error was less than 6.3%. In light of these results, the NN model shows an acceptable goodness of fit, sufficient robustness, and an adequate estimative capacity to determine the water content inside the studied range of the ILs analyzed. PMID:23708628
Scientific Electronic Library Online (English)
Ernesto, Gómez Vargas; Nelson, Obregón Neira; Virgilio, Socarras Quintero.
2010-07-01
Full Text Available Este artículo muestra los resultados obtenidos en la exploración de la bondad de la implementación del modelo neurodifuso ANFIS y de las redes neuronales para la predicción de caudales medios mensuales en la cuenca del Rio Bogotá en la ciudad de Villapinzón. Se desarrolla e implementa el modelo ANFI [...] S y se evalúa el comportamiento de seis modelos, al variar el número de entradas, y el número y tipo de conjuntos difusos (funciones de pertenencia), que son los parámetros fundamentales del modelo ANFIS. Los resultados se comparan con los obtenidos con las redes neuronales perceptrón multicapa. Abstract in english This paper shows the results in the exploration of the benefits of the implementation of neuro-fuzzy AN-FIS model and neural networks for the prediction of monthly mean flows in the basin of Bogota River in Villapinzón. The ANFIS model is developed, implemented and the performance of six models is e [...] valuated bychanging entries number, number and type of fuzzy sets (membership functions), which are the basic parameters of the ANFIS model. The results are compared with those obtained with multilayer perceptron neural networks.
Feng, Xiao; Li, Qi; Zhu, Yajie; Hou, Junxiong; Jin, Lingyan; Wang, Jingjie
2015-04-01
In the paper a novel hybrid model combining air mass trajectory analysis and wavelet transformation to improve the artificial neural network (ANN) forecast accuracy of daily average concentrations of PM2.5 two days in advance is presented. The model was developed from 13 different air pollution monitoring stations in Beijing, Tianjin, and Hebei province (Jing-Jin-Ji area). The air mass trajectory was used to recognize distinct corridors for transport of "dirty" air and "clean" air to selected stations. With each corridor, a triangular station net was constructed based on air mass trajectories and the distances between neighboring sites. Wind speed and direction were also considered as parameters in calculating this trajectory based air pollution indicator value. Moreover, the original time series of PM2.5 concentration was decomposed by wavelet transformation into a few sub-series with lower variability. The prediction strategy applied to each of them and then summed up the individual prediction results. Daily meteorological forecast variables as well as the respective pollutant predictors were used as input to a multi-layer perceptron (MLP) type of back-propagation neural network. The experimental verification of the proposed model was conducted over a period of more than one year (between September 2013 and October 2014). It is found that the trajectory based geographic model and wavelet transformation can be effective tools to improve the PM2.5 forecasting accuracy. The root mean squared error (RMSE) of the hybrid model can be reduced, on the average, by up to 40 percent. Particularly, the high PM2.5 days are almost anticipated by using wavelet decomposition and the detection rate (DR) for a given alert threshold of hybrid model can reach 90% on average. This approach shows the potential to be applied in other countries' air quality forecasting systems.
Directory of Open Access Journals (Sweden)
M.R. Mustafa
2014-05-01
Full Text Available Estimation of suspended sediments in rivers using soft computing techniques has been extensively performed around the world since 1990’s. However, accuracy in the results was always found to be highly desired and a profound crucial task. This study presents a thorough comparison between the performances of best basis function of Radial Basis Functions (RBF and the best training algorithm in Multilayer Perceptron (MLP neural networks for prediction of suspended sediments in Pari River, Perak, Malaysia. Time series data of water discharge and suspended sediments was used to develop MLP and RBF models. A comparison between six basis functions was performed to identify the most appropriate and best basis function for the selected time series of the river’s data. The performance of the models was compared using several statistical measures including coefficient of determination, coefficient of efficiency and mean absolute error. The performance of the best RBF function was compared with the previously identified best training algorithm of MLP neural networks. The results showed that comparison of various basis functions is always advantageous to achieve the most appropriate basis function for the accurate prediction of the time series data. The results also showed that the performances of both particular RBF and MLP models were close to each other and capable to capture the exact pattern of the sediment data in the river. However, the RBF model showed some inconsistency while predicting the time series data. Furthermore, RBF modeling required more investigation to choose appropriate value for the predefined parameters as compared to MLP modeling.
A multi-scale hybrid neural network retrieval model for dust storm detection, a study in Asia
Wong, Man Sing; Xiao, Fei; Nichol, Janet; Fung, Jimmy; Kim, Jhoon; Campbell, James; Chan, P. W.
2015-05-01
Dust storms are known to have adverse effects on human health and significant impact on weather, air quality, hydrological cycle, and ecosystem. Atmospheric dust loading is also one of the large uncertainties in global climate modeling, due to its significant impact on the radiation budget and atmospheric stability. Observations of dust storms in humid tropical south China (e.g. Hong Kong), are challenging due to high industrial pollution from the nearby Pearl River Delta region. This study develops a method for dust storm detection by combining ground station observations (PM10 concentration, AERONET data), geostationary satellite images (MTSAT), and numerical weather and climatic forecasting products (WRF/Chem). The method is based on a hybrid neural network (NN) retrieval model for two scales: (i) a NN model for near real-time detection of dust storms at broader regional scale; (ii) a NN model for detailed dust storm mapping for Hong Kong and Taiwan. A feed-forward multilayer perceptron (MLP) NN, trained using back propagation (BP) algorithm, was developed and validated by the k-fold cross validation approach. The accuracy of the near real-time detection MLP-BP network is 96.6%, and the accuracies for the detailed MLP-BP neural network for Hong Kong and Taiwan is 74.8%. This newly automated multi-scale hybrid method can be used to give advance near real-time mapping of dust storms for environmental authorities and the public. It is also beneficial for identifying spatial locations of adverse air quality conditions, and estimates of low visibility associated with dust events for port and airport authorities.
PLUNKETT, K; Marchman, V
1991-01-01
A three-layer back-propagation network is used to implement a pattern association task in which four types of mapping are learned. These mappings, which are considered analogous to those which characterize the relationship between the stem and past tense forms of English verbs, include arbitrary mappings, identity mappings, vowel changes, and additions of a suffix. The degree of correspondence between parallel distributed processing (PDP) models which learn mappings of this sort (e.g., Rumelh...
Directory of Open Access Journals (Sweden)
Ed Pinheiro Lima
2003-04-01
Full Text Available As capacidades de interpolação de redes perceptron multicamada (MLP foram utilizadas para resolver um sistema de equações diferencias ordinárias que modela um reator não-adiabático com leito fixo e dispersão axial. As metodologias descritas neste artigo seguem as propostas por Lagaris et al. (1998, 2000, estendidas para modelos com condições de contorno mistas e pelo uso do método da penalidade para converter o problema de otimização original de restrito para irrestrito no treinamento das redes MLP. Os resultados são compatíveis com aqueles apresentados em Luize e Biscaia (1991, que foram obtidos com técnicas numéricas já consagradas, como elementos finitos e colocação ortogonal. O método de neuro-interpolação adotado neste artigo é de fácil manuseio se comparado com os métodos clássicos para solução numérica de equações diferenciais, particularmente para sistemas diferenciais não-lineares, e define uma aproximação global, na forma analítica, para a solução de problemas.The interpolation capabilities of multilayer perceptron networks (MLP were used to solve a system of ordinary differential equations that models an axial dispersed non-adiabatic fixed bed reactor. The methodologies described in this paper follow the first ones proposed by Lagaris et al. (1998, 2000, but enlarge them to differential models with mix boundary conditions and by the use of the penalty method to convert the original constrained to unconstrained optimization problem in training the MLP networks. The results are in agreement on those in Luize e Biscaia (1991, which were obtained by well-established numerical techniques as finite element and orthogonal collocation methods. The neural interpolation method used in this paper is easier to handle than the classical methods for numerical solution of differential equations, particularly for non-linear differential systems, and defines a global approximation, in analytic form, for problems solution.
Scientific Electronic Library Online (English)
J. D, Velásquez; C. J, Franco.
2012-06-01
Full Text Available Muitas séries temporais com tendência e sazonalidade são sucesso modelado e previsto pelo modelo airline de Box e Jenkins, no entanto, este modelo negligencia a presença de não-linearidade dos dados. Neste trabalho, propomos uma nova versão não-linear do modelo airline, por isso, substituir o compon [...] ente linear das medias moviles por um perceptron multicamadas. O modelo proposto é utilizado para previsão de duas séries temporais de referência; descobrimos que o modelo proposto é capaz de prever a série de tempo com mais precisão que outros métodos tradicionais. Abstract in spanish Muchas series de tiempo con tendencia y ciclos estacionales son exitosamente modeladas y pronosticadas usando el modelo airline de Box y Jenkins; sin embargo, la presencia de no linealidades en los datos son despreciadas por este modelo. En este artículo, se propone una nueva versión no lineal del m [...] odelo airline; para esto, se reemplaza la componente lineal de promedios móviles por un perceptrón multicapa. El modelo propuesto es usado para pronosticar dos series de tiempo benchmark; se encontró que el modelo propuesto es capaz de pronosticar las series de tiempo con mayor precisión que otras aproximaciones tradicionales. Abstract in english Many time series with trend and seasonal pattern are successfully modeled and forecasted by the airline model of Box and Jenkins; however, this model neglects the presence of nonlinearity on data. In this paper, we propose a new nonlinear version of the airline model; for this, we replace the moving [...] average linear component by a multilayer perceptron neural network. The proposed model is used for forecasting two benchmark time series; we found that the proposed model is able to forecast the time series with more accuracy that other traditional approaches.
Directory of Open Access Journals (Sweden)
Mónica Bocco
2010-09-01
Full Text Available The incident solar radiation on soil is an important variable used in agricultural applications; it is also relevant in hydrology, meteorology and soil physics, among others. To estimate this variable, empirical models have been developed using several parameters and, recently, prognostic and prediction models based on artificial intelligence techniques such as neural networks. The aim of this work was to develop linear models and neural networks, multilayer perceptron, to estimate daily global solar radiation and compare their efficiency in its application to a region of the Province of Salta, Argentina. Relative sunshine duration, maximum and minimum temperature, rainfall, binary rainfall and extraterrestrial solar radiation data for the period 1996-2002, were used. All data were supplied by Experimental Station Salta, Instituto Nacional de Tecnología Agropecuaria (INTA, Argentina. For both, neural networks models and linear regressions, three alternative combinations of meteorological parameters were considered. Good results with both prediction methods were obtained, with root mean square error (RMSE values between 1.99 and 1.66 MJ m-2 d-1 for linear regressions and neural networks, and coefficients of correlation (r² between 0.88 and 0.92, respectively. Even though neural networks and linear regression models can be used to predict the daily global solar radiation appropriately, neural networks produced better estimates.La radiación solar incidente en el suelo es una variable importante usada en aplicaciones agronómicas, además es relevante en hidrología, meteorología y física del suelo, entre otros. Para estimarla se han desarrollado modelos empíricos que utilizan distintos parámetros meteorológicos y, recientemente, modelos de pronóstico y predicción basados en técnicas de inteligencia artificial tales como redes neuronales. El objetivo de este trabajo fue desarrollar modelos lineales y de redes neuronales, del tipo perceptrón multicapa, para estimar la radiación solar global diaria y comparar la eficiencia de los mismos en su aplicación para una región de la Provincia de Salta, Argentina. Se utilizaron datos de heliofanía relativa, temperaturas máxima y mínima, precipitación, precipitación binaria y radiación solar astronómica provistos por la Estación Experimental Salta, Instituto Nacional de Tecnología Agropecuaria (INTA, Argentina, correspondientes al período 1996-2002. Tanto para los modelos de redes neuronales como para las regresiones lineales se consideraron tres alternativas de combinaciones de los parámetros meteorológicos, obteniéndose buenos resultados con ambas metodologías de predicción, con valores de la raíz del error cuadrático medio variando desde 1.99 a 1.66 MJ m-2 d-1 y coeficientes de correlación de 0.88 a 0.92. Se concluye que ambos, los modelos de redes neuronales y las regresiones lineales, pueden ser usados para predecir en forma adecuada la radiación solar global diaria; si bien las redes neuronales produjeron mejores resultados.
Deepthi, Dasika Ratna; Krishna, G. R. Aditya; Eswaran, K.
2007-01-01
This paper proposes an unsupervised learning technique by using Multi-layer Mirroring Neural Network and Forgy's clustering algorithm. Multi-layer Mirroring Neural Network is a neural network that can be trained with generalized data inputs (different categories of image patterns) to perform non-linear dimensionality reduction and the resultant low-dimensional code is used for unsupervised pattern classification using Forgy's algorithm. By adapting the non-linear activation ...
Can artificial neural networks be used to predict the origin of ozone episodes?
International Nuclear Information System (INIS)
Tropospheric ozone is a secondary pollutant having a negative impact on health and environment. To control and minimize such impact the European Community established regulations to promote a clean air all over Europe. However, when an episode is related with natural mechanisms as Stratosphere–Troposphere Exchanges (STE), the benefits of an action plan to minimize precursor emissions are inefficient. Therefore, this work aims to develop a tool to identify the sources of ozone episodes in order to minimize misclassification and thus avoid the implementation of inappropriate air quality plans. For this purpose, an artificial neural network model – the Multilayer Perceptron – is used as a binary classifier of the source of an ozone episode. Long data series, between 2001 and 2010, considering the ozone precursors, 7Be activity and meteorological conditions were used. With this model, 2–7% of a mean error was achieved, which is considered as a good generalization. Accuracy measures for imbalanced data are also discussed. The MCC values show a good performance of the model (0.65–0.92). Precision and F1-measure indicate that the model specifies a little better the rare class. Thus, the results demonstrate that such a tool can be used to help authorities in the management of ozone, namely when its thresholds are exceeded due natural causes, as the above mentioned STE. Therefore, the resources used to implement an action plan to minimize ozone precursors could be better managed avoiding the implementation of inappropriate measures. - Highlights: • ANN can classify the origin of an O3 episode with a mean error around 2-7%. • The best classification is obtained when a simpler input combination is used. • ANN can help authorities to foster O3 action plans to control exceedances
Can artificial neural networks be used to predict the origin of ozone episodes?
Energy Technology Data Exchange (ETDEWEB)
Fontes, T., E-mail: trfontes@ua.pt [University Fernando Pessoa, Global Change, Energy, Environment and Bioengineering Center (CIAGEB), Praça 9 de Abril, 349, 4249-004 Porto (Portugal); University of Aveiro, Department of Mechanical Engineering/Centre for Mechanical Technology and Automation, Campus Universitário de Santiago, 3810-193 Aveiro (Portugal); Silva, L.M. [University of Aveiro, Department of Mathematics, Campus Universitário de Santiago, 3810-193 Aveiro (Portugal); INEB — Instituto de Engenharia Biomédica, Rua do Campo Alegre, 823, 4150-180 Porto (Portugal); Silva, M.P.; Barros, N. [University Fernando Pessoa, Global Change, Energy, Environment and Bioengineering Center (CIAGEB), Praça 9 de Abril, 349, 4249-004 Porto (Portugal); Carvalho, A.C. [New University of Lisbon, Faculty of Sciences and Technology/Center for Environmental and Sustainability Research (CENSE), Quinta da Torre, 2829-516 Caparica (Portugal)
2014-08-01
Tropospheric ozone is a secondary pollutant having a negative impact on health and environment. To control and minimize such impact the European Community established regulations to promote a clean air all over Europe. However, when an episode is related with natural mechanisms as Stratosphere–Troposphere Exchanges (STE), the benefits of an action plan to minimize precursor emissions are inefficient. Therefore, this work aims to develop a tool to identify the sources of ozone episodes in order to minimize misclassification and thus avoid the implementation of inappropriate air quality plans. For this purpose, an artificial neural network model – the Multilayer Perceptron – is used as a binary classifier of the source of an ozone episode. Long data series, between 2001 and 2010, considering the ozone precursors, {sup 7}Be activity and meteorological conditions were used. With this model, 2–7% of a mean error was achieved, which is considered as a good generalization. Accuracy measures for imbalanced data are also discussed. The MCC values show a good performance of the model (0.65–0.92). Precision and F{sub 1}-measure indicate that the model specifies a little better the rare class. Thus, the results demonstrate that such a tool can be used to help authorities in the management of ozone, namely when its thresholds are exceeded due natural causes, as the above mentioned STE. Therefore, the resources used to implement an action plan to minimize ozone precursors could be better managed avoiding the implementation of inappropriate measures. - Highlights: • ANN can classify the origin of an O{sub 3} episode with a mean error around 2-7%. • The best classification is obtained when a simpler input combination is used. • ANN can help authorities to foster O{sub 3} action plans to control exceedances.
Forecasting of preprocessed daily solar radiation time series using neural networks
Energy Technology Data Exchange (ETDEWEB)
Paoli, Christophe; Muselli, Marc; Nivet, Marie-Laure [University of Corsica, CNRS UMR SPE, Corte (France); Voyant, Cyril [University of Corsica, CNRS UMR SPE, Corte (France); Hospital of Castelluccio, Radiotherapy Unit, Ajaccio (France)
2010-12-15
In this paper, we present an application of Artificial Neural Networks (ANNs) in the renewable energy domain. We particularly look at the Multi-Layer Perceptron (MLP) network which has been the most used of ANNs architectures both in the renewable energy domain and in the time series forecasting. We have used a MLP and an ad hoc time series pre-processing to develop a methodology for the daily prediction of global solar radiation on a horizontal surface. First results are promising with nRMSE {proportional_to} 21% and RMSE {proportional_to} 3.59 MJ/m{sup 2}. The optimized MLP presents predictions similar to or even better than conventional and reference methods such as ARIMA techniques, Bayesian inference, Markov chains and k-Nearest-Neighbors. Moreover we found that the data pre-processing approach proposed can reduce significantly forecasting errors of about 6% compared to conventional prediction methods such as Markov chains or Bayesian inference. The simulator proposed has been obtained using 19 years of available data from the meteorological station of Ajaccio (Corsica Island, France, 41 55'N, 8 44'E, 4 m above mean sea level). The predicted whole methodology has been validated on a 1.175 kWc mono-Si PV power grid. Six prediction methods (ANN, clear sky model, combination..) allow to predict the best daily DC PV power production at horizon d + 1. The cumulated DC PV energy on a 6-months period shows a great agreement between simulated and measured data (R{sup 2} > 0.99 and nRMSE < 2%). (author)
A Neural-Network-Based Nonlinear Adaptive State-Observer for Pressurized Water Reactors
Directory of Open Access Journals (Sweden)
Zhe Dong
2013-10-01
Full Text Available Although there have been some severe nuclear accidents such as Three Mile Island (USA, Chernobyl (Ukraine and Fukushima (Japan, nuclear fission energy is still a source of clean energy that can substitute for fossil fuels in a centralized way and in a great amount with commercial availability and economic competitiveness. Since the pressurized water reactor (PWR is the most widely used nuclear fission reactor, its safe, stable and efficient operation is meaningful to the current rebirth of the nuclear fission energy industry. Power-level regulation is an important technique which can deeply affect the operation stability and efficiency of PWRs. Compared with the classical power-level controllers, the advanced power-level regulators could strengthen both the closed-loop stability and control performance by feeding back the internal state-variables. However, not all of the internal state variables of a PWR can be obtained directly by measurements. To implement advanced PWR power-level control law, it is necessary to develop a state-observer to reconstruct the unmeasurable state-variables. Since a PWR is naturally a complex nonlinear system with parameters varying with power-level, fuel burnup, xenon isotope production, control rod worth and etc., it is meaningful to design a nonlinear observer for the PWR with adaptability to system uncertainties. Due to this and the strong learning capability of the multi-layer perceptron (MLP neural network, an MLP-based nonlinear adaptive observer is given for PWRs. Based upon Lyapunov stability theory, it is proved theoretically that this newly-built observer can provide bounded and convergent state-observation. This observer is then applied to the state-observation of a special PWR, i.e., the nuclear heating reactor (NHR, and numerical simulation results not only verify its feasibility but also give the relationship between the observation performance and observer parameters.
Modeling of global horizontal irradiance in the United Arab Emirates with artificial neural networks
International Nuclear Information System (INIS)
This paper employs ANN (Artificial Neural Network) models to estimate GHI (global horizontal irradiance) for three major cities in the UAE (United Arab Emirates), namely Abu Dhabi, Dubai and Al-Ain. City data are then used to develop a comprehensive global GHI model for other nearby locations in the UAE. The ANN models use MLP (Multi-Layer Perceptron) and RBF (Radial Basis Function) techniques with comprehensive training algorithms, architectures, and different combinations of inputs. The UAE models are tested and validated against individual city models and data available from the UAE Solar Atlas with good agreement as attested by the computed statistical error parameters. The optimal ANN model is MLP-based and requires four mean daily weather parameters; namely, maximum temperature, wind speed, sunshine hours, and relative humidity. The computed statistical error parameters for the optimal MLP-ANN model in relation to the measured three-cities mean data (referred to as UAE data) are MBE (mean bias error) = ?0.0003 kWh/m2, RMSE = 0.179 kWh/m2, R2 = 99%, NSE (Nash-Sutcliffe model Efficiency coefficient) = 99%, and t-statistic = 0.005 at 5% significance level. Results prove the suitability of the ANN models for estimating the monthly mean daily GHI in different locations of the UAE. - Highlights: • ANN prediction models for the GHI (global horizontal irradiance) in the UAE. • Models used to estimate the potential of global solar radiation for UAE cities. • Data from the UAE Solar Atlas are used to validate developed ANN models. • ANN models are more efficient than regression models in predicting GHI
Wind speed spatial estimation for energy planning in Sicily: A neural kriging application
Energy Technology Data Exchange (ETDEWEB)
Cellura, M.; Marvuglia, A. [Dipartimento di Ricerche Energetiche ed Ambientali (DREAM), Universita degli Studi di Palermo, Viale delle Scienze, 90128 Palermo (Italy); Cirrincione, G. [ISSIA-CNR, Institute on Intelligent Systems for the Automation, Section of Palermo, via Dante12, Palermo (Italy); Miraoui, A. [Universite de Technologie de Belfort-Montbeliard (UTBM), Belfort (France)
2008-06-15
One of the first steps for the exploitation of any energy source is necessarily represented by its estimation and mapping at the aim of identifying the most suitable areas in terms of energy potential. In the field of renewable energies this is often a very difficult task, because the energy source is in this case characterized by relevant variations over space and time. This implies that any temporal, but also spatial, estimation model has to be able to incorporate this spatial and temporal variability. The paper deals with the spatial estimation of the wind fields in Sicily (Italy) by following a data-driven approach. Starting from the results of a preliminary study, a novel technique resulting from the integration of neural and geostatistical techniques was developed in order to obtain the wind speed maps for the region at 10 and 50 meters above the ground level. The mean values of the theoretical Weibull distribution function describing the wind regime at each of the available measurement sites were used to train a multi-layer perceptron (MLP) whose goal is to compute the most of the wind spatial trends. Other pieces of information about the territory (altitude, land coverage) were also used as inputs of the network and organized into a geographic information system (GIS) environment. The remaining de-trended linear means have been computed by using a universal kriging (UK) estimator. The results of these steps were then summed up and it was thus possible to obtain a map of the estimated wind fields. (author)
Application of neural networks to measurement methods based on radiation interactions with matter
International Nuclear Information System (INIS)
The possibility of improving by neuronal techniques the preparation and interpretation of nuclear measurements was investigated. A general methodology was developed and applied to various problems in this field. Whatever the problem to be treated, to solve it comes to determine the relation which binds the inputs to the outputs. Neural networks based on supervised training, like the multilayer Perceptron, have the capability to calculate any relation between a set of input and output data. On the other hand, the training phase is often a long and delicate operation whose difficulties grow with the size of the network: it is thus interesting to reduce it by introducing knowledge a priori and/or by reducing the number of inputs in order to extract the relevant information. If the correlations between the inputs are linear, the Principal Components Analysis (PCA) and its neuronal equivalents make it possible to obtain by orthogonal projection a reduced number of input components while preserving the maximum of initial information. If the correlations are nonlinear, the Curvilinear Components Analysis (CCA) allows, by a unsupervised training, to carry out a nonlinear projection of the inputs in a space of reduced size. Besides, it is noticed that when the dimension of the input space is equal to the intrinsic dimension of the problem, this last is practically solved by CCA. We propose a general method which consists in characterizing as well as possible the problem by its inputs and then to extract and classify the information contained in those by projection in a space of reduced size. Association between the projected data and the problem outputs is then carried out by a supervised training network. Certain results having to be provided with their associated uncertainty, a statistical method based on the bootstrap algorithm is proposed. Potential applications other that those treated are considered. (author)
Scientific Electronic Library Online (English)
Juan D., Velásquez; Sarah, Gutiérrez; Carlos J., Franco.
2013-06-01
Full Text Available La habilidad para obtener pronósticos precisos de la volatilidad es un importante problema para el analista financiero. En este artículo, se usa el modelo DAN2, un perceptrón multicapa y un modelo ARCH para pronosticar la varianza condicional mensual de una acción. Los resultados muestran que el mod [...] elo DAN2 es más preciso para pronosticar las varianzas dentro-de-la-muestra y fuera-de-la-muestra que los otros modelos considerados para el conjunto de datos utilizado. Así, el valor de esta red neuronal como herramienta predictiva es demostrado. Abstract in english The ability to obtain accurate volatility forecasts is an important issue for the financial analyst. In this paper, we use the DAN2 model, a multilayer perceptron and an ARCH model to predict the monthly conditional variance of stock prices. The results show that DAN2 model is more accurate for pred [...] icting in-sample and out-of-sample variance that the other considered models for the used dataset. Thus, the value of this neural network as a predictive tool is demonstrated.
Directory of Open Access Journals (Sweden)
F. GUNE?
2014-04-01
Full Text Available In this work, a novel multi-objective design optimization procedure is presented for the Minkowski Reflectarray RAs using a complete 3-D CST Microwave Studio MWS-based Multilayer Perceptron Neural Network MLP NN model including the substrate constant ?r with a hybrid Genetic GA and Nelder-Mead NM algorithm. The MLP NN model provides an accurate and fast model and establishes the reflection phase of a unit Minkowski RA element as a continuous function within the input domain including the substrate 1 ? ?r ? 6; 0.5mm ? h ? 3mm in the frequency between 8GHz ? f ? 12GHz. This design procedure enables a designer to obtain not only the most optimum Minkowski RA design all throughout the X- band, at the same time the optimum Minkowski RAs on the selected substrates. Moreover a design of a fully optimized X-band 15×15 Minkowski RA antenna is given as a worked example with together the tolerance analysis and its performance is also compared with those of the optimized RAs on the selected traditional substrates. Finally it may be concluded that the presented robust and systematic multi-objective design procedure is conveniently applied to the Microstrip Reflectarray RAs constructed from the advanced patches.
Directory of Open Access Journals (Sweden)
J D Velásquez
2012-06-01
Full Text Available Many time series with trend and seasonal pattern are successfully modeled and forecasted by the airline model of Box and Jenkins; however, this model neglects the presence of nonlinearity on data. In this paper, we propose a new nonlinear version of the airline model; for this, we replace the moving average linear component by a multilayer perceptron neural network. The proposedmodel is used for forecasting two benchmark time series; we found that theproposed model is able to forecast the time series with more accuracy that other traditional approaches.Muchas series de tiempo con tendencia y ciclos estacionales son exitosamente modeladas y pronosticadas usando el modelo airline de Box y Jenkins; sin embargo, la presencia de no linealidades en los datos son despreciadas por este modelo. En este artículo, se propone una nueva versión no lineal del modelo airline; para esto, se reemplaza la componente lineal de promedios móviles por un perceptrón multicapa. El modelo propuesto es usado para pronosticar dos series de tiempo benchmark; se encontró que el modelo propuesto es capaz de pronosticar las series de tiempo con mayor precisión que otras aproximaciones tradicionales.
Using Probabilistic Neural Networks for Handwritten Digit Recognition
Directory of Open Access Journals (Sweden)
Abdelkader Benyettou
2011-01-01
Full Text Available Artificial neural networks are well known in the field of pattern recognition and machine learning. Multi-layer neural networks are usually used as universal neural classifiers even though probabilistic neural networks represent a special type of artificial neural networks and have been designed to be used mainly in classification problems. In this article a study has been conducted to train a probabilistic neural network to recognize handwritten digits taken from the MINST database for handwritten digits. Results presented in this paper show good performance and generalization capacity of the proposed network for a real-world big database and no deep tuning of the parameters is required.
Directory of Open Access Journals (Sweden)
Juan D Velásquez
2008-12-01
Full Text Available Una red neuronal autorregresiva es estimada para el precio mensual brasileño de corto plazo de la electricidad, la cual describe mejor la dinámica de los precios que un modelo lineal autorregresivo y que un perceptrón multicapa clásico que usan las mismas entradas y neuronas en la capa oculta. El modelo propuesto es especificado usando un procedimiento estadístico basado en el contraste del radio de verosimilitud. El modelo pasa una batería de pruebas de diagnóstico. El procedimiento de especificación propuesto permite seleccionar el número de unidades en la capa oculta y las entradas a la red neuronal, usando pruebas estadísticas que tienen en cuenta la cantidad de los datos y el ajuste del modelo a la serie de precios. La especificación del modelo final demuestra que el precio para el próximo mes es una función no lineal del precio actual, de la energía afluente actual y de la energía almacenada en el embalse equivalente en el mes actual y dos meses atrás.An autoregressive neural network model is estimated for the monthly Brazilian electricity spot price, which describes the prices dynamics better than a linear autoregressive model and a classical multilayer perceptron using the same input and neurons in the hidden layer. The proposed model is specified using a statistical procedure based on a likelihood ratio test. The model passes a battery of diagnostic tests. The proposed specification procedure allows us to select the number of units in hidden layer and the inputs to the neural network based on statistical tests, taking into account the number of data and the model fitting to the price time series. The final model specification demonstrates that the price for the next month is a nonlinear function of the current price, the current energy inflow, and the energy saved in the equivalent reservoir in the current month and two months ago.
Directory of Open Access Journals (Sweden)
Tomas Ayala-Silva
2006-01-01
Full Text Available A fast identification of insufficiency of nutrients using spectral features would be a useful instrument in farming and in other nutrient demanding agricultural systems such as those proposed for long period space missions. A Multilayer Perceptron (MLP neural network and backpropagation algorithm was used to differentiate between normal leaves of wheat (Triticum aestivum L. and those deficient in nitrogen, phosphorus, (K and (Ca using hyperspectral data. The network consisted of three layers with spectral reflectance of the leaves in wavelengths from 401 to 770 nm as the input layer and the nutrient concentrations as the output layer. Based upon the values of actual nutrient concentrations (mg L-1, plants were classified as either deficient or standard. Wheat plants were grown for .100 days under both hydroponic conditions in the greenhouse and vermiculite media in a growth chamber using Hoagland`s complete nutrient solution with selected minerals eliminated to induce specific nutrient deficiencies. Check plants received complete nutrient solutions. The MLP model was trained and tested successfully within 1000 epochs as the MSE of the sample-training curve approached zero. The backpropagation algorithm functioned well with the following accuracies for the classification model: N 90.9, P 100, K 90 and Ca 100%. Using the regression model, the following accuracies were obtained: N 93.0, P 87.2, K 91.9 and Ca 97.4%. This affirms the potential of using spectral data coupled with either a classification or regression neural network models to quickly categorize leaves deficient in these four major minerals so that remedial applications of those nutrients can be made before the yield is drastically affected.
Forecasting Precipitation with Artificial Neural Networks (Case Study: Tehran
Directory of Open Access Journals (Sweden)
M.H. Gholizadeh
2009-01-01
Full Text Available Artificial Neural Networks (ANN, which emulate the parallel distributed processing of the human nervous system, have proven to be very successful in dealing with complicated problems, such as function approximation and pattern recognition. Rainfall forecasting has been a difficult subject due to the complexity of the physical processes involved and the variability of rainfall in space and time. Artificial Neural Networks (ANN, which perform a nonlinear mapping between inputs and outputs, are one of the techniques that are suitable for rainfall forecasting. Multiple perceptron neural networks were trained with actual monthly precipitation data from Tehran station for a time period of 53 years. Predicted amounts are of next-month-precipitation in the next year. The ANN models provided a good fit with the actual data and have shown a high feasibility in prediction of month rainfall precipitation. Combination neural networks with Genetic algorithm showed better results.
Some applications of neural networks in microwave modeling
Milovanovi? Bratislav D.; Markovi? Vera; Marinkovi? Zlatica D.; Stankovi? Zoran
2003-01-01
This paper presents some applications of neural networks in the microwave modeling. The applications are related to modeling of either passive or active structures and devices. Modeling is performed using not only simple multilayer perception network (MLP) but also advanced knowledge based neural network (KBNN) structures.
Some applications of neural networks in microwave modeling
Directory of Open Access Journals (Sweden)
Milovanovi? Bratislav D.
2003-01-01
Full Text Available This paper presents some applications of neural networks in the microwave modeling. The applications are related to modeling of either passive or active structures and devices. Modeling is performed using not only simple multilayer perception network (MLP but also advanced knowledge based neural network (KBNN structures.
Control of Multilayer Networks
Menichetti, Giulia; Bianconi, Ginestra
2015-01-01
The controllability of a network is a theoretical problem of relevance in a variety of contexts ranging from financial markets to the brain. Until now, network controllability has been characterized only on isolated networks, while the vast majority of complex systems are formed by multilayer networks. Here we build a theoretical framework for the linear controllability of multilayer networks by mapping the problem into a combinatorial matching problem. We found that correlating the external signals in the different layers can significantly reduce the multiplex network robustness to node removal, as it can be seen in conjunction with a hybrid phase transition occurring in interacting Poisson networks. Moreover we observe that multilayer networks can stabilize the fully controllable multiplex network configuration that can be stable also when the full controllability of the single network is not stable.
Scientific Electronic Library Online (English)
Luiz Moreira, Coelho Junior; José Luiz Pereira de, Rezende; André Luiz França, Batista; Adriano Ribeiro de, Mendonça; Wilian Soares, Lacerda.
2013-06-01
Full Text Available A energia é um importante fator de crescimento econômico e vital para a estabilidade de uma nação. O carvão vegetal é um recurso energético renovável, um dos insumos básicos responsáveis pelo desenvolvimento das indústrias de base florestal no Brasil. Objetivou-se, neste artigo, fazer a prognose par [...] a o ano de 2007 da série de preços do carvão vegetal, utilizando as Redes Neurais Artificiais. Foi utilizada a RNA perceptron de camadas múltiplas, feed-forward, cujos resultados são próximos da realidade. Os principais resultados encontrados foram: os preços reais do carvão vegetal foram declinantes no período de 1975 a 2000 e crescentes a partir do início do século XXI; a arquitetura da Rede Neural Artificial que realizou melhor previsão foi a com duas camadas escondidas; a taxa de aprendizagem mais eficiente foi de 0,99 e 600 ciclos, que representou treinamento da RNA mais satisfatório e mais preciso. A previsão, usando a RNA, se mostrou mais precisa quando comparada pelo erro quadrático médio de previsão de outros estudos para a série de preços de carvão vegetal em Minas Gerais. Abstract in english Energy is an important factor of economic growth and is critical to the stability of a nation. Charcoal is a renewable energy resource and is a fundamental input to the development of the Brazilian forest-based industry. The objective of this study is to provide a prognosis of the charcoal price ser [...] ies for the year 2007 by using Artificial Neural Networks. A feedforward multilayer perceptron ANN was used, the results of which are close to reality. The main findings are that: real prices of charcoal dropped between 1975 and 2000 and rose from the early 21st century; the ANN with two hidden layers was the architecture making the best prediction; the most effective learning rate was 0.99 and 600 cycles, representing the most satisfactory and accurate ANN training. Prediction using ANN was found to be more accurate when compared by the mean squared error to other studies modeling charcoal price series in Minas Gerais state.
Accurate Wavelet Neural Network for Efficient Controlling of an Active Magnetic Bearing System
Directory of Open Access Journals (Sweden)
Youssef Harkouss
2010-01-01
Full Text Available Problem statement: The synthesis of a command by the neural network has an excellent advantage over the classical one such as PID. This study presented a fast and accurate Wavelet Neural Network (WNN approach for efficient controlling of an Active Magnetic Bearing (AMB system. Approach: The proposed approach combined neural network with the wavelet theory. Wavelet theory may be exploited in deriving a good initialization for the neural network and thus improved convergence of the learning algorithm. Results: We tested two control systems based on three types of neural controllers: Multiplayer Perceptron (MLP controller, RBF Neural Network (RBFNN controller and WNN controller. The simulation results show that the proposed WNN controller provides better performance comparing with standard PID controller, MLP and RBFNN controllers. Conclusion: The proposed WNN approach was shown to be useful in controlling nonlinear dynamic mechanical system, such as the AMB system used in this study.
Representation of Functional Data in Neural Networks
Rossi, Fabrice; Conan-Guez, Brieuc; Verleysen, Michel
2005-01-01
Functional Data Analysis (FDA) is an extension of traditional data analysis to functional data, for example spectra, temporal series, spatio-temporal images, gesture recognition data, etc. Functional data are rarely known in practice; usually a regular or irregular sampling is known. For this reason, some processing is needed in order to benefit from the smooth character of functional data in the analysis methods. This paper shows how to extend the Radial-Basis Function Networks (RBFN) and Multi-Layer Perceptron (MLP) models to functional data inputs, in particular when the latter are known through lists of input-output pairs. Various possibilities for functional processing are discussed, including the projection on smooth bases, Functional Principal Component Analysis, functional centering and reduction, and the use of differential operators. It is shown how to incorporate these functional processing into the RBFN and MLP models. The functional approach is illustrated on a benchmark of spectrometric data ana...
Hruschka, Harald
2000-01-01
Attraction models are very popular in marketing research for studying the effects of marketing instruments on market shares. However, so far the marketing literature only considers attraction models with certain functional forms that exclude threshold or saturation effects on attraction values. We can achieve greater exibility by using the neural net based approach introduced here. This approach assesses brands' attraction values by means of a perceptron with one hidden layer. The approach us...
Directory of Open Access Journals (Sweden)
R Noori
2009-03-01
Full Text Available "nBackground: Municipal solid waste (MSW is the natural result of human activities. MSW generation modeling is of prime importance in designing and programming municipal solid waste management system. This study tests the short-term prediction of waste generation by artificial neural network (ANN and principal component-regression analysis."nMethods: Two forecasting techniques are presented in this paper for prediction of waste generation (WG. One of them, multivariate linear regression (MLR, is based on principal component analysis (PCA. The other technique is ANN model. For ANN, a feed-forward multi-layer perceptron was considered the best choice for this study. However, in this research after removing the problem of multicolinearity of independent variables by PCA, an appropriate model (PCA-MLR was developed for predicting WG."nResults: Correlation coefficient (R and average absolute relative error (AARE in ANN model obtained as equal to 0.837 and 4.4% respectively. In comparison whit PCA-MLR model (R= 0.445, MARE= 6.6%, ANN model has a better results. However, threshold statistic error is done for the both models in the testing stage that the maximum absolute relative error (ARE for 50% of prediction is 3.7% in ANN model but it is 6.2% for PCA-MLR model. Also we can say that the maximum ARE for 90% of prediction in testing step of ANN model is about 8.6% but it is 10.5% for PCA-MLR model."nConclusion: The ANN model has better results in comparison with the PCA-MLR model therefore this model is selected for prediction of WG in Tehran.
Piecuch, M.
1988-01-01
Diffusion experiments are usually performed at macroscopic length scales, use of multilayers can lower these scale down to the nanometer range. This paper describes the main idea governing atomic transport at such short distance and in such inhomogeneous systems. The basic experimental methods involved are also discussed. Some representative recent works are shortly described.
A COLLECTIVE APPROACH TOWARDS ENERGY-BASED STRUCTURE FOR AUTONOMOUS LEARNING
Directory of Open Access Journals (Sweden)
Ananya Pothula
2013-06-01
Full Text Available The technique of image denoising proceeds a noisy image as input and yields an image where the noise has been condensed. Neural networks have already been used to denoise images. It is probable to attain state-of-the-art denoising presentation with a simple multilayer perceptron. Multilayer perceptrons can be assumed of as widespread function approximators and are more commanding. A multi-layer perceptron is a nonlinear function that maps vector-valued input by means of numerous hidden layers to vector-valued output. The design of a multi-layer perceptron is de?ned by the number of hidden layers and by the layer sizes and it is similarly named as feed-forward neural network. The parameters of the multilayer perceptrons are projected by preparation on pairs of noisy and clean image patches by means of stochastic gradient descent. Multilayer perceptron maps noisy patches onto noise-free ones which is probable due to the capability of the multilayer perceptron selected is vast sufficient containing of adequate hidden layers with suf?ciently numerous concealed elements. The patch magnitude is selected great sufficient containing sufficient information to improve a noise-free version. Training illustrations are produced on the ?y by humiliating noise- free patches with noise. Multilayer perceptron is personalized to a single level of noise and does not simplify well to other noise levels linked to other denoising methods. Working out high capacity multilayer perceptron with big training sets is possible by means of modern Graphics Processing Units.
Learning by random walks in the weight space of the Ising perceptron
International Nuclear Information System (INIS)
Several variants of a stochastic local search process for constructing the synaptic weights of an Ising perceptron are studied. In this process, binary patterns are sequentially presented to the Ising perceptron and are then learned as the synaptic weight configuration is modified through a chain of single- or double-weight flips within the compatible weight configuration space of the earlier learned patterns. This process is able to reach a storage capacity of ??0.63 for pattern length N = 101 and ??0.41 for N = 1001. If in addition a relearning process is exploited, the learning performance is further improved to a storage capacity of ??0.80 for N = 101 and ??0.42 for N = 1001. We found that, for a given learning task, the solutions constructed by the random walk learning process are separated by a typical Hamming distance, which decreases with the constraint density ? of the learning task; at a fixed value of ?, the width of the Hamming distance distribution decreases with N
Learning by random walks in the weight space of the Ising perceptron
Huang, Haiping; Zhou, Haijun
2010-08-01
Several variants of a stochastic local search process for constructing the synaptic weights of an Ising perceptron are studied. In this process, binary patterns are sequentially presented to the Ising perceptron and are then learned as the synaptic weight configuration is modified through a chain of single- or double-weight flips within the compatible weight configuration space of the earlier learned patterns. This process is able to reach a storage capacity of ??0.63 for pattern length N = 101 and ??0.41 for N = 1001. If in addition a relearning process is exploited, the learning performance is further improved to a storage capacity of ??0.80 for N = 101 and ??0.42 for N = 1001. We found that, for a given learning task, the solutions constructed by the random walk learning process are separated by a typical Hamming distance, which decreases with the constraint density ? of the learning task; at a fixed value of ?, the width of the Hamming distance distribution decreases with N.
International Nuclear Information System (INIS)
A cooperative multi-modular neural network architecture is presented: a Multi-Layer Perceptron (MLP), followed by a Radial Basis Function network (RBF). It is shown that, in the LEP experiment of electron-positron collision run at CERN, this architecture was able to outperform both a simple multi-layer perceptron, a multi-modular MLP+LVQ (LVQ: Learning Vector Quantization) and MLP+RBF trained sequentially and a conventional technique (Discriminant Analysis). (author). 10 refs., 2 figs
A new approach to the analysis of alpha spectra based on neural network techniques
Energy Technology Data Exchange (ETDEWEB)
Baeza, A.; Miranda, J. [LARUEX, Environmental Radioactivity Laboratory, Dept. Applied Physics, Faculty of Veterinary Science, University of Extremadura, Avda. Universidad s/n, 10003 Caceres (Spain); Guillen, J., E-mail: fguillen@unex.es [LARUEX, Environmental Radioactivity Laboratory, Dept. Applied Physics, Faculty of Veterinary Science, University of Extremadura, Avda. Universidad s/n, 10003 Caceres (Spain); Corbacho, J.A. [LARUEX, Environmental Radioactivity Laboratory, Dept. Applied Physics, Faculty of Veterinary Science, University of Extremadura, Avda. Universidad s/n, 10003 Caceres (Spain); Perez, R. [Dept. Technology of Computers and Communications, Polytechnics School, University of Extremadura, Avda. Universidad s/n, 10003 Caceres (Spain)
2011-10-01
The analysis of alpha spectra requires good radiochemical procedures in order to obtain well differentiated alpha peaks in the spectrum, and the easiest way to analyze them is by directly summing the counts obtained in the Regions of Interest (ROIs). However, the low-energy tails of the alpha peaks frequently make this simple approach unworkable because some peaks partially overlap. Many fitting procedures have been proposed to solve this problem, most of them based on semi-empirical mathematical functions that emulate the shape of a theoretical alpha peak. The main drawback of these methods is that the great number of fitting parameters used means that their physical meaning is obscure or completely lacking. We propose another approach-the application of an artificial neural network. Instead of fitting the experimental data to a mathematical function, the fit is carried out by an artificial neural network (ANN) that has previously been trained to model the shape of an alpha peak using as training patterns several polonium spectra obtained from actual samples analyzed in our laboratory. In this sense, the ANN is able to learn the shape of an actual alpha peak. We have designed such an ANN as a feed-forward multi-layer perceptron with supervised training based on a back-propagation algorithm. The fitting procedure is based on the experimental observables that are characteristic of alpha peaks-the number of counts of the maximum and several peak widths at different heights. Polonium isotope spectra were selected because the alpha peaks corresponding to {sup 208}Po, {sup 209}Po, and {sup 210}Po are monoenergetic and well separated. The uncertainties introduced by this fitting procedure were less than the counting uncertainties. This new approach was applied to the problem of resolving overlapping peaks. Firstly, a theoretical study was carried out by artificially overlapping alpha peaks from actual samples in order to test the ability of the ANN to resolve each peak. Then, the ANN procedure was checked by determining the activity levels of different spectra obtained from certified samples for which one knows a priori the radioactive content, and its results were compared with those of other methods.
Multistage neural network model for dynamic scene analysis
Energy Technology Data Exchange (ETDEWEB)
Ajjimarangsee, P.
1989-01-01
This research is concerned with dynamic scene analysis. The goal of scene analysis is to recognize objects and have a meaningful interpretation of the scene from which images are obtained. The task of the dynamic scene analysis process generally consists of region identification, motion analysis and object recognition. The objective of this research is to develop clustering algorithms using neural network approach and to investigate a multi-stage neural network model for region identification and motion analysis. The research is separated into three parts. First, a clustering algorithm using Kohonens' self-organizing feature map network is developed to be capable of generating continuous membership valued outputs. A newly developed version of the updating algorithm of the network is introduced to achieve a high degree of parallelism. A neural network model for the fuzzy c-means algorithm is proposed. In the second part, the parallel algorithms of a neural network model for clustering using the self-organizing feature maps approach and a neural network that models the fuzzy c-means algorithm are modified for implementation on a distributed memory parallel architecture. In the third part, supervised and unsupervised neural network models for motion analysis are investigated. For a supervised neural network, a three layer perceptron network is trained by a series of images to recognize the movement of the objects. For the unsupervised neural network, a self-organizing feature mapping network will learn to recognize the movement of the objects without an explicit training phase.
Hybrid Neural Network Architecture for On-Line Learning
Chen, Yuhua; Wang, Lei
2008-01-01
Approaches to machine intelligence based on brain models have stressed the use of neural networks for generalization. Here we propose the use of a hybrid neural network architecture that uses two kind of neural networks simultaneously: (i) a surface learning agent that quickly adapt to new modes of operation; and, (ii) a deep learning agent that is very accurate within a specific regime of operation. The two networks of the hybrid architecture perform complementary functions that improve the overall performance. The performance of the hybrid architecture has been compared with that of back-propagation perceptrons and the CC and FC networks for chaotic time-series prediction, the CATS benchmark test, and smooth function approximation. It has been shown that the hybrid architecture provides a superior performance based on the RMS error criterion.
Research on Speech Recognition Based on Neural Networks
Directory of Open Access Journals (Sweden)
YUE Miao
2010-07-01
Full Text Available Because of good characteristics of the abstract classification, neural networks have become an effective tool for resolving issues related to recognition, and have been applied to the research and development of speech recognition system. A speech recognizer system comprises of two blocks, Feature Extractor and Recognizer. For increasing the recognition accuracy, this paper proposes two types of speech recognition system whose recognition block uses the recurrent neural network(RNN and multi layer perceptron(MLP respectively. Furthermore, the main work steps of Feature Extractor (FE block is introduced and the structure of two types of neural networks mentioned above is discussed. Using a standard LPC Cepstrum, the FE translates the input speech into a trajectory in the LPC Cepstrum feature space. The recognizer block discovers the relationships between the trajectories and recognizes the word. The results show that the MLP's recognition accuracies were better than the RNN's,while the RNN's recognition accuracies achieved 85%.
Mobile Multilayer IPsec protocol
Directory of Open Access Journals (Sweden)
T.Gayathri
2009-08-01
Full Text Available A mobile user moves around and switches between wireless cells, subnets and domains, it needs to maintain the session continuity. At the same time security of signaling and transport media should not be compromised. A multi-layer security framework involving user authentication, packet based encryption and access control mechanism can provide the desired level of security to the mobile users. Supporting streaming traffic in a mobile wireless Internet is faced with several challenges due to continuous handoff experienced by a mobile user. These challenges include dynamic binding, location management, quality of service and end-to-end security for signaling and transport. Mobile users will use heterogeneous radio access networking technologies. Mobile multilayer IPsec protocol (MML IPSec extends ML-IPSec to deal with mobility and make it suitable for wireless networks. MML-IPSec is integration of ML-IPSec and mobile IP.
Industrial Brewery Modelling by Using Artificial Neural Network
Directory of Open Access Journals (Sweden)
E. Assidjo
2006-01-01
Full Text Available Fermentation is a complex phenomenon well studied which still provides challenges to brewers. In this study, artificial neural network, precisely multi layer perceptron and recurrent one were utilised for modelling either static (yeast quantity to add to wort for fermentation or dynamic (fermentation process phenomena. In both cases, the simulated responses are very close to the observed ones with residual biases inferior to 4.5%. Thus, ANN models present good predictive ability confirming the suitability of ANN for industrial process modelling.
A comparison of artificial neural networks used for river forecasting
Dawson, C W; Wilby, R. L.
1999-01-01
This paper compares the performance of two artificial neural network (ANN) models ? the multi layer perceptron (MLP) and the radial basis function network (RBF) ? with a stepwise multiple linear regression model (SWMLR) and zero order forecasts (ZOF) of river flow. All models were trained using 15 minute rainfall-runoff data for the River Mole, a flood-prone tributary of the River Thames, UK. The models were then used to forecast river flows with a 6 hour lead time and 15 minute resolution, g...
Neural Network based Closed loop Speed Control of DC Motor using Arduino Uno.
Neerparaj Rai
2013-01-01
This paper presents the design and implementation of Arduino Uno based DC motor speed control system using Multilayer Neural Network controller and PID controller. A model reference structure is developed using PID control to obtain the neural controller .The artificial neural network is trained by Levenberg-Marquardt back propagation algorithm. Feed forward neural network with two hidden neurons and one output neuron is used. Speed of the dc motor is controlled by varying the duty cycle of t...
Application of neural network to CT
International Nuclear Information System (INIS)
This paper presents a new method for two-dimensional image reconstruction by using a multilayer neural network. Multilayer neural networks are extensively investigated and practically applied to solution of various problems such as inverse problems or time series prediction problems. From learning an input-output mapping from a set of examples, neural networks can be regarded as synthesizing an approximation of multidimensional function (that is, solving the problem of hypersurface reconstruction, including smoothing and interpolation). From this viewpoint, neural networks are well suited to the solution of CT image reconstruction. Though a conventionally used object function of a neural network is composed of a sum of squared errors of the output data, we can define an object function composed of a sum of residue of an integral equation. By employing an appropriate line integral for this integral equation, we can construct a neural network that can be used for CT. We applied this method to some model problems and obtained satisfactory results. As it is not necessary to discretized the integral equation using this reconstruction method, therefore it is application to the problem of complicated geometrical shapes is also feasible. Moreover, in neural networks, interpolation is performed quite smoothly, as a result, inverse mapping can be achieved smoothly even in case of including experimental and numerical errors, However, use of conventional back propagation technique for optimization leads to an expensive computation cost. To overcome this drawback, 2nd order optimization methods or parallel computing will be applied in future. (J.P.N.)
Unrealizable learning in binary feedforward neural networks
Sporre, M
1995-01-01
Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e. having more units than the student. It is shown that this is the same as using training data corrupted by Gaussian noise. Each machine is considered in the high temperature limit and in the replica symmetric approximation as well as for one step of replica symmetry breaking. For the perceptron a phase transition is found for low noise. However the transition is not to optimal learning. If the noise is increased the transition disappears. In both cases \\epsilon _{g} will approach optimal performance with a (\\ln\\alpha /\\alpha)^k decay for large \\alpha. For the tree committee machine noise in the input layer is studied, as well as noise in the hidden layer. If there is no noise in the input layer there is, in the case of one step of repl! ica symmetry breaking, a phase tra nsit...
Directory of Open Access Journals (Sweden)
Carlos Cassiano Denipotti Veronezi
2011-04-01
Full Text Available OBJETIVOS: Conhecer as vantagens da utilização das redes neurais artificiais no reconhecimento de padrões em radiografias de coluna lombar na incidência perfil para auxiliar no diagnóstico da osteoartrite primária. MÉTODO: Estudo transversal, descritivo, analítico, de abordagem quantitativa e com ênfase diagnóstica. O conjunto de treinamento foi composto por imagens coletadas no período de janeiro a julho de 2009 de pacientes submetidos a radiografias digitais de coluna lombar na incidência em perfil provenientes de um serviço de radiologia localizado no município de Criciúma (SC. Das 260 imagens coletadas, foram excluídas: as radiografias distorcidas, as patologias que alteram a arquitetura da coluna lombar e os padrões de difícil caracterização, resultando em um total de 206 imagens. O banco de imagens (n = 206 foi subdividido, resultando em 68 radiografias para a etapa de treinamento, 68 para testes e 70 para validação. Foi utilizada uma rede neural híbrida baseada em mapas auto-organizáveis de Kohonen e redes Multilayer Perceptron. RESULTADOS: Após 90 ciclos, foi realizada a validação com o melhor teste, alcançando acurácia de 62,85%, sensibilidade de 65,71% e especificidade de 60%. CONCLUSÃO: Apesar da demonstração de uma eficácia mediana, por se tratar de estudo de caráter inovador, seus valores mostram um futuro promissor da técnica utilizada, com sugestão para trabalhos futuros com abrangência na metodologia de processamento das imagens e ciclos com uma quantidade maior de radiografias.OBJECTIVE: To ascertain the advantages of applying artificial neural networks to recognize patterns on lumbar column radiographs in order to aid in the process of diagnosing primary osteoarthritis. METHODS: This was a cross-sectional descriptive analytical study with a quantitative approach and an emphasis on diagnosis. The training set was composed of images collected between January and July 2009 from patients who had undergone lateral-view digital radiographs of the lumbar column, which were provided by a radiology clinic located in the municipality of Criciúma (SC. Out of the total of 260 images gathered, those with distortions, those presenting pathological conditions that altered the architecture of the lumbar column and those with patterns that were difficult to characterize were discarded, thus resulting in 206 images. The image data base (n = 206 was then subdivided, resulting in 68 radiographs for the training stage, 68 images for tests and 70 for validation. A hybrid neural network based on Kohonen self-organizing maps and on Multilayer Perceptron networks was used. RESULTS: After 90 cycles, the validation was carried out on the best results, thereby reaching accuracy of 62.85%, sensitivity of 65.71% and specificity of 60%. CONCLUSIONS: Even though the effectiveness shown was moderate, this study is of innovative nature. Hence, the values show that the technique used has a promising future, thus pointing towards further studies covering the image and cycle processing methodology with a larger quantity of radiographs.
Directory of Open Access Journals (Sweden)
Mayra Luiza Marques da Silva
2009-12-01
Full Text Available Objetivou-se, neste trabalho, avaliar o ajuste do modelo volumétrico de Schumacher e Hall por diferentes algoritmos, bem como a aplicação de redes neurais artificiais para estimação do volume de madeira de eucalipto em função do diâmetro a 1,30 m do solo (DAP, da altura total (Ht e do clone. Foram utilizadas 21 cubagens de povoamentos de clones de eucalipto com DAP variando de 4,5 a 28,3 cm e altura total de 6,6 a 33,8 m, num total de 862 árvores. O modelo volumétrico de Schumacher e Hall foi ajustado nas formas linear e não linear, com os seguintes algoritmos: Gauss-Newton, Quasi-Newton, Levenberg-Marquardt, Simplex, Hooke-Jeeves Pattern, Rosenbrock Pattern, Simplex, Hooke-Jeeves e Rosenbrock, utilizado simultaneamente com o método Quasi-Newton e com o princípio da Máxima Verossimilhança. Diferentes arquiteturas e modelos (Multilayer Perceptron MLP e Radial Basis Function RBF de redes neurais artificiais foram testados, sendo selecionadas as redes que melhor representaram os dados. As estimativas dos volumes foram avaliadas por gráficos de volume estimado em função do volume observado e pelo teste estatístico L&O. Assim, conclui-se que o ajuste do modelo de Schumacher e Hall pode ser usado na sua forma linear, com boa representatividade e sem apresentar tendenciosidade; os algoritmos Gauss-Newton, Quasi-Newton e Levenberg-Marquardt mostraram-se eficientes para o ajuste do modelo volumétrico de Schumacher e Hall, e as redes neurais artificiais apresentaram boa adequação ao problema, sendo elas altamente recomendadas para realizar prognose da produção de florestas plantadas.This research aimed at evaluating the adjustment of Schumacher and Hall volumetric model by different algorithms and the application of artificial neural networks to estimate the volume of wood of eucalyptus according to the diameter at breast height (DBH, total height (Ht of the clone. For such, 21 scalings of stands of eucalyptus clones were used with DBH ranging from 4,5 to 28,3 cm and total height ranging from 6,6 to 33,8 m. The Schumacher and Hall volumetric model was adjusted linearly and nonlinearly with the following algorithms: Gauss-Newton, Quasi-Newton, Levenberg-Marquardt, Simplex, Hooke-Jeeves Pattern, Rosenbrock Pattern; Simplex, Hooke-Jeeves, and Rosenbrock, used simultaneously with the Quasi-Newton method and the principle of Maximum Likelihood. Different architectures and models (Multilayer Perceptron - MLP and Radial Basis Function - RBF of artificial neural networks were tested and the networks that best represented the data were selected. Estimates of the volumes were evaluated by graphics of estimated volume according to the observed volume and by the L&O statistical test . It was concluded that the adjustment of the Schumacher and Hall model can be used in its linear form, with good representation and without presenting bias of the data; the Gauss-Newton, Quasi-Newton and Levenberg-Marquardt algorithms were effective in the adjustment of Schumacher and Hall volumetric model. The artificial neural networks showed good adequacy to the problem and are highly recommended to perform production prognoses of planted forests.
Scientific Electronic Library Online (English)
Mayra Luiza Marques da, Silva; Daniel Henrique Breda, Binoti; José Marinaldo, Gleriani; Helio Garcia, Leite.
2009-12-01
Full Text Available Objetivou-se, neste trabalho, avaliar o ajuste do modelo volumétrico de Schumacher e Hall por diferentes algoritmos, bem como a aplicação de redes neurais artificiais para estimação do volume de madeira de eucalipto em função do diâmetro a 1,30 m do solo (DAP), da altura total (Ht) e do clone. Foram [...] utilizadas 21 cubagens de povoamentos de clones de eucalipto com DAP variando de 4,5 a 28,3 cm e altura total de 6,6 a 33,8 m, num total de 862 árvores. O modelo volumétrico de Schumacher e Hall foi ajustado nas formas linear e não linear, com os seguintes algoritmos: Gauss-Newton, Quasi-Newton, Levenberg-Marquardt, Simplex, Hooke-Jeeves Pattern, Rosenbrock Pattern, Simplex, Hooke-Jeeves e Rosenbrock, utilizado simultaneamente com o método Quasi-Newton e com o princípio da Máxima Verossimilhança. Diferentes arquiteturas e modelos (Multilayer Perceptron MLP e Radial Basis Function RBF) de redes neurais artificiais foram testados, sendo selecionadas as redes que melhor representaram os dados. As estimativas dos volumes foram avaliadas por gráficos de volume estimado em função do volume observado e pelo teste estatístico L&O. Assim, conclui-se que o ajuste do modelo de Schumacher e Hall pode ser usado na sua forma linear, com boa representatividade e sem apresentar tendenciosidade; os algoritmos Gauss-Newton, Quasi-Newton e Levenberg-Marquardt mostraram-se eficientes para o ajuste do modelo volumétrico de Schumacher e Hall, e as redes neurais artificiais apresentaram boa adequação ao problema, sendo elas altamente recomendadas para realizar prognose da produção de florestas plantadas. Abstract in english This research aimed at evaluating the adjustment of Schumacher and Hall volumetric model by different algorithms and the application of artificial neural networks to estimate the volume of wood of eucalyptus according to the diameter at breast height (DBH), total height (Ht) of the clone. For such, [...] 21 scalings of stands of eucalyptus clones were used with DBH ranging from 4,5 to 28,3 cm and total height ranging from 6,6 to 33,8 m. The Schumacher and Hall volumetric model was adjusted linearly and nonlinearly with the following algorithms: Gauss-Newton, Quasi-Newton, Levenberg-Marquardt, Simplex, Hooke-Jeeves Pattern, Rosenbrock Pattern; Simplex, Hooke-Jeeves, and Rosenbrock, used simultaneously with the Quasi-Newton method and the principle of Maximum Likelihood. Different architectures and models (Multilayer Perceptron - MLP and Radial Basis Function - RBF) of artificial neural networks were tested and the networks that best represented the data were selected. Estimates of the volumes were evaluated by graphics of estimated volume according to the observed volume and by the L&O statistical test . It was concluded that the adjustment of the Schumacher and Hall model can be used in its linear form, with good representation and without presenting bias of the data; the Gauss-Newton, Quasi-Newton and Levenberg-Marquardt algorithms were effective in the adjustment of Schumacher and Hall volumetric model. The artificial neural networks showed good adequacy to the problem and are highly recommended to perform production prognoses of planted forests.
Vadim Romanuke
2013-01-01
There is considered an image recognition problem, defined for the single hidden layer perceptron, fed with 5-by-7 monochrome images on its input under Gaussian noise of their distortion. In this neural network the hidden layer neuron number should be set optimally to maximize its productivity. For minimizing traintime duration and recognition error rate both simultaneously there are suggested two ways of solving the corresponding two-objective minimization problem. One of them deals with equi...
Bade, Richard; Bijlsma, Lubertus; Miller, Thomas H; Barron, Leon P; Sancho, Juan Vicente; Hernández, Felix
2015-12-15
The recent development of broad-scope high resolution mass spectrometry (HRMS) screening methods has resulted in a much improved capability for new compound identification in environmental samples. However, positive identifications at the ng/L concentration level rely on analytical reference standards for chromatographic retention time (tR) and mass spectral comparisons. Chromatographic tR prediction can play a role in increasing confidence in suspect screening efforts for new compounds in the environment, especially when standards are not available, but reliable methods are lacking. The current work focuses on the development of artificial neural networks (ANNs) for tR prediction in gradient reversed-phase liquid chromatography and applied along with HRMS data to suspect screening of wastewater and environmental surface water samples. Based on a compound tR dataset of >500 compounds, an optimized 4-layer back-propagation multi-layer perceptron model enabled predictions for 85% of all compounds to within 2min of their measured tR for training (n=344) and verification (n=100) datasets. To evaluate the ANN ability for generalization to new data, the model was further tested using 100 randomly selected compounds and revealed 95% prediction accuracy within the 2-minute elution interval. Given the increasing concern on the presence of drug metabolites and other transformation products (TPs) in the aquatic environment, the model was applied along with HRMS data for preliminary identification of pharmaceutically-related compounds in real samples. Examples of compounds where reference standards were subsequently acquired and later confirmed are also presented. To our knowledge, this work presents for the first time, the successful application of an accurate retention time predictor and HRMS data-mining using the largest number of compounds to preliminarily identify new or emerging contaminants in wastewater and surface waters. PMID:26363605
Energy Technology Data Exchange (ETDEWEB)
Dietzel, Matthias; Baltzer, Pascal A.T.; Groeschel, Tobias; Kaiser, Werner A. (Inst. of Diagnostic and Interventional Radiology, Friedrich-Schiller-Univ. Jena (Germany)), e-mail: matthias.dietzel@med.uni-jena.de; Dietzel, Andreas (Wilhelm-Schickard-Inst. of Computer Science, Eberhard-Karls-Univ., Tuebingen (Germany)); Vag, Tibor (Dept. of Radiology, Klinikum rechts der Isar der Technischen Universitaet, Munich (Germany)); Gajda, Mieczyslaw (Inst. of Pathology, Friedrich-Schiller-Univ., Jena (Germany)); Camara, Oumar (Clinic of Gynecology, Friedrich-Schiller-Univ., Jena (Germany))
2010-10-15
Background: In breast MRI (bMRI), prediction of lymph node metastases (N+) on the basis of dynamic and morphologic descriptors of breast cancers remains a complex task. Purpose: To predict N+ using an artificial neural network (ANN) on the basis of 17 previously published descriptors of breast lesions in bMRI. Material and Methods: Standardized protocol and study design were applied in this study (T1w-FLASH; 0.1 mmol/kg body weight Gd-DTPA; T2w-TSE; histological verification after bMRI). All lesions were evaluated by two experienced radiologists in consensus. In every lesion 17 previously published descriptors were assessed. Matched subgroups with (N+; n=97) and without N+ were created (N-; n=97), forming the dataset of this study (n=194). An ANN was constructed ('Multilayer Perceptron'; training: 'Batch'; activation function of hidden/output layer: 'Hyperbolic Tangent'/'Softmax') to predict N+ using all descriptors in combination on a randomly chosen training sample (n=123/194) and optimized on the corresponding test sample (n=71/194) using dedicated software. The discrimination power of this ANN was quantified by area under the curve (AUC) comparison (vs AUC=0.5). Training and testing cycles were repeated 20 times to quantify the robustness of the ANN (median-AUC; confidence intervals, CIs). Results: The ANN demonstrated highly significant discrimination power to classify N+ vs N- (P<0.001). Diagnostic accuracy reached 'moderate' AUC (median-AUC=0.74; CI 0.70-0.76). Conclusion: Application of ANNs for the prediction of lymph node metastases in breast MRI is feasible. Future studies should evaluate the clinical impact of the presented model
International Nuclear Information System (INIS)
Background: In breast MRI (bMRI), prediction of lymph node metastases (N+) on the basis of dynamic and morphologic descriptors of breast cancers remains a complex task. Purpose: To predict N+ using an artificial neural network (ANN) on the basis of 17 previously published descriptors of breast lesions in bMRI. Material and Methods: Standardized protocol and study design were applied in this study (T1w-FLASH; 0.1 mmol/kg body weight Gd-DTPA; T2w-TSE; histological verification after bMRI). All lesions were evaluated by two experienced radiologists in consensus. In every lesion 17 previously published descriptors were assessed. Matched subgroups with (N+; n=97) and without N+ were created (N-; n=97), forming the dataset of this study (n=194). An ANN was constructed ('Multilayer Perceptron'; training: 'Batch'; activation function of hidden/output layer: 'Hyperbolic Tangent'/'Softmax') to predict N+ using all descriptors in combination on a randomly chosen training sample (n=123/194) and optimized on the corresponding test sample (n=71/194) using dedicated software. The discrimination power of this ANN was quantified by area under the curve (AUC) comparison (vs AUC=0.5). Training and testing cycles were repeated 20 times to quantify the robustness of the ANN (median-AUC; confidence intervals, CIs). Results: The ANN demonstrated highly significant discrimination power to classify N+ vs N- (P<0.001). Diagnostic accuracy reached 'moderate' AUC (median-AUC=0.74; CI 0.70-0.76). Conclusion: Application of ANNs for the prediction of lymph node metastases in breast MRI is feasible. Future studies should evaluate the clinical impact of the presented model
Generalizing with perceptrons in case of structured phase- and pattern-spaces
Dirscherl, G; Krey, U
1998-01-01
We investigate the influence of different kinds of structure on the learning behaviour of a perceptron performing a classification task defined by a teacher rule. The underlying pattern distribution is permitted to have spatial correlations. The prior distribution for the teacher coupling vectors itself is assumed to be nonuniform. Thus classification tasks of quite different difficulty are included. As learning algorithms we discuss Hebbian learning, Gibbs learning, and Bayesian learning with different priors, using methods from statistics and the replica formalism. We find that the Hebb rule is quite sensitive to the structure of the actual learning problem, failing asymptotically in most cases. Contrarily, the behaviour of the more sophisticated methods of Gibbs and Bayes learning is influenced by the spatial correlations only in an intermediate regime of $\\alpha$, where $\\alpha$ specifies the size of the training set. Concerning the Bayesian case we show, how enhanced prior knowledge improves the performa...
Learning by random walks in the weight space of the Ising perceptron
Huang, Haiping
2010-01-01
The weight space of the Ising perceptron is explored by a random walk process where single weight flips are performed until the new presented pattern is learned. In this learning protocol, patterns are added sequentially and previous learned patterns (constraints) should be kept satisfied. Random walks are carried out until no solutions can be found. By this protocol, we are able to evaluate the overlap distribution of different solutions found on the same learning instance, and we show that solutions are far apart in Hamming distance even at small loading, implying that well-separated clusters form in the weight space. Adding the constraint that the stability of each learned pattern should be maximized before another new pattern is presented, the evolving fraction of frozen weights can be computed and shows that the simple random walk process will get trapped by the exponentially many suboptimal states. However, we suggest an additional rule by which a finite energy barrier involving only the barely learned ...
Using artificial neural networks to retrieve the aerosol type from multi-spectral lidar data
Nicolae, Doina; Belegante, Livio; Talianu, Camelia; Vasilescu, Jeni
2015-04-01
Aerosols can influence the microphysical and macrophysical properties of clouds and hence impact the energy balance, precipitation and the hydrological cycle. They have different scattering and absorption properties depending on their origin, therefore measured optical properties can be used to retrieve their physical properties, as well as to estimate their chemical composition. Due to the measurement limitations (spectral, uncertainties, range) and high variability of the aerosol properties with environmental conditions (including mixing during transport), the identification of the aerosol type from lidar data is still not solved. However, ground, airborne and space-based lidars provide more and more observations to be exploited. Since 2000, EARLINET collected more than 20,000 aerosol vertical profiles under various meteorological conditions, concerning local or long-range transport of aerosols in the free troposphere. This paper describes the basic algorithm for aerosol typing from optical data using the benefits of artificial neural networks. A relevant database was built to provide sufficient training cases for the neural network, consisting of synthetic and measured aerosol properties. Synthetic aerosols were simulated starting from the microphysical properties of basic components, internally mixed in various proportions. The algorithm combines the GADS database (Global Aerosol DataSet) to OPAC model (Optical Properties of Aerosol and Clouds) and T-Matrix code in order to compute, in an iterative way, the intensive optical properties of each aerosol type. Both pure and mixed aerosol types were considered, as well as their particular non-sphericity and hygroscopicity. Real aerosol cases were picked up from the ESA-CALIPSO database, as well as EARLINET datasets. Specific selection criteria were applied to identify cases with accurate optical data and validated sources. Cross-check of the synthetic versus measured aerosol intensive parameters was performed in order to ensure the homogeneity and consistency of the inputs considered for the neural network. Pure aerosol types are not sufficiently represented by the observations, as well as the mixtures of marine and volcanic, therefore only synthetic properties can be used for those. A Multilayer Perceptron neural network with three hidden layers was built and trained to retrieve the aerosol type based on 3a+2b+1d lidar data. Five pure aerosol types and eight mixtures were considered. About 70% of the total number of cases was used to train the network, 20% for the internal auto-testing and adjustments, and 10% for blind testing. Supervised training was applied until more than 90% of the synthetic cases, respectively more than 80% of the measurement cases were correctly identified. Preliminary results are presented, underlining the advantages and disadvantages of the neural network algorithm compared to other methods. Acknowledgements: This work was supported by a grant of the Romanian National Authority for Scientific Research, Program for research - Space Technology and Avanced Research - STAR, project no. 98/2013-DARLIOES, and by the ESA contract no. 4000110671/14/I-LG, NATALI. Keywords: EARLINET, ESA-CALIPSO, lidar, aerosol typing
Golay, Jean; Kanevski, Mikhaïl
2013-04-01
The present research deals with the exploration and modeling of a complex dataset of 200 measurement points of sediment pollution by heavy metals in Lake Geneva. The fundamental idea was to use multivariate Artificial Neural Networks (ANN) along with geostatistical models and tools in order to improve the accuracy and the interpretability of data modeling. The results obtained with ANN were compared to those of traditional geostatistical algorithms like ordinary (co)kriging and (co)kriging with an external drift. Exploratory data analysis highlighted a great variety of relationships (i.e. linear, non-linear, independence) between the 11 variables of the dataset (i.e. Cadmium, Mercury, Zinc, Copper, Titanium, Chromium, Vanadium and Nickel as well as the spatial coordinates of the measurement points and their depth). Then, exploratory spatial data analysis (i.e. anisotropic variography, local spatial correlations and moving window statistics) was carried out. It was shown that the different phenomena to be modeled were characterized by high spatial anisotropies, complex spatial correlation structures and heteroscedasticity. A feature selection procedure based on General Regression Neural Networks (GRNN) was also applied to create subsets of variables enabling to improve the predictions during the modeling phase. The basic modeling was conducted using a Multilayer Perceptron (MLP) which is a workhorse of ANN. MLP models are robust and highly flexible tools which can incorporate in a nonlinear manner different kind of high-dimensional information. In the present research, the input layer was made of either two (spatial coordinates) or three neurons (when depth as auxiliary information could possibly capture an underlying trend) and the output layer was composed of one (univariate MLP) to eight neurons corresponding to the heavy metals of the dataset (multivariate MLP). MLP models with three input neurons can be referred to as Artificial Neural Networks with EXternal drift (ANNEX). Moreover, the exact number of output neurons and the selection of the corresponding variables were based on the subsets created during the exploratory phase. Concerning hidden layers, no restriction were made and multiple architectures were tested. For each MLP model, the quality of the modeling procedure was assessed by variograms: if the variogram of the residuals demonstrates pure nugget effect and if the level of the nugget exactly corresponds to the nugget value of the theoretical variogram of the corresponding variable, all the structured information has been correctly extracted without overfitting. Finally, it is worth mentioning that simple MLP models are not always able to remove all the spatial correlation structure from the data. In that case, Neural Network Residual Kriging (NNRK) can be carried out and risk assessment can be conducted with Neural Network Residual Simulations (NNRS). Finally, the results of the ANNEX models were compared to those of ordinary (co)kriging and (co)kriging with an external drift. It was shown that the ANNEX models performed better than traditional geostatistical algorithms when the relationship between the variable of interest and the auxiliary predictor was not linear. References Kanevski, M. and Maignan, M. (2004). Analysis and Modelling of Spatial Environmental Data. Lausanne: EPFL Press.
A robust neural controller for underwater robot manipulators.
Lee, M; Choi, H S
2000-01-01
This paper presents a robust control scheme using a multilayer neural network with the error backpropagation learning algorithm. The multilayer neural network acts as a compensator of the conventional sliding mode controller to improve the control performance when initial assumptions of uncertainty bounds of system parameters are not valid. The proposed controller is applied to control a robot manipulator operating under the sea which has large uncertainties such as the buoyancy, the drag force, wave effects, currents, and the added mass/moment of inertia. Computer simulation results show that the proposed control scheme gives an effective path way to cope with those unexpected large uncertainties. PMID:18249870
International Nuclear Information System (INIS)
Utilizing self-consistent Hartree-Fock calculations, several aspects of multilayers and interfaces are explored: enhancement and reduction of the local magnetic moments, magnetic coupling at the interfaces, magnetic arrangements within each film and among non-neighboring films, global symmetry of the systems, frustration, orientation of the various moments with respect to an outside applied field, and magnetic-field induced transitions. Magnetoresistance of ferromagnetic-normal-metal multilayers is found by solving the Boltzmann equation. Results explain the giant negative magnetoresistance encountered in these systems when an initial antiparallel arrangement is changed into a parallel configuration by an external magnetic field. The calculation depends on (1) geometric parameters (thicknesses of layers), (2) intrinsic metal parameters (number of conduction electrons, magnetization, and effective masses in layers), (3) bulk sample properties (conductivity relaxation times), (4) interface scattering properties (diffuse scattering versus potential scattering at the interfaces, and (5) outer surface scattering properties (specular versus diffuse surface scattering). It is found that a large negative magnetoresistance requires considerable asymmetry in interface scattering for the two spin orientations. Features of the interfaces that may produce an asymmetrical spin-dependent scattering are studied: varying interfacial geometric random roughness with no lateral coherence, correlated (quasi-periodic) roughness, and varying chemical composition of the interfaces. The interplay between these aspects of the interfaces may enhance or suppress the magnetoresistance, depending on whether it increases or decreases the asymmetry in the spin-dependent scattering of the conduction electrons
Energy Technology Data Exchange (ETDEWEB)
Chrzan, D.C.; Dugger, M.; Follstaedt, D.M.; Friedman, Lawrence H.; Friedmann, T.A.; Knapp, J.A.; McCarty, K.F.; Medlin, D.L.; Mirkarimi, P.B.; Missert, N.; Newcomer, P.P.; Sullivan, J.P.; Tallant, D.R.
1999-05-01
We have developed a new multilayer a-tC material that is thick stress-free, adherent, low friction, and with hardness and stiffness near that of diamond. The new a-tC material is deposited by J pulsed-laser deposition (PLD) at room temperature, and fully stress-relieved by a short thermal anneal at 600°C. A thick multilayer is built up by repeated deposition and annealing steps. We measured 88 GPa hardness, 1100 GPa Young's modulus, and 0.1 friction coefficient (under high load). Significantly, these results are all well within the range reported for crystalline diamond. In fact, this material, if considered separate from crystalline diamond, is the 2nd hardest material known to man. Stress-free a-tC also has important advantages over thin film diamond; namely, it is smooth, processed at lower temperature, and can be grown on a much broader range of substrates. This breakthrough will enable a host of applications that we are actively pursuing in MEMs, sensors, LIGA, etc.
International Nuclear Information System (INIS)
We have developed a new multilayer a-tC material that is thick stress-free, adherent, low friction, and with hardness and stiffness near that of diamond. The new a-tC material is deposited by J pulsed-laser deposition (PLD) at room temperature, and fully stress-relieved by a short thermal anneal at 600 ampersand deg;C. A thick multilayer is built up by repeated deposition and annealing steps. We measured 88 GPa hardness, 1100 GPa Young's modulus, and 0.1 friction coefficient (under high load). Significantly, these results are all well within the range reported for crystalline diamond. In fact, this material, if considered separate from crystalline diamond, is the 2nd hardest material known to man. Stress-free a-tC also has important advantages over thin film diamond; namely, it is smooth, processed at lower temperature, and can be grown on a much broader range of substrates. This breakthrough will enable a host of applications that we are actively pursuing in MEMs, sensors, LIGA, etc
Directory of Open Access Journals (Sweden)
Esra Nergis Güven
2008-04-01
Full Text Available [Turkish abstract]Internet’in h?zl? geli?mesi ve yayg?nla?mas? elektronik ortamda i? ve i?lemleri h?zland?rm?? ve kolayla?t?rm??t?r. Elektronik ortamlarda depolanan, ta??nan ve i?lenen bilgilerin boyutunun her geçen gün artmas? ise bilgiye eri?im ile ilgili birçok problemi de beraberinde getirmi?tir. Kullan?c?lar?n elektronik ortamda sunulan bilgilere eri?melerindeki h?z ve do?ruluk gereksinimi nedeniyle, bu ortamlarda tutulan bilgileri s?n?fland?rma ve kategorilere ay?rma yakla??mlar?na ihtiyaç duyulmaktad?r. Say?lar? milyonun üzerinde olan arama motorlar?n?n, kullan?c?lar?n do?ru bilgilere k?sa sürede ula?mas?n? sa?lamas? için her geçen gün yeni yakla??mlar ile desteklenmesi gerekmektedir. Bu çal??mada, web sayfalar?n?n belirlenen konulara göre s?n?fland?r?labilmesi için, Çok Katmanl? (MLP yapay sinir a?? modeli kullan?lm??t?r. Özellik vektörü içeri?inin seçimi, yapay sinir a??n?n e?itilmesi ve son olarak web sayfalar?n?n do?ru kategorize edilmesi için bir yaz?l?m geli?tirilmi?tir. Bu zeki yakla??m?n, elektronik ortamlarda bilgilerin kolayl?kla ve yüksek do?rulukla s?n?fland?r?lmas?, web ortamlar?nda do?ru içeri?e ula??lmas? ve birçok güvenlik aç???n?n giderilmesine katk?lar sa?layaca?? de?erlendirilmektedir. [English abstract]Recent developments and widespread usage of the Internet have made business and processes to be completed faster and easily in electronic media. The increasing size of the stored, transferred and processed data brings many problems that affect access to information on the Web. Because of users’ need get to access to the information in electronic environment quickly, correctly and appropriately, different methods of classification and categorization of data are strictly needed. Millions of search engines should be supported with new approaches every day in order for users to get access to relevant information quickly. In this study, Multilayered Perceptrons (MLP artificial neural network model is used to classify the web sites according to the specified subjects. A software is developed to select the feature vector, to train the neural network and finally to categorize the web sites correctly. It is considered that this intelligent approach will provide more accurate and secure platform to the Internet users for classifying web contents precisely.
Neural networks approach v/s Algorithmic approach : A study through pattern recognition
Directory of Open Access Journals (Sweden)
Namrata Aneja
2011-12-01
Full Text Available There is a great scope of expansion in the field of Neural Network, as it can be viewed as massivelyparallel computing systems consisting of an extremely large number of simple processors with manyinterconnections. NN models attempt to use some organizational principles in a weighted directedgraphs in which nodes are artificial neurons and directed edges are connections between neuron outputsand neuron inputs. The main characteristic of neural network is that they have the ability to learncomplex non- linear input output relationships. A single artificial neuron is a simulation of a neuron(basic human brain cell and scientists have tried to emulate the neuron in a form of artificial neuroncalled perceptron. Pattern recognition is one of the areas where the neural approach has beensuccessfully tried. This study is concerned to see the journey of pattern recognition from algorithmicapproach to neural network approach.
Modeling hourly diffuse solar-radiation in the city of Sao Paulo using a neural-network technique
International Nuclear Information System (INIS)
In this work, a perceptron neural-network technique is applied to estimate hourly values of the diffuse solar-radiation at the surface in Sao Paulo City, Brazil, using as input the global solar-radiation and other meteorological parameters measured from 1998 to 2001. The neural-network verification was performed using the hourly measurements of diffuse solar-radiation obtained during the year 2002. The neural network was developed based on both feature determination and pattern selection techniques. It was found that the inclusion of the atmospheric long-wave radiation as input improves the neural-network performance. On the other hand traditional meteorological parameters, like air temperature and atmospheric pressure, are not as important as long-wave radiation which acts as a surrogate for cloud-cover information on the regional scale. An objective evaluation has shown that the diffuse solar-radiation is better reproduced by neural network synthetic series than by a correlation model
Structure and Swelling Behaviour of Polyelectrolyte Multilayers
Dodoo, Samuel
2011-01-01
In this thesis, the relation between structure, growth and swelling in water of polyelectrolyte multilayers are investigated. Polyelectrolyte multilayers are fabricated by alternating adsorption of polyanions and polycations on a silicon substrate. The multilayer is sensitive to external stimuli, which often counteracts the stability of the multilayer. Also the many applications of polyelectrolyte multilayers have made the interphase between the substrate and the film bulk to be of interest. ...
Neutron diffraction by multilayer systems
International Nuclear Information System (INIS)
Stract dynamical scattering theory of neutrons by multilayer systems, formed by alternating thin films of two materials, is developed. The statistical distribution of film widths is taken into account. The reflection and transmission coefficients are calculated. The neutron conductivity bands are shown to exist in multilayer systems. For the system of N bilayers a conductivity band consists of N-1 levels. In the absence of absorption such a system becomes completely transparent for neutrons, if the normal component of thear kinetic energy Esub(perpendicular) equals the energy of a conductivity band level. Systems with ferromagnetic films or polarized nuclei polarize neutrons. Multilayer systems can serve as a neutron Fabry-Perot interferometer
Directory of Open Access Journals (Sweden)
J. Szajnar
2010-01-01
Full Text Available In paper is presented the possibility of making of multi-layers cast steel castings in result of connection of casting and welding coating technologies. First layer was composite surface layer on the basis of Fe-Cr-C alloy, which was put directly in founding process of cast carbon steel 200–450 with use of preparation of mould cavity method. Second layer were padding welds, which were put with use of TIG – Tungsten Inert Gas surfacing by welding technology with filler on Ni matrix, Ni and Co matrix with wolfram carbides WC and on the basis on Fe-Cr-C alloy, which has the same chemical composition with alloy, which was used for making of composite surface layer. Usability for industrial applications of surface layers of castings were estimated by criterion of hardness and abrasive wear resistance of type metal-mineral.
Multilayer graphene condenser microphone
Todorovi?, Dejan; Matkovi?, Aleksandar; Mili?evi?, Marijana; Jovanovi?, Djordje; Gaji?, Radoš; Salom, Iva; Spasenovi?, Marko
2015-12-01
Vibrating membranes are the cornerstone of acoustic technology, forming the backbone of modern loudspeakers and microphones. Acoustic performance of a condenser microphone is derived mainly from the membrane’s size, surface mass and achievable static tension. The widely studied and available nickel has been a dominant membrane material for professional microphones for several decades. In this paper we introduce multilayer graphene as a membrane material for condenser microphones. The graphene device outperforms a high end commercial nickel-based microphone over a significant part of the audio spectrum, with a larger than 10 dB enhancement of sensitivity. Our experimental results are supported with numerical simulations, which also show that a 300 layer thick graphene membrane under maximum tension would offer excellent extension of the frequency range, up to 1 MHz.
DEFF Research Database (Denmark)
Fernandes, Armando M.; Franco, Camilo; Mendes-Ferreira, Ana; Mendes-Faia, Arlete; Leal da Costa, Pedro; Melo-Pinto, Pedro
2015-01-01
This work presents the results of measuring pH, sugars, and anthocyanin content of whole grape berries. The spectrum of each sample, composed of six whole grape berries, was collected using hyperspectral imaging in reflectance mode from 380 to 1028 nm. The spectra were converted to enological parameters by multilayer perceptrons created using 240 samples that were split for 7-fold cross-validation and test. The test set with 30 samples revealed R2 values of 0.73, 0.92 and 0.95 and RMSE of 0.18, ...
Integrated Multilayer Insulation
Dye, Scott
2009-01-01
Integrated multilayer insulation (IMLI) is being developed as an improved alternative to conventional multilayer insulation (MLI), which is more than 50 years old. A typical conventional MLI blanket comprises between 10 and 120 metallized polymer films separated by polyester nets. MLI is the best thermal- insulation material for use in a vacuum, and is the insulation material of choice for spacecraft and cryogenic systems. However, conventional MLI has several disadvantages: It is difficult or impossible to maintain the desired value of gap distance between the film layers (and consequently, it is difficult or impossible to ensure consistent performance), and fabrication and installation are labor-intensive and difficult. The development of IMLI is intended to overcome these disadvantages to some extent and to offer some additional advantages over conventional MLI. The main difference between IMLI and conventional MLI lies in the method of maintaining the gaps between the film layers. In IMLI, the film layers are separated by what its developers call a micro-molded discrete matrix, which can be loosely characterized as consisting of arrays of highly engineered, small, lightweight, polymer (typically, thermoplastic) frames attached to, and placed between, the film layers. The term "micro-molded" refers to both the smallness of the frames and the fact that they are fabricated in a process that forms precise small features, described below, that are essential to attainment of the desired properties. The term "discrete" refers to the nature of the matrix as consisting of separate frames, in contradistinction to a unitary frame spanning entire volume of an insulation blanket.
Hybrid digital signal processing and neural networks applications in PWRs
International Nuclear Information System (INIS)
Signal validation and plant subsystem tracking in power and process industries require the prediction of one or more state variables. Both heteroassociative and auotassociative neural networks were applied for characterizing relationships among sets of signals. A multi-layer neural network paradigm was applied for sensor and process monitoring in a Pressurized Water Reactor (PWR). This nonlinear interpolation technique was found to be very effective for these applications
Automated Defect Classification Using AN Artificial Neural Network
Chady, T.; Caryk, M.; Piekarczyk, B.
2009-03-01
The automated defect classification algorithm based on artificial neural network with multilayer backpropagation structure was utilized. The selected features of flaws were used as input data. In order to train the neural network it is necessary to prepare learning data which is representative database of defects. Database preparation requires the following steps: image acquisition and pre-processing, image enhancement, defect detection and feature extraction. The real digital radiographs of welded parts of a ship were used for this purpose.
Design of Jetty Piles Using Artificial Neural Networks
Yongjei Lee; Sungchil Lee; Hun-Kyun Bae
2014-01-01
To overcome the complication of jetty pile design process, artificial neural networks (ANN) are adopted. To generate the training samples for training ANN, finite element (FE) analysis was performed 50 times for 50 different design cases. The trained ANN was verified with another FE analysis case and then used as a structural analyzer. The multilayer neural network (MBPNN) with two hidden layers was used for ANN. The framework of MBPNN was defined as the input with the lateral forces on the j...
Controlling light with plasmonic multilayers
DEFF Research Database (Denmark)
Orlov, Alexey A.; Zhukovsky, Sergei
2014-01-01
Recent years have seen a new wave of interest in layered media - namely, plasmonic multilayers - in several emerging applications ranging from transparent metals to hyperbolic metamaterials. In this paper, we review the optical properties of such subwavelength metal-dielectric multilayered metamaterials and describe their use for light manipulation at the nanoscale. While demonstrating the recently emphasized hallmark effect of hyperbolic dispersion, we put special emphasis to the comparison between multilayered hyperbolic metamaterials and more broadly defined plasmonic-multilayer metamaterials A number of fundamental electromagnetic effects unique to the latter are identified and demonstrated. Examples include the evolution of isofrequency contour shape from elliptical to hyperbolic, all-angle negative refraction, and nonlocality-induced optical birefringence. Analysis of the underlying physical causes, which are spatial dispersion and optical nonlocality, is also reviewed. These recent results are extremely promising for a number of applications ranging from nanolithography to optical cloaking. © 2014 Elsevier B.V.
Data Assimilation using Artificial Neural Networks for the global FSU atmospheric model
Cintra, Rosangela; Cocke, Steven; Campos Velho, Haroldo
2015-04-01
Data assimilation is the process by which measurements and model predictions are combined to obtain an accurate representation of the state of the modeled system. Uncertainty is the characteristic of the atmosphere, coupled with inevitable inadequacies in observations and computer models and increase errors in weather forecasts. Data assimilation is a technique to generate an initial condition to a weather or climate forecasts. This paper shows the results of a data assimilation technique using artificial neural networks (ANN) to obtain the initial condition to the atmospheric general circulation model (AGCM) for the Florida State University in USA. The Local Ensemble Transform Kalman filter (LETKF) is implemented with Florida State University Global Spectral Model (FSUGSM). The ANN data assimilation is made to emulate the initial condition from LETKF to run the FSUGSM. LETKF is a version of Kalman filter with Monte-Carlo ensembles of short-term forecasts to solve the data assimilation problem. The model FSUGSM is a multilevel (27 vertical levels) spectral primitive equation model with a vertical sigma coordinate. All variables are expanded horizontally in a truncated series of spherical harmonic functions (at resolution T63) and a transform technique is applied to calculate the physical processes in real space. The LETKF data assimilation experiments are based in synthetic observations data (surface pressure, absolute temperature, zonal component wind, meridional component wind and humidity). For the ANN data assimilation scheme, we use Multilayer Perceptron (MLP-DA) with supervised training algorithm where ANN receives input vectors with their corresponding response or target output from LETKF scheme. An automatic tool that finds the optimal representation to these ANNs configures the MLP-DA in this experiment. After the training process, the scheme MLP-DA is seen as a function of data assimilation where the inputs are observations and a short-range forecast to each model grid point. The ANNs were trained with data from each month of 2001, 2002, 2003, and 2004. A hind-casting experiment for data assimilation cycle using MLP-DA was performed with synthetic observations for January 2005. The numerical results demonstrate the effectiveness of the ANN technique for atmospheric data assimilation, since the analyses (initial conditions) have similar quality to LETKF analyses. The major advantage of using MLP-DA is the computational performance, which is faster than LETKF. The reduced computational cost allows the inclusion of greater number of observations and new data sources and the use of high resolution of models, which ensures the accuracy of analysis and of its weather prediction
Multicategory nets of single-layer perceptrons: complexity and sample-size issues.
Raudys, Sarunas; Kybartas, Rimantas; Zavadskas, Edmundas Kazimieras
2010-05-01
The standard cost function of multicategory single-layer perceptrons (SLPs) does not minimize the classification error rate. In order to reduce classification error, it is necessary to: 1) refuse the traditional cost function, 2) obtain near to optimal pairwise linear classifiers by specially organized SLP training and optimal stopping, and 3) fuse their decisions properly. To obtain better classification in unbalanced training set situations, we introduce the unbalance correcting term. It was found that fusion based on the Kulback-Leibler (K-L) distance and the Wu-Lin-Weng (WLW) method result in approximately the same performance in situations where sample sizes are relatively small. The explanation for this observation is by theoretically known verity that an excessive minimization of inexact criteria becomes harmful at times. Comprehensive comparative investigations of six real-world pattern recognition (PR) problems demonstrated that employment of SLP-based pairwise classifiers is comparable and as often as not outperforming the linear support vector (SV) classifiers in moderate dimensional situations. The colored noise injection used to design pseudovalidation sets proves to be a powerful tool for facilitating finite sample problems in moderate-dimensional PR tasks. PMID:20215067
A morphological perceptron with gradient-based learning for Brazilian stock market forecasting.
Araújo, Ricardo de A
2012-04-01
Several linear and non-linear techniques have been proposed to solve the stock market forecasting problem. However, a limitation arises from all these techniques and is known as the random walk dilemma (RWD). In this scenario, forecasts generated by arbitrary models have a characteristic one step ahead delay with respect to the time series values, so that, there is a time phase distortion in stock market phenomena reconstruction. In this paper, we propose a suitable model inspired by concepts in mathematical morphology (MM) and lattice theory (LT). This model is generically called the increasing morphological perceptron (IMP). Also, we present a gradient steepest descent method to design the proposed IMP based on ideas from the back-propagation (BP) algorithm and using a systematic approach to overcome the problem of non-differentiability of morphological operations. Into the learning process we have included a procedure to overcome the RWD, which is an automatic correction step that is geared toward eliminating time phase distortions that occur in stock market phenomena. Furthermore, an experimental analysis is conducted with the IMP using four complex non-linear problems of time series forecasting from the Brazilian stock market. Additionally, two natural phenomena time series are used to assess forecasting performance of the proposed IMP with other non financial time series. At the end, the obtained results are discussed and compared to results found using models recently proposed in the literature. PMID:22391234
Energy Technology Data Exchange (ETDEWEB)
Pilato, V
1999-07-01
The possibility of improving by neuronal techniques the preparation and interpretation of nuclear measurements was investigated. A general methodology was developed and applied to various problems in this field. Whatever the problem to be treated, to solve it comes to determine the relation which binds the inputs to the outputs. Neural networks based on supervised training, like the multilayer Perceptron, have the capability to calculate any relation between a set of input and output data. On the other hand, the training phase is often a long and delicate operation whose difficulties grow with the size of the network:it is thus interesting to reduce it by introducing knowledge a priori and/or by reducing the number of inputs in order to extract the relevant information. If the correlations between the inputs are linear, the Principal Components Analysis (PCA) and its neuronal equivalents make it possible to obtain by orthogonal projection a reduced number of input components while preserving the maximum of initial information. If the correlations are nonlinear, the Curvilinear Components Analysis (CCA) allows, by a unsupervised training, to carry out a nonlinear projection of the inputs in a space of reduced size. Besides, it is noticed that when the dimension of the input space is equal to the intrinsic dimension of the problem, this last is practically solved by CCA. We propose a general method which consists in characterizing as well as possible the problem by its inputs and then to extract and classify the information contained in those by projection in a space of reduced size. Association between the projected data and the problem outputs is then carried out by a supervised training network. Certain results having to be provided with their associated uncertainty, a statistical method based on the bootstrap algorithm is proposed. Potential applications other that those treated are considered. (author)
Comparison Of Neural Network And Multivariate Discriminant Analysis In Selecting New Cowpea Variety
Adewole, Adetunji Philip; Sofoluwe, A. B.; Agwuegbo , Samuel Obi-Nnamdi
2010-01-01
In this study, neural networks (NN) algorithm and multivariate discriminant (MDA) based model were developed to classify ten (10) varieties of cowpea which were widely planted in Kano. . In order to demonstrate the validity of our model, we use the case study to build a neural network model using Multilayer Feedforward Neural Network, and compare its classification performance against theMultivariate discriminant analysis. Two groups of data (Spray and Nospray) were used. Twenty kernels were ...
Model of Information Security Risk Assessment based on Improved Wavelet Neural Network
Gang Chen; Dawei Zhao
2013-01-01
This paper concentrates on the information security risk assessment model utilizing the improved wavelet neural network. The structure of wavelet neural network is similar to the multi-layer neural network, which is a feed-forward neural network with one or more inputs. Afterwards, we point out that the training process of wavelet neural networks is made up of four steps until the value of error function can satisfy a pre-defined error criteria. In order to enhance the quality of information ...
Time series forecasting using cascade correlation networks
Directory of Open Access Journals (Sweden)
Juan David Velásquez
2010-07-01
Full Text Available Artificial neural networks, especially multilayer perceptrons, have been recognised as being a powerful technique for forecasting nonlinear time series; however, cascade-correlation architecture is a strong competitor in this task due to it incorporating several advantages related to the statistical identification of multilayer perceptrons. This paper compares the accuracy of a cascade-co- rrelation neural network to the linear approach, multilayer perceptrons and dynamic architecture for artificial neural networks (DAN2 to determine whether the cascade-correlation network was able to forecast the time series being studied with more accu- racy. It was concluded that cascade-correlation was able to forecast time series with more accuracy than other approaches.
Irreversible Multilayer Adsorption
Nielaba, P; Wang, J S
1993-01-01
Random sequential adsorption (RSA) models have been studied due to their relevance to deposition processes on surfaces. The depositing particles are represented by hard-core extended objects; they are not allowed to overlap. Numerical Monte Carlo studies and analytical considerations are reported for 1D and 2D models of multilayer adsorption processes. Deposition without screening is investigated, in certain models the density may actually increase away from the substrate. Analytical studies of the late stage coverage behavior show the crossover from exponential time dependence for the lattice case to the power law behavior in the continuum deposition. 2D lattice and continuum simulations rule out some "exact" conjectures for the jamming coverage. For the deposition of dimers on a 1D lattice with diffusional relaxation we find that the limiting coverage (100%) is approached according to the ~1/t**0.5 power-law preceded, for fast diffusion, by the mean-field crossover regime with the intermediate ~1/t behavior...
From neural-based object recognition toward microelectronic eyes
Sheu, Bing J.; Bang, Sa Hyun
1994-01-01
Engineering neural network systems are best known for their abilities to adapt to the changing characteristics of the surrounding environment by adjusting system parameter values during the learning process. Rapid advances in analog current-mode design techniques have made possible the implementation of major neural network functions in custom VLSI chips. An electrically programmable analog synapse cell with large dynamic range can be realized in a compact silicon area. New designs of the synapse cells, neurons, and analog processor are presented. A synapse cell based on Gilbert multiplier structure can perform the linear multiplication for back-propagation networks. A double differential-pair synapse cell can perform the Gaussian function for radial-basis network. The synapse cells can be biased in the strong inversion region for high-speed operation or biased in the subthreshold region for low-power operation. The voltage gain of the sigmoid-function neurons is externally adjustable which greatly facilitates the search of optimal solutions in certain networks. Various building blocks can be intelligently connected to form useful industrial applications. Efficient data communication is a key system-level design issue for large-scale networks. We also present analog neural processors based on perceptron architecture and Hopfield network for communication applications. Biologically inspired neural networks have played an important role towards the creation of powerful intelligent machines. Accuracy, limitations, and prospects of analog current-mode design of the biologically inspired vision processing chips and cellular neural network chips are key design issues.
A Neural Network Based Real Time Controller for Turning Process
Directory of Open Access Journals (Sweden)
Bahaa Ibraheem Kazem
2007-09-01
Full Text Available In this paper, the design and implementation of an effective neural network model for turning process identification as well as a neural network controller to track a desired vibration level of the turning machine is as an example of using the neural network for manufacturing process control. Multi – Layer Perceptron (MLP neural network architecture with Levenberg Marquardt (LM algorithm has been utilized to train the turning process identifier. Two different strategies have been used for training turning process identifier, and for training the controller model, where there is no mathematical model till now could relate the vibration level to the input turning process parameters “feed, speed, and depth of cut”. The vibration signal obtained by the experimental work has been used to train a neural network for identification and control of the turning process. The developed Neuro – controller has been checked by applying different reference vibration signals where it isfound that the controller has good ability to track the reference within maximum settling time that does not exceed (4 sec for 95% of the signal; maximum overshot not exceed (30% of the reference signal used for checking.
System Identification, Prediction, Simulation and Control with Neural Networks
DEFF Research Database (Denmark)
SØrensen, O.
1997-01-01
The intention of this paper is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed study of the networks themselves. With this end in view the following restrictions have been made: 1) Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. 2) Amongst numerous training algorithms, only the Recursive Prediction Error Method using a Gauss-Newton search direction is applied. 3) Amongst numerous model types, often met in control applications, only the Non-linear ARMAX (NARMAX) model, representing input/output description, is examined. A simulated example confirms that a neural network has the potential to perform excellent System Identification, Prediction, Simulation and Control of a dynamic, non-linear and noisy process. Further, the difficulties to control a practical non-linear laboratory process in a satisfactory way by using a traditional controller are overcomed by using a trained neural network to perform non-linear System Identification in a pole-placement control structure.
International Nuclear Information System (INIS)
The 1980s saw a tremendous renewal of interest in 'neural' information processing systems, or 'artificial neural networks', among computer scientists and computational biologists studying cognition. Since then, the growth of interest in neural networks in high energy physics, fueled by the need for new information processing technologies for the next generation of high energy proton colliders, can only be described as explosive
Scientific Electronic Library Online (English)
David, Santillán; Jesús, Fraile-Ardanuy; Miguel Ángel, Toledo.
2014-06-01
Full Text Available Las redes neuronales artificiales son estructuras matemáticas inspiradas en el cerebro de los seres vivos, capaces de generar modelos numéricos no lineales de calibración relativamente sencilla. En el presente trabajo se modela el caudal de agua filtrado a través del cimiento rocoso de una presa bóv [...] eda piloto con una red neuronal tipo perceptrón multicapa. La filtración a través de un macizo rocoso es un fenómeno difícil de modelar debido a la imposibilidad de caracterizar con detalle el medio en el que discurre y por la complejidad del propio fenómeno. El resultado final es un modelo compuesto por tres neuronas ocultas agrupadas en una capa y cuyas variables de entrada son el nivel de agua en el embalse y tres velocidades de la misma en periodos anteriores. La estructura de la red neuronal se determina teniendo en cuenta la influencia de cada una de las variables de entrada sobre las variables de salida. Para ello, se parte de un conjunto extenso de posibles variables de entrada extraídas de los modelos analíticos o conceptuales del fenómeno físico a modelar. Abstract in english Artificial neural networks are mathematical structures inspired by the brain of live beings which can generate relatively simple non-linear numerical calibration models. The present work models the flow of water filtered through the rocky base of a pilot arch dam using a multi-layer perceptron neura [...] l network. Seepage through a rock mass is difficult to model because it is impossible to obtain a detailed characterization of the medium through which it passes and because of the complexity of the process. The final result is a model composed of three hidden neurons grouped in a layer, using as input variables the water level in the reservoir and their three velocities from prior periods. The structure of the neural network is determined considering the influence of each of the input variables on the output variables. This is based on an extensive set of possible input variables extracted from analytical or conceptual models of the physical phenomenon to be modeled.
Scientific Electronic Library Online (English)
Mónica, Bocco; Enrique, Willington; Mónica, Arias.
2010-09-01
Full Text Available La radiación solar incidente en el suelo es una variable importante usada en aplicaciones agronómicas, además es relevante en hidrología, meteorología y física del suelo, entre otros. Para estimarla se han desarrollado modelos empíricos que utilizan distintos parámetros meteorológicos y, recientemen [...] te, modelos de pronóstico y predicción basados en técnicas de inteligencia artificial tales como redes neuronales. El objetivo de este trabajo fue desarrollar modelos lineales y de redes neuronales, del tipo perceptrón multicapa, para estimar la radiación solar global diaria y comparar la eficiencia de los mismos en su aplicación para una región de la Provincia de Salta, Argentina. Se utilizaron datos de heliofanía relativa, temperaturas máxima y mínima, precipitación, precipitación binaria y radiación solar astronómica provistos por la Estación Experimental Salta, Instituto Nacional de Tecnología Agropecuaria (INTA), Argentina, correspondientes al período 1996-2002. Tanto para los modelos de redes neuronales como para las regresiones lineales se consideraron tres alternativas de combinaciones de los parámetros meteorológicos, obteniéndose buenos resultados con ambas metodologías de predicción, con valores de la raíz del error cuadrático medio variando desde 1.99 a 1.66 MJ m-2 d-1 y coeficientes de correlación de 0.88 a 0.92. Se concluye que ambos, los modelos de redes neuronales y las regresiones lineales, pueden ser usados para predecir en forma adecuada la radiación solar global diaria; si bien las redes neuronales produjeron mejores resultados. Abstract in english The incident solar radiation on soil is an important variable used in agricultural applications; it is also relevant in hydrology, meteorology and soil physics, among others. To estimate this variable, empirical models have been developed using several parameters and, recently, prognostic and predic [...] tion models based on artificial intelligence techniques such as neural networks. The aim of this work was to develop linear models and neural networks, multilayer perceptron, to estimate daily global solar radiation and compare their efficiency in its application to a region of the Province of Salta, Argentina. Relative sunshine duration, maximum and minimum temperature, rainfall, binary rainfall and extraterrestrial solar radiation data for the period 1996-2002, were used. All data were supplied by Experimental Station Salta, Instituto Nacional de Tecnología Agropecuaria (INTA), Argentina. For both, neural networks models and linear regressions, three alternative combinations of meteorological parameters were considered. Good results with both prediction methods were obtained, with root mean square error (RMSE) values between 1.99 and 1.66 MJ m-2 d-1 for linear regressions and neural networks, and coefficients of correlation (r²) between 0.88 and 0.92, respectively. Even though neural networks and linear regression models can be used to predict the daily global solar radiation appropriately, neural networks produced better estimates.
Modeling and prediction of Turkey's electricity consumption using Artificial Neural Networks
International Nuclear Information System (INIS)
Artificial Neural Networks are proposed to model and predict electricity consumption of Turkey. Multi layer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. These input-output network models are a result of relationships that exist among electricity consumption and several other socioeconomic variables. Electricity consumption is modeled as a function of economic indicators such as population, gross national product, imports and exports. It is also modeled using export-import ratio and time input only. Performance comparison among different models is made based on absolute and percentage mean square error. Electricity consumption of Turkey is predicted until 2027 using data from 1975 to 2006 along with other economic indicators. The results show that electricity consumption can be modeled using Artificial Neural Networks, and the models can be used to predict future electricity consumption.
Prediction of Rainfall in India using Artificial Neural Network (ANN Models
Directory of Open Access Journals (Sweden)
Santosh Kumar Nanda
2013-11-01
Full Text Available In this paper, ARIMA(1,1,1 model and Artificial Neural Network (ANN models like Multi Layer Perceptron (MLP, Functional-link Artificial Neural Network (FLANN and Legendre Polynomial Equation ( LPE were used to predict the time series data. MLP, FLANN and LPE gave very accurate results for complex time series model. All the Artificial Neural Network model results matched closely with the ARIMA(1,1,1 model with minimum Absolute Average Percentage Error(AAPE. Comparing the different ANN models for time series analysis, it was found that FLANN gives better prediction results as compared to ARIMA model with less Absolute Average Percentage Error (AAPE for the measured rainfall data.
Modeling and prediction of Turkey's electricity consumption using Artificial Neural Networks
International Nuclear Information System (INIS)
Artificial Neural Networks are proposed to model and predict electricity consumption of Turkey. Multi layer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. These input-output network models are a result of relationships that exist among electricity consumption and several other socioeconomic variables. Electricity consumption is modeled as a function of economic indicators such as population, gross national product, imports and exports. It is also modeled using export-import ratio and time input only. Performance comparison among different models is made based on absolute and percentage mean square error. Electricity consumption of Turkey is predicted until 2027 using data from 1975 to 2006 along with other economic indicators. The results show that electricity consumption can be modeled using Artificial Neural Networks, and the models can be used to predict future electricity consumption. (author)
Transient Stability Assessment of a Power System Using Probabilistic Neural Network
Directory of Open Access Journals (Sweden)
Noor I.A. Wahab
2008-01-01
Full Text Available This study presents transient stability assessment of electrical power system using Probabilistic Neural Network (PNN and principle component analysis. Transient stability of a power system is first determined based on the generator relative rotor angles obtained from time domain simulation outputs. Simulations were carried out on the IEEE 9-bus test system considering three phase faults on the system. The data collected from the time domain simulations are then used as inputs to the PNN in which PNN is used as a classifier to determine whether the power system is stable or unstable. Principle component analysis is applied to extract useful input features to the PNN so that training time of the PNN can be reduced. To verify the effectiveness of the proposed PNN method, it is compared with the multi layer perceptron neural network. Results show that the PNN gives faster and more accurate transient stability assessment compared to the multi layer perceptron neural network in terms of classification results.
Directory of Open Access Journals (Sweden)
M. Zakermoshfegh
2008-01-01
Full Text Available River flow forecasting is required to provide important information on a wide range of cases related to design and operation of river systems. Since there are a lot of parameters with uncertainties and non-linear relationships, the calibration of conceptual or physically-based models is often a difficult and time consuming procedure. So it is preferred to implement a heuristic black box model to perform a non-linear mapping between the input and output spaces without detailed consideration of the internal structure of the physical process. In this study, the capability of artificial neural networks for stream flow forecasting in Kashkan River in West of Iran is investigated and compared to a NAM model which is a lumped conceptual model with shuffled complex evolution algorithm for auto calibration. Multi Layer Perceptron and Radial Basis Function neural networks are introduced and implemented. The results show that the discharge can be more adequately forecasted by Multi Layer Perceptron neural network, compared to other implemented models, in case of both peak discharge and base flow forecasting.
Gap-filling eddy-covariance data using a complex system of neural networks
Dúbrava, Matúš; Rebok, Tomáš; Havránková, Kate?ina; Pavelka, Marian
2014-05-01
The eddy-covariance technique measures the flux of matter and energy between various ecosystems and the atmosphere. The fluxes characterize an interaction of the ecosystems with their surroundings and provide valuable knowledge to Global Climate Change issues. Among the main assets of the method belongs the possible evaluation of the carbon balance, expressed as the Net Ecosystem carbon Exchange (NEE) parameter. However, when unfavorable micro-meteorological conditions (e.g., stable stratification and low turbulent mixing) happen, measured fluxes are inaccurate and need to be corrected and/or gap-filled. Thus, there is a long-term challenge for many research teams from the flux community to develop the most accurate gap-filling method -- many statistical as well as empirical approaches have been proposed so far (e.g., mean replacement, interpolation, extrapolation, regression analysis, methods based on plant physiology depending on meteorological variables, etc.), each of them having its strengths and weaknesses. The artificial neural networks (ANNs) -- purely empirical non-linear regression models generally able to solve any fitness approximation and pattern recognition problem -- were proven as a promising approach and one of the most precise method for gap-filling the eddy-covariance data. However, even though providing encouraging results when considering a prediction error throughout the whole dataset, they considerably fail in fitting inherently present spikes in the NEE values. This drawback results from the nature of ANNs, since their ability to fit spikes is partly in contrast with their ability to reliably approximate previously unseen data -- while the spike fitting can be improved by an increasing number of training epochs, this often leads to ANNs over-fitting and thus losing their generalization ability, resulting in higher overall prediction error. Since the proper generalization ability has greater impact on the precision of the results, current applications of ANNs on the gap-filling problem do not take the precise spike estimation into consideration, limiting their ability to get as precise seasonal and annual sums of carbon dioxide flux as possible. Our research focuses on an application of various types of ANNs to the gap-filling of eddy-covariance data problem, aiming to improve the precision of the ANNs reliability through keeping their generalization ability as well as better fitting the spikes in the NEE dataset. We present an evaluation of several different types of up-to-date ANNs -- e.g., multilayer perceptron, wavelet neural networks, focused time-lagged neural networks, etc., -- including their variants, as well as the main aim of our research: an elaborated framework, which is able to precisely fit the spikes by building a system of several ANNs of a particular type where each one had been trained for special conditions. To achieve the best precision possible, several types of ANNs simultaneously estimating the particular NEE value are supported -- the final value is then chosen according to several statistical properties. The current results show a considerable improvement, resulting in greater than 90 percent correlation between synthetic and real NEE values as well as significantly improving the precision of the spike fitting.
Optimization of milling parameters using artificial neural network and artificial immune system
International Nuclear Information System (INIS)
The present paper is an attempt to predict the effective milling parameters on the final surface roughness of the work piece made of Ti 6Al 4V using a multi perceptron artificial neural network. The required data were collected during the experiments conducted on the mentioned material. These parameters include cutting speed, feed per tooth and depth of cut. A relatively newly discovered optimization algorithm entitled, artificial immune system is used to find the best cutting conditions resulting in minimum surface roughness. Finally, the process of validation of the optimum condition is presented
Neural Networks in Control Applications
DEFF Research Database (Denmark)
SØrensen, O.
1994-01-01
The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically examined, and it appears that considering 'normal' neural network models with, say, 500 samples, the problem of over-fitting is neglible, and therefore it is not taken into consideration afterwards. Numerous model types, often met in control applications, are implemented as neural network models are examined. The models are separated into three groups representing input/output descriptions as well as state space descriptions: - Models, where all in- and outputs are measurable (static networks). - Models, where some inputs are non-measurable (recurrent networks). - Models, where some in- and some outputs are non-measurable (recurrent networks with incomplete state information). The three groups are ordered in increasing complexity, and for each group it is shown how to solve the problems concerning training and application of the specific model type. Of particular interest are the model types concerning canonical, observable state space forms (minimum realizable form) for SISO as wll as MIMO processes. The tests show that all models, after succeeeful training, which is judged by correlation analysis of the prediction errors, are able to perform non-linear system identification, prediction, simulation and filtering of dynamic, non-linear, multi-variable and noisy processes in a very satisfactory manner. The further examinations mainly concentrate on two models, the Non-linear ARMAX (NARMAX) model representing input/output description, and the Non-linear Innovation state Space (NISS) model (a Kalmann filter) representing state space description. The potentials of neural networks for control of non-linear processes are also examined, focusing on three different groups of control concepts, all considered as generalizations of known linear control concepts to handle also non-linear processes. - Control concepts including parameter estimation - Control concepts including inverse modelling - Control concepts including optimal control For each of the three groups, different control concepts and specific training methods are detailed described.Further, all control concepts are tested on the same simulated process and compared. The closing chapter describes some practical experiments, where the different control concepts and training methods are tested on the same practical process operating in very noisy environments. All tests confirm that neural networks also have the potential to be trained to perform excellent control of dynamic, non-linear, multi-variable and noisy processes.
Uezu, T
2001-01-01
In a previous letter, we studied learning from stochastic examples by perceptrons with Ising weights in the framework of statistical mechanics. Under the one-step replica symmetry breaking ansatz, the behaviours of learning curves were classified according to some local property of the rules by which examples were drawn. Further, the conditions for the existence of the Perfect Learning together with other behaviors of the learning curves were given. In this paper, we give the detailed derivation about these results and further argument about the Perfect Learning together with extensive numerical calculations.
Computing and fabricating multilayer models
Holroyd, Michael; Baran, Ilya; Lawrence, Jason; Matusik, Wojciech
2011-01-01
We present a method for automatically converting a digital 3D model into a multilayer model: a parallel stack of high-resolution 2D images embedded within a semi-transparent medium. Multilayer models can be produced quickly and cheaply and provide a strong sense of an object's 3D shape and texture over a wide range of viewing directions. Our method is designed to minimize visible cracks and other artifacts that can arise when projecting an input model onto a small number of parallel planes, a...
Transfer matrices for multilayer structures
International Nuclear Information System (INIS)
We consider four of the transfer matrices defined to deal with multilayer structures. We deduce algorithms to calculate them numerically, in a simple and neat way. We illustrate their application to semi-infinite systems using SGFM formulae. These algorithms are of fast convergence and allow a calculation of bulk-, surface- and inner-layers band structure in good agreement with much more sophisticated calculations. Supermatrices, interfaces and multilayer structures can be calculated in this way with a small computational effort. (author). 10 refs
Elasticity of polyelectrolyte multilayer microcapsules
Lulevich, V V; Vinogradova, O I
2003-01-01
We present a novel approach to probe elastic properties of polyelectrolyte multilayer microcapsules. The method is based on measurements of the capsule load-deformation curves with the atomic force microscope. The experiment suggests that at low applied load deformations of the capsule shell are elastic. Using elastic theory of membranes we relate force, deformation, elastic moduli, and characteristic sizes of the capsule. Fitting to the prediction of the model yields the lower limit for Young's modulus of the polyelectrolyte multilayers of the order of a few MPa. This value corresponds to Young's modulus of a highly elastic polymer.
Image quality of figured multilayered optics
International Nuclear Information System (INIS)
The reflectivity and resolution of a multilayer structure is strongly affected by the roughness at the interfaces between two successive layers and by the amount that the constituent materials will diffuse into one another at the interfaces. Performance is also affected by the variations in individual layer thicknesses and by inhomogeneities in the materials. These deviations from the ideal multilayer will also affect the quality of the image from a figured multilayer optical element. The theory used to model the effects of non-ideal multilayers on the image quality of figured optics will be discussed. The relationship between image quality and multilayer structure quality will be illustrated with several examples
New developments in Ni/Ti multilayers
Energy Technology Data Exchange (ETDEWEB)
Anderson, I.; Hoghoj, P. [Institut Max von Laue - Paul Langevin (ILL), 38 - Grenoble (France)
1997-04-01
It is now 20 years since super-mirrors were first used as a neutron optical element. Since then the field of multilayer neutron-optics has matured with multilayers finding their way to application in many neutron scattering instruments. However, there is still room for progress in terms of multilayer quality, performance and application. Along with work on multilayers for neutron polarisation Ni/Ti super-mirrors have been optimised. The state-of-the-art Ni/Ti super-mirror performance and the results obtained in two neutron-optics applications of Ni/Ti multilayers are presented. (author).
Unrealizable learning in binary feed-forward neural networks
Sporre, M
1995-01-01
Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e. having more units than the student. It is shown that this is the same as using training data corrupted by Gaussian noise. Each machine is considered in the high temperature limit and in the replica symmetric approximation as well as for one step of replica symmetry breaking. For the perceptron a phase transition is found for low noise. However the transition is not to optimal learning. If the noise is increased the transition disappears. In both cases \\epsilon _{g} will approach optimal performance with a (\\ln\\alpha /\\alpha)^k decay for large \\alpha. For the tree committee machine noise in the input layer is studied, as well as noise in the hidden layer. If there is no noise in the input layer there is, in the case of one step of repl! ica symmetry breaking, a phase tra nsit...
Directory of Open Access Journals (Sweden)
León-Camacho, M.
2013-04-01
Full Text Available The triacylglycerols in the subcutaneous fat from Iberian pigs reared on four different feeding types, Montanera, Recebo, extensive Cebo and intensive Cebo, have been determined by gas chromatography with a flame ionization detector. Analyses were performed in a column coated with a bonded stationary phase (50% phenyl-50% methylpolysiloxane with hydrogen as the carrier gas. Lipids were extracted by melting the subcutaneous fat in a microwave oven and then filtering and dissolving it in hexane. A total amount of 2783 samples from several campaigns were considered. Using the triacylglycerols as chemical descriptors, a study on the discriminating power to differentiate samples according to the pig feeding type and system was performed. With this aim, pattern recognition techniques, such as linear discriminant analysis (LDA and multilayer perceptron artificial neural networks (MLPANN, have been used. ANN performed better than LDA, with a mean prediction ability of approximately 97% in the differentiation of fattening diets such as Montanera, extensive Cebo and intensive Cebo. In the case of including the recebo fattening diet, the model presents a mean performance of 82%. The differentiation of fattening systems has also been achieved by means of ANN, with a mean performance of 96%.Se ha determinado mediante cromatografía de gases con detector de ionización de llama los triglicéridos de la grasa subcutánea de cerdos ibéricos, cebados con cuatro tipos de alimentación: montanera, recebo, cebo extensivo y cebo intensivo. Los análisis se realizaron en una columna con una fase estacionaria ligada químicamente (50% fenil-50% metilpolisiloxano usando hidrógeno como gas portador. La grasa subcutánea se extrajo por fusión en horno de microondas, posteriormente se filtró y se disolvió en hexano. Un total de 2.783 muestras de varias campañas fueron analizadas. Usando los triglicéridos como descriptores químicos se ha llevado a cabo un estudio sobre la capacidad de discriminación de éstos para diferenciar el tipo y régimen de alimentación de los cerdos. A tal fin, se han empleado técnicas de reconocimiento de patrones, tales como análisis discriminante lineal (LDA y redes neuronales artificiales de perceptores multicapa (ANN-MLP. Las ANN presentan mejores resultados que el LDA, con una capacidad de predicción media de aproximadamente 97% en la diferenciación del tipo de alimentación entre Montanera, Cebo extensivo y Cebo intensivo. Al incluir el recebo, el modelo presenta un rendimiento promedio de 82%. La diferenciación del régimen de cebado también se ha llevado a cabo por medio de la ANN, con un rendimiento promedio del 96%.
Landeras, G.; López, J. J.; Kisi, O.; Shiri, J.
2012-04-01
The correct observation/estimation of surface incoming solar radiation (RS) is very important for many agricultural, meteorological and hydrological related applications. While most weather stations are provided with sensors for air temperature detection, the presence of sensors necessary for the detection of solar radiation is not so habitual and the data quality provided by them is sometimes poor. In these cases it is necessary to estimate this variable. Temperature based modeling procedures are reported in this study for estimating daily incoming solar radiation by using Gene Expression Programming (GEP) for the first time, and other artificial intelligence models such as Artificial Neural Networks (ANNs), and Adaptive Neuro-Fuzzy Inference System (ANFIS). Traditional temperature based solar radiation equations were also included in this study and compared with artificial intelligence based approaches. Root mean square error (RMSE), mean absolute error (MAE) RMSE-based skill score (SSRMSE), MAE-based skill score (SSMAE) and r2 criterion of Nash and Sutcliffe criteria were used to assess the models' performances. An ANN (a four-input multilayer perceptron with ten neurons in the hidden layer) presented the best performance among the studied models (2.93 MJ m-2 d-1 of RMSE). A four-input ANFIS model revealed as an interesting alternative to ANNs (3.14 MJ m-2 d-1 of RMSE). Very limited number of studies has been done on estimation of solar radiation based on ANFIS, and the present one demonstrated the ability of ANFIS to model solar radiation based on temperatures and extraterrestrial radiation. By the way this study demonstrated, for the first time, the ability of GEP models to model solar radiation based on daily atmospheric variables. Despite the accuracy of GEP models was slightly lower than the ANFIS and ANN models the genetic programming models (i.e., GEP) are superior to other artificial intelligence models in giving a simple explicit equation for the phenomenon which shows the relationship between the input and output parameters. This study provided new alternatives for solar radiation estimation based on temperatures.
Scientific Electronic Library Online (English)
Aníbal, Guerra; Joel, Rivas.
2011-09-01
Full Text Available El cáncer de mama es una de las principales causas de muerte entre las mujeres a nivel mundial, según la Asociación Americana del Cáncer. El factor clave para reducir el impacto de esta enfermedad es su detección temprana. El presente documento, describe el desarrollo de un software que tiene como o [...] bjetivo principal constituirse como base de un mecanismo de segunda opinión en el proceso de detección de microcalcificaciones, a través del estudio de imágenes mamográficas. El software trabaja a partir de una mamografía digitalizada, la cual es procesada para ingresarla como dato de entrada a una Red Neuronal Artificial (RNA) del tipo perceptrón multicapas; ésta se encarga de detectar si la imagen presenta microcalcificaciones. La RNA se implementó en lenguaje C++, con una arquitectura de una capa oculta y el algoritmo de aprendizaje Backpropagation, en combinación con técnicas basadas en el análisis estadístico sobre la textura de imágenes. La data base para el desarrollo de la aplicación proviene de la base de datos de la Sociedad de Análisis de Imágenes Mamográficas (MIAS, en sus siglas en inglés). La efectividad alcanzada en la evaluación del software fue de 94.4% de aciertos en su predicción, mostrando así el potencial de la aplicación de ambas técnicas para el abordaje del problema planteado. Abstract in english According to the American Cancer Society, breast cancer is one of the leading causes of death in women worldwide. The key factor to reduce the impact of this disease is an early diagnosis. The software described in this document aims to be a mechanism for second opinion in detection of micro-calcifi [...] cations in mammographic images. In this software, digitalized mammographies are processed and inserted as entry data to a multi-layer perceptron, which is able to detect presence of micro-calcifications in the provided images. The neural network was implemented in C++ language; its architecture has one hidden layer and uses a back-propagation learning algorithm in combination with techniques of statistical analysis over the image texture. The data used in this research was extracted from the MIAS database. The software assessment reported 94.4% of sensitivity in prediction tasks, showing the potential of both techniques in the resolution of the problem.
Wave transmission prediction of multilayer floating breakwater using neural network
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Patil, S.G.; Hegde, A.V.
and Mani, J S. 1997. Performance of Cage Floating Breakwater. J. Waterway, Port, Coastal and Ocean Eng, ASCE, 123(4), 172-179. Sannasiraj, S A; Sundar, V and Sundaravadivelu, R. 1998. Mooring forces and motion response of pontoon-type floating... stress on the coastal zone is rapidly growing and there is a need to protect the coastal environment. The development of structures to provide protection against the destructive forces of the sea waves and to withstand the action of waves has been...
Evolvable synthetic neural system
Curtis, Steven A. (Inventor)
2009-01-01
An evolvable synthetic neural system includes an evolvable neural interface operably coupled to at least one neural basis function. Each neural basis function includes an evolvable neural interface operably coupled to a heuristic neural system to perform high-level functions and an autonomic neural system to perform low-level functions. In some embodiments, the evolvable synthetic neural system is operably coupled to one or more evolvable synthetic neural systems in a hierarchy.
Material characterization through neural network technique
International Nuclear Information System (INIS)
Ultrasonic back wall echoes received from zircaloy 2 samples of fixed thickness and different microstructures have been classified through neural network analysis. The time domain ultrasonic echoes were first sampled and digitized, and then subjected to Fast Fourier Transform to reduce the dimensionality, as the energy content of the signal in the frequency domain would remain concentrated in the initial few discrete frequency components. A multilayered feed forward artificial neural network was trained by the concentrated energy portion of the frequency domain spectra. Ultrasonic signals from samples of four different microstructures were grouped into two classes in various combinations. The performance of the network was quite reliable for those combinations whenever the two classes constituted samples of different microstructures. The results indicate that the zircaloy 2 sample of different microstructure can be characterized by the neural network approach. (author). 7 refs., 5 figs., 7 tabs
Parameter estimation using compensatory neural networks
Indian Academy of Sciences (India)
M Sinha; P K Kalra; K Kumar
2000-04-01
Proposed here is a new neuron model, a basis for Compensatory Neural Network Architecture (CNNA), which not only reduces the total number of interconnections among neurons but also reduces the total computing time for training. The suggested model has properties of the basic neuron model as well as the higher neuron model (multiplicative aggregation function). It can adapt to standard neuron and higher order neuron, as well as a combination of the two. This approach is found to estimate the orbit with accuracy significantly better than Kalman Filter (KF) and Feedforward Multilayer Neural Network (FMNN) (also simply referred to as Artificial Neural Network, ANN) with lambda-gamma learning. The typical simulation runs also bring out the superiority of the proposed scheme over Kalman filter from the standpoint of computation time and the amount of data needed for the desired degree of estimated accuracy for the specific problem of orbit determination.
Multilayer Controller for Outdoor Vehicle
DEFF Research Database (Denmark)
Reske-Nielsen, Anders; Mejnertsen, Asbjørn; Andersen, Nils Axel; Ravn, Ole; Nørremark, Michael; Griepentrog, Hans Werner
2006-01-01
A full software and hardware solution has been designed, implemented and tested for control of a small agricultural automatic tractor. The objective was to realise a user-friendly, multi-layer controller architecture for an outdoor platform. The collaborative research work was done as a part of a research project within the field of automated agriculture and precision farming.
Prior Knowledge Input Method In Device Modeling
HEK?MHAN, Serdar; MENEKAY, Serdar; ?ENGÖR, N. Serap
2005-01-01
The artificial neural networks are being used in modelling electronic elements and devices especially at microwave frequencies where non-linearity and dependence on frequency cannot be neglected. In this paper, instead of using artificial neural networks as a unique modelling device prior knowledge input method based on feed-forward artificial neural network structures as multi-layer perceptrons and wavelet-based neural networks is investigated. The benefits of prior knowledge input ...
Identification of discrete chaotic maps with singular points
Ivanov, V. V.; Antoniou, I.; Akritas, P.; P. G. Akishin
2001-01-01
We investigate the ability of artificial neural networks to reconstruct discrete chaotic maps with singular points. We use as a simple test model the Cusp map. We compare the traditional Multilayer Perceptron, the Chebyshev Neural Network and the Wavelet Neural Network. The numerical scheme for the accurate determination of a singular point is also developed. We show that combining a neural network with the numerical algorithm for the determination of the singular point we are able to accurat...
International Nuclear Information System (INIS)
The determination of the family of optimum core loading patterns for Pressurized Water Reactors (PWRs) involves the assessment of the core attributes, such as the power peaking factor for thousands of candidate loading patterns. Despite the rapid advances in computer architecture, the direct calculation of these attributes by a neutronic code needs a lot of of time and memory. With the goal of reducing the calculation time and optimizing the loading pattern, we propose in this thesis a method based on ideas of neural and statistical learning to provide a feed forward neural network capable of calculating the power peaking corresponding to an eighth core PWR. We use statistical methods to deduct judicious inputs (reduction of the input space dimension) and neural methods to train the model (learning capabilities). Indeed, on one hand, a principal component analysis allows us to characterize more efficiently the fuel assemblies (neural model inputs) and the other hand, the introduction of the a priori knowledge allows us to reducing the number of freedom parameters in the neural network. The model was built using a multi layered perceptron trained with the standard back propagation algorithm. We introduced our neural network in the automatic optimization code FORMOSA, and on EDF real problems we showed an important saving in time. Finally, we propose an hybrid method which combining the best characteristics of the linear local approximator GPT (Generalized Perturbation Theory) and the artificial neural network. (author)
International Nuclear Information System (INIS)
Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing information [2]. Each one of these cells acts as a simple processor. When individual cells interact with one another, the complex abilities of the brain are made possible. In neural networks, the input or data are processed by a propagation function that adds up the values of all the incoming data. The ending value is then compared with a threshold or specific value. The resulting value must exceed the activation function value in order to become output. The activation function is a mathematical function that a neuron uses to produce an output referring to its input value. [8] Figure 1 depicts this process. Neural networks usually have three components an input, a hidden, and an output. These layers create the end result of the neural network. A real world example is a child associating the word dog with a picture. The child says dog and simultaneously looks a picture of a dog. The input is the spoken word ''dog'', the hidden is the brain processing, and the output will be the category of the word dog based on the picture. This illustration describes how a neural network functions
Disruption prediction with adaptive neural networks for ASDEX Upgrade
International Nuclear Information System (INIS)
In this paper, an adaptive neural system has been built to predict the risk of disruption at ASDEX Upgrade. The system contains a Self Organizing Map, which determines the 'novelty' of the input of a Multi Layer Perceptron predictor module. The answer of the MLP predictor will be inhibited whenever a novel sample is detected. Furthermore, it is possible that the predictor produces a wrong answer although it is fed with known samples. In this case, a retraining procedure will be performed to update the MLP predictor in an incremental fashion using data coming from both the novelty detection, and from wrong predictions. In particular, a new update is performed whenever a missed alarm is triggered by the predictor. The performance of the adaptive predictor during the more recent experimental campaigns until November 2009 has been evaluated.
Disruption prediction with adaptive neural networks for ASDEX Upgrade
Energy Technology Data Exchange (ETDEWEB)
Cannas, B.; Fanni, A. [Electrical and Electronic Engineering Dept., University of Cagliari, Piazza D' Armi, 09123 Cagliari (Italy); Pautasso, G. [Max-Planck-Institut fuer Plasmaphysik, EURATOM Association, Garching (Germany); Sias, G., E-mail: giuliana.sias@diee.unica.it [Electrical and Electronic Engineering Dept., University of Cagliari, Piazza D' Armi, 09123 Cagliari (Italy)
2011-10-15
In this paper, an adaptive neural system has been built to predict the risk of disruption at ASDEX Upgrade. The system contains a Self Organizing Map, which determines the 'novelty' of the input of a Multi Layer Perceptron predictor module. The answer of the MLP predictor will be inhibited whenever a novel sample is detected. Furthermore, it is possible that the predictor produces a wrong answer although it is fed with known samples. In this case, a retraining procedure will be performed to update the MLP predictor in an incremental fashion using data coming from both the novelty detection, and from wrong predictions. In particular, a new update is performed whenever a missed alarm is triggered by the predictor. The performance of the adaptive predictor during the more recent experimental campaigns until November 2009 has been evaluated.
Polyelectrolyte Multilayering in Spherical Geometry
Messina, R; Kremer, K; Messina, Rene; Holm, Christian; Kremer, Kurt
2003-01-01
The adsorption of highly \\textit{oppositely} charged flexible polyelectrolytes onto a charged spherical surface is investigated by means of Monte Carlo simulations in a fashion which resembles the layer-by-layer deposition technique introduced by Decher. Electroneutrality is insured at each step by the presence of monovalent counterions (anions and cations). We study in detail the structure of the \\textit{equilibrium} complex. Our investigations of the first few layer formations strongly suggest that multilayering in spherical geometry is not possible as an equilibrium process with purely electrostatic interactions. We especially focus on the influence of specific (non-electrostatic) short range attractive interactions (e.g., Van der Waals) on the stability of the multilayers.
Metallic multilayers at the nanoscale
Energy Technology Data Exchange (ETDEWEB)
Jankowski, A.F.
1994-11-01
The development of multilayer structures has been driven by a wide range of commercial applications requiring enhanced material behaviors. Innovations in physical vapor deposition technologies, in particular magnetron sputtering, have enabled the synthesis of metallic-based structures with nanoscaled layer dimensions as small as one-to-two monolayers. Parameters used in the deposition process are paramount to the Formation of these small layer dimensions and the stability of the structure. Therefore, optimization of the desired material properties must be related to assessment of the actual microstructure. Characterization techniques as x-ray diffraction and high resolution microscopy are useful to reveal the interface and layer structure-whether ordered or disordered crystalline, amorphous, compositionally abrupt or graded, and/or lattice strained Techniques for the synthesis of metallic multilayers with subnanometric layers will be reviewed with applications based on enhancing material behaviors as reflectivity and magnetic anisotropy but with emphasis on experimental studies of mechanical properties.
Anomalous magnetoresistance in Fibonacci multilayers.
Energy Technology Data Exchange (ETDEWEB)
Machado, L. D.; Bezerra, C. G.; Correa, M. A.; Chesman, C.; Pearson, J. E.; Hoffmann, A. (Materials Science Division); (Universidade Federal do Rio Grande do Norte)
2012-01-01
We theoretically investigated magnetoresistance curves in quasiperiodic magnetic multilayers for two different growth directions, namely, [110] and [100]. We considered identical ferromagnetic layers separated by nonmagnetic layers with two different thicknesses chosen based on the Fibonacci sequence. Using parameters for Fe/Cr multilayers, four terms were included in our description of the magnetic energy: Zeeman, cubic anisotropy, bilinear coupling, and biquadratic coupling. The minimum energy was determined by the gradient method and the equilibrium magnetization directions found were used to calculate magnetoresistance curves. By choosing spacers with a thickness such that biquadratic coupling is stronger than bilinear coupling, unusual behaviors for the magnetoresistance were observed: (i) for the [110] case, there is a different behavior for structures based on even and odd Fibonacci generations, and, more interesting, (ii) for the [100] case, we found magnetic field ranges for which the magnetoresistance increases with magnetic field.
Non-Linear Unsteady Aerodynamic Response Approximation Using Multi-Layer Functionals
Scientific Electronic Library Online (English)
F. D., Marques; J., Anderson.
2002-03-01
Full Text Available Non-linear functional representation of the aerodynamic response provides a convenient mathematical model for motion-induced unsteady transonic aerodynamic loads response, that accounts for both complex non-linearities and time-history effects. A recent development, based on functional approximation [...] theory, has established a novel functional form; namely, the multi-layer functional. For a large class of non-linear dynamic systems, such multi-layer functional representations can be realised via finite impulse response (FIR) neural networks. Identification of an appropriate FIR neural network model is facilitated by means of a supervised training process in which a limited sample of system input-output data sets is presented to the temporal neural network. The present work describes a procedure for the systematic identification of parameterised neural network models of motion-induced unsteady transonic aerodynamic loads response. The training process is based on a conventional genetic algorithm to optimise the network architecture, combined with a simplified random search algorithm to update weight and bias values. Application of the scheme to representative transonic aerodynamic loads response data for a bidimensional airfoil executing finite-amplitude motion in transonic flow is used to demonstrate the feasibility of the approach. The approach is shown to furnish a satisfactory generalisation property to different motion histories over a range of Mach numbers in the transonic regime.
Centrality in Interconnected Multilayer Networks
De Domenico, Manlio; Solé-Ribalta, Albert; Omodei, Elisa; Gómez, Sergio; Arenas, Alex
2013-01-01
Real-world complex systems exhibit multiple levels of relationships. In many cases, they require to be modeled by interconnected multilayer networks, characterizing interactions on several levels simultaneously. It is of crucial importance in many fields, from economics to biology, from urban planning to social sciences, to identify the most (or the less) influent nodes in a network. However, defining the centrality of actors in an interconnected structure is not trivial. ...
Mathematical Formulation of Multilayer Networks
De Domenico, Manlio; Solé-Ribalta, Albert; Cozzo, Emanuele; Kivelä, Mikko; Moreno, Yamir; Porter, Mason A.; Gómez, Sergio; Arenas, Alex
2013-10-01
A network representation is useful for describing the structure of a large variety of complex systems. However, most real and engineered systems have multiple subsystems and layers of connectivity, and the data produced by such systems are very rich. Achieving a deep understanding of such systems necessitates generalizing “traditional” network theory, and the newfound deluge of data now makes it possible to test increasingly general frameworks for the study of networks. In particular, although adjacency matrices are useful to describe traditional single-layer networks, such a representation is insufficient for the analysis and description of multiplex and time-dependent networks. One must therefore develop a more general mathematical framework to cope with the challenges posed by multilayer complex systems. In this paper, we introduce a tensorial framework to study multilayer networks, and we discuss the generalization of several important network descriptors and dynamical processes—including degree centrality, clustering coefficients, eigenvector centrality, modularity, von Neumann entropy, and diffusion—for this framework. We examine the impact of different choices in constructing these generalizations, and we illustrate how to obtain known results for the special cases of single-layer and multiplex networks. Our tensorial approach will be helpful for tackling pressing problems in multilayer complex systems, such as inferring who is influencing whom (and by which media) in multichannel social networks and developing routing techniques for multimodal transportation systems.
Localized modes in defective multilayer structures
Entezar, S. Roshan; Namdar, A.
2009-01-01
In this paper, the localized surface modes in a defective multilayer structure has been investigated. It is shown that the defective multilayer structures can support two different kind of localized modes depending on the position and the thickness of the defect layer. One of these modes is localized at the interface between the multilayer structure and a homogeneous medium (the so-called surface mode) and the other one is localized at the defect layer (defect localized mode...
Electrical conductivity of collapsed multilayer graphene tubes
D. Mendoza
2011-01-01
Synthesis of multilayer graphene on copper wires by a chemical vapor deposition method is reported. After copper etching, the multilayer tube collapses forming stripes of graphitic films, their electrical conductance as a function of temperature indicate a semiconductor-like behavior. Using the multilayer graphene stripes, a cross junction is built and owing to its electrical behavior we propose that a tunneling process exists in the device.
Multilayer Analysis and Visualization of Networks
De Domenico, Manlio; Arenas, Alex
2014-01-01
Multilayer relationships among and information about biological entities must be accompanied by the means to analyze, visualize, and obtain insights from such data. We report a methodology and a collection of algorithms for the analysis of multilayer networks in our new open-source software (muxViz). We demonstrate the ability of muxViz to analyze and interactively visualize multilayer data using empirical genetic and neuronal networks.
Polarizability and Screening in Chiral Multilayer Graphene
Min, Hongki; Hwang, E. H.; Sarma, S. Das
2012-01-01
We calculate the static polarizability of multilayer graphene and study the effect of stacking arrangement, carrier density, and onsite energy difference on graphene screening properties. At low densities, the energy spectrum of multilayer graphene is described by a set of chiral two-dimensional electron systems and the associated chiral nature determines the screening properties of multilayer graphene showing very different behavior depending on whether the chirality index ...