Algorithms for Reinforcement Learning
Szepesvari, Csaba
2010-01-01
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms'
Unsupervised learning algorithms
Aydin, Kemal
2016-01-01
This book summarizes the state-of-the-art in unsupervised learning. The contributors discuss how with the proliferation of massive amounts of unlabeled data, unsupervised learning algorithms, which can automatically discover interesting and useful patterns in such data, have gained popularity among researchers and practitioners. The authors outline how these algorithms have found numerous applications including pattern recognition, market basket analysis, web mining, social network analysis, information retrieval, recommender systems, market research, intrusion detection, and fraud detection. They present how the difficulty of developing theoretically sound approaches that are amenable to objective evaluation have resulted in the proposal of numerous unsupervised learning algorithms over the past half-century. The intended audience includes researchers and practitioners who are increasingly using unsupervised learning algorithms to analyze their data. Topics of interest include anomaly detection, clustering,...
Cascade Error Projection Learning Algorithm
Duong, T. A.; Stubberud, A. R.; Daud, T.
1995-01-01
A detailed mathematical analysis is presented for a new learning algorithm termed cascade error projection (CEP) and a general learning frame work. This frame work can be used to obtain the cascade correlation learning algorithm by choosing a particular set of parameters.
Machine Learning an algorithmic perspective
Marsland, Stephen
2009-01-01
Traditional books on machine learning can be divided into two groups - those aimed at advanced undergraduates or early postgraduates with reasonable mathematical knowledge and those that are primers on how to code algorithms. The field is ready for a text that not only demonstrates how to use the algorithms that make up machine learning methods, but also provides the background needed to understand how and why these algorithms work. Machine Learning: An Algorithmic Perspective is that text.Theory Backed up by Practical ExamplesThe book covers neural networks, graphical models, reinforcement le
Empirical tests of the Gradual Learning Algorithm
Boersma, P.; Hayes, B.
1999-01-01
The Gradual Learning Algorithm (Boersma 1997) is a constraint ranking algorithm for learning Optimality-theoretic grammars. The purpose of this article is to assess the capabilities of the Gradual Learning Algorithm, particularly in comparison with the Constraint Demotion algorithm of Tesar and
Empirical tests of the Gradual Learning Algorithm
Boersma, P.; Hayes, B.
2001-01-01
The Gradual Learning Algorithm (Boersma 1997) is a constraint-ranking algorithm for learning optimality-theoretic grammars. The purpose of this article is to assess the capabilities of the Gradual Learning Algorithm, particularly in comparison with the Constraint Demotion algorithm of Tesar and
Storage capacity of the Tilinglike Learning Algorithm
International Nuclear Information System (INIS)
Buhot, Arnaud; Gordon, Mirta B.
2001-01-01
The storage capacity of an incremental learning algorithm for the parity machine, the Tilinglike Learning Algorithm, is analytically determined in the limit of a large number of hidden perceptrons. Different learning rules for the simple perceptron are investigated. The usual Gardner-Derrida rule leads to a storage capacity close to the upper bound, which is independent of the learning algorithm considered
The Dropout Learning Algorithm
Baldi, Pierre; Sadowski, Peter
2014-01-01
Dropout is a recently introduced algorithm for training neural network by randomly dropping units during training to prevent their co-adaptation. A mathematical analysis of some of the static and dynamic properties of dropout is provided using Bernoulli gating variables, general enough to accommodate dropout on units or connections, and with variable rates. The framework allows a complete analysis of the ensemble averaging properties of dropout in linear networks, which is useful to understand the non-linear case. The ensemble averaging properties of dropout in non-linear logistic networks result from three fundamental equations: (1) the approximation of the expectations of logistic functions by normalized geometric means, for which bounds and estimates are derived; (2) the algebraic equality between normalized geometric means of logistic functions with the logistic of the means, which mathematically characterizes logistic functions; and (3) the linearity of the means with respect to sums, as well as products of independent variables. The results are also extended to other classes of transfer functions, including rectified linear functions. Approximation errors tend to cancel each other and do not accumulate. Dropout can also be connected to stochastic neurons and used to predict firing rates, and to backpropagation by viewing the backward propagation as ensemble averaging in a dropout linear network. Moreover, the convergence properties of dropout can be understood in terms of stochastic gradient descent. Finally, for the regularization properties of dropout, the expectation of the dropout gradient is the gradient of the corresponding approximation ensemble, regularized by an adaptive weight decay term with a propensity for self-consistent variance minimization and sparse representations. PMID:24771879
Cascade Error Projection: A New Learning Algorithm
Duong, T. A.; Stubberud, A. R.; Daud, T.; Thakoor, A. P.
1995-01-01
A new neural network architecture and a hardware implementable learning algorithm is proposed. The algorithm, called cascade error projection (CEP), handles lack of precision and circuit noise better than existing algorithms.
Quantum learning algorithms for quantum measurements
Energy Technology Data Exchange (ETDEWEB)
Bisio, Alessandro, E-mail: alessandro.bisio@unipv.it [QUIT Group, Dipartimento di Fisica ' A. Volta' and INFN, via Bassi 6, 27100 Pavia (Italy); D' Ariano, Giacomo Mauro, E-mail: dariano@unipv.it [QUIT Group, Dipartimento di Fisica ' A. Volta' and INFN, via Bassi 6, 27100 Pavia (Italy); Perinotti, Paolo, E-mail: paolo.perinotti@unipv.it [QUIT Group, Dipartimento di Fisica ' A. Volta' and INFN, via Bassi 6, 27100 Pavia (Italy); Sedlak, Michal, E-mail: michal.sedlak@unipv.it [QUIT Group, Dipartimento di Fisica ' A. Volta' and INFN, via Bassi 6, 27100 Pavia (Italy); Institute of Physics, Slovak Academy of Sciences, Dubravska cesta 9, 845 11 Bratislava (Slovakia)
2011-09-12
We study quantum learning algorithms for quantum measurements. The optimal learning algorithm is derived for arbitrary von Neumann measurements in the case of training with one or two examples. The analysis of the case of three examples reveals that, differently from the learning of unitary gates, the optimal algorithm for learning of quantum measurements cannot be parallelized, and requires quantum memories for the storage of information. -- Highlights: → Optimal learning algorithm for von Neumann measurements. → From 2 copies to 1 copy: the optimal strategy is parallel. → From 3 copies to 1 copy: the optimal strategy must be non-parallel.
Quantum learning algorithms for quantum measurements
International Nuclear Information System (INIS)
Bisio, Alessandro; D'Ariano, Giacomo Mauro; Perinotti, Paolo; Sedlak, Michal
2011-01-01
We study quantum learning algorithms for quantum measurements. The optimal learning algorithm is derived for arbitrary von Neumann measurements in the case of training with one or two examples. The analysis of the case of three examples reveals that, differently from the learning of unitary gates, the optimal algorithm for learning of quantum measurements cannot be parallelized, and requires quantum memories for the storage of information. -- Highlights: → Optimal learning algorithm for von Neumann measurements. → From 2 copies to 1 copy: the optimal strategy is parallel. → From 3 copies to 1 copy: the optimal strategy must be non-parallel.
Learning algorithms and automatic processing of languages
International Nuclear Information System (INIS)
Fluhr, Christian Yves Andre
1977-01-01
This research thesis concerns the field of artificial intelligence. It addresses learning algorithms applied to automatic processing of languages. The author first briefly describes some mechanisms of human intelligence in order to describe how these mechanisms are simulated on a computer. He outlines the specific role of learning in various manifestations of intelligence. Then, based on the Markov's algorithm theory, the author discusses the notion of learning algorithm. Two main types of learning algorithms are then addressed: firstly, an 'algorithm-teacher dialogue' type sanction-based algorithm which aims at learning how to solve grammatical ambiguities in submitted texts; secondly, an algorithm related to a document system which structures semantic data automatically obtained from a set of texts in order to be able to understand by references to any question on the content of these texts
Exploitation of linkage learning in evolutionary algorithms
Chen, Ying-ping
2010-01-01
The exploitation of linkage learning is enhancing the performance of evolutionary algorithms. This monograph examines recent progress in linkage learning, with a series of focused technical chapters that cover developments and trends in the field.
Learning Intelligent Genetic Algorithms Using Japanese Nonograms
Tsai, Jinn-Tsong; Chou, Ping-Yi; Fang, Jia-Cen
2012-01-01
An intelligent genetic algorithm (IGA) is proposed to solve Japanese nonograms and is used as a method in a university course to learn evolutionary algorithms. The IGA combines the global exploration capabilities of a canonical genetic algorithm (CGA) with effective condensed encoding, improved fitness function, and modified crossover and…
Learning theory of distributed spectral algorithms
International Nuclear Information System (INIS)
Guo, Zheng-Chu; Lin, Shao-Bo; Zhou, Ding-Xuan
2017-01-01
Spectral algorithms have been widely used and studied in learning theory and inverse problems. This paper is concerned with distributed spectral algorithms, for handling big data, based on a divide-and-conquer approach. We present a learning theory for these distributed kernel-based learning algorithms in a regression framework including nice error bounds and optimal minimax learning rates achieved by means of a novel integral operator approach and a second order decomposition of inverse operators. Our quantitative estimates are given in terms of regularity of the regression function, effective dimension of the reproducing kernel Hilbert space, and qualification of the filter function of the spectral algorithm. They do not need any eigenfunction or noise conditions and are better than the existing results even for the classical family of spectral algorithms. (paper)
Kernel learning algorithms for face recognition
Li, Jun-Bao; Pan, Jeng-Shyang
2013-01-01
Kernel Learning Algorithms for Face Recognition covers the framework of kernel based face recognition. This book discusses the advanced kernel learning algorithms and its application on face recognition. This book also focuses on the theoretical deviation, the system framework and experiments involving kernel based face recognition. Included within are algorithms of kernel based face recognition, and also the feasibility of the kernel based face recognition method. This book provides researchers in pattern recognition and machine learning area with advanced face recognition methods and its new
Quantum algorithms and learning theory
Arunachalam, S.
2018-01-01
This thesis studies strengths and weaknesses of quantum computers. In the first part we present three contributions to quantum algorithms. 1) consider a search space of N elements. One of these elements is "marked" and our goal is to find this. We describe a quantum algorithm to solve this problem
Parallelization of TMVA Machine Learning Algorithms
Hajili, Mammad
2017-01-01
This report reflects my work on Parallelization of TMVA Machine Learning Algorithms integrated to ROOT Data Analysis Framework during summer internship at CERN. The report consists of 4 impor- tant part - data set used in training and validation, algorithms that multiprocessing applied on them, parallelization techniques and re- sults of execution time changes due to number of workers.
Top Tagging by Deep Learning Algorithm
Akil, Ali
2015-01-01
In this report I will show the application of a deep learning algorithm on a Monte Carlo simulation sample to test its performance in tagging hadronic decays of boosted top quarks and compare what we get with the results of the application of some other algorithms.
A distributed algorithm for machine learning
Chen, Shihong
2018-04-01
This paper considers a distributed learning problem in which a group of machines in a connected network, each learning its own local dataset, aim to reach a consensus at an optimal model, by exchanging information only with their neighbors but without transmitting data. A distributed algorithm is proposed to solve this problem under appropriate assumptions.
Algorithmic learning in a random world
Vovk, Vladimir; Shafer, Glenn
2005-01-01
A new scientific monograph developing significant new algorithmic foundations in machine learning theory. Researchers and postgraduates in CS, statistics, and A.I. will find the book an authoritative and formal presentation of some of the most promising theoretical developments in machine learning.
A Learning Algorithm for Multimodal Grammar Inference.
D'Ulizia, A; Ferri, F; Grifoni, P
2011-12-01
The high costs of development and maintenance of multimodal grammars in integrating and understanding input in multimodal interfaces lead to the investigation of novel algorithmic solutions in automating grammar generation and in updating processes. Many algorithms for context-free grammar inference have been developed in the natural language processing literature. An extension of these algorithms toward the inference of multimodal grammars is necessary for multimodal input processing. In this paper, we propose a novel grammar inference mechanism that allows us to learn a multimodal grammar from its positive samples of multimodal sentences. The algorithm first generates the multimodal grammar that is able to parse the positive samples of sentences and, afterward, makes use of two learning operators and the minimum description length metrics in improving the grammar description and in avoiding the over-generalization problem. The experimental results highlight the acceptable performances of the algorithm proposed in this paper since it has a very high probability of parsing valid sentences.
Learning from nature: Nature-inspired algorithms
DEFF Research Database (Denmark)
Albeanu, Grigore; Madsen, Henrik; Popentiu-Vladicescu, Florin
2016-01-01
.), genetic and evolutionary strategies, artificial immune systems etc. Well-known examples of applications include: aircraft wing design, wind turbine design, bionic car, bullet train, optimal decisions related to traffic, appropriate strategies to survive under a well-adapted immune system etc. Based......During last decade, the nature has inspired researchers to develop new algorithms. The largest collection of nature-inspired algorithms is biology-inspired: swarm intelligence (particle swarm optimization, ant colony optimization, cuckoo search, bees' algorithm, bat algorithm, firefly algorithm etc...... on collective social behaviour of organisms, researchers have developed optimization strategies taking into account not only the individuals, but also groups and environment. However, learning from nature, new classes of approaches can be identified, tested and compared against already available algorithms...
A Decomposition Algorithm for Learning Bayesian Network Structures from Data
DEFF Research Database (Denmark)
Zeng, Yifeng; Cordero Hernandez, Jorge
2008-01-01
It is a challenging task of learning a large Bayesian network from a small data set. Most conventional structural learning approaches run into the computational as well as the statistical problems. We propose a decomposition algorithm for the structure construction without having to learn...... the complete network. The new learning algorithm firstly finds local components from the data, and then recover the complete network by joining the learned components. We show the empirical performance of the decomposition algorithm in several benchmark networks....
TAO-robust backpropagation learning algorithm.
Pernía-Espinoza, Alpha V; Ordieres-Meré, Joaquín B; Martínez-de-Pisón, Francisco J; González-Marcos, Ana
2005-03-01
In several fields, as industrial modelling, multilayer feedforward neural networks are often used as universal function approximations. These supervised neural networks are commonly trained by a traditional backpropagation learning format, which minimises the mean squared error (mse) of the training data. However, in the presence of corrupted data (outliers) this training scheme may produce wrong models. We combine the benefits of the non-linear regression model tau-estimates [introduced by Tabatabai, M. A. Argyros, I. K. Robust Estimation and testing for general nonlinear regression models. Applied Mathematics and Computation. 58 (1993) 85-101] with the backpropagation algorithm to produce the TAO-robust learning algorithm, in order to deal with the problems of modelling with outliers. The cost function of this approach has a bounded influence function given by the weighted average of two psi functions, one corresponding to a very robust estimate and the other to a highly efficient estimate. The advantages of the proposed algorithm are studied with an example.
A Learning Algorithm based on High School Teaching Wisdom
Philip, Ninan Sajeeth
2010-01-01
A learning algorithm based on primary school teaching and learning is presented. The methodology is to continuously evaluate a student and to give them training on the examples for which they repeatedly fail, until, they can correctly answer all types of questions. This incremental learning procedure produces better learning curves by demanding the student to optimally dedicate their learning time on the failed examples. When used in machine learning, the algorithm is found to train a machine...
Specific radioimmunoassay for ovine bone gla-protein (osteocalcin)
International Nuclear Information System (INIS)
Pastoureau, P.; Merle, B.; Delmas, P.D.
1988-01-01
We developed a sensitive and specific radioimmunoassay for ovine bone gla-protein (osteocalcin) using a polyclonal rabbit antibody raised against ovine bone gla-protein. Bone from lambs was extracted in 0.5 mol/l EDTA and desalted on Sephadex G-25. Bone gla-protein was purified by gel filtration chromatography over Sephadex G-100 and ion-exchange chromatography on DEAE-Sephadex A-25. The protein, subjected to monodimensional electrophoresis migrated as a single spot in SDS PAGE with the same apparent molecular weight of 12 kD as bovine bone gla-protein. The amino acid composition of pufified bone gla-protein was in agreement with a previous publication. The competitive RIA uses 125 I-labelled bone gla-protein as a tracer and a complex of a second antibody and polyethylene glycol to separate free and antibody-bound 125 I-labelled bone gla-protein. The intra- and inter-assay variations are less than 6 and 10%, respectively. There is no reactivity of our antisera with dog sera. The cross-reactivity is only partial with calf and human sera and complete with ovine sera. We measured bone gla-protein levels in serum of 96 normal male sheep of different ages. Serum bone gla-protein rapidly and significantly (P<0.001) decreased from 532 ± 169 μg/l at birth, to 240 ± 43 μg/l at 45 days, 152 ± 44 μg/l at 90 days, and 5.9 ± 0.7 μg/l at 7 years age. In addition, bone gla-protein levels at birth were higher in normal birth weight than in hypotrophic lambs with low birth weight (535 ± 169 vs 271 ± 156 μg/l, P<0.0001). Furthermore, lambs raised outside in free conditions tended to have higher serum bone gla-protein levels than lambs raised under shelter (1984 ± 53 vs 137 ± 34 μg/l), suggesting a role of breeding factors such as diet or relative immobilization on bone gla-protein levels. These results emphasize the interest of a RIA for the bone-specific protein bone gla-protein as a potential tool for experimental studies on skeletal growth and bone remodelling in a
"Accelerated Perceptron": A Self-Learning Linear Decision Algorithm
Zuev, Yu. A.
2003-01-01
The class of linear decision rules is studied. A new algorithm for weight correction, called an "accelerated perceptron", is proposed. In contrast to classical Rosenblatt's perceptron this algorithm modifies the weight vector at each step. The algorithm may be employed both in learning and in self-learning modes. The theoretical aspects of the behaviour of the algorithm are studied when the algorithm is used for the purpose of increasing the decision reliability by means of weighted voting. I...
A Newton-type neural network learning algorithm
International Nuclear Information System (INIS)
Ivanov, V.V.; Puzynin, I.V.; Purehvdorzh, B.
1993-01-01
First- and second-order learning methods for feed-forward multilayer networks are considered. A Newton-type algorithm is proposed and compared with the common back-propagation algorithm. It is shown that the proposed algorithm provides better learning quality. Some recommendations for their usage are given. 11 refs.; 1 fig.; 1 tab
Specific radioimmunoassay for ovine bone gla-protein (osteocalcin)
Energy Technology Data Exchange (ETDEWEB)
Pastoureau, P; Merle, B; Delmas, P D
1988-01-01
We developed a sensitive and specific radioimmunoassay for ovine bone gla-protein (osteocalcin) using a polyclonal rabbit antibody raised against ovine bone gla-protein. Bone from lambs was extracted in 0.5 mol/l EDTA and desalted on Sephadex G-25. Bone gla-protein was purified by gel filtration chromatography over Sephadex G-100 and ion-exchange chromatography on DEAE-Sephadex A-25. The protein, subjected to monodimensional electrophoresis migrated as a single spot in SDS PAGE with the same apparent molecular weight of 12 kD as bovine bone gla-protein. The amino acid composition of pufified bone gla-protein was in agreement with a previous publication. The competitive RIA uses /sup 125/I-labelled bone gla-protein as a tracer and a complex of a second antibody and polyethylene glycol to separate free and antibody-bound /sup 125/I-labelled bone gla-protein. The intra- and inter-assay variations are less than 6 and 10%, respectively. There is no reactivity of our antisera with dog sera. The cross-reactivity is only partial with calf and human sera and complete with ovine sera. We measured bone gla-protein levels in serum of 96 normal male sheep of different ages. Serum bone gla-protein rapidly and significantly (P<0.001) decreased from 532 +- 169 ..mu..g/l at birth, to 240 +- 43 ..mu..g/l at 45 days, 152 +- 44 ..mu..g/l at 90 days, and 5.9 +- 0.7 ..mu..g/l at 7 years age. In addition, bone gla-protein levels at birth were higher in normal birth weight than in hypotrophic lambs with low birth weight (535 +- 169 vs 271 +- 156 ..mu..g/l, P<0.0001). Furthermore, lambs raised outside in free conditions tended to have higher serum bone gla-protein levels than lambs raised under shelter (1984 +- 53 vs 137 +- 34 ..mu..g/l), suggesting a role of breeding factors such as diet or relative immobilization on bone gla-protein levels. (Abstract Truncated)
Energy Technology Data Exchange (ETDEWEB)
Fluhr, Christian Yves Andre
1977-06-15
This research thesis concerns the field of artificial intelligence. It addresses learning algorithms applied to automatic processing of languages. The author first briefly describes some mechanisms of human intelligence in order to describe how these mechanisms are simulated on a computer. He outlines the specific role of learning in various manifestations of intelligence. Then, based on the Markov's algorithm theory, the author discusses the notion of learning algorithm. Two main types of learning algorithms are then addressed: firstly, an 'algorithm-teacher dialogue' type sanction-based algorithm which aims at learning how to solve grammatical ambiguities in submitted texts; secondly, an algorithm related to a document system which structures semantic data automatically obtained from a set of texts in order to be able to understand by references to any question on the content of these texts.
Online learning algorithm for ensemble of decision rules
Chikalov, Igor; Moshkov, Mikhail; Zielosko, Beata
2011-01-01
We describe an online learning algorithm that builds a system of decision rules for a classification problem. Rules are constructed according to the minimum description length principle by a greedy algorithm or using the dynamic programming approach
Cascade Error Projection: An Efficient Hardware Learning Algorithm
Duong, T. A.
1995-01-01
A new learning algorithm termed cascade error projection (CEP) is presented. CEP is an adaption of a constructive architecture from cascade correlation and the dynamical stepsize of A/D conversion from the cascade back propagation algorithm.
Boosting Learning Algorithm for Stock Price Forecasting
Wang, Chengzhang; Bai, Xiaoming
2018-03-01
To tackle complexity and uncertainty of stock market behavior, more studies have introduced machine learning algorithms to forecast stock price. ANN (artificial neural network) is one of the most successful and promising applications. We propose a boosting-ANN model in this paper to predict the stock close price. On the basis of boosting theory, multiple weak predicting machines, i.e. ANNs, are assembled to build a stronger predictor, i.e. boosting-ANN model. New error criteria of the weak studying machine and rules of weights updating are adopted in this study. We select technical factors from financial markets as forecasting input variables. Final results demonstrate the boosting-ANN model works better than other ones for stock price forecasting.
Research on machine learning framework based on random forest algorithm
Ren, Qiong; Cheng, Hui; Han, Hai
2017-03-01
With the continuous development of machine learning, industry and academia have released a lot of machine learning frameworks based on distributed computing platform, and have been widely used. However, the existing framework of machine learning is limited by the limitations of machine learning algorithm itself, such as the choice of parameters and the interference of noises, the high using threshold and so on. This paper introduces the research background of machine learning framework, and combined with the commonly used random forest algorithm in machine learning classification algorithm, puts forward the research objectives and content, proposes an improved adaptive random forest algorithm (referred to as ARF), and on the basis of ARF, designs and implements the machine learning framework.
An algorithm for learning real-time automata
Verwer, S.E.; De Weerdt, M.M.; Witteveen, C.
2007-01-01
We describe an algorithm for learning simple timed automata, known as real-time automata. The transitions of real-time automata can have a temporal constraint on the time of occurrence of the current symbol relative to the previous symbol. The learning algorithm is similar to the redblue fringe
Relevance as a metric for evaluating machine learning algorithms
Kota Gopalakrishna, A.; Ozcelebi, T.; Liotta, A.; Lukkien, J.J.
2013-01-01
In machine learning, the choice of a learning algorithm that is suitable for the application domain is critical. The performance metric used to compare different algorithms must also reflect the concerns of users in the application domain under consideration. In this work, we propose a novel
Challenges in the Verification of Reinforcement Learning Algorithms
Van Wesel, Perry; Goodloe, Alwyn E.
2017-01-01
Machine learning (ML) is increasingly being applied to a wide array of domains from search engines to autonomous vehicles. These algorithms, however, are notoriously complex and hard to verify. This work looks at the assumptions underlying machine learning algorithms as well as some of the challenges in trying to verify ML algorithms. Furthermore, we focus on the specific challenges of verifying reinforcement learning algorithms. These are highlighted using a specific example. Ultimately, we do not offer a solution to the complex problem of ML verification, but point out possible approaches for verification and interesting research opportunities.
Location-Aware Mobile Learning of Spatial Algorithms
Karavirta, Ville
2013-01-01
Learning an algorithm--a systematic sequence of operations for solving a problem with given input--is often difficult for students due to the abstract nature of the algorithms and the data they process. To help students understand the behavior of algorithms, a subfield in computing education research has focused on algorithm…
Gradient descent learning algorithm overview: a general dynamical systems perspective.
Baldi, P
1995-01-01
Gives a unified treatment of gradient descent learning algorithms for neural networks using a general framework of dynamical systems. This general approach organizes and simplifies all the known algorithms and results which have been originally derived for different problems (fixed point/trajectory learning), for different models (discrete/continuous), for different architectures (forward/recurrent), and using different techniques (backpropagation, variational calculus, adjoint methods, etc.). The general approach can also be applied to derive new algorithms. The author then briefly examines some of the complexity issues and limitations intrinsic to gradient descent learning. Throughout the paper, the author focuses on the problem of trajectory learning.
Automated training for algorithms that learn from genomic data.
Cilingir, Gokcen; Broschat, Shira L
2015-01-01
Supervised machine learning algorithms are used by life scientists for a variety of objectives. Expert-curated public gene and protein databases are major resources for gathering data to train these algorithms. While these data resources are continuously updated, generally, these updates are not incorporated into published machine learning algorithms which thereby can become outdated soon after their introduction. In this paper, we propose a new model of operation for supervised machine learning algorithms that learn from genomic data. By defining these algorithms in a pipeline in which the training data gathering procedure and the learning process are automated, one can create a system that generates a classifier or predictor using information available from public resources. The proposed model is explained using three case studies on SignalP, MemLoci, and ApicoAP in which existing machine learning models are utilized in pipelines. Given that the vast majority of the procedures described for gathering training data can easily be automated, it is possible to transform valuable machine learning algorithms into self-evolving learners that benefit from the ever-changing data available for gene products and to develop new machine learning algorithms that are similarly capable.
SOL: A Library for Scalable Online Learning Algorithms
Wu, Yue; Hoi, Steven C. H.; Liu, Chenghao; Lu, Jing; Sahoo, Doyen; Yu, Nenghai
2016-01-01
SOL is an open-source library for scalable online learning algorithms, and is particularly suitable for learning with high-dimensional data. The library provides a family of regular and sparse online learning algorithms for large-scale binary and multi-class classification tasks with high efficiency, scalability, portability, and extensibility. SOL was implemented in C++, and provided with a collection of easy-to-use command-line tools, python wrappers and library calls for users and develope...
Human resource recommendation algorithm based on ensemble learning and Spark
Cong, Zihan; Zhang, Xingming; Wang, Haoxiang; Xu, Hongjie
2017-08-01
Aiming at the problem of “information overload” in the human resources industry, this paper proposes a human resource recommendation algorithm based on Ensemble Learning. The algorithm considers the characteristics and behaviours of both job seeker and job features in the real business circumstance. Firstly, the algorithm uses two ensemble learning methods-Bagging and Boosting. The outputs from both learning methods are then merged to form user interest model. Based on user interest model, job recommendation can be extracted for users. The algorithm is implemented as a parallelized recommendation system on Spark. A set of experiments have been done and analysed. The proposed algorithm achieves significant improvement in accuracy, recall rate and coverage, compared with recommendation algorithms such as UserCF and ItemCF.
A strategy for quantum algorithm design assisted by machine learning
International Nuclear Information System (INIS)
Bang, Jeongho; Lee, Jinhyoung; Ryu, Junghee; Yoo, Seokwon; Pawłowski, Marcin
2014-01-01
We propose a method for quantum algorithm design assisted by machine learning. The method uses a quantum–classical hybrid simulator, where a ‘quantum student’ is being taught by a ‘classical teacher’. In other words, in our method, the learning system is supposed to evolve into a quantum algorithm for a given problem, assisted by a classical main-feedback system. Our method is applicable for designing quantum oracle-based algorithms. We chose, as a case study, an oracle decision problem, called a Deutsch–Jozsa problem. We showed by using Monte Carlo simulations that our simulator can faithfully learn a quantum algorithm for solving the problem for a given oracle. Remarkably, the learning time is proportional to the square root of the total number of parameters, rather than showing the exponential dependence found in the classical machine learning-based method. (paper)
A strategy for quantum algorithm design assisted by machine learning
Bang, Jeongho; Ryu, Junghee; Yoo, Seokwon; Pawłowski, Marcin; Lee, Jinhyoung
2014-07-01
We propose a method for quantum algorithm design assisted by machine learning. The method uses a quantum-classical hybrid simulator, where a ‘quantum student’ is being taught by a ‘classical teacher’. In other words, in our method, the learning system is supposed to evolve into a quantum algorithm for a given problem, assisted by a classical main-feedback system. Our method is applicable for designing quantum oracle-based algorithms. We chose, as a case study, an oracle decision problem, called a Deutsch-Jozsa problem. We showed by using Monte Carlo simulations that our simulator can faithfully learn a quantum algorithm for solving the problem for a given oracle. Remarkably, the learning time is proportional to the square root of the total number of parameters, rather than showing the exponential dependence found in the classical machine learning-based method.
Imbalanced learning foundations, algorithms, and applications
He, Haibo
2013-01-01
The first book of its kind to review the current status and future direction of the exciting new branch of machine learning/data mining called imbalanced learning Imbalanced learning focuses on how an intelligent system can learn when it is provided with imbalanced data. Solving imbalanced learning problems is critical in numerous data-intensive networked systems, including surveillance, security, Internet, finance, biomedical, defense, and more. Due to the inherent complex characteristics of imbalanced data sets, learning from such data requires new understandings, principles,
Leave-two-out stability of ontology learning algorithm
International Nuclear Information System (INIS)
Wu, Jianzhang; Yu, Xiao; Zhu, Linli; Gao, Wei
2016-01-01
Ontology is a semantic analysis and calculation model, which has been applied to many subjects. Ontology similarity calculation and ontology mapping are employed as machine learning approaches. The purpose of this paper is to study the leave-two-out stability of ontology learning algorithm. Several leave-two-out stabilities are defined in ontology learning setting and the relationship among these stabilities are presented. Furthermore, the results manifested reveal that leave-two-out stability is a sufficient and necessary condition for ontology learning algorithm.
QUEST : Eliminating online supervised learning for efficient classification algorithms
Zwartjes, Ardjan; Havinga, Paul J.M.; Smit, Gerard J.M.; Hurink, Johann L.
2016-01-01
In this work, we introduce QUEST (QUantile Estimation after Supervised Training), an adaptive classification algorithm for Wireless Sensor Networks (WSNs) that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting
Teaching learning based optimization algorithm and its engineering applications
Rao, R Venkata
2016-01-01
Describing a new optimization algorithm, the “Teaching-Learning-Based Optimization (TLBO),” in a clear and lucid style, this book maximizes reader insights into how the TLBO algorithm can be used to solve continuous and discrete optimization problems involving single or multiple objectives. As the algorithm operates on the principle of teaching and learning, where teachers influence the quality of learners’ results, the elitist version of TLBO algorithm (ETLBO) is described along with applications of the TLBO algorithm in the fields of electrical engineering, mechanical design, thermal engineering, manufacturing engineering, civil engineering, structural engineering, computer engineering, electronics engineering, physics and biotechnology. The book offers a valuable resource for scientists, engineers and practitioners involved in the development and usage of advanced optimization algorithms.
Extreme learning machines 2013 algorithms and applications
Toh, Kar-Ann; Romay, Manuel; Mao, Kezhi
2014-01-01
In recent years, ELM has emerged as a revolutionary technique of computational intelligence, and has attracted considerable attentions. An extreme learning machine (ELM) is a single layer feed-forward neural network alike learning system, whose connections from the input layer to the hidden layer are randomly generated, while the connections from the hidden layer to the output layer are learned through linear learning methods. The outstanding merits of extreme learning machine (ELM) are its fast learning speed, trivial human intervene and high scalability. This book contains some selected papers from the International Conference on Extreme Learning Machine 2013, which was held in Beijing China, October 15-17, 2013. This conference aims to bring together the researchers and practitioners of extreme learning machine from a variety of fields including artificial intelligence, biomedical engineering and bioinformatics, system modelling and control, and signal and image processing, to promote research and discu...
A parallel ILP algorithm that incorporates incremental batch learning
Nuno Fonseca; Rui Camacho; Fernado Silva
2003-01-01
In this paper we tackle the problems of eciency and scala-bility faced by Inductive Logic Programming (ILP) systems. We proposethe use of parallelism to improve eciency and the use of an incrementalbatch learning to address the scalability problem. We describe a novelparallel algorithm that incorporates into ILP the method of incremen-tal batch learning. The theoretical complexity of the algorithm indicatesthat a linear speedup can be achieved.
Machine Learning in Production Systems Design Using Genetic Algorithms
Abu Qudeiri Jaber; Yamamoto Hidehiko Rizauddin Ramli
2008-01-01
To create a solution for a specific problem in machine learning, the solution is constructed from the data or by use a search method. Genetic algorithms are a model of machine learning that can be used to find nearest optimal solution. While the great advantage of genetic algorithms is the fact that they find a solution through evolution, this is also the biggest disadvantage. Evolution is inductive, in nature life does not evolve towards a good solution but it evolves aw...
Online learning algorithm for ensemble of decision rules
Chikalov, Igor
2011-01-01
We describe an online learning algorithm that builds a system of decision rules for a classification problem. Rules are constructed according to the minimum description length principle by a greedy algorithm or using the dynamic programming approach. © 2011 Springer-Verlag.
Mind the Gaps: Controversies about Algorithms, Learning and Trendy Knowledge
Argenton, Gerald
2017-01-01
This article critically explores the ways by which the Web could become a more learning-oriented medium in the age of, but also in spite of, the newly bred algorithmic cultures. The social dimension of algorithms is reported in literature as being a socio-technological entanglement that has a powerful influence on users' practices and their lived…
Recommending Learning Activities in Social Network Using Data Mining Algorithms
Mahnane, Lamia
2017-01-01
In this paper, we show how data mining algorithms (e.g. Apriori Algorithm (AP) and Collaborative Filtering (CF)) is useful in New Social Network (NSN-AP-CF). "NSN-AP-CF" processes the clusters based on different learning styles. Next, it analyzes the habits and the interests of the users through mining the frequent episodes by the…
Machine learning algorithms for datasets popularity prediction
Kancys, Kipras
2016-01-01
This report represents continued study where ML algorithms were used to predict databases popularity. Three topics were covered. First of all, there was a discrepancy between old and new meta-data collection procedures, so a reason for that had to be found. Secondly, different parameters were analysed and dropped to make algorithms perform better. And third, it was decided to move modelling part on Spark.
Assessment of various supervised learning algorithms using different performance metrics
Susheel Kumar, S. M.; Laxkar, Deepak; Adhikari, Sourav; Vijayarajan, V.
2017-11-01
Our work brings out comparison based on the performance of supervised machine learning algorithms on a binary classification task. The supervised machine learning algorithms which are taken into consideration in the following work are namely Support Vector Machine(SVM), Decision Tree(DT), K Nearest Neighbour (KNN), Naïve Bayes(NB) and Random Forest(RF). This paper mostly focuses on comparing the performance of above mentioned algorithms on one binary classification task by analysing the Metrics such as Accuracy, F-Measure, G-Measure, Precision, Misclassification Rate, False Positive Rate, True Positive Rate, Specificity, Prevalence.
Convergence analysis of Chauvin's PCA learning algorithm with a constant learning rate
International Nuclear Information System (INIS)
Lv Jiancheng; Yi Zhang
2007-01-01
The convergence of Chauvin's PCA learning algorithm with a constant learning rate is studied in this paper by using a DDT method (deterministic discrete-time system method). Different from the DCT method (deterministic continuous-time system method), the DDT method does not require that the learning rate converges to zero. An invariant set of Chauvin's algorithm with a constant learning rate is obtained so that the non-divergence of this algorithm can be guaranteed. Rigorous mathematic proofs are provided to prove the local convergence of this algorithm
Convergence analysis of Chauvin's PCA learning algorithm with a constant learning rate
Energy Technology Data Exchange (ETDEWEB)
Lv Jiancheng [Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054 (China); Yi Zhang [Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054 (China)]. E-mail: zhangyi@uestc.edu.cn
2007-05-15
The convergence of Chauvin's PCA learning algorithm with a constant learning rate is studied in this paper by using a DDT method (deterministic discrete-time system method). Different from the DCT method (deterministic continuous-time system method), the DDT method does not require that the learning rate converges to zero. An invariant set of Chauvin's algorithm with a constant learning rate is obtained so that the non-divergence of this algorithm can be guaranteed. Rigorous mathematic proofs are provided to prove the local convergence of this algorithm.
Learning motor skills from algorithms to robot experiments
Kober, Jens
2014-01-01
This book presents the state of the art in reinforcement learning applied to robotics both in terms of novel algorithms and applications. It discusses recent approaches that allow robots to learn motor skills and presents tasks that need to take into account the dynamic behavior of the robot and its environment, where a kinematic movement plan is not sufficient. The book illustrates a method that learns to generalize parameterized motor plans which is obtained by imitation or reinforcement learning, by adapting a small set of global parameters, and appropriate kernel-based reinforcement learning algorithms. The presented applications explore highly dynamic tasks and exhibit a very efficient learning process. All proposed approaches have been extensively validated with benchmarks tasks, in simulation, and on real robots. These tasks correspond to sports and games but the presented techniques are also applicable to more mundane household tasks. The book is based on the first author’s doctoral thesis, which wo...
Cognitive Radio Transceivers: RF, Spectrum Sensing, and Learning Algorithms Review
Directory of Open Access Journals (Sweden)
Lise Safatly
2014-01-01
reconfigurable radio frequency (RF parts, enhanced spectrum sensing algorithms, and sophisticated machine learning techniques. In this paper, we present a review of the recent advances in CR transceivers hardware design and algorithms. For the RF part, three types of antennas are presented: UWB antennas, frequency-reconfigurable/tunable antennas, and UWB antennas with reconfigurable band notches. The main challenges faced by the design of the other RF blocks are also discussed. Sophisticated spectrum sensing algorithms that overcome main sensing challenges such as model uncertainty, hardware impairments, and wideband sensing are highlighted. The cognitive engine features are discussed. Moreover, we study unsupervised classification algorithms and a reinforcement learning (RL algorithm that has been proposed to perform decision-making in CR networks.
Evolving Stochastic Learning Algorithm based on Tsallis entropic index
Anastasiadis, A. D.; Magoulas, G. D.
2006-03-01
In this paper, inspired from our previous algorithm, which was based on the theory of Tsallis statistical mechanics, we develop a new evolving stochastic learning algorithm for neural networks. The new algorithm combines deterministic and stochastic search steps by employing a different adaptive stepsize for each network weight, and applies a form of noise that is characterized by the nonextensive entropic index q, regulated by a weight decay term. The behavior of the learning algorithm can be made more stochastic or deterministic depending on the trade off between the temperature T and the q values. This is achieved by introducing a formula that defines a time-dependent relationship between these two important learning parameters. Our experimental study verifies that there are indeed improvements in the convergence speed of this new evolving stochastic learning algorithm, which makes learning faster than using the original Hybrid Learning Scheme (HLS). In addition, experiments are conducted to explore the influence of the entropic index q and temperature T on the convergence speed and stability of the proposed method.
Optimal quantum sample complexity of learning algorithms
Arunachalam, S.; de Wolf, R.
2017-01-01
In learning theory, the VC dimension of a concept class C is the most common way to measure its "richness." A fundamental result says that the number of examples needed to learn an unknown target concept c 2 C under an unknown distribution D, is tightly determined by the VC dimension d of the
Optimizing learning path selection through memetic algorithms
Acampora, G.; Gaeta, M.; Loia, V.; Ritrovato, P.; Salerno, S.
2008-01-01
e-Learning is a critical support mechanism for industrial and academic organizations to enhance the skills of employees and students and, consequently, the overall competitiveness in the new economy. The remarkable velocity and volatility of modern knowledge require novel learning methods offering
Interactive Algorithms for Unsupervised Machine Learning
2015-06-01
in Neural Information Processing Systems, 2013. 14 [3] Louigi Addario-Berry, Nicolas Broutin, Luc Devroye, and Gábor Lugosi. On combinato- rial...Myung Jin Choi, Vincent Y F Tan , Animashree Anandkumar, and Alan S Willsky. Learn- ing Latent Tree Graphical Models. Journal of Machine Learning
QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms
Directory of Open Access Journals (Sweden)
Ardjan Zwartjes
2016-10-01
Full Text Available In this work, we introduce QUEST (QUantile Estimation after Supervised Training, an adaptive classification algorithm for Wireless Sensor Networks (WSNs that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.
QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms.
Zwartjes, Ardjan; Havinga, Paul J M; Smit, Gerard J M; Hurink, Johann L
2016-10-01
In this work, we introduce QUEST (QUantile Estimation after Supervised Training), an adaptive classification algorithm for Wireless Sensor Networks (WSNs) that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.
Trans-algorithmic nature of learning in biological systems.
Shimansky, Yury P
2018-05-02
Learning ability is a vitally important, distinctive property of biological systems, which provides dynamic stability in non-stationary environments. Although several different types of learning have been successfully modeled using a universal computer, in general, learning cannot be described by an algorithm. In other words, algorithmic approach to describing the functioning of biological systems is not sufficient for adequate grasping of what is life. Since biosystems are parts of the physical world, one might hope that adding some physical mechanisms and principles to the concept of algorithm could provide extra possibilities for describing learning in its full generality. However, a straightforward approach to that through the so-called physical hypercomputation so far has not been successful. Here an alternative approach is proposed. Biosystems are described as achieving enumeration of possible physical compositions though random incremental modifications inflicted on them by active operating resources (AORs) in the environment. Biosystems learn through algorithmic regulation of the intensity of the above modifications according to a specific optimality criterion. From the perspective of external observers, biosystems move in the space of different algorithms driven by random modifications imposed by the environmental AORs. A particular algorithm is only a snapshot of that motion, while the motion itself is essentially trans-algorithmic. In this conceptual framework, death of unfit members of a population, for example, is viewed as a trans-algorithmic modification made in the population as a biosystem by environmental AORs. Numerous examples of AOR utilization in biosystems of different complexity, from viruses to multicellular organisms, are provided.
Some chaotic behaviors in a MCA learning algorithm with a constant learning rate
International Nuclear Information System (INIS)
Lv Jiancheng; Yi Zhang
2007-01-01
Douglas's minor component analysis algorithm with a constant learning rate has both stability and chaotic dynamical behavior under some conditions. The paper explores such dynamical behavior of this algorithm. Certain stability and chaos of this algorithm are derived. Waveform plots, Lyapunov exponents and bifurcation diagrams are presented to illustrate the existence of chaotic behavior
Gradient Learning Algorithms for Ontology Computing
Gao, Wei; Zhu, Linli
2014-01-01
The gradient learning model has been raising great attention in view of its promising perspectives for applications in statistics, data dimensionality reducing, and other specific fields. In this paper, we raise a new gradient learning model for ontology similarity measuring and ontology mapping in multidividing setting. The sample error in this setting is given by virtue of the hypothesis space and the trick of ontology dividing operator. Finally, two experiments presented on plant and humanoid robotics field verify the efficiency of the new computation model for ontology similarity measure and ontology mapping applications in multidividing setting. PMID:25530752
Gradient Learning Algorithms for Ontology Computing
Directory of Open Access Journals (Sweden)
Wei Gao
2014-01-01
Full Text Available The gradient learning model has been raising great attention in view of its promising perspectives for applications in statistics, data dimensionality reducing, and other specific fields. In this paper, we raise a new gradient learning model for ontology similarity measuring and ontology mapping in multidividing setting. The sample error in this setting is given by virtue of the hypothesis space and the trick of ontology dividing operator. Finally, two experiments presented on plant and humanoid robotics field verify the efficiency of the new computation model for ontology similarity measure and ontology mapping applications in multidividing setting.
Machine-Learning Algorithms to Code Public Health Spending Accounts.
Brady, Eoghan S; Leider, Jonathon P; Resnick, Beth A; Alfonso, Y Natalia; Bishai, David
Government public health expenditure data sets require time- and labor-intensive manipulation to summarize results that public health policy makers can use. Our objective was to compare the performances of machine-learning algorithms with manual classification of public health expenditures to determine if machines could provide a faster, cheaper alternative to manual classification. We used machine-learning algorithms to replicate the process of manually classifying state public health expenditures, using the standardized public health spending categories from the Foundational Public Health Services model and a large data set from the US Census Bureau. We obtained a data set of 1.9 million individual expenditure items from 2000 to 2013. We collapsed these data into 147 280 summary expenditure records, and we followed a standardized method of manually classifying each expenditure record as public health, maybe public health, or not public health. We then trained 9 machine-learning algorithms to replicate the manual process. We calculated recall, precision, and coverage rates to measure the performance of individual and ensembled algorithms. Compared with manual classification, the machine-learning random forests algorithm produced 84% recall and 91% precision. With algorithm ensembling, we achieved our target criterion of 90% recall by using a consensus ensemble of ≥6 algorithms while still retaining 93% coverage, leaving only 7% of the summary expenditure records unclassified. Machine learning can be a time- and cost-saving tool for estimating public health spending in the United States. It can be used with standardized public health spending categories based on the Foundational Public Health Services model to help parse public health expenditure information from other types of health-related spending, provide data that are more comparable across public health organizations, and evaluate the impact of evidence-based public health resource allocation.
Learning Sorting Algorithms through Visualization Construction
Cetin, Ibrahim; Andrews-Larson, Christine
2016-01-01
Recent increased interest in computational thinking poses an important question to researchers: What are the best ways to teach fundamental computing concepts to students? Visualization is suggested as one way of supporting student learning. This mixed-method study aimed to (i) examine the effect of instruction in which students constructed…
Fast algorithm selection using learning curves
Rijn, van J.N.; Abdulrahman, S.M.; Brazdil, P.; Vanschoren, J.; Fromont, E.; De Bie, T.; Leeuwen, van M.
2015-01-01
One of the challenges in Machine Learning to find a classifier and parameter settings that work well on a given dataset. Evaluating all possible combinations typically takes too much time, hence many solutions have been proposed that attempt to predict which classifiers are most promising to try. As
Evolutionary Pseudo-Relaxation Learning Algorithm for Bidirectional Associative Memory
Institute of Scientific and Technical Information of China (English)
Sheng-Zhi Du; Zeng-Qiang Chen; Zhu-Zhi Yuan
2005-01-01
This paper analyzes the sensitivity to noise in BAM (Bidirectional Associative Memory), and then proves the noise immunity of BAM relates not only to the minimum absolute value of net inputs (MAV) but also to the variance of weights associated with synapse connections. In fact, it is a positive monotonically increasing function of the quotient of MAV divided by the variance of weights. Besides, the performance of pseudo-relaxation method depends on learning parameters (λ and ζ), but the relation of them is not linear. So it is hard to find a best combination of λ and ζ which leads to the best BAM performance. And it is obvious that pseudo-relaxation is a kind of local optimization method, so it cannot guarantee to get the global optimal solution. In this paper, a novel learning algorithm EPRBAM (evolutionary psendo-relaxation learning algorithm for bidirectional association memory) employing genetic algorithm and pseudo-relaxation method is proposed to get feasible solution of BAM weight matrix. This algorithm uses the quotient as the fitness of each individual and employs pseudo-relaxation method to adjust individual solution when it does not satisfy constraining condition any more after genetic operation. Experimental results show this algorithm improves noise immunity of BAM greatly. At the same time, EPRBAM does not depend on learning parameters and can get global optimal solution.
Algorithm-Dependent Generalization Bounds for Multi-Task Learning.
Liu, Tongliang; Tao, Dacheng; Song, Mingli; Maybank, Stephen J
2017-02-01
Often, tasks are collected for multi-task learning (MTL) because they share similar feature structures. Based on this observation, in this paper, we present novel algorithm-dependent generalization bounds for MTL by exploiting the notion of algorithmic stability. We focus on the performance of one particular task and the average performance over multiple tasks by analyzing the generalization ability of a common parameter that is shared in MTL. When focusing on one particular task, with the help of a mild assumption on the feature structures, we interpret the function of the other tasks as a regularizer that produces a specific inductive bias. The algorithm for learning the common parameter, as well as the predictor, is thereby uniformly stable with respect to the domain of the particular task and has a generalization bound with a fast convergence rate of order O(1/n), where n is the sample size of the particular task. When focusing on the average performance over multiple tasks, we prove that a similar inductive bias exists under certain conditions on the feature structures. Thus, the corresponding algorithm for learning the common parameter is also uniformly stable with respect to the domains of the multiple tasks, and its generalization bound is of the order O(1/T), where T is the number of tasks. These theoretical analyses naturally show that the similarity of feature structures in MTL will lead to specific regularizations for predicting, which enables the learning algorithms to generalize fast and correctly from a few examples.
A globally convergent MC algorithm with an adaptive learning rate.
Peng, Dezhong; Yi, Zhang; Xiang, Yong; Zhang, Haixian
2012-02-01
This brief deals with the problem of minor component analysis (MCA). Artificial neural networks can be exploited to achieve the task of MCA. Recent research works show that convergence of neural networks based MCA algorithms can be guaranteed if the learning rates are less than certain thresholds. However, the computation of these thresholds needs information about the eigenvalues of the autocorrelation matrix of data set, which is unavailable in online extraction of minor component from input data stream. In this correspondence, we introduce an adaptive learning rate into the OJAn MCA algorithm, such that its convergence condition does not depend on any unobtainable information, and can be easily satisfied in practical applications.
MINING ON CAR DATABASE EMPLOYING LEARNING AND CLUSTERING ALGORITHMS
Muhammad Rukunuddin Ghalib; Shivam Vohra; Sunish Vohra; Akash Juneja
2013-01-01
In data mining, classification is a form of data analysis that can be used to extract models describing important data classes. Two of the known learning algorithms used are Naïve Bayesian (NB) and SMO (Self-Minimal-Optimisation) .Thus the following two learning algorithms are used on a Car review database and thus a model is hence created which predicts the characteristic of a review comment after getting trained. It was found that model successfully predicted correctly about the review comm...
Learning Search Algorithms: An Educational View
Directory of Open Access Journals (Sweden)
Ales Janota
2014-12-01
Full Text Available Artificial intelligence methods find their practical usage in many applications including maritime industry. The paper concentrates on the methods of uninformed and informed search, potentially usable in solving of complex problems based on the state space representation. The problem of introducing the search algorithms to newcomers has its technical and psychological dimensions. The authors show how it is possible to cope with both of them through design and use of specialized authoring systems. A typical example of searching a path through the maze is used to demonstrate how to test, observe and compare properties of various search strategies. Performance of search methods is evaluated based on the common criteria.
Randomized Algorithms for Scalable Machine Learning
Kleiner, Ariel Jacob
2012-01-01
Many existing procedures in machine learning and statistics are computationally intractable in the setting of large-scale data. As a result, the advent of rapidly increasing dataset sizes, which should be a boon yielding improved statistical performance, instead severely blunts the usefulness of a variety of existing inferential methods. In this work, we use randomness to ameliorate this lack of scalability by reducing complex, computationally difficult inferential problems to larger sets o...
Reinforcement Learning for Online Control of Evolutionary Algorithms
Eiben, A.; Horvath, Mark; Kowalczyk, Wojtek; Schut, Martijn
2007-01-01
The research reported in this paper is concerned with assessing the usefulness of reinforcment learning (RL) for on-line calibration of parameters in evolutionary algorithms (EA). We are running an RL procedure and the EA simultaneously and the RL is changing the EA parameters on-the-fly. We
Four Machine Learning Algorithms for Biometrics Fusion: A Comparative Study
Directory of Open Access Journals (Sweden)
I. G. Damousis
2012-01-01
Full Text Available We examine the efficiency of four machine learning algorithms for the fusion of several biometrics modalities to create a multimodal biometrics security system. The algorithms examined are Gaussian Mixture Models (GMMs, Artificial Neural Networks (ANNs, Fuzzy Expert Systems (FESs, and Support Vector Machines (SVMs. The fusion of biometrics leads to security systems that exhibit higher recognition rates and lower false alarms compared to unimodal biometric security systems. Supervised learning was carried out using a number of patterns from a well-known benchmark biometrics database, and the validation/testing took place with patterns from the same database which were not included in the training dataset. The comparison of the algorithms reveals that the biometrics fusion system is superior to the original unimodal systems and also other fusion schemes found in the literature.
An Efficient Inductive Genetic Learning Algorithm for Fuzzy Relational Rules
Directory of Open Access Journals (Sweden)
Antonio
2012-04-01
Full Text Available Fuzzy modelling research has traditionally focused on certain types of fuzzy rules. However, the use of alternative rule models could improve the ability of fuzzy systems to represent a specific problem. In this proposal, an extended fuzzy rule model, that can include relations between variables in the antecedent of rules is presented. Furthermore, a learning algorithm based on the iterative genetic approach which is able to represent the knowledge using this model is proposed as well. On the other hand, potential relations among initial variables imply an exponential growth in the feasible rule search space. Consequently, two filters for detecting relevant potential relations are added to the learning algorithm. These filters allows to decrease the search space complexity and increase the algorithm efficiency. Finally, we also present an experimental study to demonstrate the benefits of using fuzzy relational rules.
Learning sorting algorithms through visualization construction
Cetin, Ibrahim; Andrews-Larson, Christine
2016-01-01
Recent increased interest in computational thinking poses an important question to researchers: What are the best ways to teach fundamental computing concepts to students? Visualization is suggested as one way of supporting student learning. This mixed-method study aimed to (i) examine the effect of instruction in which students constructed visualizations on students' programming achievement and students' attitudes toward computer programming, and (ii) explore how this kind of instruction supports students' learning according to their self-reported experiences in the course. The study was conducted with 58 pre-service teachers who were enrolled in their second programming class. They expect to teach information technology and computing-related courses at the primary and secondary levels. An embedded experimental model was utilized as a research design. Students in the experimental group were given instruction that required students to construct visualizations related to sorting, whereas students in the control group viewed pre-made visualizations. After the instructional intervention, eight students from each group were selected for semi-structured interviews. The results showed that the intervention based on visualization construction resulted in significantly better acquisition of sorting concepts. However, there was no significant difference between the groups with respect to students' attitudes toward computer programming. Qualitative data analysis indicated that students in the experimental group constructed necessary abstractions through their engagement in visualization construction activities. The authors of this study argue that the students' active engagement in the visualization construction activities explains only one side of students' success. The other side can be explained through the instructional approach, constructionism in this case, used to design instruction. The conclusions and implications of this study can be used by researchers and
Generalized SMO algorithm for SVM-based multitask learning.
Cai, Feng; Cherkassky, Vladimir
2012-06-01
Exploiting additional information to improve traditional inductive learning is an active research area in machine learning. In many supervised-learning applications, training data can be naturally separated into several groups, and incorporating this group information into learning may improve generalization. Recently, Vapnik proposed a general approach to formalizing such problems, known as "learning with structured data" and its support vector machine (SVM) based optimization formulation called SVM+. Liang and Cherkassky showed the connection between SVM+ and multitask learning (MTL) approaches in machine learning, and proposed an SVM-based formulation for MTL called SVM+MTL for classification. Training the SVM+MTL classifier requires the solution of a large quadratic programming optimization problem which scales as O(n(3)) with sample size n. So there is a need to develop computationally efficient algorithms for implementing SVM+MTL. This brief generalizes Platt's sequential minimal optimization (SMO) algorithm to the SVM+MTL setting. Empirical results show that, for typical SVM+MTL problems, the proposed generalized SMO achieves over 100 times speed-up, in comparison with general-purpose optimization routines.
Inverse Problems in Geodynamics Using Machine Learning Algorithms
Shahnas, M. H.; Yuen, D. A.; Pysklywec, R. N.
2018-01-01
During the past few decades numerical studies have been widely employed to explore the style of circulation and mixing in the mantle of Earth and other planets. However, in geodynamical studies there are many properties from mineral physics, geochemistry, and petrology in these numerical models. Machine learning, as a computational statistic-related technique and a subfield of artificial intelligence, has rapidly emerged recently in many fields of sciences and engineering. We focus here on the application of supervised machine learning (SML) algorithms in predictions of mantle flow processes. Specifically, we emphasize on estimating mantle properties by employing machine learning techniques in solving an inverse problem. Using snapshots of numerical convection models as training samples, we enable machine learning models to determine the magnitude of the spin transition-induced density anomalies that can cause flow stagnation at midmantle depths. Employing support vector machine algorithms, we show that SML techniques can successfully predict the magnitude of mantle density anomalies and can also be used in characterizing mantle flow patterns. The technique can be extended to more complex geodynamic problems in mantle dynamics by employing deep learning algorithms for putting constraints on properties such as viscosity, elastic parameters, and the nature of thermal and chemical anomalies.
Component Pin Recognition Using Algorithms Based on Machine Learning
Xiao, Yang; Hu, Hong; Liu, Ze; Xu, Jiangchang
2018-04-01
The purpose of machine vision for a plug-in machine is to improve the machine’s stability and accuracy, and recognition of the component pin is an important part of the vision. This paper focuses on component pin recognition using three different techniques. The first technique involves traditional image processing using the core algorithm for binary large object (BLOB) analysis. The second technique uses the histogram of oriented gradients (HOG), to experimentally compare the effect of the support vector machine (SVM) and the adaptive boosting machine (AdaBoost) learning meta-algorithm classifiers. The third technique is the use of an in-depth learning method known as convolution neural network (CNN), which involves identifying the pin by comparing a sample to its training. The main purpose of the research presented in this paper is to increase the knowledge of learning methods used in the plug-in machine industry in order to achieve better results.
Automated Essay Grading using Machine Learning Algorithm
Ramalingam, V. V.; Pandian, A.; Chetry, Prateek; Nigam, Himanshu
2018-04-01
Essays are paramount for of assessing the academic excellence along with linking the different ideas with the ability to recall but are notably time consuming when they are assessed manually. Manual grading takes significant amount of evaluator’s time and hence it is an expensive process. Automated grading if proven effective will not only reduce the time for assessment but comparing it with human scores will also make the score realistic. The project aims to develop an automated essay assessment system by use of machine learning techniques by classifying a corpus of textual entities into small number of discrete categories, corresponding to possible grades. Linear regression technique will be utilized for training the model along with making the use of various other classifications and clustering techniques. We intend to train classifiers on the training set, make it go through the downloaded dataset, and then measure performance our dataset by comparing the obtained values with the dataset values. We have implemented our model using java.
DNA Cryptography and Deep Learning using Genetic Algorithm with NW algorithm for Key Generation.
Kalsi, Shruti; Kaur, Harleen; Chang, Victor
2017-12-05
Cryptography is not only a science of applying complex mathematics and logic to design strong methods to hide data called as encryption, but also to retrieve the original data back, called decryption. The purpose of cryptography is to transmit a message between a sender and receiver such that an eavesdropper is unable to comprehend it. To accomplish this, not only we need a strong algorithm, but a strong key and a strong concept for encryption and decryption process. We have introduced a concept of DNA Deep Learning Cryptography which is defined as a technique of concealing data in terms of DNA sequence and deep learning. In the cryptographic technique, each alphabet of a letter is converted into a different combination of the four bases, namely; Adenine (A), Cytosine (C), Guanine (G) and Thymine (T), which make up the human deoxyribonucleic acid (DNA). Actual implementations with the DNA don't exceed laboratory level and are expensive. To bring DNA computing on a digital level, easy and effective algorithms are proposed in this paper. In proposed work we have introduced firstly, a method and its implementation for key generation based on the theory of natural selection using Genetic Algorithm with Needleman-Wunsch (NW) algorithm and Secondly, a method for implementation of encryption and decryption based on DNA computing using biological operations Transcription, Translation, DNA Sequencing and Deep Learning.
Denoising of gravitational wave signals via dictionary learning algorithms
Torres-Forné, Alejandro; Marquina, Antonio; Font, José A.; Ibáñez, José M.
2016-12-01
Gravitational wave astronomy has become a reality after the historical detections accomplished during the first observing run of the two advanced LIGO detectors. In the following years, the number of detections is expected to increase significantly with the full commissioning of the advanced LIGO, advanced Virgo and KAGRA detectors. The development of sophisticated data analysis techniques to improve the opportunities of detection for low signal-to-noise-ratio events is, hence, a most crucial effort. In this paper, we present one such technique, dictionary-learning algorithms, which have been extensively developed in the last few years and successfully applied mostly in the context of image processing. However, to the best of our knowledge, such algorithms have not yet been employed to denoise gravitational wave signals. By building dictionaries from numerical relativity templates of both binary black holes mergers and bursts of rotational core collapse, we show how machine-learning algorithms based on dictionaries can also be successfully applied for gravitational wave denoising. We use a subset of signals from both catalogs, embedded in nonwhite Gaussian noise, to assess our techniques with a large sample of tests and to find the best model parameters. The application of our method to the actual signal GW150914 shows promising results. Dictionary-learning algorithms could be a complementary addition to the gravitational wave data analysis toolkit. They may be used to extract signals from noise and to infer physical parameters if the data are in good enough agreement with the morphology of the dictionary atoms.
Genetic algorithm enhanced by machine learning in dynamic aperture optimization
Li, Yongjun; Cheng, Weixing; Yu, Li Hua; Rainer, Robert
2018-05-01
With the aid of machine learning techniques, the genetic algorithm has been enhanced and applied to the multi-objective optimization problem presented by the dynamic aperture of the National Synchrotron Light Source II (NSLS-II) Storage Ring. During the evolution processes employed by the genetic algorithm, the population is classified into different clusters in the search space. The clusters with top average fitness are given "elite" status. Intervention on the population is implemented by repopulating some potentially competitive candidates based on the experience learned from the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is therefore improved while diversity is not lost. Maintaining diversity ensures that the optimization is global rather than local. The quality of the population increases and produces more competitive descendants accelerating the evolution process significantly. When identifying the distribution of optimal candidates, they appear to be located in isolated islands within the search space. Some of these optimal candidates have been experimentally confirmed at the NSLS-II storage ring. The machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm.
Dynamics of the evolution of learning algorithms by selection
International Nuclear Information System (INIS)
Neirotti, Juan Pablo; Caticha, Nestor
2003-01-01
We study the evolution of artificial learning systems by means of selection. Genetic programming is used to generate populations of programs that implement algorithms used by neural network classifiers to learn a rule in a supervised learning scenario. In contrast to concentrating on final results, which would be the natural aim while designing good learning algorithms, we study the evolution process. Phenotypic and genotypic entropies, which describe the distribution of fitness and of symbols, respectively, are used to monitor the dynamics. We identify significant functional structures responsible for the improvements in the learning process. In particular, some combinations of variables and operators are useful in assessing performance in rule extraction and can thus implement annealing of the learning schedule. We also find combinations that can signal surprise, measured on a single example, by the difference between predicted and correct classification. When such favorable structures appear, they are disseminated on very short time scales throughout the population. Due to such abruptness they can be thought of as dynamical transitions. But foremost, we find a strict temporal order of such discoveries. Structures that measure performance are never useful before those for measuring surprise. Invasions of the population by such structures in the reverse order were never observed. Asymptotically, the generalization ability approaches Bayesian results
Predicting Smoking Status Using Machine Learning Algorithms and Statistical Analysis
Directory of Open Access Journals (Sweden)
Charles Frank
2018-03-01
Full Text Available Smoking has been proven to negatively affect health in a multitude of ways. As of 2009, smoking has been considered the leading cause of preventable morbidity and mortality in the United States, continuing to plague the country’s overall health. This study aims to investigate the viability and effectiveness of some machine learning algorithms for predicting the smoking status of patients based on their blood tests and vital readings results. The analysis of this study is divided into two parts: In part 1, we use One-way ANOVA analysis with SAS tool to show the statistically significant difference in blood test readings between smokers and non-smokers. The results show that the difference in INR, which measures the effectiveness of anticoagulants, was significant in favor of non-smokers which further confirms the health risks associated with smoking. In part 2, we use five machine learning algorithms: Naïve Bayes, MLP, Logistic regression classifier, J48 and Decision Table to predict the smoking status of patients. To compare the effectiveness of these algorithms we use: Precision, Recall, F-measure and Accuracy measures. The results show that the Logistic algorithm outperformed the four other algorithms with Precision, Recall, F-Measure, and Accuracy of 83%, 83.4%, 83.2%, 83.44%, respectively.
Comparison of machine learning algorithms for detecting coral reef
Directory of Open Access Journals (Sweden)
Eduardo Tusa
2014-09-01
Full Text Available (Received: 2014/07/31 - Accepted: 2014/09/23This work focuses on developing a fast coral reef detector, which is used for an autonomous underwater vehicle, AUV. A fast detection secures the AUV stabilization respect to an area of reef as fast as possible, and prevents devastating collisions. We use the algorithm of Purser et al. (2009 because of its precision. This detector has two parts: feature extraction that uses Gabor Wavelet filters, and feature classification that uses machine learning based on Neural Networks. Due to the extensive time of the Neural Networks, we exchange for a classification algorithm based on Decision Trees. We use a database of 621 images of coral reef in Belize (110 images for training and 511 images for testing. We implement the bank of Gabor Wavelets filters using C++ and the OpenCV library. We compare the accuracy and running time of 9 machine learning algorithms, whose result was the selection of the Decision Trees algorithm. Our coral detector performs 70ms of running time in comparison to 22s executed by the algorithm of Purser et al. (2009.
Video game for learning and metaphorization of recursive algorithms
Directory of Open Access Journals (Sweden)
Ricardo Inacio Alvares Silva
2013-09-01
Full Text Available The learning of recursive algorithms in computer programming is problematic, because its execution and resolution is not natural to the thinking way people are trained and used to since young. As with other topics in algorithms, we use metaphors to make parallels between the abstract and the concrete to help in understanding the operation of recursive algorithms. However, the classic metaphors employed in this area, such as calculating factorial recursively and Towers of Hanoi game, may just confuse more or be insufficient. In this work, we produced a computer game to assist students in computer courses in learning recursive algorithms. It was designed to have regular video game characteristics, with narrative and classical gameplay elements, commonly found in this kind of product. Aiding to education occurs through metaphorization, or in other words, through experiences provided by game situations that refer to recursive algorithms. To this end, we designed and imbued in the game four valid metaphors related to the theory, and other minor references to the subject.
Advanced Machine learning Algorithm Application for Rotating Machine Health Monitoring
Energy Technology Data Exchange (ETDEWEB)
Kanemoto, Shigeru; Watanabe, Masaya [The University of Aizu, Aizuwakamatsu (Japan); Yusa, Noritaka [Tohoku University, Sendai (Japan)
2014-08-15
The present paper tries to evaluate the applicability of conventional sound analysis techniques and modern machine learning algorithms to rotating machine health monitoring. These techniques include support vector machine, deep leaning neural network, etc. The inner ring defect and misalignment anomaly sound data measured by a rotating machine mockup test facility are used to verify the above various kinds of algorithms. Although we cannot find remarkable difference of anomaly discrimination performance, some methods give us the very interesting eigen patterns corresponding to normal and abnormal states. These results will be useful for future more sensitive and robust anomaly monitoring technology.
Advanced Machine learning Algorithm Application for Rotating Machine Health Monitoring
International Nuclear Information System (INIS)
Kanemoto, Shigeru; Watanabe, Masaya; Yusa, Noritaka
2014-01-01
The present paper tries to evaluate the applicability of conventional sound analysis techniques and modern machine learning algorithms to rotating machine health monitoring. These techniques include support vector machine, deep leaning neural network, etc. The inner ring defect and misalignment anomaly sound data measured by a rotating machine mockup test facility are used to verify the above various kinds of algorithms. Although we cannot find remarkable difference of anomaly discrimination performance, some methods give us the very interesting eigen patterns corresponding to normal and abnormal states. These results will be useful for future more sensitive and robust anomaly monitoring technology
Energy Technology Data Exchange (ETDEWEB)
Bornholdt, S. [Heidelberg Univ., (Germany). Inst., fuer Theoretische Physik; Graudenz, D. [Lawrence Berkeley Lab., CA (United States)
1993-07-01
A learning algorithm based on genetic algorithms for asymmetric neural networks with an arbitrary structure is presented. It is suited for the learning of temporal patterns and leads to stable neural networks with feedback.
International Nuclear Information System (INIS)
Bornholdt, S.
1993-07-01
A learning algorithm based on genetic algorithms for asymmetric neural networks with an arbitrary structure is presented. It is suited for the learning of temporal patterns and leads to stable neural networks with feedback
Directory of Open Access Journals (Sweden)
Wenjing Zhao
2018-01-01
Full Text Available SGK (sequential generalization of K-means dictionary learning denoising algorithm has the characteristics of fast denoising speed and excellent denoising performance. However, the noise standard deviation must be known in advance when using SGK algorithm to process the image. This paper presents a denoising algorithm combined with SGK dictionary learning and the principal component analysis (PCA noise estimation. At first, the noise standard deviation of the image is estimated by using the PCA noise estimation algorithm. And then it is used for SGK dictionary learning algorithm. Experimental results show the following: (1 The SGK algorithm has the best denoising performance compared with the other three dictionary learning algorithms. (2 The SGK algorithm combined with PCA is superior to the SGK algorithm combined with other noise estimation algorithms. (3 Compared with the original SGK algorithm, the proposed algorithm has higher PSNR and better denoising performance.
An Educational System for Learning Search Algorithms and Automatically Assessing Student Performance
Grivokostopoulou, Foteini; Perikos, Isidoros; Hatzilygeroudis, Ioannis
2017-01-01
In this paper, first we present an educational system that assists students in learning and tutors in teaching search algorithms, an artificial intelligence topic. Learning is achieved through a wide range of learning activities. Algorithm visualizations demonstrate the operational functionality of algorithms according to the principles of active…
Alignment of Custom Standards by Machine Learning Algorithms
Directory of Open Access Journals (Sweden)
Adela Sirbu
2010-09-01
Full Text Available Building an efficient model for automatic alignment of terminologies would bring a significant improvement to the information retrieval process. We have developed and compared two machine learning based algorithms whose aim is to align 2 custom standards built on a 3 level taxonomy, using kNN and SVM classifiers that work on a vector representation consisting of several similarity measures. The weights utilized by the kNN were optimized with an evolutionary algorithm, while the SVM classifier's hyper-parameters were optimized with a grid search algorithm. The database used for train was semi automatically obtained by using the Coma++ tool. The performance of our aligners is shown by the results obtained on the test set.
Implementation of dictionary pair learning algorithm for image quality improvement
Vimala, C.; Aruna Priya, P.
2018-04-01
This paper proposes an image denoising on dictionary pair learning algorithm. Visual information is transmitted in the form of digital images is becoming a major method of communication in the modern age, but the image obtained after transmissions is often corrupted with noise. The received image needs processing before it can be used in applications. Image denoising involves the manipulation of the image data to produce a visually high quality image.
Towards the compression of parton densities through machine learning algorithms
Carrazza, Stefano
2016-01-01
One of the most fascinating challenges in the context of parton density function (PDF) is the determination of the best combined PDF uncertainty from individual PDF sets. Since 2014 multiple methodologies have been developed to achieve this goal. In this proceedings we first summarize the strategy adopted by the PDF4LHC15 recommendation and then, we discuss about a new approach to Monte Carlo PDF compression based on clustering through machine learning algorithms.
Optimization in Quaternion Dynamic Systems: Gradient, Hessian, and Learning Algorithms.
Xu, Dongpo; Xia, Yili; Mandic, Danilo P
2016-02-01
The optimization of real scalar functions of quaternion variables, such as the mean square error or array output power, underpins many practical applications. Solutions typically require the calculation of the gradient and Hessian. However, real functions of quaternion variables are essentially nonanalytic, which are prohibitive to the development of quaternion-valued learning systems. To address this issue, we propose new definitions of quaternion gradient and Hessian, based on the novel generalized Hamilton-real (GHR) calculus, thus making a possible efficient derivation of general optimization algorithms directly in the quaternion field, rather than using the isomorphism with the real domain, as is current practice. In addition, unlike the existing quaternion gradients, the GHR calculus allows for the product and chain rule, and for a one-to-one correspondence of the novel quaternion gradient and Hessian with their real counterparts. Properties of the quaternion gradient and Hessian relevant to numerical applications are also introduced, opening a new avenue of research in quaternion optimization and greatly simplified the derivations of learning algorithms. The proposed GHR calculus is shown to yield the same generic algorithm forms as the corresponding real- and complex-valued algorithms. Advantages of the proposed framework are illuminated over illustrative simulations in quaternion signal processing and neural networks.
Learning-based meta-algorithm for MRI brain extraction.
Shi, Feng; Wang, Li; Gilmore, John H; Lin, Weili; Shen, Dinggang
2011-01-01
Multiple-segmentation-and-fusion method has been widely used for brain extraction, tissue segmentation, and region of interest (ROI) localization. However, such studies are hindered in practice by their computational complexity, mainly coming from the steps of template selection and template-to-subject nonlinear registration. In this study, we address these two issues and propose a novel learning-based meta-algorithm for MRI brain extraction. Specifically, we first use exemplars to represent the entire template library, and assign the most similar exemplar to the test subject. Second, a meta-algorithm combining two existing brain extraction algorithms (BET and BSE) is proposed to conduct multiple extractions directly on test subject. Effective parameter settings for the meta-algorithm are learned from the training data and propagated to subject through exemplars. We further develop a level-set based fusion method to combine multiple candidate extractions together with a closed smooth surface, for obtaining the final result. Experimental results show that, with only a small portion of subjects for training, the proposed method is able to produce more accurate and robust brain extraction results, at Jaccard Index of 0.956 +/- 0.010 on total 340 subjects under 6-fold cross validation, compared to those by the BET and BSE even using their best parameter combinations.
MACHINE LEARNING METHODS IN DIGITAL AGRICULTURE: ALGORITHMS AND CASES
Directory of Open Access Journals (Sweden)
Aleksandr Vasilyevich Koshkarov
2018-05-01
Full Text Available Ensuring food security is a major challenge in many countries. With a growing global population, the issues of improving the efficiency of agriculture have become most relevant. Farmers are looking for new ways to increase yields, and governments of different countries are developing new programs to support agriculture. This contributes to a more active implementation of digital technologies in agriculture, helping farmers to make better decisions, increase yields and take care of the environment. The central point is the collection and analysis of data. In the industry of agriculture, data can be collected from different sources and may contain useful patterns that identify potential problems or opportunities. Data should be analyzed using machine learning algorithms to extract useful insights. Such methods of precision farming allow the farmer to monitor individual parts of the field, optimize the consumption of water and chemicals, and identify problems quickly. Purpose: to make an overview of the machine learning algorithms used for data analysis in agriculture. Methodology: an overview of the relevant literature; a survey of farmers. Results: relevant algorithms of machine learning for the analysis of data in agriculture at various levels were identified: soil analysis (soil assessment, soil classification, soil fertility predictions, weather forecast (simulation of climate change, temperature and precipitation prediction, and analysis of vegetation (weed identification, vegetation classification, plant disease identification, crop forecasting. Practical implications: agriculture, crop production.
Inference algorithms and learning theory for Bayesian sparse factor analysis
International Nuclear Information System (INIS)
Rattray, Magnus; Sharp, Kevin; Stegle, Oliver; Winn, John
2009-01-01
Bayesian sparse factor analysis has many applications; for example, it has been applied to the problem of inferring a sparse regulatory network from gene expression data. We describe a number of inference algorithms for Bayesian sparse factor analysis using a slab and spike mixture prior. These include well-established Markov chain Monte Carlo (MCMC) and variational Bayes (VB) algorithms as well as a novel hybrid of VB and Expectation Propagation (EP). For the case of a single latent factor we derive a theory for learning performance using the replica method. We compare the MCMC and VB/EP algorithm results with simulated data to the theoretical prediction. The results for MCMC agree closely with the theory as expected. Results for VB/EP are slightly sub-optimal but show that the new algorithm is effective for sparse inference. In large-scale problems MCMC is infeasible due to computational limitations and the VB/EP algorithm then provides a very useful computationally efficient alternative.
Inference algorithms and learning theory for Bayesian sparse factor analysis
Energy Technology Data Exchange (ETDEWEB)
Rattray, Magnus; Sharp, Kevin [School of Computer Science, University of Manchester, Manchester M13 9PL (United Kingdom); Stegle, Oliver [Max-Planck-Institute for Biological Cybernetics, Tuebingen (Germany); Winn, John, E-mail: magnus.rattray@manchester.ac.u [Microsoft Research Cambridge, Roger Needham Building, Cambridge, CB3 0FB (United Kingdom)
2009-12-01
Bayesian sparse factor analysis has many applications; for example, it has been applied to the problem of inferring a sparse regulatory network from gene expression data. We describe a number of inference algorithms for Bayesian sparse factor analysis using a slab and spike mixture prior. These include well-established Markov chain Monte Carlo (MCMC) and variational Bayes (VB) algorithms as well as a novel hybrid of VB and Expectation Propagation (EP). For the case of a single latent factor we derive a theory for learning performance using the replica method. We compare the MCMC and VB/EP algorithm results with simulated data to the theoretical prediction. The results for MCMC agree closely with the theory as expected. Results for VB/EP are slightly sub-optimal but show that the new algorithm is effective for sparse inference. In large-scale problems MCMC is infeasible due to computational limitations and the VB/EP algorithm then provides a very useful computationally efficient alternative.
Exploration Of Deep Learning Algorithms Using Openacc Parallel Programming Model
Hamam, Alwaleed A.
2017-03-13
Deep learning is based on a set of algorithms that attempt to model high level abstractions in data. Specifically, RBM is a deep learning algorithm that used in the project to increase it\\'s time performance using some efficient parallel implementation by OpenACC tool with best possible optimizations on RBM to harness the massively parallel power of NVIDIA GPUs. GPUs development in the last few years has contributed to growing the concept of deep learning. OpenACC is a directive based ap-proach for computing where directives provide compiler hints to accelerate code. The traditional Restricted Boltzmann Ma-chine is a stochastic neural network that essentially perform a binary version of factor analysis. RBM is a useful neural net-work basis for larger modern deep learning model, such as Deep Belief Network. RBM parameters are estimated using an efficient training method that called Contrastive Divergence. Parallel implementation of RBM is available using different models such as OpenMP, and CUDA. But this project has been the first attempt to apply OpenACC model on RBM.
Robust Semi-Supervised Manifold Learning Algorithm for Classification
Directory of Open Access Journals (Sweden)
Mingxia Chen
2018-01-01
Full Text Available In the recent years, manifold learning methods have been widely used in data classification to tackle the curse of dimensionality problem, since they can discover the potential intrinsic low-dimensional structures of the high-dimensional data. Given partially labeled data, the semi-supervised manifold learning algorithms are proposed to predict the labels of the unlabeled points, taking into account label information. However, these semi-supervised manifold learning algorithms are not robust against noisy points, especially when the labeled data contain noise. In this paper, we propose a framework for robust semi-supervised manifold learning (RSSML to address this problem. The noisy levels of the labeled points are firstly predicted, and then a regularization term is constructed to reduce the impact of labeled points containing noise. A new robust semi-supervised optimization model is proposed by adding the regularization term to the traditional semi-supervised optimization model. Numerical experiments are given to show the improvement and efficiency of RSSML on noisy data sets.
Exploration Of Deep Learning Algorithms Using Openacc Parallel Programming Model
Hamam, Alwaleed A.; Khan, Ayaz H.
2017-01-01
Deep learning is based on a set of algorithms that attempt to model high level abstractions in data. Specifically, RBM is a deep learning algorithm that used in the project to increase it's time performance using some efficient parallel implementation by OpenACC tool with best possible optimizations on RBM to harness the massively parallel power of NVIDIA GPUs. GPUs development in the last few years has contributed to growing the concept of deep learning. OpenACC is a directive based ap-proach for computing where directives provide compiler hints to accelerate code. The traditional Restricted Boltzmann Ma-chine is a stochastic neural network that essentially perform a binary version of factor analysis. RBM is a useful neural net-work basis for larger modern deep learning model, such as Deep Belief Network. RBM parameters are estimated using an efficient training method that called Contrastive Divergence. Parallel implementation of RBM is available using different models such as OpenMP, and CUDA. But this project has been the first attempt to apply OpenACC model on RBM.
An augmented Lagrangian multi-scale dictionary learning algorithm
Directory of Open Access Journals (Sweden)
Ye Meng
2011-01-01
Full Text Available Abstract Learning overcomplete dictionaries for sparse signal representation has become a hot topic fascinated by many researchers in the recent years, while most of the existing approaches have a serious problem that they always lead to local minima. In this article, we present a novel augmented Lagrangian multi-scale dictionary learning algorithm (ALM-DL, which is achieved by first recasting the constrained dictionary learning problem into an AL scheme, and then updating the dictionary after each inner iteration of the scheme during which majorization-minimization technique is employed for solving the inner subproblem. Refining the dictionary from low scale to high makes the proposed method less dependent on the initial dictionary hence avoiding local optima. Numerical tests for synthetic data and denoising applications on real images demonstrate the superior performance of the proposed approach.
Head pose estimation algorithm based on deep learning
Cao, Yuanming; Liu, Yijun
2017-05-01
Head pose estimation has been widely used in the field of artificial intelligence, pattern recognition and intelligent human-computer interaction and so on. Good head pose estimation algorithm should deal with light, noise, identity, shelter and other factors robustly, but so far how to improve the accuracy and robustness of attitude estimation remains a major challenge in the field of computer vision. A method based on deep learning for pose estimation is presented. Deep learning with a strong learning ability, it can extract high-level image features of the input image by through a series of non-linear operation, then classifying the input image using the extracted feature. Such characteristics have greater differences in pose, while they are robust of light, identity, occlusion and other factors. The proposed head pose estimation is evaluated on the CAS-PEAL data set. Experimental results show that this method is effective to improve the accuracy of pose estimation.
Behavioral Modeling for Mental Health using Machine Learning Algorithms.
Srividya, M; Mohanavalli, S; Bhalaji, N
2018-04-03
Mental health is an indicator of emotional, psychological and social well-being of an individual. It determines how an individual thinks, feels and handle situations. Positive mental health helps one to work productively and realize their full potential. Mental health is important at every stage of life, from childhood and adolescence through adulthood. Many factors contribute to mental health problems which lead to mental illness like stress, social anxiety, depression, obsessive compulsive disorder, drug addiction, and personality disorders. It is becoming increasingly important to determine the onset of the mental illness to maintain proper life balance. The nature of machine learning algorithms and Artificial Intelligence (AI) can be fully harnessed for predicting the onset of mental illness. Such applications when implemented in real time will benefit the society by serving as a monitoring tool for individuals with deviant behavior. This research work proposes to apply various machine learning algorithms such as support vector machines, decision trees, naïve bayes classifier, K-nearest neighbor classifier and logistic regression to identify state of mental health in a target group. The responses obtained from the target group for the designed questionnaire were first subject to unsupervised learning techniques. The labels obtained as a result of clustering were validated by computing the Mean Opinion Score. These cluster labels were then used to build classifiers to predict the mental health of an individual. Population from various groups like high school students, college students and working professionals were considered as target groups. The research presents an analysis of applying the aforementioned machine learning algorithms on the target groups and also suggests directions for future work.
Validating module network learning algorithms using simulated data.
Michoel, Tom; Maere, Steven; Bonnet, Eric; Joshi, Anagha; Saeys, Yvan; Van den Bulcke, Tim; Van Leemput, Koenraad; van Remortel, Piet; Kuiper, Martin; Marchal, Kathleen; Van de Peer, Yves
2007-05-03
In recent years, several authors have used probabilistic graphical models to learn expression modules and their regulatory programs from gene expression data. Despite the demonstrated success of such algorithms in uncovering biologically relevant regulatory relations, further developments in the area are hampered by a lack of tools to compare the performance of alternative module network learning strategies. Here, we demonstrate the use of the synthetic data generator SynTReN for the purpose of testing and comparing module network learning algorithms. We introduce a software package for learning module networks, called LeMoNe, which incorporates a novel strategy for learning regulatory programs. Novelties include the use of a bottom-up Bayesian hierarchical clustering to construct the regulatory programs, and the use of a conditional entropy measure to assign regulators to the regulation program nodes. Using SynTReN data, we test the performance of LeMoNe in a completely controlled situation and assess the effect of the methodological changes we made with respect to an existing software package, namely Genomica. Additionally, we assess the effect of various parameters, such as the size of the data set and the amount of noise, on the inference performance. Overall, application of Genomica and LeMoNe to simulated data sets gave comparable results. However, LeMoNe offers some advantages, one of them being that the learning process is considerably faster for larger data sets. Additionally, we show that the location of the regulators in the LeMoNe regulation programs and their conditional entropy may be used to prioritize regulators for functional validation, and that the combination of the bottom-up clustering strategy with the conditional entropy-based assignment of regulators improves the handling of missing or hidden regulators. We show that data simulators such as SynTReN are very well suited for the purpose of developing, testing and improving module network
A Comparison of the Effects of K-Anonymity on Machine Learning Algorithms
Hayden Wimmer; Loreen Powell
2014-01-01
While research has been conducted in machine learning algorithms and in privacy preserving in data mining (PPDM), a gap in the literature exists which combines the aforementioned areas to determine how PPDM affects common machine learning algorithms. The aim of this research is to narrow this literature gap by investigating how a common PPDM algorithm, K-Anonymity, affects common machine learning and data mining algorithms, namely neural networks, logistic regression, decision trees, and Baye...
A numeric comparison of variable selection algorithms for supervised learning
International Nuclear Information System (INIS)
Palombo, G.; Narsky, I.
2009-01-01
Datasets in modern High Energy Physics (HEP) experiments are often described by dozens or even hundreds of input variables. Reducing a full variable set to a subset that most completely represents information about data is therefore an important task in analysis of HEP data. We compare various variable selection algorithms for supervised learning using several datasets such as, for instance, imaging gamma-ray Cherenkov telescope (MAGIC) data found at the UCI repository. We use classifiers and variable selection methods implemented in the statistical package StatPatternRecognition (SPR), a free open-source C++ package developed in the HEP community ( (http://sourceforge.net/projects/statpatrec/)). For each dataset, we select a powerful classifier and estimate its learning accuracy on variable subsets obtained by various selection algorithms. When possible, we also estimate the CPU time needed for the variable subset selection. The results of this analysis are compared with those published previously for these datasets using other statistical packages such as R and Weka. We show that the most accurate, yet slowest, method is a wrapper algorithm known as generalized sequential forward selection ('Add N Remove R') implemented in SPR.
A Dynamic Neighborhood Learning-Based Gravitational Search Algorithm.
Zhang, Aizhu; Sun, Genyun; Ren, Jinchang; Li, Xiaodong; Wang, Zhenjie; Jia, Xiuping
2018-01-01
Balancing exploration and exploitation according to evolutionary states is crucial to meta-heuristic search (M-HS) algorithms. Owing to its simplicity in theory and effectiveness in global optimization, gravitational search algorithm (GSA) has attracted increasing attention in recent years. However, the tradeoff between exploration and exploitation in GSA is achieved mainly by adjusting the size of an archive, named , which stores those superior agents after fitness sorting in each iteration. Since the global property of remains unchanged in the whole evolutionary process, GSA emphasizes exploitation over exploration and suffers from rapid loss of diversity and premature convergence. To address these problems, in this paper, we propose a dynamic neighborhood learning (DNL) strategy to replace the model and thereby present a DNL-based GSA (DNLGSA). The method incorporates the local and global neighborhood topologies for enhancing the exploration and obtaining adaptive balance between exploration and exploitation. The local neighborhoods are dynamically formed based on evolutionary states. To delineate the evolutionary states, two convergence criteria named limit value and population diversity, are introduced. Moreover, a mutation operator is designed for escaping from the local optima on the basis of evolutionary states. The proposed algorithm was evaluated on 27 benchmark problems with different characteristic and various difficulties. The results reveal that DNLGSA exhibits competitive performances when compared with a variety of state-of-the-art M-HS algorithms. Moreover, the incorporation of local neighborhood topology reduces the numbers of calculations of gravitational force and thus alleviates the high computational cost of GSA.
Fall detection using supervised machine learning algorithms: A comparative study
Zerrouki, Nabil; Harrou, Fouzi; Houacine, Amrane; Sun, Ying
2017-01-01
Fall incidents are considered as the leading cause of disability and even mortality among older adults. To address this problem, fall detection and prevention fields receive a lot of intention over the past years and attracted many researcher efforts. We present in the current study an overall performance comparison between fall detection systems using the most popular machine learning approaches which are: Naïve Bayes, K nearest neighbor, neural network, and support vector machine. The analysis of the classification power associated to these most widely utilized algorithms is conducted on two fall detection databases namely FDD and URFD. Since the performance of the classification algorithm is inherently dependent on the features, we extracted and used the same features for all classifiers. The classification evaluation is conducted using different state of the art statistical measures such as the overall accuracy, the F-measure coefficient, and the area under ROC curve (AUC) value.
Fall detection using supervised machine learning algorithms: A comparative study
Zerrouki, Nabil
2017-01-05
Fall incidents are considered as the leading cause of disability and even mortality among older adults. To address this problem, fall detection and prevention fields receive a lot of intention over the past years and attracted many researcher efforts. We present in the current study an overall performance comparison between fall detection systems using the most popular machine learning approaches which are: Naïve Bayes, K nearest neighbor, neural network, and support vector machine. The analysis of the classification power associated to these most widely utilized algorithms is conducted on two fall detection databases namely FDD and URFD. Since the performance of the classification algorithm is inherently dependent on the features, we extracted and used the same features for all classifiers. The classification evaluation is conducted using different state of the art statistical measures such as the overall accuracy, the F-measure coefficient, and the area under ROC curve (AUC) value.
Machine learning based global particle indentification algorithms at LHCb experiment
Derkach, Denis; Likhomanenko, Tatiana; Rogozhnikov, Aleksei; Ratnikov, Fedor
2017-01-01
One of the most important aspects of data processing at LHC experiments is the particle identification (PID) algorithm. In LHCb, several different sub-detector systems provide PID information: the Ring Imaging CHerenkov (RICH) detector, the hadronic and electromagnetic calorimeters, and the muon chambers. To improve charged particle identification, several neural networks including a deep architecture and gradient boosting have been applied to data. These new approaches provide higher identification efficiencies than existing implementations for all charged particle types. It is also necessary to achieve a flat dependency between efficiencies and spectator variables such as particle momentum, in order to reduce systematic uncertainties during later stages of data analysis. For this purpose, "flat” algorithms that guarantee the flatness property for efficiencies have also been developed. This talk presents this new approach based on machine learning and its performance.
Q-learning-based adjustable fixed-phase quantum Grover search algorithm
International Nuclear Information System (INIS)
Guo Ying; Shi Wensha; Wang Yijun; Hu, Jiankun
2017-01-01
We demonstrate that the rotation phase can be suitably chosen to increase the efficiency of the phase-based quantum search algorithm, leading to a dynamic balance between iterations and success probabilities of the fixed-phase quantum Grover search algorithm with Q-learning for a given number of solutions. In this search algorithm, the proposed Q-learning algorithm, which is a model-free reinforcement learning strategy in essence, is used for performing a matching algorithm based on the fraction of marked items λ and the rotation phase α. After establishing the policy function α = π(λ), we complete the fixed-phase Grover algorithm, where the phase parameter is selected via the learned policy. Simulation results show that the Q-learning-based Grover search algorithm (QLGA) enables fewer iterations and gives birth to higher success probabilities. Compared with the conventional Grover algorithms, it avoids the optimal local situations, thereby enabling success probabilities to approach one. (author)
A self-learning algorithm for biased molecular dynamics
Tribello, Gareth A.; Ceriotti, Michele; Parrinello, Michele
2010-01-01
A new self-learning algorithm for accelerated dynamics, reconnaissance metadynamics, is proposed that is able to work with a very large number of collective coordinates. Acceleration of the dynamics is achieved by constructing a bias potential in terms of a patchwork of one-dimensional, locally valid collective coordinates. These collective coordinates are obtained from trajectory analyses so that they adapt to any new features encountered during the simulation. We show how this methodology can be used to enhance sampling in real chemical systems citing examples both from the physics of clusters and from the biological sciences. PMID:20876135
Directory of Open Access Journals (Sweden)
Vivek Patel
2012-08-01
Full Text Available Nature inspired population based algorithms is a research field which simulates different natural phenomena to solve a wide range of problems. Researchers have proposed several algorithms considering different natural phenomena. Teaching-Learning-based optimization (TLBO is one of the recently proposed population based algorithm which simulates the teaching-learning process of the class room. This algorithm does not require any algorithm-specific control parameters. In this paper, elitism concept is introduced in the TLBO algorithm and its effect on the performance of the algorithm is investigated. The effects of common controlling parameters such as the population size and the number of generations on the performance of the algorithm are also investigated. The proposed algorithm is tested on 35 constrained benchmark functions with different characteristics and the performance of the algorithm is compared with that of other well known optimization algorithms. The proposed algorithm can be applied to various optimization problems of the industrial environment.
MODIS Science Algorithms and Data Systems Lessons Learned
Wolfe, Robert E.; Ridgway, Bill L.; Patt, Fred S.; Masuoka, Edward J.
2009-01-01
For almost 10 years, standard global products from NASA's Earth Observing System s (EOS) two Moderate Resolution Imaging Spectroradiometer (MODIS) sensors are being used world-wide for earth science research and applications. This paper discusses the lessons learned in developing the science algorithms and the data systems needed to produce these high quality data products for the earth sciences community. Strong science team leadership and communication, an evolvable and scalable data system, and central coordination of QA and validation activities enabled the data system to grow by two orders of magnitude from the initial at-launch system to the current system able to reprocess data from both the Terra and Aqua missions in less than a year. Many of the lessons learned from MODIS are already being applied to follow-on missions.
Prediction of Baseflow Index of Catchments using Machine Learning Algorithms
Yadav, B.; Hatfield, K.
2017-12-01
We present the results of eight machine learning techniques for predicting the baseflow index (BFI) of ungauged basins using a surrogate of catchment scale climate and physiographic data. The tested algorithms include ordinary least squares, ridge regression, least absolute shrinkage and selection operator (lasso), elasticnet, support vector machine, gradient boosted regression trees, random forests, and extremely randomized trees. Our work seeks to identify the dominant controls of BFI that can be readily obtained from ancillary geospatial databases and remote sensing measurements, such that the developed techniques can be extended to ungauged catchments. More than 800 gauged catchments spanning the continental United States were selected to develop the general methodology. The BFI calculation was based on the baseflow separated from daily streamflow hydrograph using HYSEP filter. The surrogate catchment attributes were compiled from multiple sources including digital elevation model, soil, landuse, climate data, other publicly available ancillary and geospatial data. 80% catchments were used to train the ML algorithms, and the remaining 20% of the catchments were used as an independent test set to measure the generalization performance of fitted models. A k-fold cross-validation using exhaustive grid search was used to fit the hyperparameters of each model. Initial model development was based on 19 independent variables, but after variable selection and feature ranking, we generated revised sparse models of BFI prediction that are based on only six catchment attributes. These key predictive variables selected after the careful evaluation of bias-variance tradeoff include average catchment elevation, slope, fraction of sand, permeability, temperature, and precipitation. The most promising algorithms exceeding an accuracy score (r-square) of 0.7 on test data include support vector machine, gradient boosted regression trees, random forests, and extremely randomized
Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks.
Walter, Florian; Röhrbein, Florian; Knoll, Alois
2015-12-01
The application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even today, carrying out these simulations efficiently at appropriate timescales is challenging. Neuromorphic chip designs specially tailored to this task therefore offer an interesting perspective for neurorobotics. Unlike Von Neumann CPUs, these chips cannot be simply programmed with a standard programming language. Like real brains, their functionality is determined by the structure of neural connectivity and synaptic efficacies. Enabling higher cognitive functions for neurorobotics consequently requires the application of neurobiological learning algorithms to adjust synaptic weights in a biologically plausible way. In this paper, we therefore investigate how to program neuromorphic chips by means of learning. First, we provide an overview over selected neuromorphic chip designs and analyze them in terms of neural computation, communication systems and software infrastructure. On the theoretical side, we review neurobiological learning techniques. Based on this overview, we then examine on-die implementations of these learning algorithms on the considered neuromorphic chips. A final discussion puts the findings of this work into context and highlights how neuromorphic hardware can potentially advance the field of autonomous robot systems. The paper thus gives an in-depth overview of neuromorphic implementations of basic mechanisms of synaptic plasticity which are required to realize advanced cognitive capabilities with spiking neural networks. Copyright © 2015 Elsevier Ltd. All rights reserved.
From the social learning theory to a social learning algorithm for global optimization
Gong, Yue-Jiao; Zhang, Jun; Li, Yun
2014-01-01
Traditionally, the Evolutionary Computation (EC) paradigm is inspired by Darwinian evolution or the swarm intelligence of animals. Bandura's Social Learning Theory pointed out that the social learning behavior of humans indicates a high level of intelligence in nature. We found that such intelligence of human society can be implemented by numerical computing and be utilized in computational algorithms for solving optimization problems. In this paper, we design a novel and generic optimization...
Spike sorting based upon machine learning algorithms (SOMA).
Horton, P M; Nicol, A U; Kendrick, K M; Feng, J F
2007-02-15
We have developed a spike sorting method, using a combination of various machine learning algorithms, to analyse electrophysiological data and automatically determine the number of sampled neurons from an individual electrode, and discriminate their activities. We discuss extensions to a standard unsupervised learning algorithm (Kohonen), as using a simple application of this technique would only identify a known number of clusters. Our extra techniques automatically identify the number of clusters within the dataset, and their sizes, thereby reducing the chance of misclassification. We also discuss a new pre-processing technique, which transforms the data into a higher dimensional feature space revealing separable clusters. Using principal component analysis (PCA) alone may not achieve this. Our new approach appends the features acquired using PCA with features describing the geometric shapes that constitute a spike waveform. To validate our new spike sorting approach, we have applied it to multi-electrode array datasets acquired from the rat olfactory bulb, and from the sheep infero-temporal cortex, and using simulated data. The SOMA sofware is available at http://www.sussex.ac.uk/Users/pmh20/spikes.
Two Algorithms for Learning the Parameters of Stochastic Context-Free Grammars
National Research Council Canada - National Science Library
Heeringa, Brent; Oates, Tim
2001-01-01
.... Most algorithms for learning them require storage and repeated processing of a sentence corpus. The memory and computational demands of such algorithms are illsuited for embedded agents such as a mobile robot...
Objective. Factors associated with mineralization and osteophyte formation in osteoarthritis (OA) are incompletely understood. Genetic polymorphisms of matrix Gla protein (MGP), a mineralization inhibitor, have been associated clinically with conditions of abnormal calcification. We therefore evalua...
Genetic algorithm learning in a New Keynesian macroeconomic setup.
Hommes, Cars; Makarewicz, Tomasz; Massaro, Domenico; Smits, Tom
2017-01-01
In order to understand heterogeneous behavior amongst agents, empirical data from Learning-to-Forecast (LtF) experiments can be used to construct learning models. This paper follows up on Assenza et al. (2013) by using a Genetic Algorithms (GA) model to replicate the results from their LtF experiment. In this GA model, individuals optimize an adaptive, a trend following and an anchor coefficient in a population of general prediction heuristics. We replicate experimental treatments in a New-Keynesian environment with increasing complexity and use Monte Carlo simulations to investigate how well the model explains the experimental data. We find that the evolutionary learning model is able to replicate the three different types of behavior, i.e. convergence to steady state, stable oscillations and dampened oscillations in the treatments using one GA model. Heterogeneous behavior can thus be explained by an adaptive, anchor and trend extrapolating component and the GA model can be used to explain heterogeneous behavior in LtF experiments with different types of complexity.
Directory of Open Access Journals (Sweden)
R. Venkata Rao
2013-01-01
Full Text Available Teaching-Learning-based optimization (TLBO is a recently proposed population based algorithm, which simulates the teaching-learning process of the class room. This algorithm requires only the common control parameters and does not require any algorithm-specific control parameters. In this paper, the effect of elitism on the performance of the TLBO algorithm is investigated while solving unconstrained benchmark problems. The effects of common control parameters such as the population size and the number of generations on the performance of the algorithm are also investigated. The proposed algorithm is tested on 76 unconstrained benchmark functions with different characteristics and the performance of the algorithm is compared with that of other well known optimization algorithms. A statistical test is also performed to investigate the results obtained using different algorithms. The results have proved the effectiveness of the proposed elitist TLBO algorithm.
Two-Stage Electricity Demand Modeling Using Machine Learning Algorithms
Directory of Open Access Journals (Sweden)
Krzysztof Gajowniczek
2017-10-01
Full Text Available Forecasting of electricity demand has become one of the most important areas of research in the electric power industry, as it is a critical component of cost-efficient power system management and planning. In this context, accurate and robust load forecasting is supposed to play a key role in reducing generation costs, and deals with the reliability of the power system. However, due to demand peaks in the power system, forecasts are inaccurate and prone to high numbers of errors. In this paper, our contributions comprise a proposed data-mining scheme for demand modeling through peak detection, as well as the use of this information to feed the forecasting system. For this purpose, we have taken a different approach from that of time series forecasting, representing it as a two-stage pattern recognition problem. We have developed a peak classification model followed by a forecasting model to estimate an aggregated demand volume. We have utilized a set of machine learning algorithms to benefit from both accurate detection of the peaks and precise forecasts, as applied to the Polish power system. The key finding is that the algorithms can detect 96.3% of electricity peaks (load value equal to or above the 99th percentile of the load distribution and deliver accurate forecasts, with mean absolute percentage error (MAPE of 3.10% and resistant mean absolute percentage error (r-MAPE of 2.70% for the 24 h forecasting horizon.
Experiments on Supervised Learning Algorithms for Text Categorization
Namburu, Setu Madhavi; Tu, Haiying; Luo, Jianhui; Pattipati, Krishna R.
2005-01-01
Modern information society is facing the challenge of handling massive volume of online documents, news, intelligence reports, and so on. How to use the information accurately and in a timely manner becomes a major concern in many areas. While the general information may also include images and voice, we focus on the categorization of text data in this paper. We provide a brief overview of the information processing flow for text categorization, and discuss two supervised learning algorithms, viz., support vector machines (SVM) and partial least squares (PLS), which have been successfully applied in other domains, e.g., fault diagnosis [9]. While SVM has been well explored for binary classification and was reported as an efficient algorithm for text categorization, PLS has not yet been applied to text categorization. Our experiments are conducted on three data sets: Reuter's- 21578 dataset about corporate mergers and data acquisitions (ACQ), WebKB and the 20-Newsgroups. Results show that the performance of PLS is comparable to SVM in text categorization. A major drawback of SVM for multi-class categorization is that it requires a voting scheme based on the results of pair-wise classification. PLS does not have this drawback and could be a better candidate for multi-class text categorization.
Overlay improvements using a real time machine learning algorithm
Schmitt-Weaver, Emil; Kubis, Michael; Henke, Wolfgang; Slotboom, Daan; Hoogenboom, Tom; Mulkens, Jan; Coogans, Martyn; ten Berge, Peter; Verkleij, Dick; van de Mast, Frank
2014-04-01
While semiconductor manufacturing is moving towards the 14nm node using immersion lithography, the overlay requirements are tightened to below 5nm. Next to improvements in the immersion scanner platform, enhancements in the overlay optimization and process control are needed to enable these low overlay numbers. Whereas conventional overlay control methods address wafer and lot variation autonomously with wafer pre exposure alignment metrology and post exposure overlay metrology, we see a need to reduce these variations by correlating more of the TWINSCAN system's sensor data directly to the post exposure YieldStar metrology in time. In this paper we will present the results of a study on applying a real time control algorithm based on machine learning technology. Machine learning methods use context and TWINSCAN system sensor data paired with post exposure YieldStar metrology to recognize generic behavior and train the control system to anticipate on this generic behavior. Specific for this study, the data concerns immersion scanner context, sensor data and on-wafer measured overlay data. By making the link between the scanner data and the wafer data we are able to establish a real time relationship. The result is an inline controller that accounts for small changes in scanner hardware performance in time while picking up subtle lot to lot and wafer to wafer deviations introduced by wafer processing.
Effective and efficient optics inspection approach using machine learning algorithms
International Nuclear Information System (INIS)
Abdulla, G.; Kegelmeyer, L.; Liao, Z.; Carr, W.
2010-01-01
The Final Optics Damage Inspection (FODI) system automatically acquires and utilizes the Optics Inspection (OI) system to analyze images of the final optics at the National Ignition Facility (NIF). During each inspection cycle up to 1000 images acquired by FODI are examined by OI to identify and track damage sites on the optics. The process of tracking growing damage sites on the surface of an optic can be made more effective by identifying and removing signals associated with debris or reflections. The manual process to filter these false sites is daunting and time consuming. In this paper we discuss the use of machine learning tools and data mining techniques to help with this task. We describe the process to prepare a data set that can be used for training and identifying hardware reflections in the image data. In order to collect training data, the images are first automatically acquired and analyzed with existing software and then relevant features such as spatial, physical and luminosity measures are extracted for each site. A subset of these sites is 'truthed' or manually assigned a class to create training data. A supervised classification algorithm is used to test if the features can predict the class membership of new sites. A suite of self-configuring machine learning tools called 'Avatar Tools' is applied to classify all sites. To verify, we used 10-fold cross correlation and found the accuracy was above 99%. This substantially reduces the number of false alarms that would otherwise be sent for more extensive investigation.
Creating Engaging Online Learning Material with the JSAV JavaScript Algorithm Visualization Library
Karavirta, Ville; Shaffer, Clifford A.
2016-01-01
Data Structures and Algorithms are a central part of Computer Science. Due to their abstract and dynamic nature, they are a difficult topic to learn for many students. To alleviate these learning difficulties, instructors have turned to algorithm visualizations (AV) and AV systems. Research has shown that especially engaging AVs can have an impact…
International Nuclear Information System (INIS)
Dong Yun Kim; Poong Hyun Seong; .
1997-01-01
In this research, we propose a fuzzy gain scheduler (FGS) with an intelligent learning algorithm for a reactor control. In the proposed algorithm, the gradient descent method is used in order to generate the rule bases of a fuzzy algorithm by learning. These rule bases are obtained by minimizing an objective function, which is called a performance cost function. The objective of the FGS with an intelligent learning algorithm is to generate gains, which minimize the error of system. The proposed algorithm can reduce the time and effort required for obtaining the fuzzy rules through the intelligent learning function. It is applied to reactor control of nuclear power plant (NPP), and the results are compared with those of a conventional PI controller with fixed gains. As a result, it is shown that the proposed algorithm is superior to the conventional PI controller. (author)
Stability and chaos of LMSER PCA learning algorithm
International Nuclear Information System (INIS)
Lv Jiancheng; Y, Zhang
2007-01-01
LMSER PCA algorithm is a principal components analysis algorithm. It is used to extract principal components on-line from input data. The algorithm has both stability and chaotic dynamic behavior under some conditions. This paper studies the local stability of the LMSER PCA algorithm via a corresponding deterministic discrete time system. Conditions for local stability are derived. The paper also explores the chaotic behavior of this algorithm. It shows that the LMSER PCA algorithm can produce chaos. Waveform plots, Lyapunov exponents and bifurcation diagrams are presented to illustrate the existence of chaotic behavior of this algorithm
Directory of Open Access Journals (Sweden)
Weilin Nie
2017-01-01
Full Text Available Abstract Convex risk minimization is a commonly used setting in learning theory. In this paper, we firstly give a perturbation analysis for such algorithms, and then we apply this result to differential private learning algorithms. Our analysis needs the objective functions to be strongly convex. This leads to an extension of our previous analysis to the non-differentiable loss functions, when constructing differential private algorithms. Finally, an error analysis is then provided to show the selection for the parameters.
Modeling the Swift Bat Trigger Algorithm with Machine Learning
Graff, Philip B.; Lien, Amy Y.; Baker, John G.; Sakamoto, Takanori
2016-01-01
To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift / BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of greater than or equal to 97 percent (less than or equal to 3 percent error), which is a significant improvement on a cut in GRB flux, which has an accuracy of 89.6 percent (10.4 percent error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of n (sub 0) approaching 0.48 (sup plus 0.41) (sub minus 0.23) per cubic gigaparsecs per year with power-law indices of n (sub 1) approaching 1.7 (sup plus 0.6) (sub minus 0.5) and n (sub 2) approaching minus 5.9 (sup plus 5.7) (sub minus 0.1) for GRBs above and below a break point of z (redshift) (sub 1) approaching 6.8 (sup plus 2.8) (sub minus 3.2). This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting.
Efficient generation of image chips for training deep learning algorithms
Han, Sanghui; Fafard, Alex; Kerekes, John; Gartley, Michael; Ientilucci, Emmett; Savakis, Andreas; Law, Charles; Parhan, Jason; Turek, Matt; Fieldhouse, Keith; Rovito, Todd
2017-05-01
Training deep convolutional networks for satellite or aerial image analysis often requires a large amount of training data. For a more robust algorithm, training data need to have variations not only in the background and target, but also radiometric variations in the image such as shadowing, illumination changes, atmospheric conditions, and imaging platforms with different collection geometry. Data augmentation is a commonly used approach to generating additional training data. However, this approach is often insufficient in accounting for real world changes in lighting, location or viewpoint outside of the collection geometry. Alternatively, image simulation can be an efficient way to augment training data that incorporates all these variations, such as changing backgrounds, that may be encountered in real data. The Digital Imaging and Remote Sensing Image Image Generation (DIRSIG) model is a tool that produces synthetic imagery using a suite of physics-based radiation propagation modules. DIRSIG can simulate images taken from different sensors with variation in collection geometry, spectral response, solar elevation and angle, atmospheric models, target, and background. Simulation of Urban Mobility (SUMO) is a multi-modal traffic simulation tool that explicitly models vehicles that move through a given road network. The output of the SUMO model was incorporated into DIRSIG to generate scenes with moving vehicles. The same approach was used when using helicopters as targets, but with slight modifications. Using the combination of DIRSIG and SUMO, we quickly generated many small images, with the target at the center with different backgrounds. The simulations generated images with vehicles and helicopters as targets, and corresponding images without targets. Using parallel computing, 120,000 training images were generated in about an hour. Some preliminary results show an improvement in the deep learning algorithm when real image training data are augmented with
Modeling the Swift BAT Trigger Algorithm with Machine Learning
Graff, Philip B.; Lien, Amy Y.; Baker, John G.; Sakamoto, Takanori
2015-01-01
To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. (2014) is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of approximately greater than 97% (approximately less than 3% error), which is a significant improvement on a cut in GRB flux which has an accuracy of 89:6% (10:4% error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of eta(sub 0) approximately 0.48(+0.41/-0.23) Gpc(exp -3) yr(exp -1) with power-law indices of eta(sub 1) approximately 1.7(+0.6/-0.5) and eta(sub 2) approximately -5.9(+5.7/-0.1) for GRBs above and below a break point of z(sub 1) approximately 6.8(+2.8/-3.2). This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting. The code used in this is analysis is publicly available online.
Indian Academy of Sciences (India)
polynomial) division have been found in Vedic Mathematics which are dated much before Euclid's algorithm. A programming language Is used to describe an algorithm for execution on a computer. An algorithm expressed using a programming.
Huang, Yin; Chen, Jianhua; Xiong, Shaojun
2009-07-01
Mobile-Learning (M-learning) makes many learners get the advantages of both traditional learning and E-learning. Currently, Web-based Mobile-Learning Systems have created many new ways and defined new relationships between educators and learners. Association rule mining is one of the most important fields in data mining and knowledge discovery in databases. Rules explosion is a serious problem which causes great concerns, as conventional mining algorithms often produce too many rules for decision makers to digest. Since Web-based Mobile-Learning System collects vast amounts of student profile data, data mining and knowledge discovery techniques can be applied to find interesting relationships between attributes of learners, assessments, the solution strategies adopted by learners and so on. Therefore ,this paper focus on a new data-mining algorithm, combined with the advantages of genetic algorithm and simulated annealing algorithm , called ARGSA(Association rules based on an improved Genetic Simulated Annealing Algorithm), to mine the association rules. This paper first takes advantage of the Parallel Genetic Algorithm and Simulated Algorithm designed specifically for discovering association rules. Moreover, the analysis and experiment are also made to show the proposed method is superior to the Apriori algorithm in this Mobile-Learning system.
GLA-AF, an emulsion-free vaccine adjuvant for pandemic influenza.
Clegg, Christopher H; Roque, Richard; Perrone, Lucy A; Rininger, Joseph A; Bowen, Richard; Reed, Steven G
2014-01-01
The ongoing threat from Influenza necessitates the development of new vaccine and adjuvant technologies that can maximize vaccine immunogenicity, shorten production cycles, and increase global vaccine supply. Currently, the most successful adjuvants for Influenza vaccines are squalene-based oil-in-water emulsions. These adjuvants enhance seroprotective antibody titers to homologous and heterologous strains of virus, and augment a significant dose sparing activity that could improve vaccine manufacturing capacity. As an alternative to an emulsion, we tested a simple lipid-based aqueous formulation containing a synthetic TLR4 ligand (GLA-AF) for its ability to enhance protection against H5N1 infection. GLA-AF was very effective in adjuvanting recombinant H5 hemagglutinin antigen (rH5) in mice and was as potent as the stable emulsion, SE. Both adjuvants induced similar antibody titers using a sub-microgram dose of rH5, and both conferred complete protection against a highly pathogenic H5N1 challenge. However, GLA-AF was the superior adjuvant in ferrets. GLA-AF stimulated a broader antibody response than SE after both the prime and boost immunization with rH5, and ferrets were better protected against homologous and heterologous strains of H5N1 virus. Thus, GLA-AF is a potent emulsion-free adjuvant that warrants consideration for pandemic influenza vaccine development.
A rank-based Prediction Algorithm of Learning User's Intention
Shen, Jie; Gao, Ying; Chen, Cang; Gong, HaiPing
Internet search has become an important part in people's daily life. People can find many types of information to meet different needs through search engines on the Internet. There are two issues for the current search engines: first, the users should predetermine the types of information they want and then change to the appropriate types of search engine interfaces. Second, most search engines can support multiple kinds of search functions, each function has its own separate search interface. While users need different types of information, they must switch between different interfaces. In practice, most queries are corresponding to various types of information results. These queries can search the relevant results in various search engines, such as query "Palace" contains the websites about the introduction of the National Palace Museum, blog, Wikipedia, some pictures and video information. This paper presents a new aggregative algorithm for all kinds of search results. It can filter and sort the search results by learning three aspects about the query words, search results and search history logs to achieve the purpose of detecting user's intention. Experiments demonstrate that this rank-based method for multi-types of search results is effective. It can meet the user's search needs well, enhance user's satisfaction, provide an effective and rational model for optimizing search engines and improve user's search experience.
Self-learning health monitoring algorithm in composite structures
Grassia, Luigi; Iannone, Michele; Califano, America; D'Amore, Alberto
2018-02-01
The paper describes a system that it is able of monitoring the health state of a composite structure in real time. The hardware of the system consists of a wire of strain sensors connected to a control unit. The software of the system elaborates the strain data and in real time is able to detect the presence of an eventual damage of the structures monitored with the strain sensors. The algorithm requires as input only the strains of the monitored structured measured on real time, i.e. those strains coming from the deformations of the composite structure due to the working loads. The health monitoring system does not require any additional device to interrogate the structure as often used in the literature, instead it is based on a self-learning procedure. The strain data acquired when the structure is healthy are used to set up the correlations between the strain in different positions of structure by means of neural network. Once the correlations between the strains in different position have been set up, these correlations act as a fingerprint of the healthy structure. In case of damage the correlation between the strains in the position of the structure near the damage will change due to the change of the stiffness of the structure caused by the damage. The developed software is able to recognize the change of the transfer function between the strains and consequently is able to detect the damage.
Bejnordi, Babak Ehteshami; Veta, Mitko; van Diest, Paul Johannes; Van Ginneken, Bram; Karssemeijer, Nico; Litjens, Geert; van der Laak, Jeroen A.W.M.; Hermsen, Meyke; Manson, Quirine F.; Balkenhol, Maschenka; Geessink, Oscar; Stathonikos, Nikolaos; Van Dijk, Marcory C.R.F.; Bult, Peter; Beca, Francisco; Beck, Andrew H.; Wang, Dayong; Khosla, Aditya; Gargeya, Rishab; Irshad, Humayun; Zhong, Aoxiao; Dou, Qi; Li, Quanzheng; Chen, Hao; Lin, Huang Jing; Heng, Pheng Ann; Haß, Christian; Bruni, Elia; Wong, Quincy; Halici, Ugur; Öner, Mustafa Ümit; Cetin-Atalay, Rengul; Berseth, Matt; Khvatkov, Vitali; Vylegzhanin, Alexei; Kraus, Oren; Shaban, Muhammad; Rajpoot, Nasir; Awan, Ruqayya; Sirinukunwattana, Korsuk; Qaiser, Talha; Tsang, Yee Wah; Tellez, David; Annuscheit, Jonas; Hufnagl, Peter; Valkonen, Mira; Kartasalo, Kimmo; Latonen, Leena; Ruusuvuori, Pekka; Liimatainen, Kaisa
2017-01-01
IMPORTANCE: Application of deep learning algorithms to whole-slide pathology imagescan potentially improve diagnostic accuracy and efficiency. OBJECTIVE: Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph
Fidelity-Based Ant Colony Algorithm with Q-learning of Quantum System
Liao, Qin; Guo, Ying; Tu, Yifeng; Zhang, Hang
2018-03-01
Quantum ant colony algorithm (ACA) has potential applications in quantum information processing, such as solutions of traveling salesman problem, zero-one knapsack problem, robot route planning problem, and so on. To shorten the search time of the ACA, we suggest the fidelity-based ant colony algorithm (FACA) for the control of quantum system. Motivated by structure of the Q-learning algorithm, we demonstrate the combination of a FACA with the Q-learning algorithm and suggest the design of a fidelity-based ant colony algorithm with the Q-learning to improve the performance of the FACA in a spin-1/2 quantum system. The numeric simulation results show that the FACA with the Q-learning can efficiently avoid trapping into local optimal policies and increase the speed of convergence process of quantum system.
A Coupled User Clustering Algorithm Based on Mixed Data for Web-Based Learning Systems
Directory of Open Access Journals (Sweden)
Ke Niu
2015-01-01
Full Text Available In traditional Web-based learning systems, due to insufficient learning behaviors analysis and personalized study guides, a few user clustering algorithms are introduced. While analyzing the behaviors with these algorithms, researchers generally focus on continuous data but easily neglect discrete data, each of which is generated from online learning actions. Moreover, there are implicit coupled interactions among the data but are frequently ignored in the introduced algorithms. Therefore, a mass of significant information which can positively affect clustering accuracy is neglected. To solve the above issues, we proposed a coupled user clustering algorithm for Wed-based learning systems by taking into account both discrete and continuous data, as well as intracoupled and intercoupled interactions of the data. The experiment result in this paper demonstrates the outperformance of the proposed algorithm.
Forsström, J
1992-01-01
The ID3 algorithm for inductive learning was tested using preclassified material for patients suspected to have a thyroid illness. Classification followed a rule-based expert system for the diagnosis of thyroid function. Thus, the knowledge to be learned was limited to the rules existing in the knowledge base of that expert system. The learning capability of the ID3 algorithm was tested with an unselected learning material (with some inherent missing data) and with a selected learning material (no missing data). The selected learning material was a subgroup which formed a part of the unselected learning material. When the number of learning cases was increased, the accuracy of the program improved. When the learning material was large enough, an increase in the learning material did not improve the results further. A better learning result was achieved with the selected learning material not including missing data as compared to unselected learning material. With this material we demonstrate a weakness in the ID3 algorithm: it can not find available information from good example cases if we add poor examples to the data.
New Dandelion Algorithm Optimizes Extreme Learning Machine for Biomedical Classification Problems
Directory of Open Access Journals (Sweden)
Xiguang Li
2017-01-01
Full Text Available Inspired by the behavior of dandelion sowing, a new novel swarm intelligence algorithm, namely, dandelion algorithm (DA, is proposed for global optimization of complex functions in this paper. In DA, the dandelion population will be divided into two subpopulations, and different subpopulations will undergo different sowing behaviors. Moreover, another sowing method is designed to jump out of local optimum. In order to demonstrate the validation of DA, we compare the proposed algorithm with other existing algorithms, including bat algorithm, particle swarm optimization, and enhanced fireworks algorithm. Simulations show that the proposed algorithm seems much superior to other algorithms. At the same time, the proposed algorithm can be applied to optimize extreme learning machine (ELM for biomedical classification problems, and the effect is considerable. At last, we use different fusion methods to form different fusion classifiers, and the fusion classifiers can achieve higher accuracy and better stability to some extent.
Research on B Cell Algorithm for Learning to Rank Method Based on Parallel Strategy.
Tian, Yuling; Zhang, Hongxian
2016-01-01
For the purposes of information retrieval, users must find highly relevant documents from within a system (and often a quite large one comprised of many individual documents) based on input query. Ranking the documents according to their relevance within the system to meet user needs is a challenging endeavor, and a hot research topic-there already exist several rank-learning methods based on machine learning techniques which can generate ranking functions automatically. This paper proposes a parallel B cell algorithm, RankBCA, for rank learning which utilizes a clonal selection mechanism based on biological immunity. The novel algorithm is compared with traditional rank-learning algorithms through experimentation and shown to outperform the others in respect to accuracy, learning time, and convergence rate; taken together, the experimental results show that the proposed algorithm indeed effectively and rapidly identifies optimal ranking functions.
Developing robust arsenic awareness prediction models using machine learning algorithms.
Singh, Sushant K; Taylor, Robert W; Rahman, Mohammad Mahmudur; Pradhan, Biswajeet
2018-04-01
Arsenic awareness plays a vital role in ensuring the sustainability of arsenic mitigation technologies. Thus far, however, few studies have dealt with the sustainability of such technologies and its associated socioeconomic dimensions. As a result, arsenic awareness prediction has not yet been fully conceptualized. Accordingly, this study evaluated arsenic awareness among arsenic-affected communities in rural India, using a structured questionnaire to record socioeconomic, demographic, and other sociobehavioral factors with an eye to assessing their association with and influence on arsenic awareness. First a logistic regression model was applied and its results compared with those produced by six state-of-the-art machine-learning algorithms (Support Vector Machine [SVM], Kernel-SVM, Decision Tree [DT], k-Nearest Neighbor [k-NN], Naïve Bayes [NB], and Random Forests [RF]) as measured by their accuracy at predicting arsenic awareness. Most (63%) of the surveyed population was found to be arsenic-aware. Significant arsenic awareness predictors were divided into three types: (1) socioeconomic factors: caste, education level, and occupation; (2) water and sanitation behavior factors: number of family members involved in water collection, distance traveled and time spent for water collection, places for defecation, and materials used for handwashing after defecation; and (3) social capital and trust factors: presence of anganwadi and people's trust in other community members, NGOs, and private agencies. Moreover, individuals' having higher social network positively contributed to arsenic awareness in the communities. Results indicated that both the SVM and the RF algorithms outperformed at overall prediction of arsenic awareness-a nonlinear classification problem. Lower-caste, less educated, and unemployed members of the population were found to be the most vulnerable, requiring immediate arsenic mitigation. To this end, local social institutions and NGOs could play a
Learning Path Recommendation Based on Modified Variable Length Genetic Algorithm
Dwivedi, Pragya; Kant, Vibhor; Bharadwaj, Kamal K.
2018-01-01
With the rapid advancement of information and communication technologies, e-learning has gained a considerable attention in recent years. Many researchers have attempted to develop various e-learning systems with personalized learning mechanisms for assisting learners so that they can learn more efficiently. In this context, curriculum sequencing…
Boxma, P.Y.; Berg, van den E.; Geleijnse, J.M.; Laverman, G.D.; Schurgers, L.J.; Vermeer, C.; Kema, I.P.; Muskiet, F.A.J.; Navis, G.; Bakker, S.J.L.; Borst, de M.H.
2012-01-01
Vitamin K is essential for activation of ¿-carboxyglutamate (Gla)-proteins including the vascular calcification inhibitor matrix Gla-protein (MGP). Insufficient vitamin K intake leads to production of uncarboxylated, mostly inactive proteins and contributes to an increased cardiovascular risk. In
A controllable sensor management algorithm capable of learning
Osadciw, Lisa A.; Veeramacheneni, Kalyan K.
2005-03-01
Sensor management technology progress is challenged by the geographic space it spans, the heterogeneity of the sensors, and the real-time timeframes within which plans controlling the assets are executed. This paper presents a new sensor management paradigm and demonstrates its application in a sensor management algorithm designed for a biometric access control system. This approach consists of an artificial intelligence (AI) algorithm focused on uncertainty measures, which makes the high level decisions to reduce uncertainties and interfaces with the user, integrated cohesively with a bottom up evolutionary algorithm, which optimizes the sensor network"s operation as determined by the AI algorithm. The sensor management algorithm presented is composed of a Bayesian network, the AI algorithm component, and a swarm optimization algorithm, the evolutionary algorithm. Thus, the algorithm can change its own performance goals in real-time and will modify its own decisions based on observed measures within the sensor network. The definition of the measures as well as the Bayesian network determine the robustness of the algorithm and its utility in reacting dynamically to changes in the global system.
The efficiency of the RULES-4 classification learning algorithm in predicting the density of agents
Directory of Open Access Journals (Sweden)
Ziad Salem
2014-12-01
Full Text Available Learning is the act of obtaining new or modifying existing knowledge, behaviours, skills or preferences. The ability to learn is found in humans, other organisms and some machines. Learning is always based on some sort of observations or data such as examples, direct experience or instruction. This paper presents a classification algorithm to learn the density of agents in an arena based on the measurements of six proximity sensors of a combined actuator sensor units (CASUs. Rules are presented that were induced by the learning algorithm that was trained with data-sets based on the CASU’s sensor data streams collected during a number of experiments with “Bristlebots (agents in the arena (environment”. It was found that a set of rules generated by the learning algorithm is able to predict the number of bristlebots in the arena based on the CASU’s sensor readings with satisfying accuracy.
Indian Academy of Sciences (India)
to as 'divide-and-conquer'. Although there has been a large effort in realizing efficient algorithms, there are not many universally accepted algorithm design paradigms. In this article, we illustrate algorithm design techniques such as balancing, greedy strategy, dynamic programming strategy, and backtracking or traversal of ...
Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality.
Braithwaite, Scott R; Giraud-Carrier, Christophe; West, Josh; Barnes, Michael D; Hanson, Carl Lee
2016-05-16
One of the leading causes of death in the United States (US) is suicide and new methods of assessment are needed to track its risk in real time. Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Our findings show that people who are at high suicidal risk can be easily differentiated from those who are not by machine learning algorithms, which accurately identify the clinically significant suicidal rate in 92% of cases (sensitivity: 53%, specificity: 97%, positive predictive value: 75%, negative predictive value: 93%). Machine learning algorithms are efficient in differentiating people who are at a suicidal risk from those who are not. Evidence for suicidality can be measured in nonclinical populations using social media data.
Elements of Causal Inference: Foundations and Learning Algorithms
DEFF Research Database (Denmark)
Peters, Jonas Martin; Janzing, Dominik; Schölkopf, Bernhard
A concise and self-contained introduction to causal inference, increasingly important in data science and machine learning......A concise and self-contained introduction to causal inference, increasingly important in data science and machine learning...
Directory of Open Access Journals (Sweden)
REIS, M V. S. de A.
2017-06-01
Full Text Available This paper aims to evaluate the use of machine learning techniques in a database of marine accidents. We analyzed and evaluated the main causes and types of marine accidents in the Northern Fluminense region. For this, machine learning techniques were used. The study showed that the modeling can be done in a satisfactory manner using different configurations of classification algorithms, varying the activation functions and training parameters. The SMO (Sequential Minimal Optimization algorithm showed the best performance result.
An analysis dictionary learning algorithm under a noisy data model with orthogonality constraint.
Zhang, Ye; Yu, Tenglong; Wang, Wenwu
2014-01-01
Two common problems are often encountered in analysis dictionary learning (ADL) algorithms. The first one is that the original clean signals for learning the dictionary are assumed to be known, which otherwise need to be estimated from noisy measurements. This, however, renders a computationally slow optimization process and potentially unreliable estimation (if the noise level is high), as represented by the Analysis K-SVD (AK-SVD) algorithm. The other problem is the trivial solution to the dictionary, for example, the null dictionary matrix that may be given by a dictionary learning algorithm, as discussed in the learning overcomplete sparsifying transform (LOST) algorithm. Here we propose a novel optimization model and an iterative algorithm to learn the analysis dictionary, where we directly employ the observed data to compute the approximate analysis sparse representation of the original signals (leading to a fast optimization procedure) and enforce an orthogonality constraint on the optimization criterion to avoid the trivial solutions. Experiments demonstrate the competitive performance of the proposed algorithm as compared with three baselines, namely, the AK-SVD, LOST, and NAAOLA algorithms.
International Nuclear Information System (INIS)
Park, Gee Yong; Seong, Poong Hyun
1994-01-01
In order to reduce the load of tuning works by trial-and-error for obtaining the best control performance of conventional fuzzy control algorithm, a fuzzy control algorithm with learning function is investigated in this work. This fuzzy control algorithm can make its rule base and tune the membership functions automatically by use of learning function which needs the data from the control actions of the plant operator or other controllers. Learning process in fuzzy control algorithm is to find the optimal values of parameters, which consist of the membership functions and the rule base, by gradient descent method. Learning speed of gradient descent is significantly improved in this work with the addition of modified momentum. This control algorithm is applied to the steam generator level control by computer simulations. The simulation results confirm the good performance of this control algorithm for level control and show that the fuzzy learning algorithm has the generalization capability for the relation of inputs and outputs and it also has the excellent capability of disturbance rejection
An Analysis Dictionary Learning Algorithm under a Noisy Data Model with Orthogonality Constraint
Directory of Open Access Journals (Sweden)
Ye Zhang
2014-01-01
Full Text Available Two common problems are often encountered in analysis dictionary learning (ADL algorithms. The first one is that the original clean signals for learning the dictionary are assumed to be known, which otherwise need to be estimated from noisy measurements. This, however, renders a computationally slow optimization process and potentially unreliable estimation (if the noise level is high, as represented by the Analysis K-SVD (AK-SVD algorithm. The other problem is the trivial solution to the dictionary, for example, the null dictionary matrix that may be given by a dictionary learning algorithm, as discussed in the learning overcomplete sparsifying transform (LOST algorithm. Here we propose a novel optimization model and an iterative algorithm to learn the analysis dictionary, where we directly employ the observed data to compute the approximate analysis sparse representation of the original signals (leading to a fast optimization procedure and enforce an orthogonality constraint on the optimization criterion to avoid the trivial solutions. Experiments demonstrate the competitive performance of the proposed algorithm as compared with three baselines, namely, the AK-SVD, LOST, and NAAOLA algorithms.
International Nuclear Information System (INIS)
Kim, Dong Yun
1997-02-01
In this research, we propose a fuzzy gain scheduler (FGS) with an intelligent learning algorithm for a reactor control. In the proposed algorithm, the gradient descent method is used in order to generate the rule bases of a fuzzy algorithm by learning. These rule bases are obtained by minimizing an objective function, which is called a performance cost function. The objective of the FGS with an intelligent learning algorithm is to generate adequate gains, which minimize the error of system. The proposed algorithm can reduce the time and efforts required for obtaining the fuzzy rules through the intelligent learning function. The evolutionary programming algorithm is modified and adopted as the method in order to find the optimal gains which are used as the initial gains of FGS with learning function. It is applied to reactor control of nuclear power plant (NPP), and the results are compared with those of a conventional PI controller with fixed gains. As a result, it is shown that the proposed algorithm is superior to the conventional PI controller
Identification of chaotic systems by neural network with hybrid learning algorithm
International Nuclear Information System (INIS)
Pan, S.-T.; Lai, C.-C.
2008-01-01
Based on the genetic algorithm (GA) and steepest descent method (SDM), this paper proposes a hybrid algorithm for the learning of neural networks to identify chaotic systems. The systems in question are the logistic map and the Duffing equation. Different identification schemes are used to identify both the logistic map and the Duffing equation, respectively. Simulation results show that our hybrid algorithm is more efficient than that of other methods
A new supervised learning algorithm for spiking neurons.
Xu, Yan; Zeng, Xiaoqin; Zhong, Shuiming
2013-06-01
The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by the precise firing times of spikes. If only running time is considered, the supervised learning for a spiking neuron is equivalent to distinguishing the times of desired output spikes and the other time during the running process of the neuron through adjusting synaptic weights, which can be regarded as a classification problem. Based on this idea, this letter proposes a new supervised learning method for spiking neurons with temporal encoding; it first transforms the supervised learning into a classification problem and then solves the problem by using the perceptron learning rule. The experiment results show that the proposed method has higher learning accuracy and efficiency over the existing learning methods, so it is more powerful for solving complex and real-time problems.
Smid, B.E.; Hollak, C.E.M.; Poorthuis, B.J.H.M.; Bergh-Weerman, M.A. van den; Florquin, S.; Kok, W.E.; Deprez, R.H.L.; Timmermans, J.; Linthorst, G.E.
2015-01-01
Fabry disease' (FD) phenotype is heterogeneous: alpha-galactosidase A gene mutations (GLA) can lead to classical or non-classical FD, or no FD. The aim of this study is to describe pitfalls in diagnosing non-classical FD and assess the diagnostic value of plasma globotriaosylsphingosine. This is a
DEFF Research Database (Denmark)
Houghton-Larsen, J.; Pedersen, Per Amstrup
2003-01-01
This article reports a novel strategy for the cloning of glucoamylase genes using conserved sequences and semi-nested PCR and its application in cloning the GlaM glucoamylase gene and cDNA from the dimorphic zygomycete Mucor circinelloides. The deduced 609-amino-acid enzyme (including signal...
Directory of Open Access Journals (Sweden)
Jiří Fejfar
2012-01-01
Full Text Available We are presenting results comparison of three artificial intelligence algorithms in a classification of time series derived from musical excerpts in this paper. Algorithms were chosen to represent different principles of classification – statistic approach, neural networks and competitive learning. The first algorithm is a classical k-Nearest neighbours algorithm, the second algorithm is Multilayer Perceptron (MPL, an example of artificial neural network and the third one is a Learning Vector Quantization (LVQ algorithm representing supervised counterpart to unsupervised Self Organizing Map (SOM.After our own former experiments with unlabelled data we moved forward to the data labels utilization, which generally led to a better accuracy of classification results. As we need huge data set of labelled time series (a priori knowledge of correct class which each time series instance belongs to, we used, with a good experience in former studies, musical excerpts as a source of real-world time series. We are using standard deviation of the sound signal as a descriptor of a musical excerpts volume level.We are describing principle of each algorithm as well as its implementation briefly, giving links for further research. Classification results of each algorithm are presented in a confusion matrix showing numbers of misclassifications and allowing to evaluate overall accuracy of the algorithm. Results are compared and particular misclassifications are discussed for each algorithm. Finally the best solution is chosen and further research goals are given.
An improved clustering algorithm based on reverse learning in intelligent transportation
Qiu, Guoqing; Kou, Qianqian; Niu, Ting
2017-05-01
With the development of artificial intelligence and data mining technology, big data has gradually entered people's field of vision. In the process of dealing with large data, clustering is an important processing method. By introducing the reverse learning method in the clustering process of PAM clustering algorithm, to further improve the limitations of one-time clustering in unsupervised clustering learning, and increase the diversity of clustering clusters, so as to improve the quality of clustering. The algorithm analysis and experimental results show that the algorithm is feasible.
A Computer Environment for Beginners' Learning of Sorting Algorithms: Design and Pilot Evaluation
Kordaki, M.; Miatidis, M.; Kapsampelis, G.
2008-01-01
This paper presents the design, features and pilot evaluation study of a web-based environment--the SORTING environment--for the learning of sorting algorithms by secondary level education students. The design of this environment is based on modeling methodology, taking into account modern constructivist and social theories of learning while at…
Interactive Learning Environment for Bio-Inspired Optimization Algorithms for UAV Path Planning
Duan, Haibin; Li, Pei; Shi, Yuhui; Zhang, Xiangyin; Sun, Changhao
2015-01-01
This paper describes the development of BOLE, a MATLAB-based interactive learning environment, that facilitates the process of learning bio-inspired optimization algorithms, and that is dedicated exclusively to unmanned aerial vehicle path planning. As a complement to conventional teaching methods, BOLE is designed to help students consolidate the…
Bandyopadhyay, Sanghamitra
2007-01-01
This book provides a unified framework that describes how genetic learning can be used to design pattern recognition and learning systems. It examines how a search technique, the genetic algorithm, can be used for pattern classification mainly through approximating decision boundaries. Coverage also demonstrates the effectiveness of the genetic classifiers vis-à-vis several widely used classifiers, including neural networks.
Lago Garcia, J.; De Ridder, Fjo; De Schutter, B.H.K.
2018-01-01
In this paper, a novel modeling framework for forecasting electricity prices is proposed. While many predictive models have been already proposed to perform this task, the area of deep learning algorithms remains yet unexplored. To fill this scientific gap, we propose four different deep learning
Beyond the "c" and the "x": Learning with Algorithms in Massive Open Online Courses (MOOCs)
Knox, Jeremy
2018-01-01
This article examines how algorithms are shaping student learning in massive open online courses (MOOCs). Following the dramatic rise of MOOC platform organisations in 2012, over 4,500 MOOCs have been offered to date, in increasingly diverse languages, and with a growing requirement for fees. However, discussions of "learning" in MOOCs…
Upper-Lower Bounds Candidate Sets Searching Algorithm for Bayesian Network Structure Learning
Directory of Open Access Journals (Sweden)
Guangyi Liu
2014-01-01
Full Text Available Bayesian network is an important theoretical model in artificial intelligence field and also a powerful tool for processing uncertainty issues. Considering the slow convergence speed of current Bayesian network structure learning algorithms, a fast hybrid learning method is proposed in this paper. We start with further analysis of information provided by low-order conditional independence testing, and then two methods are given for constructing graph model of network, which is theoretically proved to be upper and lower bounds of the structure space of target network, so that candidate sets are given as a result; after that a search and scoring algorithm is operated based on the candidate sets to find the final structure of the network. Simulation results show that the algorithm proposed in this paper is more efficient than similar algorithms with the same learning precision.
Directory of Open Access Journals (Sweden)
OMER MAHMOUD
2007-08-01
Full Text Available One of the essential factors that affect the performance of Artificial Neural Networks is the learning algorithm. The performance of Multilayer Feed Forward Artificial Neural Network performance in image compression using different learning algorithms is examined in this paper. Based on Gradient Descent, Conjugate Gradient, Quasi-Newton techniques three different error back propagation algorithms have been developed for use in training two types of neural networks, a single hidden layer network and three hidden layers network. The essence of this study is to investigate the most efficient and effective training methods for use in image compression and its subsequent applications. The obtained results show that the Quasi-Newton based algorithm has better performance as compared to the other two algorithms.
Dynamic gradient descent learning algorithms for enhanced empirical modeling of power plants
International Nuclear Information System (INIS)
Parlos, A.G.; Atiya, Amir; Chong, K.T.
1991-01-01
A newly developed dynamic gradient descent-based learning algorithm is used to train a recurrent multilayer perceptron network for use in empirical modeling of power plants. The two main advantages of the proposed learning algorithm are its ability to consider past error gradient information for future use and the two forward passes associated with its implementation, instead of one forward and one backward pass of the backpropagation algorithm. The latter advantage results in computational time saving because both passes can be performed simultaneously. The dynamic learning algorithm is used to train a hybrid feedforward/feedback neural network, a recurrent multilayer perceptron, which was previously found to exhibit good interpolation and extrapolation capabilities in modeling nonlinear dynamic systems. One of the drawbacks, however, of the previously reported work has been the long training times associated with accurate empirical models. The enhanced learning capabilities provided by the dynamic gradient descent-based learning algorithm are demonstrated by a case study of a steam power plant. The number of iterations required for accurate empirical modeling has been reduced from tens of thousands to hundreds, thus significantly expediting the learning process
Singal, Amit G.; Mukherjee, Ashin; Elmunzer, B. Joseph; Higgins, Peter DR; Lok, Anna S.; Zhu, Ji; Marrero, Jorge A; Waljee, Akbar K
2015-01-01
Background Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine learning algorithms. Methods We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared to the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. Results After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95%CI 0.56-0.67), whereas the machine learning algorithm had a c-statistic of 0.64 (95%CI 0.60–0.69) in the validation cohort. The machine learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (pmachine learning algorithm (p=0.047). Conclusion Machine learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC. PMID:24169273
Optimal design of the heat pipe using TLBO (teaching–learning-based optimization) algorithm
International Nuclear Information System (INIS)
Rao, R.V.; More, K.C.
2015-01-01
Heat pipe is a highly efficient and reliable heat transfer component. It is a closed container designed to transfer a large amount of heat in system. Since the heat pipe operates on a closed two-phase cycle, the heat transfer capacity is greater than for solid conductors. Also, the thermal response time is less than with solid conductors. The three major elemental parts of the rotating heat pipe are: a cylindrical evaporator, a truncated cone condenser, and a fixed amount of working fluid. In this paper, a recently proposed new stochastic advanced optimization algorithm called TLBO (Teaching–Learning-Based Optimization) algorithm is used for single objective as well as multi-objective design optimization of heat pipe. It is easy to implement, does not make use of derivatives and it can be applied to unconstrained or constrained problems. Two examples of heat pipe are presented in this paper. The results of application of TLBO algorithm for the design optimization of heat pipe are compared with the NPGA (Niched Pareto Genetic Algorithm), GEM (Grenade Explosion Method) and GEO (Generalized External optimization). It is found that the TLBO algorithm has produced better results as compared to those obtained by using NPGA, GEM and GEO algorithms. - Highlights: • The TLBO (Teaching–Learning-Based Optimization) algorithm is used for the design and optimization of a heat pipe. • Two examples of heat pipe design and optimization are presented. • The TLBO algorithm is proved better than the other optimization algorithms in terms of results and the convergence
An Adaptive Bacterial Foraging Optimization Algorithm with Lifecycle and Social Learning
Directory of Open Access Journals (Sweden)
Xiaohui Yan
2012-01-01
Full Text Available Bacterial Foraging Algorithm (BFO is a recently proposed swarm intelligence algorithm inspired by the foraging and chemotactic phenomenon of bacteria. However, its optimization ability is not so good compared with other classic algorithms as it has several shortages. This paper presents an improved BFO Algorithm. In the new algorithm, a lifecycle model of bacteria is founded. The bacteria could split, die, or migrate dynamically in the foraging processes, and population size varies as the algorithm runs. Social learning is also introduced so that the bacteria will tumble towards better directions in the chemotactic steps. Besides, adaptive step lengths are employed in chemotaxis. The new algorithm is named BFOLS and it is tested on a set of benchmark functions with dimensions of 2 and 20. Canonical BFO, PSO, and GA algorithms are employed for comparison. Experiment results and statistic analysis show that the BFOLS algorithm offers significant improvements than original BFO algorithm. Particulary with dimension of 20, it has the best performance among the four algorithms.
Indian Academy of Sciences (India)
ticians but also forms the foundation of computer science. Two ... with methods of developing algorithms for solving a variety of problems but ... applications of computers in science and engineer- ... numerical calculus are as important. We will ...
Végh, Ladislav
2016-01-01
The first data structure that first-year undergraduate students learn during the programming and algorithms courses is the one-dimensional array. For novice programmers, it might be hard to understand different algorithms on arrays (e.g. searching, mirroring, sorting algorithms), because the algorithms dynamically change the values of elements. In…
Algorithms that Defy the Gravity of Learning Curve
2017-04-28
yield the best perform- ing 1NN ensembles There is no magic to the gravity-defiant algorithms such as aNNE and iNNE which mani- fest that small data...isolation using nearest neighbour en- semble. Proceedings of the 2014 IEEE international conference on data mining, work- shop on incremental
Spectral Regularization Algorithms for Learning Large Incomplete Matrices.
Mazumder, Rahul; Hastie, Trevor; Tibshirani, Robert
2010-03-01
We use convex relaxation techniques to provide a sequence of regularized low-rank solutions for large-scale matrix completion problems. Using the nuclear norm as a regularizer, we provide a simple and very efficient convex algorithm for minimizing the reconstruction error subject to a bound on the nuclear norm. Our algorithm Soft-Impute iteratively replaces the missing elements with those obtained from a soft-thresholded SVD. With warm starts this allows us to efficiently compute an entire regularization path of solutions on a grid of values of the regularization parameter. The computationally intensive part of our algorithm is in computing a low-rank SVD of a dense matrix. Exploiting the problem structure, we show that the task can be performed with a complexity linear in the matrix dimensions. Our semidefinite-programming algorithm is readily scalable to large matrices: for example it can obtain a rank-80 approximation of a 10(6) × 10(6) incomplete matrix with 10(5) observed entries in 2.5 hours, and can fit a rank 40 approximation to the full Netflix training set in 6.6 hours. Our methods show very good performance both in training and test error when compared to other competitive state-of-the art techniques.
Variants of Learning Algorithm Based on Kolmogorov Theorem
Czech Academy of Sciences Publication Activity Database
Neruda, Roman; Štědrý, Arnošt; Drkošová, Jitka
2002-01-01
Roč. 12, č. 6 (2002), s. 587-597 ISSN 1210-0552 R&D Projects: GA AV ČR IAB1030006 Institutional research plan: AV0Z1030915 Keywords : Kolmogorov networks * approximation theory * parallel algorithms Subject RIV: BA - General Mathematics
Learning JavaScript data structures and algorithms
Groner, Loiane
2014-01-01
If you are a JavaScript developer or someone who has basic knowledge of JavaScript, and want to explore its optimum ability, this fast-paced book is definitely for you. Programming logic is the only thing you need to know to start having fun with algorithms.
Schwarz, Daniel; Štourač, Petr; Komenda, Martin; Harazim, Hana; Kosinová, Martina; Gregor, Jakub; Hůlek, Richard; Smékalová, Olga; Křikava, Ivo; Štoudek, Roman; Dušek, Ladislav
2013-07-08
Medical Faculties Network (MEFANET) has established itself as the authority for setting standards for medical educators in the Czech Republic and Slovakia, 2 independent countries with similar languages that once comprised a federation and that still retain the same curricular structure for medical education. One of the basic goals of the network is to advance medical teaching and learning with the use of modern information and communication technologies. We present the education portal AKUTNE.CZ as an important part of the MEFANET's content. Our focus is primarily on simulation-based tools for teaching and learning acute medicine issues. Three fundamental elements of the MEFANET e-publishing system are described: (1) medical disciplines linker, (2) authentication/authorization framework, and (3) multidimensional quality assessment. A new set of tools for technology-enhanced learning have been introduced recently: Sandbox (works in progress), WikiLectures (collaborative content authoring), Moodle-MEFANET (central learning management system), and Serious Games (virtual casuistics and interactive algorithms). The latest development in MEFANET is designed for indexing metadata about simulation-based learning objects, also known as electronic virtual patients or virtual clinical cases. The simulations assume the form of interactive algorithms for teaching and learning acute medicine. An anonymous questionnaire of 10 items was used to explore students' attitudes and interests in using the interactive algorithms as part of their medical or health care studies. Data collection was conducted over 10 days in February 2013. In total, 25 interactive algorithms in the Czech and English languages have been developed and published on the AKUTNE.CZ education portal to allow the users to test and improve their knowledge and skills in the field of acute medicine. In the feedback survey, 62 participants completed the online questionnaire (13.5%) from the total 460 addressed
Empirical Studies On Machine Learning Based Text Classification Algorithms
Shweta C. Dharmadhikari; Maya Ingle; Parag Kulkarni
2011-01-01
Automatic classification of text documents has become an important research issue now days. Properclassification of text documents requires information retrieval, machine learning and Natural languageprocessing (NLP) techniques. Our aim is to focus on important approaches to automatic textclassification based on machine learning techniques viz. supervised, unsupervised and semi supervised.In this paper we present a review of various text classification approaches under machine learningparadig...
A Weighted Block Dictionary Learning Algorithm for Classification
Shi, Zhongrong
2016-01-01
Discriminative dictionary learning, playing a critical role in sparse representation based classification, has led to state-of-the-art classification results. Among the existing discriminative dictionary learning methods, two different approaches, shared dictionary and class-specific dictionary, which associate each dictionary atom to all classes or a single class, have been studied. The shared dictionary is a compact method but with lack of discriminative information; the class-specific dict...
Automatic learning algorithm for the MD-logic artificial pancreas system.
Miller, Shahar; Nimri, Revital; Atlas, Eran; Grunberg, Eli A; Phillip, Moshe
2011-10-01
Applying real-time learning into an artificial pancreas system could effectively track the unpredictable behavior of glucose-insulin dynamics and adjust insulin treatment accordingly. We describe a novel learning algorithm and its performance when integrated into the MD-Logic Artificial Pancreas (MDLAP) system developed by the Diabetes Technology Center, Schneider Children's Medical Center of Israel, Petah Tikva, Israel. The algorithm was designed to establish an initial patient profile using open-loop data (Initial Learning Algorithm component) and then make periodic adjustments during closed-loop operation (Runtime Learning Algorithm component). The MDLAP system, integrated with the learning algorithm, was tested in seven different experiments using the University of Virginia/Padova simulator, comprising adults, adolescents, and children. The experiments included simulations using the open-loop and closed-loop control strategy under nominal and varying insulin sensitivity conditions. The learning algorithm was automatically activated at the end of the open-loop segment and after every day of the closed-loop operation. Metabolic control parameters achieved at selected time points were compared. The percentage of time glucose levels were maintained within 70-180 mg/dL for children and adolescents significantly improved when open-loop was compared with day 6 of closed-loop control (Psignificantly reduced by approximately sevenfold (Psignificant reduction in the Low Blood Glucose Index (P<0.001). The new algorithm was effective in characterizing the patient profiles from open-loop data and in adjusting treatment to provide better glycemic control during closed-loop control in both conditions. These findings warrant corroboratory clinical trials.
Beyond the "c" and the "x": Learning with algorithms in massive open online courses (MOOCs)
Knox, Jeremy
2018-02-01
This article examines how algorithms are shaping student learning in massive open online courses (MOOCs). Following the dramatic rise of MOOC platform organisations in 2012, over 4,500 MOOCs have been offered to date, in increasingly diverse languages, and with a growing requirement for fees. However, discussions of learning in MOOCs remain polarised around the "xMOOC" and "cMOOC" designations. In this narrative, the more recent extended or platform MOOC ("xMOOC") adopts a broadcast pedagogy, assuming a direct transmission of information to its largely passive audience (i.e. a teacher-centred approach), while the slightly older connectivist model ("cMOOC") offers only a simplistic reversal of the hierarchy, posing students as highly motivated, self-directed and collaborative learners (i.e. a learner-centred approach). The online nature of both models generates data (e.g. on how many times a particular resource was viewed, or the ways in which participants communicated with each other) which MOOC providers use for analysis, albeit only after these data have been selectively processed. Central to many learning analytics approaches is the desire to predict students' future behaviour. Educators need to be aware that MOOC learning is not just about teachers and students, but that it also involves algorithms: instructions which perform automated calculations on data. Education is becoming embroiled in an "algorithmic culture" that defines educational roles, forecasts attainment, and influences pedagogy. Established theories of learning appear wholly inadequate in addressing the agential role of algorithms in the educational domain of the MOOC. This article identifies and examines four key areas where algorithms influence the activities of the MOOC: (1) data capture and discrimination; (2) calculated learners; (3) feedback and entanglement; and (4) learning with algorithms. The article concludes with a call for further research in these areas to surface a critical
A fast and accurate online sequential learning algorithm for feedforward networks.
Liang, Nan-Ying; Huang, Guang-Bin; Saratchandran, P; Sundararajan, N
2006-11-01
In this paper, we develop an online sequential learning algorithm for single hidden layer feedforward networks (SLFNs) with additive or radial basis function (RBF) hidden nodes in a unified framework. The algorithm is referred to as online sequential extreme learning machine (OS-ELM) and can learn data one-by-one or chunk-by-chunk (a block of data) with fixed or varying chunk size. The activation functions for additive nodes in OS-ELM can be any bounded nonconstant piecewise continuous functions and the activation functions for RBF nodes can be any integrable piecewise continuous functions. In OS-ELM, the parameters of hidden nodes (the input weights and biases of additive nodes or the centers and impact factors of RBF nodes) are randomly selected and the output weights are analytically determined based on the sequentially arriving data. The algorithm uses the ideas of ELM of Huang et al. developed for batch learning which has been shown to be extremely fast with generalization performance better than other batch training methods. Apart from selecting the number of hidden nodes, no other control parameters have to be manually chosen. Detailed performance comparison of OS-ELM is done with other popular sequential learning algorithms on benchmark problems drawn from the regression, classification and time series prediction areas. The results show that the OS-ELM is faster than the other sequential algorithms and produces better generalization performance.
Super-resolution reconstruction of MR image with a novel residual learning network algorithm
Shi, Jun; Liu, Qingping; Wang, Chaofeng; Zhang, Qi; Ying, Shihui; Xu, Haoyu
2018-04-01
Spatial resolution is one of the key parameters of magnetic resonance imaging (MRI). The image super-resolution (SR) technique offers an alternative approach to improve the spatial resolution of MRI due to its simplicity. Convolutional neural networks (CNN)-based SR algorithms have achieved state-of-the-art performance, in which the global residual learning (GRL) strategy is now commonly used due to its effectiveness for learning image details for SR. However, the partial loss of image details usually happens in a very deep network due to the degradation problem. In this work, we propose a novel residual learning-based SR algorithm for MRI, which combines both multi-scale GRL and shallow network block-based local residual learning (LRL). The proposed LRL module works effectively in capturing high-frequency details by learning local residuals. One simulated MRI dataset and two real MRI datasets have been used to evaluate our algorithm. The experimental results show that the proposed SR algorithm achieves superior performance to all of the other compared CNN-based SR algorithms in this work.
Behavioral Profiling of Scada Network Traffic Using Machine Learning Algorithms
2014-03-27
Acquisition ( SCADA ) System Overview SCADA systems control and monitor processes for water distribution, oil and natural gas pipelines , electrical...the desire for remote control and monitoring of industrial processes. The ability to identify SCADA devices on a mixed traffic network with zero...optimal attribute subset, while maintaining the desired TPR of .99 for SCADA network traffic. The attributes and ML algorithms chosen for
The D313Y variant in the GLA gene - no evidence of a pathogenic role in Fabry disease
DEFF Research Database (Denmark)
Hasholt, Lis; Ballegaard, Martin; Bundgaard, Henning
2017-01-01
Fabry disease is an X- linked inherited lysosomal storage disease caused by mutations in the GLA gene encoding the lysosomal enzyme alpha-galactosidase A (α-Gal A). The possible pathological significance of the D313Y variant in the GLA gene has not been verified and it may be a Fabry variant. Our......, and the presence in Fabry females did not significantly enhance the phenotype of a known causative mutation in the GLA gene (G271S). Our findings indicate that the D313Y variant is not causative to nor enhancing Fabry disease phenotype. The D313Y variant in the GLA gene was not disease causative in 2 Danish...... families. Investigating male family members were crucial in excluding the Fabry phenotype, and thus very important for proper genetic counceling of all family members, as well as overdiagnosing a devastating genetic disease....
Asymmetric Variate Generation via a Parameterless Dual Neural Learning Algorithm
Directory of Open Access Journals (Sweden)
Simone Fiori
2008-01-01
Full Text Available In a previous work (S. Fiori, 2006, we proposed a random number generator based on a tunable non-linear neural system, whose learning rule is designed on the basis of a cardinal equation from statistics and whose implementation is based on look-up tables (LUTs. The aim of the present manuscript is to improve the above-mentioned random number generation method by changing the learning principle, while retaining the efficient LUT-based implementation. The new method proposed here proves easier to implement and relaxes some previous limitations.
International Nuclear Information System (INIS)
Liu, Hui; Tian, Hong-qi; Li, Yan-fei
2015-01-01
Highlights: • A hybrid architecture is proposed for the wind speed forecasting. • Four algorithms are used for the wind speed multi-scale decomposition. • The extreme learning machines are employed for the wind speed forecasting. • All the proposed hybrid models can generate the accurate results. - Abstract: Realization of accurate wind speed forecasting is important to guarantee the safety of wind power utilization. In this paper, a new hybrid forecasting architecture is proposed to realize the wind speed accurate forecasting. In this architecture, four different hybrid models are presented by combining four signal decomposing algorithms (e.g., Wavelet Decomposition/Wavelet Packet Decomposition/Empirical Mode Decomposition/Fast Ensemble Empirical Mode Decomposition) and Extreme Learning Machines. The originality of the study is to investigate the promoted percentages of the Extreme Learning Machines by those mainstream signal decomposing algorithms in the multiple step wind speed forecasting. The results of two forecasting experiments indicate that: (1) the method of Extreme Learning Machines is suitable for the wind speed forecasting; (2) by utilizing the decomposing algorithms, all the proposed hybrid algorithms have better performance than the single Extreme Learning Machines; (3) in the comparisons of the decomposing algorithms in the proposed hybrid architecture, the Fast Ensemble Empirical Mode Decomposition has the best performance in the three-step forecasting results while the Wavelet Packet Decomposition has the best performance in the one and two step forecasting results. At the same time, the Wavelet Packet Decomposition and the Fast Ensemble Empirical Mode Decomposition are better than the Wavelet Decomposition and the Empirical Mode Decomposition in all the step predictions, respectively; and (4) the proposed algorithms are effective in the wind speed accurate predictions
A New Fuzzy Cognitive Map Learning Algorithm for Speech Emotion Recognition
Zhang, Wei; Zhang, Xueying; Sun, Ying
2017-01-01
Selecting an appropriate recognition method is crucial in speech emotion recognition applications. However, the current methods do not consider the relationship between emotions. Thus, in this study, a speech emotion recognition system based on the fuzzy cognitive map (FCM) approach is constructed. Moreover, a new FCM learning algorithm for speech emotion recognition is proposed. This algorithm includes the use of the pleasure-arousal-dominance emotion scale to calculate the weights between e...
CAT-PUMA: CME Arrival Time Prediction Using Machine learning Algorithms
Liu, Jiajia; Ye, Yudong; Shen, Chenglong; Wang, Yuming; Erdélyi, Robert
2018-04-01
CAT-PUMA (CME Arrival Time Prediction Using Machine learning Algorithms) quickly and accurately predicts the arrival of Coronal Mass Ejections (CMEs) of CME arrival time. The software was trained via detailed analysis of CME features and solar wind parameters using 182 previously observed geo-effective partial-/full-halo CMEs and uses algorithms of the Support Vector Machine (SVM) to make its predictions, which can be made within minutes of providing the necessary input parameters of a CME.
A review of recent research on improvement of physical parameterizations in the GLA GCM
Sud, Y. C.; Walker, G. K.
1990-01-01
A systematic assessment of the effect of a series of improvements in physical parameterizations of the Goddard Laboratory for Atmospheres (GLA) general circulation model (GCM) are summarized. The implementation of the Simple Biosphere Model (SiB) in the GCM is followed by a comparison of SiB GCM simulations with that of the earlier slab soil hydrology GCM (SSH-GCM) simulations. In the Sahelian context, the biogeophysical component of desertification was analyzed for SiB-GCM simulations. Cumulus parameterization is found to be the primary determinant of the organization of the simulated tropical rainfall of the GLA GCM using Arakawa-Schubert cumulus parameterization. A comparison of model simulations with station data revealed excessive shortwave radiation accompanied by excessive drying and heating to the land. The perpetual July simulations with and without interactive soil moisture shows that 30 to 40 day oscillations may be a natural mode of the simulated earth atmosphere system.
Good Life with osteoArthritis in Denmark (GLA:D™)
DEFF Research Database (Denmark)
Skou, Søren Thorgaard; Roos, Ewa M.
2017-01-01
BACKGROUND: The uptake of evidence-based guidelines in clinical practice is suboptimal in osteoarthritis (OA) and other chronic diseases. Good Life with osteoArthritis in Denmark (GLA:D) was launched in 2013 with the aim of implementing guidelines for the treatment of knee and hip OA in clinical...... disability and Osteoarthritis Outcome Score (HOOS) quality of life subscale, 0-100, worst to best), number of patients on painkillers and sick leave, and access to care according to guidelines. RESULTS: Data from 9,825 participants from the GLA:D registry were utilised in the analyses. It was demonstrated...... months are pain intensity (0 to 100, best to worst), objective physical function (30-s chair-stand test and 40-m fast-paced walk test), physical activity (number of days per week being physically active for at least 30 min), quality of life (Knee injury and Osteoarthritis Outcome Score (KOOS) and the Hip...
International Nuclear Information System (INIS)
Kim, Dong Yun; Seong, Poong Hyun
1996-01-01
In this study, we proposed a fuzzy gain scheduler with intelligent learning algorithm for a reactor control. In the proposed algorithm, we used the gradient descent method to learn the rule bases of a fuzzy algorithm. These rule bases are learned toward minimizing an objective function, which is called a performance cost function. The objective of fuzzy gain scheduler with intelligent learning algorithm is the generation of adequate gains, which minimize the error of system. The condition of every plant is generally changed as time gose. That is, the initial gains obtained through the analysis of system are no longer suitable for the changed plant. And we need to set new gains, which minimize the error stemmed from changing the condition of a plant. In this paper, we applied this strategy for reactor control of nuclear power plant (NPP), and the results were compared with those of a simple PI controller, which has fixed gains. As a result, it was shown that the proposed algorithm was superior to the simple PI controller
Bisele, Maria; Bencsik, Martin; Lewis, Martin G C; Barnett, Cleveland T
2017-01-01
Assessment methods in human locomotion often involve the description of normalised graphical profiles and/or the extraction of discrete variables. Whilst useful, these approaches may not represent the full complexity of gait data. Multivariate statistical methods, such as Principal Component Analysis (PCA) and Discriminant Function Analysis (DFA), have been adopted since they have the potential to overcome these data handling issues. The aim of the current study was to develop and optimise a specific machine learning algorithm for processing human locomotion data. Twenty participants ran at a self-selected speed across a 15m runway in barefoot and shod conditions. Ground reaction forces (BW) and kinematics were measured at 1000 Hz and 100 Hz, respectively from which joint angles (°), joint moments (N.m.kg-1) and joint powers (W.kg-1) for the hip, knee and ankle joints were calculated in all three anatomical planes. Using PCA and DFA, power spectra of the kinematic and kinetic variables were used as a training database for the development of a machine learning algorithm. All possible combinations of 10 out of 20 participants were explored to find the iteration of individuals that would optimise the machine learning algorithm. The results showed that the algorithm was able to successfully predict whether a participant ran shod or barefoot in 93.5% of cases. To the authors' knowledge, this is the first study to optimise the development of a machine learning algorithm.
An Improved Brain-Inspired Emotional Learning Algorithm for Fast Classification
Directory of Open Access Journals (Sweden)
Ying Mei
2017-06-01
Full Text Available Classification is an important task of machine intelligence in the field of information. The artificial neural network (ANN is widely used for classification. However, the traditional ANN shows slow training speed, and it is hard to meet the real-time requirement for large-scale applications. In this paper, an improved brain-inspired emotional learning (BEL algorithm is proposed for fast classification. The BEL algorithm was put forward to mimic the high speed of the emotional learning mechanism in mammalian brain, which has the superior features of fast learning and low computational complexity. To improve the accuracy of BEL in classification, the genetic algorithm (GA is adopted for optimally tuning the weights and biases of amygdala and orbitofrontal cortex in the BEL neural network. The combinational algorithm named as GA-BEL has been tested on eight University of California at Irvine (UCI datasets and two well-known databases (Japanese Female Facial Expression, Cohn–Kanade. The comparisons of experiments indicate that the proposed GA-BEL is more accurate than the original BEL algorithm, and it is much faster than the traditional algorithm.
SVC control enhancement applying self-learning fuzzy algorithm for islanded microgrid
Directory of Open Access Journals (Sweden)
Hossam Gabbar
2016-03-01
Full Text Available Maintaining voltage stability, within acceptable levels, for islanded Microgrids (MGs is a challenge due to limited exchange power between generation and loads. This paper proposes an algorithm to enhance the dynamic performance of islanded MGs in presence of load disturbance using Static VAR Compensator (SVC with Fuzzy Model Reference Learning Controller (FMRLC. The proposed algorithm compensates MG nonlinearity via fuzzy membership functions and inference mechanism imbedded in both controller and inverse model. Hence, MG keeps the desired performance as required at any operating condition. Furthermore, the self-learning capability of the proposed control algorithm compensates for grid parameter’s variation even with inadequate information about load dynamics. A reference model was designed to reject bus voltage disturbance with achievable performance by the proposed fuzzy controller. Three simulations scenarios have been presented to investigate effectiveness of proposed control algorithm in improving steady-state and transient performance of islanded MGs. The first scenario conducted without SVC, second conducted with SVC using PID controller and third conducted using FMRLC algorithm. A comparison for results shows ability of proposed control algorithm to enhance disturbance rejection due to learning process.
Indian Academy of Sciences (India)
algorithm design technique called 'divide-and-conquer'. One of ... Turtle graphics, September. 1996. 5. ... whole list named 'PO' is a pointer to the first element of the list; ..... Program for computing matrices X and Y and placing the result in C *).
Indian Academy of Sciences (India)
algorithm that it is implicitly understood that we know how to generate the next natural ..... Explicit comparisons are made in line (1) where maximum and minimum is ... It can be shown that the function T(n) = 3/2n -2 is the solution to the above ...
Extracting quantum dynamics from genetic learning algorithms through principal control analysis
International Nuclear Information System (INIS)
White, J L; Pearson, B J; Bucksbaum, P H
2004-01-01
Genetic learning algorithms are widely used to control ultrafast optical pulse shapes for photo-induced quantum control of atoms and molecules. An unresolved issue is how to use the solutions found by these algorithms to learn about the system's quantum dynamics. We propose a simple method based on covariance analysis of the control space, which can reveal the degrees of freedom in the effective control Hamiltonian. We have applied this technique to stimulated Raman scattering in liquid methanol. A simple model of two-mode stimulated Raman scattering is consistent with the results. (letter to the editor)
Forecasting with Universal Approximators and a Learning Algorithm
DEFF Research Database (Denmark)
Kock, Anders Bredahl
2011-01-01
to the performance of the best single model in the set of models combined from. The use of universal approximators along with a combination scheme for which explicit loss bounds exist should give a solid theoretical foundation to the way the forecasts are performed. The practical performance will be investigated...... combination has a long history in econometrics focus has not been on proving loss bounds for the combination rules applied. We apply the Weighted Average Algorithm (WAA) of Kivinen & Warmuth (1999) for which such loss bounds exist. Specifically, one can bound the worst case performance of the WAA compared...
Forecasting with Universal Approximators and a Learning Algorithm
DEFF Research Database (Denmark)
Kock, Anders Bredahl
bounds for the combination rules applied. We apply the Weighted Average Algorithm (WAA) of Kivinen and Warmuth (1999) for which such loss bounds exist. Specifically, one can bound the worst case performance of the WAA compared to the performance of the best single model in the set of models combined from....... The use of universal approximators along with a combination scheme for which explicit loss bounds exist should give a solid theoretical foundation to the way the forecasts are performed. The practical performance will be investigated by considering various monthly postwar macroeconomic data sets for the G...
Niazmardi, S.; Safari, A.; Homayouni, S.
2017-09-01
Crop mapping through classification of Satellite Image Time-Series (SITS) data can provide very valuable information for several agricultural applications, such as crop monitoring, yield estimation, and crop inventory. However, the SITS data classification is not straightforward. Because different images of a SITS data have different levels of information regarding the classification problems. Moreover, the SITS data is a four-dimensional data that cannot be classified using the conventional classification algorithms. To address these issues in this paper, we presented a classification strategy based on Multiple Kernel Learning (MKL) algorithms for SITS data classification. In this strategy, initially different kernels are constructed from different images of the SITS data and then they are combined into a composite kernel using the MKL algorithms. The composite kernel, once constructed, can be used for the classification of the data using the kernel-based classification algorithms. We compared the computational time and the classification performances of the proposed classification strategy using different MKL algorithms for the purpose of crop mapping. The considered MKL algorithms are: MKL-Sum, SimpleMKL, LPMKL and Group-Lasso MKL algorithms. The experimental tests of the proposed strategy on two SITS data sets, acquired by SPOT satellite sensors, showed that this strategy was able to provide better performances when compared to the standard classification algorithm. The results also showed that the optimization method of the used MKL algorithms affects both the computational time and classification accuracy of this strategy.
Yuldashev, M. N.; Vlasov, A. I.; Novikov, A. N.
2018-05-01
This paper focuses on the development of an energy-efficient algorithm for classification of states of a wireless sensor network using machine learning methods. The proposed algorithm reduces energy consumption by: 1) elimination of monitoring of parameters that do not affect the state of the sensor network, 2) reduction of communication sessions over the network (the data are transmitted only if their values can affect the state of the sensor network). The studies of the proposed algorithm have shown that at classification accuracy close to 100%, the number of communication sessions can be reduced by 80%.
A method for classification of network traffic based on C5.0 Machine Learning Algorithm
DEFF Research Database (Denmark)
Bujlow, Tomasz; Riaz, M. Tahir; Pedersen, Jens Myrup
2012-01-01
current network traffic. To overcome the drawbacks of existing methods for traffic classification, usage of C5.0 Machine Learning Algorithm (MLA) was proposed. On the basis of statistical traffic information received from volunteers and C5.0 algorithm we constructed a boosted classifier, which was shown...... and classification, an algorithm for recognizing flow direction and the C5.0 itself. Classified applications include Skype, FTP, torrent, web browser traffic, web radio, interactive gaming and SSH. We performed subsequent tries using different sets of parameters and both training and classification options...
A new evolutionary algorithm with LQV learning for combinatorial problems optimization
International Nuclear Information System (INIS)
Machado, Marcelo Dornellas; Schirru, Roberto
2000-01-01
Genetic algorithms are biologically motivated adaptive systems which have been used, with good results, for combinatorial problems optimization. In this work, a new learning mode, to be used by the population-based incremental learning algorithm, has the aim to build a new evolutionary algorithm to be used in optimization of numerical problems and combinatorial problems. This new learning mode uses a variable learning rate during the optimization process, constituting a process known as proportional reward. The development of this new algorithm aims its application in the optimization of reload problem of PWR nuclear reactors, in order to increase the useful life of the nuclear fuel. For the test, two classes of problems are used: numerical problems and combinatorial problems. Due to the fact that the reload problem is a combinatorial problem, the major interest relies on the last class. The results achieved with the tests indicate the applicability of the new learning mode, showing its potential as a developing tool in the solution of reload problem. (author)
A Probability-based Evolutionary Algorithm with Mutations to Learn Bayesian Networks
Directory of Open Access Journals (Sweden)
Sho Fukuda
2014-12-01
Full Text Available Bayesian networks are regarded as one of the essential tools to analyze causal relationship between events from data. To learn the structure of highly-reliable Bayesian networks from data as quickly as possible is one of the important problems that several studies have been tried to achieve. In recent years, probability-based evolutionary algorithms have been proposed as a new efficient approach to learn Bayesian networks. In this paper, we target on one of the probability-based evolutionary algorithms called PBIL (Probability-Based Incremental Learning, and propose a new mutation operator. Through performance evaluation, we found that the proposed mutation operator has a good performance in learning Bayesian networks
The Design and Analysis of Efficient Learning Algorithms
1991-01-01
31] describe in detail how this can be done efficiently; see also Duda and Hart [22]. Let a&,..., &d be the resulting solution, and let h0 = Fd=1 af...Measure. Wiley, second edition, 1986. [13] Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, and Manfred K. Warmuth. Occam’s razor. Information...Processing Letters, 24(6):377-380, April 1987. [14] Anselm Blumer, Andrzej Ehrenfeucht, David Haussler, and Manfred K. Warmuth. Learn- ability and the
Prediction of Employee Turnover in Organizations using Machine Learning Algorithms
Rohit Punnoose; Pankaj Ajit
2016-01-01
Employee turnover has been identified as a key issue for organizations because of its adverse impact on work place productivity and long term growth strategies. To solve this problem, organizations use machine learning techniques to predict employee turnover. Accurate predictions enable organizations to take action for retention or succession planning of employees. However, the data for this modeling problem comes from HR Information Systems (HRIS); these are typically under-funded compared t...
Learning Activity Predictors from Sensor Data: Algorithms, Evaluation, and Applications.
Minor, Bryan; Doppa, Janardhan Rao; Cook, Diane J
2017-12-01
Recent progress in Internet of Things (IoT) platforms has allowed us to collect large amounts of sensing data. However, there are significant challenges in converting this large-scale sensing data into decisions for real-world applications. Motivated by applications like health monitoring and intervention and home automation we consider a novel problem called Activity Prediction , where the goal is to predict future activity occurrence times from sensor data. In this paper, we make three main contributions. First, we formulate and solve the activity prediction problem in the framework of imitation learning and reduce it to a simple regression learning problem. This approach allows us to leverage powerful regression learners that can reason about the relational structure of the problem with negligible computational overhead. Second, we present several metrics to evaluate activity predictors in the context of real-world applications. Third, we evaluate our approach using real sensor data collected from 24 smart home testbeds. We also embed the learned predictor into a mobile-device-based activity prompter and evaluate the app for 9 participants living in smart homes. Our results indicate that our activity predictor performs better than the baseline methods, and offers a simple approach for predicting activities from sensor data.
Machine Learning Algorithms for $b$-Jet Tagging at the ATLAS Experiment
Paganini, Michela; The ATLAS collaboration
2017-01-01
The separation of $b$-quark initiated jets from those coming from lighter quark flavors ($b$-tagging) is a fundamental tool for the ATLAS physics program at the CERN Large Hadron Collider. The most powerful $b$-tagging algorithms combine information from low-level taggers, exploiting reconstructed track and vertex information, into machine learning classifiers. The potential of modern deep learning techniques is explored using simulated events, and compared to that achievable from more traditional classifiers such as boosted decision trees.
Cheng, Hong
2015-01-01
This unique text/reference presents a comprehensive review of the state of the art in sparse representations, modeling and learning. The book examines both the theoretical foundations and details of algorithm implementation, highlighting the practical application of compressed sensing research in visual recognition and computer vision. Topics and features: provides a thorough introduction to the fundamentals of sparse representation, modeling and learning, and the application of these techniques in visual recognition; describes sparse recovery approaches, robust and efficient sparse represen
Indian Academy of Sciences (India)
will become clear in the next article when we discuss a simple logo like programming language. ... Rod B may be used as an auxiliary store. The problem is to find an algorithm which performs this task. ... No disks are moved from A to Busing C as auxiliary rod. • move _disk (A, C);. (No + l)th disk is moved from A to C directly ...
International Nuclear Information System (INIS)
Roche-Lima, Abiel; Thulasiram, Ruppa K
2012-01-01
Finite automata, in which each transition is augmented with an output label in addition to the familiar input label, are considered finite-state transducers. Transducers have been used to analyze some fundamental issues in bioinformatics. Weighted finite-state transducers have been proposed to pairwise alignments of DNA and protein sequences; as well as to develop kernels for computational biology. Machine learning algorithms for conditional transducers have been implemented and used for DNA sequence analysis. Transducer learning algorithms are based on conditional probability computation. It is calculated by using techniques, such as pair-database creation, normalization (with Maximum-Likelihood normalization) and parameters optimization (with Expectation-Maximization - EM). These techniques are intrinsically costly for computation, even worse when are applied to bioinformatics, because the databases sizes are large. In this work, we describe a parallel implementation of an algorithm to learn conditional transducers using these techniques. The algorithm is oriented to bioinformatics applications, such as alignments, phylogenetic trees, and other genome evolution studies. Indeed, several experiences were developed using the parallel and sequential algorithm on Westgrid (specifically, on the Breeze cluster). As results, we obtain that our parallel algorithm is scalable, because execution times are reduced considerably when the data size parameter is increased. Another experience is developed by changing precision parameter. In this case, we obtain smaller execution times using the parallel algorithm. Finally, number of threads used to execute the parallel algorithm on the Breezy cluster is changed. In this last experience, we obtain as result that speedup is considerably increased when more threads are used; however there is a convergence for number of threads equal to or greater than 16.
Machine learning algorithms to classify spinal muscular atrophy subtypes.
Srivastava, Tuhin; Darras, Basil T; Wu, Jim S; Rutkove, Seward B
2012-07-24
The development of better biomarkers for disease assessment remains an ongoing effort across the spectrum of neurologic illnesses. One approach for refining biomarkers is based on the concept of machine learning, in which individual, unrelated biomarkers are simultaneously evaluated. In this cross-sectional study, we assess the possibility of using machine learning, incorporating both quantitative muscle ultrasound (QMU) and electrical impedance myography (EIM) data, for classification of muscles affected by spinal muscular atrophy (SMA). Twenty-one normal subjects, 15 subjects with SMA type 2, and 10 subjects with SMA type 3 underwent EIM and QMU measurements of unilateral biceps, wrist extensors, quadriceps, and tibialis anterior. EIM and QMU parameters were then applied in combination using a support vector machine (SVM), a type of machine learning, in an attempt to accurately categorize 165 individual muscles. For all 3 classification problems, normal vs SMA, normal vs SMA 3, and SMA 2 vs SMA 3, use of SVM provided the greatest accuracy in discrimination, surpassing both EIM and QMU individually. For example, the accuracy, as measured by the receiver operating characteristic area under the curve (ROC-AUC) for the SVM discriminating SMA 2 muscles from SMA 3 muscles was 0.928; in comparison, the ROC-AUCs for EIM and QMU parameters alone were only 0.877 (p < 0.05) and 0.627 (p < 0.05), respectively. Combining EIM and QMU data categorizes individual SMA-affected muscles with very high accuracy. Further investigation of this approach for classifying and for following the progression of neuromuscular illness is warranted.
LMS learning algorithms: misconceptions and new results on converence.
Wang, Z Q; Manry, M T; Schiano, J L
2000-01-01
The Widrow-Hoff delta rule is one of the most popular rules used in training neural networks. It was originally proposed for the ADALINE, but has been successfully applied to a few nonlinear neural networks as well. Despite its popularity, there exist a few misconceptions on its convergence properties. In this paper we consider repetitive learning (i.e., a fixed set of samples are used for training) and provide an in-depth analysis in the least mean square (LMS) framework. Our main result is that contrary to common belief, the nonbatch Widrow-Hoff rule does not converge in general. It converges only to a limit cycle.
Algorithms for Learning Preferences for Sets of Objects
Wagstaff, Kiri L.; desJardins, Marie; Eaton, Eric
2010-01-01
A method is being developed that provides for an artificial-intelligence system to learn a user's preferences for sets of objects and to thereafter automatically select subsets of objects according to those preferences. The method was originally intended to enable automated selection, from among large sets of images acquired by instruments aboard spacecraft, of image subsets considered to be scientifically valuable enough to justify use of limited communication resources for transmission to Earth. The method is also applicable to other sets of objects: examples of sets of objects considered in the development of the method include food menus, radio-station music playlists, and assortments of colored blocks for creating mosaics. The method does not require the user to perform the often-difficult task of quantitatively specifying preferences; instead, the user provides examples of preferred sets of objects. This method goes beyond related prior artificial-intelligence methods for learning which individual items are preferred by the user: this method supports a concept of setbased preferences, which include not only preferences for individual items but also preferences regarding types and degrees of diversity of items in a set. Consideration of diversity in this method involves recognition that members of a set may interact with each other in the sense that when considered together, they may be regarded as being complementary, redundant, or incompatible to various degrees. The effects of such interactions are loosely summarized in the term portfolio effect. The learning method relies on a preference representation language, denoted DD-PREF, to express set-based preferences. In DD-PREF, a preference is represented by a tuple that includes quality (depth) functions to estimate how desired a specific value is, weights for each feature preference, the desired diversity of feature values, and the relative importance of diversity versus depth. The system applies statistical
Energy Technology Data Exchange (ETDEWEB)
Aziz, H. M. Abdul [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Zhu, Feng [Purdue University, West Lafayette, IN (United States). Lyles School of Civil Engineering; Ukkusuri, Satish V. [Purdue University, West Lafayette, IN (United States). Lyles School of Civil Engineering
2017-10-04
Here, this research applies R-Markov Average Reward Technique based reinforcement learning (RL) algorithm, namely RMART, for vehicular signal control problem leveraging information sharing among signal controllers in connected vehicle environment. We implemented the algorithm in a network of 18 signalized intersections and compare the performance of RMART with fixed, adaptive, and variants of the RL schemes. Results show significant improvement in system performance for RMART algorithm with information sharing over both traditional fixed signal timing plans and real time adaptive control schemes. Additionally, the comparison with reinforcement learning algorithms including Q learning and SARSA indicate that RMART performs better at higher congestion levels. Further, a multi-reward structure is proposed that dynamically adjusts the reward function with varying congestion states at the intersection. Finally, the results from test networks show significant reduction in emissions (CO, CO_{2}, NO_{x}, VOC, PM_{10}) when RL algorithms are implemented compared to fixed signal timings and adaptive schemes.
A learning algorithm for oscillatory cellular neural networks.
Ho, C Y.; Kurokawa, H
1999-07-01
We present a cellular type oscillatory neural network for temporal segregation of stationary input patterns. The model comprises an array of locally connected neural oscillators with connections limited to a 4-connected neighborhood. The architecture is reminiscent of the well-known cellular neural network that consists of local connection for feature extraction. By means of a novel learning rule and an initialization scheme, global synchronization can be accomplished without incurring any erroneous synchrony among uncorrelated objects. Each oscillator comprises two mutually coupled neurons, and neurons share a piecewise-linear activation function characteristic. The dynamics of traditional oscillatory models is simplified by using only one plastic synapse, and the overall complexity for hardware implementation is reduced. Based on the connectedness of image segments, it is shown that global synchronization and desynchronization can be achieved by means of locally connected synapses, and this opens up a tremendous application potential for the proposed architecture. Furthermore, by using special grouping synapses it is demonstrated that temporal segregation of overlapping gray-level and color segments can also be achieved. Finally, simulation results show that the learning rule proposed circumvents the problem of component mismatches, and hence facilitates a large-scale integration.
Application of Machine Learning Algorithms for the Query Performance Prediction
Directory of Open Access Journals (Sweden)
MILICEVIC, M.
2015-08-01
Full Text Available This paper analyzes the relationship between the system load/throughput and the query response time in a real Online transaction processing (OLTP system environment. Although OLTP systems are characterized by short transactions, which normally entail high availability and consistent short response times, the need for operational reporting may jeopardize these objectives. We suggest a new approach to performance prediction for concurrent database workloads, based on the system state vector which consists of 36 attributes. There is no bias to the importance of certain attributes, but the machine learning methods are used to determine which attributes better describe the behavior of the particular database server and how to model that system. During the learning phase, the system's profile is created using multiple reference queries, which are selected to represent frequent business processes. The possibility of the accurate response time prediction may be a foundation for automated decision-making for database (DB query scheduling. Possible applications of the proposed method include adaptive resource allocation, quality of service (QoS management or real-time dynamic query scheduling (e.g. estimation of the optimal moment for a complex query execution.
Think big: learning contexts, algorithms and data science
Directory of Open Access Journals (Sweden)
Baldassarre Michele
2016-12-01
Full Text Available Due to the increasing growth in available data in recent years, all areas of research and the managements of institutions and organisations, specifically schools and universities, feel the need to give meaning to this availability of data. This article, after a brief reference to the definition of big data, intends to focus attention and reflection on their type to proceed to an extension of their characterisation. One of the hubs to make feasible the use of Big Data in operational contexts is to give a theoretical basis to which to refer. The Data, Information, Knowledge and Wisdom (DIKW model correlates these four aspects, concluding in Data Science, which in many ways could revolutionise the established pattern of scientific investigation. The Learning Analytics applications on online learning platforms can be tools for evaluating the quality of teaching. And that is where some problems arise. It becomes necessary to handle with care the available data. Finally, a criterion for deciding whether it makes sense to think of an analysis based on Big Data can be to think about the interpretability and relevance in relation to both institutional and personal processes.
DEFF Research Database (Denmark)
Yoo, C.; Gernaey, Krist
2008-01-01
importance in the projection (VIP) information of the DPLS method. The power of the gene selection method and the proposed supervised hierarchical clustering method is illustrated on a three microarray data sets of leukemia, breast, and colon cancer. Supervised machine learning algorithms thus enable...
Evaluation of a Didactic Method for the Active Learning of Greedy Algorithms
Esteban-Sánchez, Natalia; Pizarro, Celeste; Velázquez-Iturbide, J. Ángel
2014-01-01
An evaluation of the educational effectiveness of a didactic method for the active learning of greedy algorithms is presented. The didactic method sets students structured-inquiry challenges to be addressed with a specific experimental method, supported by the interactive system GreedEx. This didactic method has been refined over several years of…
Using machine learning algorithms to guide rehabilitation planning for home care clients.
Zhu, Mu; Zhang, Zhanyang; Hirdes, John P; Stolee, Paul
2007-12-20
Targeting older clients for rehabilitation is a clinical challenge and a research priority. We investigate the potential of machine learning algorithms - Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) - to guide rehabilitation planning for home care clients. This study is a secondary analysis of data on 24,724 longer-term clients from eight home care programs in Ontario. Data were collected with the RAI-HC assessment system, in which the Activities of Daily Living Clinical Assessment Protocol (ADLCAP) is used to identify clients with rehabilitation potential. For study purposes, a client is defined as having rehabilitation potential if there was: i) improvement in ADL functioning, or ii) discharge home. SVM and KNN results are compared with those obtained using the ADLCAP. For comparison, the machine learning algorithms use the same functional and health status indicators as the ADLCAP. The KNN and SVM algorithms achieved similar substantially improved performance over the ADLCAP, although false positive and false negative rates were still fairly high (FP > .18, FN > .34 versus FP > .29, FN. > .58 for ADLCAP). Results are used to suggest potential revisions to the ADLCAP. Machine learning algorithms achieved superior predictions than the current protocol. Machine learning results are less readily interpretable, but can also be used to guide development of improved clinical protocols.
A semi-learning algorithm for noise rejection: an fNIRS study on ADHD children
Sutoko, Stephanie; Funane, Tsukasa; Katura, Takusige; Sato, Hiroki; Kiguchi, Masashi; Maki, Atsushi; Monden, Yukifumi; Nagashima, Masako; Yamagata, Takanori; Dan, Ippeita
2017-02-01
In pediatrics studies, the quality of functional near infrared spectroscopy (fNIRS) signals is often reduced by motion artifacts. These artifacts likely mislead brain functionality analysis, causing false discoveries. While noise correction methods and their performance have been investigated, these methods require several parameter assumptions that apparently result in noise overfitting. In contrast, the rejection of noisy signals serves as a preferable method because it maintains the originality of the signal waveform. Here, we describe a semi-learning algorithm to detect and eliminate noisy signals. The algorithm dynamically adjusts noise detection according to the predetermined noise criteria, which are spikes, unusual activation values (averaged amplitude signals within the brain activation period), and high activation variances (among trials). Criteria were sequentially organized in the algorithm and orderly assessed signals based on each criterion. By initially setting an acceptable rejection rate, particular criteria causing excessive data rejections are neglected, whereas others with tolerable rejections practically eliminate noises. fNIRS data measured during the attention response paradigm (oddball task) in children with attention deficit/hyperactivity disorder (ADHD) were utilized to evaluate and optimize the algorithm's performance. This algorithm successfully substituted the visual noise identification done in the previous studies and consistently found significantly lower activation of the right prefrontal and parietal cortices in ADHD patients than in typical developing children. Thus, we conclude that the semi-learning algorithm confers more objective and standardized judgment for noise rejection and presents a promising alternative to visual noise rejection
Directory of Open Access Journals (Sweden)
C. Sunil Kumar
2014-07-01
Full Text Available Automation of descriptive answers evaluation is the need of the hour because of the huge increase in the number of students enrolling each year in educational institutions and the limited staff available to spare their time for evaluations. In this paper, we use a machine learning workbench called LightSIDE to accomplish auto evaluation and scoring of descriptive answers. We attempted to identify the best supervised machine learning algorithm given a limited training set sample size scenario. We evaluated performances of Bayes, SVM, Logistic Regression, Random forests, Decision stump and Decision trees algorithms. We confirmed SVM as best performing algorithm based on quantitative measurements across accuracy, kappa, training speed and prediction accuracy with supplied test set.
Directory of Open Access Journals (Sweden)
A. A. Salama
2015-03-01
Full Text Available In this paper, we present a review of different recommender system algorithms that are utilized in social networks based e-Learning systems. Future research will include our proposed our e-Learning system that utilizes Recommender System and Social Network. Since the world is full of indeterminacy, the neutrosophics found their place into contemporary research. The fundamental concepts of neutrosophic set, introduced by Smarandache in [21, 22, 23] and Salama et al. in [24-66].The purpose of this paper is to utilize a neutrosophic set to analyze social networks data conducted through learning activities.
Efficient Online Learning Algorithms Based on LSTM Neural Networks.
Ergen, Tolga; Kozat, Suleyman Serdar
2017-09-13
We investigate online nonlinear regression and introduce novel regression structures based on the long short term memory (LSTM) networks. For the introduced structures, we also provide highly efficient and effective online training methods. To train these novel LSTM-based structures, we put the underlying architecture in a state space form and introduce highly efficient and effective particle filtering (PF)-based updates. We also provide stochastic gradient descent and extended Kalman filter-based updates. Our PF-based training method guarantees convergence to the optimal parameter estimation in the mean square error sense provided that we have a sufficient number of particles and satisfy certain technical conditions. More importantly, we achieve this performance with a computational complexity in the order of the first-order gradient-based methods by controlling the number of particles. Since our approach is generic, we also introduce a gated recurrent unit (GRU)-based approach by directly replacing the LSTM architecture with the GRU architecture, where we demonstrate the superiority of our LSTM-based approach in the sequential prediction task via different real life data sets. In addition, the experimental results illustrate significant performance improvements achieved by the introduced algorithms with respect to the conventional methods over several different benchmark real life data sets.
A stochastic learning algorithm for layered neural networks
International Nuclear Information System (INIS)
Bartlett, E.B.; Uhrig, R.E.
1992-01-01
The random optimization method typically uses a Gaussian probability density function (PDF) to generate a random search vector. In this paper the random search technique is applied to the neural network training problem and is modified to dynamically seek out the optimal probability density function (OPDF) from which to select the search vector. The dynamic OPDF search process, combined with an auto-adaptive stratified sampling technique and a dynamic node architecture (DNA) learning scheme, completes the modifications of the basic method. The DNA technique determines the appropriate number of hidden nodes needed for a given training problem. By using DNA, researchers do not have to set the neural network architectures before training is initiated. The approach is applied to networks of generalized, fully interconnected, continuous perceptions. Computer simulation results are given
Computational Modeling of Teaching and Learning through Application of Evolutionary Algorithms
Directory of Open Access Journals (Sweden)
Richard Lamb
2015-09-01
Full Text Available Within the mind, there are a myriad of ideas that make sense within the bounds of everyday experience, but are not reflective of how the world actually exists; this is particularly true in the domain of science. Classroom learning with teacher explanation are a bridge through which these naive understandings can be brought in line with scientific reality. The purpose of this paper is to examine how the application of a Multiobjective Evolutionary Algorithm (MOEA can work in concert with an existing computational-model to effectively model critical-thinking in the science classroom. An evolutionary algorithm is an algorithm that iteratively optimizes machine learning based computational models. The research question is, does the application of an evolutionary algorithm provide a means to optimize the Student Task and Cognition Model (STAC-M and does the optimized model sufficiently represent and predict teaching and learning outcomes in the science classroom? Within this computational study, the authors outline and simulate the effect of teaching on the ability of a “virtual” student to solve a Piagetian task. Using the Student Task and Cognition Model (STAC-M a computational model of student cognitive processing in science class developed in 2013, the authors complete a computational experiment which examines the role of cognitive retraining on student learning. Comparison of the STAC-M and the STAC-M with inclusion of the Multiobjective Evolutionary Algorithm shows greater success in solving the Piagetian science-tasks post cognitive retraining with the Multiobjective Evolutionary Algorithm. This illustrates the potential uses of cognitive and neuropsychological computational modeling in educational research. The authors also outline the limitations and assumptions of computational modeling.
Gaur, Pallavi; Chaturvedi, Anoop
2017-07-22
The clustering pattern and motifs give immense information about any biological data. An application of machine learning algorithms for clustering and candidate motif detection in miRNAs derived from exosomes is depicted in this paper. Recent progress in the field of exosome research and more particularly regarding exosomal miRNAs has led much bioinformatic-based research to come into existence. The information on clustering pattern and candidate motifs in miRNAs of exosomal origin would help in analyzing existing, as well as newly discovered miRNAs within exosomes. Along with obtaining clustering pattern and candidate motifs in exosomal miRNAs, this work also elaborates the usefulness of the machine learning algorithms that can be efficiently used and executed on various programming languages/platforms. Data were clustered and sequence candidate motifs were detected successfully. The results were compared and validated with some available web tools such as 'BLASTN' and 'MEME suite'. The machine learning algorithms for aforementioned objectives were applied successfully. This work elaborated utility of machine learning algorithms and language platforms to achieve the tasks of clustering and candidate motif detection in exosomal miRNAs. With the information on mentioned objectives, deeper insight would be gained for analyses of newly discovered miRNAs in exosomes which are considered to be circulating biomarkers. In addition, the execution of machine learning algorithms on various language platforms gives more flexibility to users to try multiple iterations according to their requirements. This approach can be applied to other biological data-mining tasks as well.
Efficient Actor-Critic Algorithm with Hierarchical Model Learning and Planning
Fu, QiMing
2016-01-01
To improve the convergence rate and the sample efficiency, two efficient learning methods AC-HMLP and RAC-HMLP (AC-HMLP with ℓ 2-regularization) are proposed by combining actor-critic algorithm with hierarchical model learning and planning. The hierarchical models consisting of the local and the global models, which are learned at the same time during learning of the value function and the policy, are approximated by local linear regression (LLR) and linear function approximation (LFA), respectively. Both the local model and the global model are applied to generate samples for planning; the former is used only if the state-prediction error does not surpass the threshold at each time step, while the latter is utilized at the end of each episode. The purpose of taking both models is to improve the sample efficiency and accelerate the convergence rate of the whole algorithm through fully utilizing the local and global information. Experimentally, AC-HMLP and RAC-HMLP are compared with three representative algorithms on two Reinforcement Learning (RL) benchmark problems. The results demonstrate that they perform best in terms of convergence rate and sample efficiency. PMID:27795704
Kondo, Shuhei; Shibata, Tadashi; Ohmi, Tadahiro
1995-02-01
We have investigated the learning performance of the hardware backpropagation (HBP) algorithm, a hardware-oriented learning algorithm developed for the self-learning architecture of neural networks constructed using neuron MOS (metal-oxide-semiconductor) transistors. The solution to finding a mirror symmetry axis in a 4×4 binary pixel array was tested by computer simulation based on the HBP algorithm. Despite the inherent restrictions imposed on the hardware-learning algorithm, HBP exhibits equivalent learning performance to that of the original backpropagation (BP) algorithm when all the pertinent parameters are optimized. Very importantly, we have found that HBP has a superior generalization capability over BP; namely, HBP exhibits higher performance in solving problems that the network has not yet learnt.
Night-Time Vehicle Detection Algorithm Based on Visual Saliency and Deep Learning
Directory of Open Access Journals (Sweden)
Yingfeng Cai
2016-01-01
Full Text Available Night vision systems get more and more attention in the field of automotive active safety field. In this area, a number of researchers have proposed far-infrared sensor based night-time vehicle detection algorithm. However, existing algorithms have low performance in some indicators such as the detection rate and processing time. To solve this problem, we propose a far-infrared image vehicle detection algorithm based on visual saliency and deep learning. Firstly, most of the nonvehicle pixels will be removed with visual saliency computation. Then, vehicle candidate will be generated by using prior information such as camera parameters and vehicle size. Finally, classifier trained with deep belief networks will be applied to verify the candidates generated in last step. The proposed algorithm is tested in around 6000 images and achieves detection rate of 92.3% and processing time of 25 Hz which is better than existing methods.
Wang, Donghao; Wan, Jiangwen; Chen, Junying; Zhang, Qiang
2016-09-22
To adapt to sense signals of enormous diversities and dynamics, and to decrease the reconstruction errors caused by ambient noise, a novel online dictionary learning method-based compressive data gathering (ODL-CDG) algorithm is proposed. The proposed dictionary is learned from a two-stage iterative procedure, alternately changing between a sparse coding step and a dictionary update step. The self-coherence of the learned dictionary is introduced as a penalty term during the dictionary update procedure. The dictionary is also constrained with sparse structure. It's theoretically demonstrated that the sensing matrix satisfies the restricted isometry property (RIP) with high probability. In addition, the lower bound of necessary number of measurements for compressive sensing (CS) reconstruction is given. Simulation results show that the proposed ODL-CDG algorithm can enhance the recovery accuracy in the presence of noise, and reduce the energy consumption in comparison with other dictionary based data gathering methods.
An Online Dictionary Learning-Based Compressive Data Gathering Algorithm in Wireless Sensor Networks
Directory of Open Access Journals (Sweden)
Donghao Wang
2016-09-01
Full Text Available To adapt to sense signals of enormous diversities and dynamics, and to decrease the reconstruction errors caused by ambient noise, a novel online dictionary learning method-based compressive data gathering (ODL-CDG algorithm is proposed. The proposed dictionary is learned from a two-stage iterative procedure, alternately changing between a sparse coding step and a dictionary update step. The self-coherence of the learned dictionary is introduced as a penalty term during the dictionary update procedure. The dictionary is also constrained with sparse structure. It’s theoretically demonstrated that the sensing matrix satisfies the restricted isometry property (RIP with high probability. In addition, the lower bound of necessary number of measurements for compressive sensing (CS reconstruction is given. Simulation results show that the proposed ODL-CDG algorithm can enhance the recovery accuracy in the presence of noise, and reduce the energy consumption in comparison with other dictionary based data gathering methods.
Algorithm Building and Learning Programming Languages Using a New Educational Paradigm
Jain, Anshul K.; Singhal, Manik; Gupta, Manu Sheel
2011-08-01
This research paper presents a new concept of using a single tool to associate syntax of various programming languages, algorithms and basic coding techniques. A simple framework has been programmed in Python that helps students learn skills to develop algorithms, and implement them in various programming languages. The tool provides an innovative and a unified graphical user interface for development of multimedia objects, educational games and applications. It also aids collaborative learning amongst students and teachers through an integrated mechanism based on Remote Procedure Calls. The paper also elucidates an innovative method for code generation to enable students to learn the basics of programming languages using drag-n-drop methods for image objects.
Directory of Open Access Journals (Sweden)
Mazyar Seraj
2014-06-01
Full Text Available In recent years, many studies have been carried out on how to engage and support students in e-learning environments. Portable devices such as Personal Digital Assistants (PDAs, Tablet PCs, mobile phones and other mobile equipment have been used as parts of electronic learning environments to facilitate learning and teaching for both lecturers and students. However, there is still a dearth of study investigating the effects of small screen interfaces on mobile-based learning environments. This study aims to address two objectives: (i investigate lecturer and student difficulties encountered in teaching-learning process in traditional face-to-face classroom settings, and (ii to explore lecturer and student perceptions about learning the subject through mobile devices. This paper presents the results of a qualitative study using structured interviews to investigate lecturer and student experiences and perceptions on teaching and learning Dijkstra’s shortest path algorithm via mobile devices. The interview insights were then used as inputs to define user requirements for a mobile learning prototype. The findings show that the lecturers and students raised many issues about interactivity and the flexibility of effective learning applications on small screen devices, especially for a technical subject.
Learning Algorithm of Boltzmann Machine Based on Spatial Monte Carlo Integration Method
Directory of Open Access Journals (Sweden)
Muneki Yasuda
2018-04-01
Full Text Available The machine learning techniques for Markov random fields are fundamental in various fields involving pattern recognition, image processing, sparse modeling, and earth science, and a Boltzmann machine is one of the most important models in Markov random fields. However, the inference and learning problems in the Boltzmann machine are NP-hard. The investigation of an effective learning algorithm for the Boltzmann machine is one of the most important challenges in the field of statistical machine learning. In this paper, we study Boltzmann machine learning based on the (first-order spatial Monte Carlo integration method, referred to as the 1-SMCI learning method, which was proposed in the author’s previous paper. In the first part of this paper, we compare the method with the maximum pseudo-likelihood estimation (MPLE method using a theoretical and a numerical approaches, and show the 1-SMCI learning method is more effective than the MPLE. In the latter part, we compare the 1-SMCI learning method with other effective methods, ratio matching and minimum probability flow, using a numerical experiment, and show the 1-SMCI learning method outperforms them.
Wahyudin; Riza, L. S.; Putro, B. L.
2018-05-01
E-learning as a learning activity conducted online by the students with the usual tools is favoured by students. The use of computer media in learning provides benefits that are not owned by other learning media that is the ability of computers to interact individually with students. But the weakness of many learning media is to assume that all students have a uniform ability, when in reality this is not the case. The concept of Intelligent Tutorial System (ITS) combined with cyberblog application can overcome the weaknesses in neglecting diversity. An Intelligent Tutorial System-based Cyberblog application (ITS) is a web-based interactive application program that implements artificial intelligence which can be used as a learning and evaluation media in the learning process. The use of ITS-based Cyberblog in learning is one of the alternative learning media that is interesting and able to help students in measuring ability in understanding the material. This research will be associated with the improvement of logical thinking ability (logical thinking) of students, especially in algorithm subjects.
The algorithm for duration acceleration of repetitive projects considering the learning effect
Chen, Hongtao; Wang, Keke; Du, Yang; Wang, Liwan
2018-03-01
Repetitive project optimization problem is common in project scheduling. Repetitive Scheduling Method (RSM) has many irreplaceable advantages in the field of repetitive projects. As the same or similar work is repeated, the proficiency of workers will be correspondingly low to high, and workers will gain experience and improve the efficiency of operations. This is learning effect. Learning effect is one of the important factors affecting the optimization results in repetitive project scheduling. This paper analyzes the influence of the learning effect on the controlling path in RSM from two aspects: one is that the learning effect changes the controlling path, the other is that the learning effect doesn't change the controlling path. This paper proposes corresponding methods to accelerate duration for different types of critical activities and proposes the algorithm for duration acceleration based on the learning effect in RSM. And the paper chooses graphical method to identity activities' types and considers the impacts of the learning effect on duration. The method meets the requirement of duration while ensuring the lowest acceleration cost. A concrete bridge construction project is given to verify the effectiveness of the method. The results of this study will help project managers understand the impacts of the learning effect on repetitive projects, and use the learning effect to optimize project scheduling.
Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?
Karim, Mohammad Ehsanul; Pang, Menglan; Platt, Robert W
2018-03-01
The use of retrospective health care claims datasets is frequently criticized for the lack of complete information on potential confounders. Utilizing patient's health status-related information from claims datasets as surrogates or proxies for mismeasured and unobserved confounders, the high-dimensional propensity score algorithm enables us to reduce bias. Using a previously published cohort study of postmyocardial infarction statin use (1998-2012), we compare the performance of the algorithm with a number of popular machine learning approaches for confounder selection in high-dimensional covariate spaces: random forest, least absolute shrinkage and selection operator, and elastic net. Our results suggest that, when the data analysis is done with epidemiologic principles in mind, machine learning methods perform as well as the high-dimensional propensity score algorithm. Using a plasmode framework that mimicked the empirical data, we also showed that a hybrid of machine learning and high-dimensional propensity score algorithms generally perform slightly better than both in terms of mean squared error, when a bias-based analysis is used.
An Orthogonal Learning Differential Evolution Algorithm for Remote Sensing Image Registration
Directory of Open Access Journals (Sweden)
Wenping Ma
2014-01-01
Full Text Available We introduce an area-based method for remote sensing image registration. We use orthogonal learning differential evolution algorithm to optimize the similarity metric between the reference image and the target image. Many local and global methods have been used to achieve the optimal similarity metric in the last few years. Because remote sensing images are usually influenced by large distortions and high noise, local methods will fail in some cases. For this reason, global methods are often required. The orthogonal learning (OL strategy is efficient when searching in complex problem spaces. In addition, it can discover more useful information via orthogonal experimental design (OED. Differential evolution (DE is a heuristic algorithm. It has shown to be efficient in solving the remote sensing image registration problem. So orthogonal learning differential evolution algorithm (OLDE is efficient for many optimization problems. The OLDE method uses the OL strategy to guide the DE algorithm to discover more useful information. Experiments show that the OLDE method is more robust and efficient for registering remote sensing images.
An efficient dictionary learning algorithm and its application to 3-D medical image denoising.
Li, Shutao; Fang, Leyuan; Yin, Haitao
2012-02-01
In this paper, we propose an efficient dictionary learning algorithm for sparse representation of given data and suggest a way to apply this algorithm to 3-D medical image denoising. Our learning approach is composed of two main parts: sparse coding and dictionary updating. On the sparse coding stage, an efficient algorithm named multiple clusters pursuit (MCP) is proposed. The MCP first applies a dictionary structuring strategy to cluster the atoms with high coherence together, and then employs a multiple-selection strategy to select several competitive atoms at each iteration. These two strategies can greatly reduce the computation complexity of the MCP and assist it to obtain better sparse solution. On the dictionary updating stage, the alternating optimization that efficiently approximates the singular value decomposition is introduced. Furthermore, in the 3-D medical image denoising application, a joint 3-D operation is proposed for taking the learning capabilities of the presented algorithm to simultaneously capture the correlations within each slice and correlations across the nearby slices, thereby obtaining better denoising results. The experiments on both synthetically generated data and real 3-D medical images demonstrate that the proposed approach has superior performance compared to some well-known methods. © 2011 IEEE
A New Fuzzy Cognitive Map Learning Algorithm for Speech Emotion Recognition
Directory of Open Access Journals (Sweden)
Wei Zhang
2017-01-01
Full Text Available Selecting an appropriate recognition method is crucial in speech emotion recognition applications. However, the current methods do not consider the relationship between emotions. Thus, in this study, a speech emotion recognition system based on the fuzzy cognitive map (FCM approach is constructed. Moreover, a new FCM learning algorithm for speech emotion recognition is proposed. This algorithm includes the use of the pleasure-arousal-dominance emotion scale to calculate the weights between emotions and certain mathematical derivations to determine the network structure. The proposed algorithm can handle a large number of concepts, whereas a typical FCM can handle only relatively simple networks (maps. Different acoustic features, including fundamental speech features and a new spectral feature, are extracted to evaluate the performance of the proposed method. Three experiments are conducted in this paper, namely, single feature experiment, feature combination experiment, and comparison between the proposed algorithm and typical networks. All experiments are performed on TYUT2.0 and EMO-DB databases. Results of the feature combination experiments show that the recognition rates of the combination features are 10%–20% better than those of single features. The proposed FCM learning algorithm generates 5%–20% performance improvement compared with traditional classification networks.
Narula, Sukrit; Shameer, Khader; Salem Omar, Alaa Mabrouk; Dudley, Joel T; Sengupta, Partho P
2016-11-29
Machine-learning models may aid cardiac phenotypic recognition by using features of cardiac tissue deformation. This study investigated the diagnostic value of a machine-learning framework that incorporates speckle-tracking echocardiographic data for automated discrimination of hypertrophic cardiomyopathy (HCM) from physiological hypertrophy seen in athletes (ATH). Expert-annotated speckle-tracking echocardiographic datasets obtained from 77 ATH and 62 HCM patients were used for developing an automated system. An ensemble machine-learning model with 3 different machine-learning algorithms (support vector machines, random forests, and artificial neural networks) was developed and a majority voting method was used for conclusive predictions with further K-fold cross-validation. Feature selection using an information gain (IG) algorithm revealed that volume was the best predictor for differentiating between HCM ands. ATH (IG = 0.24) followed by mid-left ventricular segmental (IG = 0.134) and average longitudinal strain (IG = 0.131). The ensemble machine-learning model showed increased sensitivity and specificity compared with early-to-late diastolic transmitral velocity ratio (p 13 mm. In this subgroup analysis, the automated model continued to show equal sensitivity, but increased specificity relative to early-to-late diastolic transmitral velocity ratio, e', and strain. Our results suggested that machine-learning algorithms can assist in the discrimination of physiological versus pathological patterns of hypertrophic remodeling. This effort represents a step toward the development of a real-time, machine-learning-based system for automated interpretation of echocardiographic images, which may help novice readers with limited experience. Copyright © 2016 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.
A Comparison Study of Machine Learning Based Algorithms for Fatigue Crack Growth Calculation.
Wang, Hongxun; Zhang, Weifang; Sun, Fuqiang; Zhang, Wei
2017-05-18
The relationships between the fatigue crack growth rate ( d a / d N ) and stress intensity factor range ( Δ K ) are not always linear even in the Paris region. The stress ratio effects on fatigue crack growth rate are diverse in different materials. However, most existing fatigue crack growth models cannot handle these nonlinearities appropriately. The machine learning method provides a flexible approach to the modeling of fatigue crack growth because of its excellent nonlinear approximation and multivariable learning ability. In this paper, a fatigue crack growth calculation method is proposed based on three different machine learning algorithms (MLAs): extreme learning machine (ELM), radial basis function network (RBFN) and genetic algorithms optimized back propagation network (GABP). The MLA based method is validated using testing data of different materials. The three MLAs are compared with each other as well as the classical two-parameter model ( K * approach). The results show that the predictions of MLAs are superior to those of K * approach in accuracy and effectiveness, and the ELM based algorithms show overall the best agreement with the experimental data out of the three MLAs, for its global optimization and extrapolation ability.
Sampling algorithms for validation of supervised learning models for Ising-like systems
Portman, Nataliya; Tamblyn, Isaac
2017-12-01
In this paper, we build and explore supervised learning models of ferromagnetic system behavior, using Monte-Carlo sampling of the spin configuration space generated by the 2D Ising model. Given the enormous size of the space of all possible Ising model realizations, the question arises as to how to choose a reasonable number of samples that will form physically meaningful and non-intersecting training and testing datasets. Here, we propose a sampling technique called ;ID-MH; that uses the Metropolis-Hastings algorithm creating Markov process across energy levels within the predefined configuration subspace. We show that application of this method retains phase transitions in both training and testing datasets and serves the purpose of validation of a machine learning algorithm. For larger lattice dimensions, ID-MH is not feasible as it requires knowledge of the complete configuration space. As such, we develop a new ;block-ID; sampling strategy: it decomposes the given structure into square blocks with lattice dimension N ≤ 5 and uses ID-MH sampling of candidate blocks. Further comparison of the performance of commonly used machine learning methods such as random forests, decision trees, k nearest neighbors and artificial neural networks shows that the PCA-based Decision Tree regressor is the most accurate predictor of magnetizations of the Ising model. For energies, however, the accuracy of prediction is not satisfactory, highlighting the need to consider more algorithmically complex methods (e.g., deep learning).
Directory of Open Access Journals (Sweden)
Marc Wieland
2014-03-01
Full Text Available In this study, a classification and performance evaluation framework for the recognition of urban patterns in medium (Landsat ETM, TM and MSS and very high resolution (WorldView-2, Quickbird, Ikonos multi-spectral satellite images is presented. The study aims at exploring the potential of machine learning algorithms in the context of an object-based image analysis and to thoroughly test the algorithm’s performance under varying conditions to optimize their usage for urban pattern recognition tasks. Four classification algorithms, Normal Bayes, K Nearest Neighbors, Random Trees and Support Vector Machines, which represent different concepts in machine learning (probabilistic, nearest neighbor, tree-based, function-based, have been selected and implemented on a free and open-source basis. Particular focus is given to assess the generalization ability of machine learning algorithms and the transferability of trained learning machines between different image types and image scenes. Moreover, the influence of the number and choice of training data, the influence of the size and composition of the feature vector and the effect of image segmentation on the classification accuracy is evaluated.
Unsupervised Learning Through Randomized Algorithms for High-Volume High-Velocity Data (ULTRA-HV).
Energy Technology Data Exchange (ETDEWEB)
Pinar, Ali [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Kolda, Tamara G. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Carlberg, Kevin Thomas [Wake Forest Univ., Winston-Salem, MA (United States); Ballard, Grey [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Mahoney, Michael [Univ. of California, Berkeley, CA (United States)
2018-01-01
Through long-term investments in computing, algorithms, facilities, and instrumentation, DOE is an established leader in massive-scale, high-fidelity simulations, as well as science-leading experimentation. In both cases, DOE is generating more data than it can analyze and the problem is intensifying quickly. The need for advanced algorithms that can automatically convert the abundance of data into a wealth of useful information by discovering hidden structures is well recognized. Such efforts however, are hindered by the massive volume of the data and its high velocity. Here, the challenge is developing unsupervised learning methods to discover hidden structure in high-volume, high-velocity data.
Modified Bat Algorithm Based on Lévy Flight and Opposition Based Learning
Directory of Open Access Journals (Sweden)
Xian Shan
2016-01-01
Full Text Available Bat Algorithm (BA is a swarm intelligence algorithm which has been intensively applied to solve academic and real life optimization problems. However, due to the lack of good balance between exploration and exploitation, BA sometimes fails at finding global optimum and is easily trapped into local optima. In order to overcome the premature problem and improve the local searching ability of Bat Algorithm for optimization problems, we propose an improved BA called OBMLBA. In the proposed algorithm, a modified search equation with more useful information from the search experiences is introduced to generate a candidate solution, and Lévy Flight random walk is incorporated with BA in order to avoid being trapped into local optima. Furthermore, the concept of opposition based learning (OBL is embedded to BA to enhance the diversity and convergence capability. To evaluate the performance of the proposed approach, 16 benchmark functions have been employed. The results obtained by the experiments demonstrate the effectiveness and efficiency of OBMLBA for global optimization problems. Comparisons with some other BA variants and other state-of-the-art algorithms have shown the proposed approach significantly improves the performance of BA. Performances of the proposed algorithm on large scale optimization problems and real world optimization problems are not discussed in the paper, and it will be studied in the future work.
Impedance learning for robotic contact tasks using natural actor-critic algorithm.
Kim, Byungchan; Park, Jooyoung; Park, Shinsuk; Kang, Sungchul
2010-04-01
Compared with their robotic counterparts, humans excel at various tasks by using their ability to adaptively modulate arm impedance parameters. This ability allows us to successfully perform contact tasks even in uncertain environments. This paper considers a learning strategy of motor skill for robotic contact tasks based on a human motor control theory and machine learning schemes. Our robot learning method employs impedance control based on the equilibrium point control theory and reinforcement learning to determine the impedance parameters for contact tasks. A recursive least-square filter-based episodic natural actor-critic algorithm is used to find the optimal impedance parameters. The effectiveness of the proposed method was tested through dynamic simulations of various contact tasks. The simulation results demonstrated that the proposed method optimizes the performance of the contact tasks in uncertain conditions of the environment.
An e-Learning environment for algorithmic: toward an active construction of skills
Directory of Open Access Journals (Sweden)
Abdelghani Babori
2016-07-01
Full Text Available Assimilating an algorithmic course is a persistent problem for many undergraduate students. The major problem faced by students is the lack of problem solving ability and flexibility. Therefore, students are generally passive, unmotivated and unable to mobilize all the acquired knowledge (loops, test, variables, etc. to deal with new encountered problems. Our study is structured around building, step by step, problem solving skills among novice learners. Our approach is based on the use of problem based learning in an e-Learning environment. We begin by establishing a cognitive model which represents knowledge elements, grouped into categories of skills, judged necessary to be appropriated. We then propose a problem built on a concrete situation which aims to actively construct a skill category. We conclude by presenting around the proposed problem a pedagogical scenario for the set of learning activities designed to be incorporated in an E-learning platform.
Machine Learning Algorithms for $b$-Jet Tagging at the ATLAS Experiment
Paganini, Michela; The ATLAS collaboration
2017-01-01
The separation of b-quark initiated jets from those coming from lighter quark flavours (b-tagging) is a fundamental tool for the ATLAS physics program at the CERN Large Hadron Collider. The most powerful b-tagging algorithms combine information from low-level taggers exploiting reconstructed track and vertex information using a multivariate classifier. The potential of modern Machine Learning techniques such as Recurrent Neural Networks and Deep Learning is explored using simulated events, and compared to that achievable from more traditional classifiers such as boosted decision trees.
Schwaibold, M; Schöchlin, J; Bolz, A
2002-01-01
For classification tasks in biosignal processing, several strategies and algorithms can be used. Knowledge-based systems allow prior knowledge about the decision process to be integrated, both by the developer and by self-learning capabilities. For the classification stages in a sleep stage detection framework, three inference strategies were compared regarding their specific strengths: a classical signal processing approach, artificial neural networks and neuro-fuzzy systems. Methodological aspects were assessed to attain optimum performance and maximum transparency for the user. Due to their effective and robust learning behavior, artificial neural networks could be recommended for pattern recognition, while neuro-fuzzy systems performed best for the processing of contextual information.
Classification of large-sized hyperspectral imagery using fast machine learning algorithms
Xia, Junshi; Yokoya, Naoto; Iwasaki, Akira
2017-07-01
We present a framework of fast machine learning algorithms in the context of large-sized hyperspectral images classification from the theoretical to a practical viewpoint. In particular, we assess the performance of random forest (RF), rotation forest (RoF), and extreme learning machine (ELM) and the ensembles of RF and ELM. These classifiers are applied to two large-sized hyperspectral images and compared to the support vector machines. To give the quantitative analysis, we pay attention to comparing these methods when working with high input dimensions and a limited/sufficient training set. Moreover, other important issues such as the computational cost and robustness against the noise are also discussed.
Zhang, Shang; Dong, Yuhan; Fu, Hongyan; Huang, Shao-Lun; Zhang, Lin
2018-02-22
The miniaturization of spectrometer can broaden the application area of spectrometry, which has huge academic and industrial value. Among various miniaturization approaches, filter-based miniaturization is a promising implementation by utilizing broadband filters with distinct transmission functions. Mathematically, filter-based spectral reconstruction can be modeled as solving a system of linear equations. In this paper, we propose an algorithm of spectral reconstruction based on sparse optimization and dictionary learning. To verify the feasibility of the reconstruction algorithm, we design and implement a simple prototype of a filter-based miniature spectrometer. The experimental results demonstrate that sparse optimization is well applicable to spectral reconstruction whether the spectra are directly sparse or not. As for the non-directly sparse spectra, their sparsity can be enhanced by dictionary learning. In conclusion, the proposed approach has a bright application prospect in fabricating a practical miniature spectrometer.
Development of fuzzy algorithm with learning function for nuclear steam generator level control
International Nuclear Information System (INIS)
Park, Gee Yong; Seong, Poong Hyun
1993-01-01
A fuzzy algorithm with learning function is applied to the steam generator level control of nuclear power plant. This algorithm can make its rule base and membership functions suited for steam generator level control by use of the data obtained from the control actions of a skilled operator or of other controllers (i.e., PID controller). The rule base of fuzzy controller with learning function is divided into two parts. One part of the rule base is provided to level control of steam generator at low power level (0 % - 30 % of full power) and the other to level control at high power level (30 % - 100 % of full power). Response time of steam generator level control at low power range with this rule base is shown to be shorter than that of fuzzy controller with direct inference. (Author)
Shuxin, Li; Zhilong, Zhang; Biao, Li
2018-01-01
Plane is an important target category in remote sensing targets and it is of great value to detect the plane targets automatically. As remote imaging technology developing continuously, the resolution of the remote sensing image has been very high and we can get more detailed information for detecting the remote sensing targets automatically. Deep learning network technology is the most advanced technology in image target detection and recognition, which provided great performance improvement in the field of target detection and recognition in the everyday scenes. We combined the technology with the application in the remote sensing target detection and proposed an algorithm with end to end deep network, which can learn from the remote sensing images to detect the targets in the new images automatically and robustly. Our experiments shows that the algorithm can capture the feature information of the plane target and has better performance in target detection with the old methods.
Zhang, Shang; Fu, Hongyan; Huang, Shao-Lun; Zhang, Lin
2018-01-01
The miniaturization of spectrometer can broaden the application area of spectrometry, which has huge academic and industrial value. Among various miniaturization approaches, filter-based miniaturization is a promising implementation by utilizing broadband filters with distinct transmission functions. Mathematically, filter-based spectral reconstruction can be modeled as solving a system of linear equations. In this paper, we propose an algorithm of spectral reconstruction based on sparse optimization and dictionary learning. To verify the feasibility of the reconstruction algorithm, we design and implement a simple prototype of a filter-based miniature spectrometer. The experimental results demonstrate that sparse optimization is well applicable to spectral reconstruction whether the spectra are directly sparse or not. As for the non-directly sparse spectra, their sparsity can be enhanced by dictionary learning. In conclusion, the proposed approach has a bright application prospect in fabricating a practical miniature spectrometer. PMID:29470406
Meyer, Hanna; Kühnlein, Meike; Appelhans, Tim; Nauss, Thomas
2016-03-01
Machine learning (ML) algorithms have successfully been demonstrated to be valuable tools in satellite-based rainfall retrievals which show the practicability of using ML algorithms when faced with high dimensional and complex data. Moreover, recent developments in parallel computing with ML present new possibilities for training and prediction speed and therefore make their usage in real-time systems feasible. This study compares four ML algorithms - random forests (RF), neural networks (NNET), averaged neural networks (AVNNET) and support vector machines (SVM) - for rainfall area detection and rainfall rate assignment using MSG SEVIRI data over Germany. Satellite-based proxies for cloud top height, cloud top temperature, cloud phase and cloud water path serve as predictor variables. The results indicate an overestimation of rainfall area delineation regardless of the ML algorithm (averaged bias = 1.8) but a high probability of detection ranging from 81% (SVM) to 85% (NNET). On a 24-hour basis, the performance of the rainfall rate assignment yielded R2 values between 0.39 (SVM) and 0.44 (AVNNET). Though the differences in the algorithms' performance were rather small, NNET and AVNNET were identified as the most suitable algorithms. On average, they demonstrated the best performance in rainfall area delineation as well as in rainfall rate assignment. NNET's computational speed is an additional advantage in work with large datasets such as in remote sensing based rainfall retrievals. However, since no single algorithm performed considerably better than the others we conclude that further research in providing suitable predictors for rainfall is of greater necessity than an optimization through the choice of the ML algorithm.
Directory of Open Access Journals (Sweden)
Qingyang Zhang
2015-02-01
Full Text Available Bird Mating Optimizer (BMO is a novel meta-heuristic optimization algorithm inspired by intelligent mating behavior of birds. However, it is still insufficient in convergence of speed and quality of solution. To overcome these drawbacks, this paper proposes a hybrid algorithm (TLBMO, which is established by combining the advantages of Teaching-learning-based optimization (TLBO and Bird Mating Optimizer (BMO. The performance of TLBMO is evaluated on 23 benchmark functions, and compared with seven state-of-the-art approaches, namely BMO, TLBO, Artificial Bee Bolony (ABC, Particle Swarm Optimization (PSO, Fast Evolution Programming (FEP, Differential Evolution (DE, Group Search Optimization (GSO. Experimental results indicate that the proposed method performs better than other existing algorithms for global numerical optimization.
International Nuclear Information System (INIS)
Sánchez-Oro, J.; Duarte, A.; Salcedo-Sanz, S.
2016-01-01
Highlights: • The total energy demand in Spain is estimated with a Variable Neighborhood algorithm. • Socio-economic variables are used, and one year ahead prediction horizon is considered. • Improvement of the prediction with an Extreme Learning Machine network is considered. • Experiments are carried out in real data for the case of Spain. - Abstract: Energy demand prediction is an important problem whose solution is evaluated by policy makers in order to take key decisions affecting the economy of a country. A number of previous approaches to improve the quality of this estimation have been proposed in the last decade, the majority of them applying different machine learning techniques. In this paper, the performance of a robust hybrid approach, composed of a Variable Neighborhood Search algorithm and a new class of neural network called Extreme Learning Machine, is discussed. The Variable Neighborhood Search algorithm is focused on obtaining the most relevant features among the set of initial ones, by including an exponential prediction model. While previous approaches consider that the number of macroeconomic variables used for prediction is a parameter of the algorithm (i.e., it is fixed a priori), the proposed Variable Neighborhood Search method optimizes both: the number of variables and the best ones. After this first step of feature selection, an Extreme Learning Machine network is applied to obtain the final energy demand prediction. Experiments in a real case of energy demand estimation in Spain show the excellent performance of the proposed approach. In particular, the whole method obtains an estimation of the energy demand with an error lower than 2%, even when considering the crisis years, which are a real challenge.
Anomaly detection in wide area network mesh using two machine learning anomaly detection algorithms
Zhang, James; Vukotic, Ilija; Gardner, Robert
2018-01-01
Anomaly detection is the practice of identifying items or events that do not conform to an expected behavior or do not correlate with other items in a dataset. It has previously been applied to areas such as intrusion detection, system health monitoring, and fraud detection in credit card transactions. In this paper, we describe a new method for detecting anomalous behavior over network performance data, gathered by perfSONAR, using two machine learning algorithms: Boosted Decision Trees (BDT...
Wu, Jianning; Wu, Bin
2015-01-01
The accurate identification of gait asymmetry is very beneficial to the assessment of at-risk gait in the clinical applications. This paper investigated the application of classification method based on statistical learning algorithm to quantify gait symmetry based on the assumption that the degree of intrinsic change in dynamical system of gait is associated with the different statistical distributions between gait variables from left-right side of lower limbs; that is, the discrimination of...
Simulating Visual Learning and Optical Illusions via a Network-Based Genetic Algorithm
Siu, Theodore; Vivar, Miguel; Shinbrot, Troy
We present a neural network model that uses a genetic algorithm to identify spatial patterns. We show that the model both learns and reproduces common visual patterns and optical illusions. Surprisingly, we find that the illusions generated are a direct consequence of the network architecture used. We discuss the implications of our results and the insights that we gain on how humans fall for optical illusions
Nishizuka, N.; Sugiura, K.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M.
2017-02-01
We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010-2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite. We detected active regions (ARs) from the full-disk magnetogram, from which ˜60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.
Energy Technology Data Exchange (ETDEWEB)
Nishizuka, N.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M. [Applied Electromagnetic Research Institute, National Institute of Information and Communications Technology, 4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795 (Japan); Sugiura, K., E-mail: nishizuka.naoto@nict.go.jp [Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology (Japan)
2017-02-01
We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010–2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite . We detected active regions (ARs) from the full-disk magnetogram, from which ∼60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.
International Nuclear Information System (INIS)
Nishizuka, N.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M.; Sugiura, K.
2017-01-01
We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010–2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite . We detected active regions (ARs) from the full-disk magnetogram, from which ∼60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.
Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression
Sato, Jo?o R.; Moll, Jorge; Green, Sophie; Deakin, John F.W.; Thomaz, Carlos E.; Zahn, Roland
2015-01-01
Standard functional magnetic resonance imaging (fMRI) analyses cannot assess the potential of a neuroimaging signature as a biomarker to predict individual vulnerability to major depression (MD). Here, we use machine learning for the first time to address this question. Using a recently identified neural signature of guilt-selective functional disconnection, the classification algorithm was able to distinguish remitted MD from control participants with 78.3% accuracy. This demonstrates the hi...
Chen, Fangyue; Chen, Guanrong Ron; He, Guolong; Xu, Xiubin; He, Qinbin
2009-10-01
Universal perceptron (UP), a generalization of Rosenblatt's perceptron, is considered in this paper, which is capable of implementing all Boolean functions (BFs). In the classification of BFs, there are: 1) linearly separable Boolean function (LSBF) class, 2) parity Boolean function (PBF) class, and 3) non-LSBF and non-PBF class. To implement these functions, UP takes different kinds of simple topological structures in which each contains at most one hidden layer along with the smallest possible number of hidden neurons. Inspired by the concept of DNA sequences in biological systems, a novel learning algorithm named DNA-like learning is developed, which is able to quickly train a network with any prescribed BF. The focus is on performing LSBF and PBF by a single-layer perceptron (SLP) with the new algorithm. Two criteria for LSBF and PBF are proposed, respectively, and a new measure for a BF, named nonlinearly separable degree (NLSD), is introduced. In the sense of this measure, the PBF is the most complex one. The new algorithm has many advantages including, in particular, fast running speed, good robustness, and no need of considering the convergence property. For example, the number of iterations and computations in implementing the basic 2-bit logic operations such as AND, OR, and XOR by using the new algorithm is far smaller than the ones needed by using other existing algorithms such as error-correction (EC) and backpropagation (BP) algorithms. Moreover, the synaptic weights and threshold values derived from UP can be directly used in designing of the template of cellular neural networks (CNNs), which has been considered as a new spatial-temporal sensory computing paradigm.
How the machine ‘thinks’: Understanding opacity in machine learning algorithms
Directory of Open Access Journals (Sweden)
Jenna Burrell
2016-01-01
Full Text Available This article considers the issue of opacity as a problem for socially consequential mechanisms of classification and ranking, such as spam filters, credit card fraud detection, search engines, news trends, market segmentation and advertising, insurance or loan qualification, and credit scoring. These mechanisms of classification all frequently rely on computational algorithms, and in many cases on machine learning algorithms to do this work. In this article, I draw a distinction between three forms of opacity: (1 opacity as intentional corporate or state secrecy, (2 opacity as technical illiteracy, and (3 an opacity that arises from the characteristics of machine learning algorithms and the scale required to apply them usefully. The analysis in this article gets inside the algorithms themselves. I cite existing literatures in computer science, known industry practices (as they are publicly presented, and do some testing and manipulation of code as a form of lightweight code audit. I argue that recognizing the distinct forms of opacity that may be coming into play in a given application is a key to determining which of a variety of technical and non-technical solutions could help to prevent harm.
Directory of Open Access Journals (Sweden)
Juan Pardo
2015-04-01
Full Text Available Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.
Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma
2015-01-01
Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources. PMID:25905698
AUTOCLASSIFICATION OF THE VARIABLE 3XMM SOURCES USING THE RANDOM FOREST MACHINE LEARNING ALGORITHM
International Nuclear Information System (INIS)
Farrell, Sean A.; Murphy, Tara; Lo, Kitty K.
2015-01-01
In the current era of large surveys and massive data sets, autoclassification of astrophysical sources using intelligent algorithms is becoming increasingly important. In this paper we present the catalog of variable sources in the Third XMM-Newton Serendipitous Source catalog (3XMM) autoclassified using the Random Forest machine learning algorithm. We used a sample of manually classified variable sources from the second data release of the XMM-Newton catalogs (2XMMi-DR2) to train the classifier, obtaining an accuracy of ∼92%. We also evaluated the effectiveness of identifying spurious detections using a sample of spurious sources, achieving an accuracy of ∼95%. Manual investigation of a random sample of classified sources confirmed these accuracy levels and showed that the Random Forest machine learning algorithm is highly effective at automatically classifying 3XMM sources. Here we present the catalog of classified 3XMM variable sources. We also present three previously unidentified unusual sources that were flagged as outlier sources by the algorithm: a new candidate supergiant fast X-ray transient, a 400 s X-ray pulsar, and an eclipsing 5 hr binary system coincident with a known Cepheid.
Premaladha, J; Ravichandran, K S
2016-04-01
Dermoscopy is a technique used to capture the images of skin, and these images are useful to analyze the different types of skin diseases. Malignant melanoma is a kind of skin cancer whose severity even leads to death. Earlier detection of melanoma prevents death and the clinicians can treat the patients to increase the chances of survival. Only few machine learning algorithms are developed to detect the melanoma using its features. This paper proposes a Computer Aided Diagnosis (CAD) system which equips efficient algorithms to classify and predict the melanoma. Enhancement of the images are done using Contrast Limited Adaptive Histogram Equalization technique (CLAHE) and median filter. A new segmentation algorithm called Normalized Otsu's Segmentation (NOS) is implemented to segment the affected skin lesion from the normal skin, which overcomes the problem of variable illumination. Fifteen features are derived and extracted from the segmented images are fed into the proposed classification techniques like Deep Learning based Neural Networks and Hybrid Adaboost-Support Vector Machine (SVM) algorithms. The proposed system is tested and validated with nearly 992 images (malignant & benign lesions) and it provides a high classification accuracy of 93 %. The proposed CAD system can assist the dermatologists to confirm the decision of the diagnosis and to avoid excisional biopsies.
A comparison of algorithms for inference and learning in probabilistic graphical models.
Frey, Brendan J; Jojic, Nebojsa
2005-09-01
Research into methods for reasoning under uncertainty is currently one of the most exciting areas of artificial intelligence, largely because it has recently become possible to record, store, and process large amounts of data. While impressive achievements have been made in pattern classification problems such as handwritten character recognition, face detection, speaker identification, and prediction of gene function, it is even more exciting that researchers are on the verge of introducing systems that can perform large-scale combinatorial analyses of data, decomposing the data into interacting components. For example, computational methods for automatic scene analysis are now emerging in the computer vision community. These methods decompose an input image into its constituent objects, lighting conditions, motion patterns, etc. Two of the main challenges are finding effective representations and models in specific applications and finding efficient algorithms for inference and learning in these models. In this paper, we advocate the use of graph-based probability models and their associated inference and learning algorithms. We review exact techniques and various approximate, computationally efficient techniques, including iterated conditional modes, the expectation maximization (EM) algorithm, Gibbs sampling, the mean field method, variational techniques, structured variational techniques and the sum-product algorithm ("loopy" belief propagation). We describe how each technique can be applied in a vision model of multiple, occluding objects and contrast the behaviors and performances of the techniques using a unifying cost function, free energy.
Evaluation of machine learning algorithms for improved risk assessment for Down's syndrome.
Koivu, Aki; Korpimäki, Teemu; Kivelä, Petri; Pahikkala, Tapio; Sairanen, Mikko
2018-05-04
Prenatal screening generates a great amount of data that is used for predicting risk of various disorders. Prenatal risk assessment is based on multiple clinical variables and overall performance is defined by how well the risk algorithm is optimized for the population in question. This article evaluates machine learning algorithms to improve performance of first trimester screening of Down syndrome. Machine learning algorithms pose an adaptive alternative to develop better risk assessment models using the existing clinical variables. Two real-world data sets were used to experiment with multiple classification algorithms. Implemented models were tested with a third, real-world, data set and performance was compared to a predicate method, a commercial risk assessment software. Best performing deep neural network model gave an area under the curve of 0.96 and detection rate of 78% with 1% false positive rate with the test data. Support vector machine model gave area under the curve of 0.95 and detection rate of 61% with 1% false positive rate with the same test data. When compared with the predicate method, the best support vector machine model was slightly inferior, but an optimized deep neural network model was able to give higher detection rates with same false positive rate or similar detection rate but with markedly lower false positive rate. This finding could further improve the first trimester screening for Down syndrome, by using existing clinical variables and a large training data derived from a specific population. Copyright © 2018 Elsevier Ltd. All rights reserved.
Directory of Open Access Journals (Sweden)
Jianning Wu
2015-01-01
Full Text Available The accurate identification of gait asymmetry is very beneficial to the assessment of at-risk gait in the clinical applications. This paper investigated the application of classification method based on statistical learning algorithm to quantify gait symmetry based on the assumption that the degree of intrinsic change in dynamical system of gait is associated with the different statistical distributions between gait variables from left-right side of lower limbs; that is, the discrimination of small difference of similarity between lower limbs is considered the reorganization of their different probability distribution. The kinetic gait data of 60 participants were recorded using a strain gauge force platform during normal walking. The classification method is designed based on advanced statistical learning algorithm such as support vector machine algorithm for binary classification and is adopted to quantitatively evaluate gait symmetry. The experiment results showed that the proposed method could capture more intrinsic dynamic information hidden in gait variables and recognize the right-left gait patterns with superior generalization performance. Moreover, our proposed techniques could identify the small significant difference between lower limbs when compared to the traditional symmetry index method for gait. The proposed algorithm would become an effective tool for early identification of the elderly gait asymmetry in the clinical diagnosis.
Wu, Jianning; Wu, Bin
2015-01-01
The accurate identification of gait asymmetry is very beneficial to the assessment of at-risk gait in the clinical applications. This paper investigated the application of classification method based on statistical learning algorithm to quantify gait symmetry based on the assumption that the degree of intrinsic change in dynamical system of gait is associated with the different statistical distributions between gait variables from left-right side of lower limbs; that is, the discrimination of small difference of similarity between lower limbs is considered the reorganization of their different probability distribution. The kinetic gait data of 60 participants were recorded using a strain gauge force platform during normal walking. The classification method is designed based on advanced statistical learning algorithm such as support vector machine algorithm for binary classification and is adopted to quantitatively evaluate gait symmetry. The experiment results showed that the proposed method could capture more intrinsic dynamic information hidden in gait variables and recognize the right-left gait patterns with superior generalization performance. Moreover, our proposed techniques could identify the small significant difference between lower limbs when compared to the traditional symmetry index method for gait. The proposed algorithm would become an effective tool for early identification of the elderly gait asymmetry in the clinical diagnosis.
Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma
2015-04-21
Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.
Separation of pulsar signals from noise using supervised machine learning algorithms
Bethapudi, S.; Desai, S.
2018-04-01
We evaluate the performance of four different machine learning (ML) algorithms: an Artificial Neural Network Multi-Layer Perceptron (ANN MLP), Adaboost, Gradient Boosting Classifier (GBC), and XGBoost, for the separation of pulsars from radio frequency interference (RFI) and other sources of noise, using a dataset obtained from the post-processing of a pulsar search pipeline. This dataset was previously used for the cross-validation of the SPINN-based machine learning engine, obtained from the reprocessing of the HTRU-S survey data (Morello et al., 2014). We have used the Synthetic Minority Over-sampling Technique (SMOTE) to deal with high-class imbalance in the dataset. We report a variety of quality scores from all four of these algorithms on both the non-SMOTE and SMOTE datasets. For all the above ML methods, we report high accuracy and G-mean for both the non-SMOTE and SMOTE cases. We study the feature importances using Adaboost, GBC, and XGBoost and also from the minimum Redundancy Maximum Relevance approach to report algorithm-agnostic feature ranking. From these methods, we find that the signal to noise of the folded profile to be the best feature. We find that all the ML algorithms report FPRs about an order of magnitude lower than the corresponding FPRs obtained in Morello et al. (2014), for the same recall value.
Development of a general learning algorithm with applications in nuclear reactor systems
International Nuclear Information System (INIS)
Brittain, C.R.; Otaduy, P.J.; Perez, R.B.
1989-12-01
The objective of this study was development of a generalized learning algorithm that can learn to predict a particular feature of a process by observation of a set of representative input examples. The algorithm uses pattern matching and statistical analysis techniques to find a functional relationship between descriptive attributes of the input examples and the feature to be predicted. The algorithm was tested by applying it to a set of examples consisting of performance descriptions for 277 fuel cycles of Oak Ridge National Laboratory's High Flux Isotope Reactor (HFIR). The program learned to predict the critical rod position for the HFIR from core configuration data prior to reactor startup. The functional relationship bases its predictions on initial core reactivity, the number of certain targets placed in the center of the reactor, and the total exposure of the control plates. Twelve characteristic fuel cycle clusters were identified. Nine fuel cycles were diagnosed as having noisy data, and one could not be predicted by the functional relationship. 13 refs., 6 figs
Development of a general learning algorithm with applications in nuclear reactor systems
Energy Technology Data Exchange (ETDEWEB)
Brittain, C.R.; Otaduy, P.J.; Perez, R.B.
1989-12-01
The objective of this study was development of a generalized learning algorithm that can learn to predict a particular feature of a process by observation of a set of representative input examples. The algorithm uses pattern matching and statistical analysis techniques to find a functional relationship between descriptive attributes of the input examples and the feature to be predicted. The algorithm was tested by applying it to a set of examples consisting of performance descriptions for 277 fuel cycles of Oak Ridge National Laboratory's High Flux Isotope Reactor (HFIR). The program learned to predict the critical rod position for the HFIR from core configuration data prior to reactor startup. The functional relationship bases its predictions on initial core reactivity, the number of certain targets placed in the center of the reactor, and the total exposure of the control plates. Twelve characteristic fuel cycle clusters were identified. Nine fuel cycles were diagnosed as having noisy data, and one could not be predicted by the functional relationship. 13 refs., 6 figs.
Sequence-based prediction of protein protein interaction using a deep-learning algorithm.
Sun, Tanlin; Zhou, Bo; Lai, Luhua; Pei, Jianfeng
2017-05-25
Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational methods for predicting PPI have been developed, their robustness for prediction with external datasets is unknown. Deep-learning algorithms have achieved successful results in diverse areas, but their effectiveness for PPI prediction has not been tested. We used a stacked autoencoder, a type of deep-learning algorithm, to study the sequence-based PPI prediction. The best model achieved an average accuracy of 97.19% with 10-fold cross-validation. The prediction accuracies for various external datasets ranged from 87.99% to 99.21%, which are superior to those achieved with previous methods. To our knowledge, this research is the first to apply a deep-learning algorithm to sequence-based PPI prediction, and the results demonstrate its potential in this field.
Directory of Open Access Journals (Sweden)
R. Venkata Rao
2014-01-01
Full Text Available The present work proposes a multi-objective improved teaching-learning based optimization (MO-ITLBO algorithm for unconstrained and constrained multi-objective function optimization. The MO-ITLBO algorithm is the improved version of basic teaching-learning based optimization (TLBO algorithm adapted for multi-objective problems. The basic TLBO algorithm is improved to enhance its exploration and exploitation capacities by introducing the concept of number of teachers, adaptive teaching factor, tutorial training and self-motivated learning. The MO-ITLBO algorithm uses a grid-based approach to adaptively assess the non-dominated solutions (i.e. Pareto front maintained in an external archive. The performance of the MO-ITLBO algorithm is assessed by implementing it on unconstrained and constrained test problems proposed for the Congress on Evolutionary Computation 2009 (CEC 2009 competition. The performance assessment is done by using the inverted generational distance (IGD measure. The IGD measures obtained by using the MO-ITLBO algorithm are compared with the IGD measures of the other state-of-the-art algorithms available in the literature. Finally, Lexicographic ordering is used to assess the overall performance of competitive algorithms. Results have shown that the proposed MO-ITLBO algorithm has obtained the 1st rank in the optimization of unconstrained test functions and the 3rd rank in the optimization of constrained test functions.
Buddala, Raviteja; Mahapatra, Siba Sankar
2017-11-01
Flexible flow shop (or a hybrid flow shop) scheduling problem is an extension of classical flow shop scheduling problem. In a simple flow shop configuration, a job having `g' operations is performed on `g' operation centres (stages) with each stage having only one machine. If any stage contains more than one machine for providing alternate processing facility, then the problem becomes a flexible flow shop problem (FFSP). FFSP which contains all the complexities involved in a simple flow shop and parallel machine scheduling problems is a well-known NP-hard (Non-deterministic polynomial time) problem. Owing to high computational complexity involved in solving these problems, it is not always possible to obtain an optimal solution in a reasonable computation time. To obtain near-optimal solutions in a reasonable computation time, a large variety of meta-heuristics have been proposed in the past. However, tuning algorithm-specific parameters for solving FFSP is rather tricky and time consuming. To address this limitation, teaching-learning-based optimization (TLBO) and JAYA algorithm are chosen for the study because these are not only recent meta-heuristics but they do not require tuning of algorithm-specific parameters. Although these algorithms seem to be elegant, they lose solution diversity after few iterations and get trapped at the local optima. To alleviate such drawback, a new local search procedure is proposed in this paper to improve the solution quality. Further, mutation strategy (inspired from genetic algorithm) is incorporated in the basic algorithm to maintain solution diversity in the population. Computational experiments have been conducted on standard benchmark problems to calculate makespan and computational time. It is found that the rate of convergence of TLBO is superior to JAYA. From the results, it is found that TLBO and JAYA outperform many algorithms reported in the literature and can be treated as efficient methods for solving the FFSP.
A STUDENT MODEL AND LEARNING ALGORITHM FOR THE EXPERT TUTORING SYSTEM OF POLISH GRAMMAR
Directory of Open Access Journals (Sweden)
Kostikov Mykola
2014-11-01
Full Text Available When creating computer-assisted language learning software, it is necessary to use the potential of information technology in controlling the learning process fully. Modern intelligent tutoring systems help to make this process adaptive and personalized thanks to modeling the domain and students’ knowledge. The aim of the paper is to investigate possibilities for applying these methods in teaching Polish grammar in Ukraine taking into account its specifics. The article is concerned with the approaches of using student models in modern intelligent tutoring systems in order to provide personalized learning. A structure of the student model and a general working algorithm of the expert tutoring system of Polish grammar have been developed. The modeling of knowing and forgetting particular learning elements within the probabilistic (stochastic model has been studied, as well as the prognostication of future probabilities of students’ knowledge, taking into account their individual forgetting rates. The objective function of instruction quality with allowance for frequency of grammar rules within a certain amount of words being learned and their connections to another rules has been formulated. The problem of generating the next learning step taking into account the need for mastering previous, connected rules has been studied, as well as determining the optimal time period between the lessons depending on the current knowledge level.
Directory of Open Access Journals (Sweden)
R. Venkata Rao
2015-12-01
Full Text Available This paper presents the performance of teaching–learning-based optimization (TLBO algorithm to obtain the optimum set of design and operating parameters for a smooth flat plate solar air heater (SFPSAH. The TLBO algorithm is a recently proposed population-based algorithm, which simulates the teaching–learning process of the classroom. Maximization of thermal efficiency is considered as an objective function for the thermal performance of SFPSAH. The number of glass plates, irradiance, and the Reynolds number are considered as the design parameters and wind velocity, tilt angle, ambient temperature, and emissivity of the plate are considered as the operating parameters to obtain the thermal performance of the SFPSAH using the TLBO algorithm. The computational results have shown that the TLBO algorithm is better or competitive to other optimization algorithms recently reported in the literature for the considered problem.
Shahinfar, Saleh; Page, David; Guenther, Jerry; Cabrera, Victor; Fricke, Paul; Weigel, Kent
2014-02-01
When making the decision about whether or not to breed a given cow, knowledge about the expected outcome would have an economic impact on profitability of the breeding program and net income of the farm. The outcome of each breeding can be affected by many management and physiological features that vary between farms and interact with each other. Hence, the ability of machine learning algorithms to accommodate complex relationships in the data and missing values for explanatory variables makes these algorithms well suited for investigation of reproduction performance in dairy cattle. The objective of this study was to develop a user-friendly and intuitive on-farm tool to help farmers make reproduction management decisions. Several different machine learning algorithms were applied to predict the insemination outcomes of individual cows based on phenotypic and genotypic data. Data from 26 dairy farms in the Alta Genetics (Watertown, WI) Advantage Progeny Testing Program were used, representing a 10-yr period from 2000 to 2010. Health, reproduction, and production data were extracted from on-farm dairy management software, and estimated breeding values were downloaded from the US Department of Agriculture Agricultural Research Service Animal Improvement Programs Laboratory (Beltsville, MD) database. The edited data set consisted of 129,245 breeding records from primiparous Holstein cows and 195,128 breeding records from multiparous Holstein cows. Each data point in the final data set included 23 and 25 explanatory variables and 1 binary outcome for of 0.756 ± 0.005 and 0.736 ± 0.005 for primiparous and multiparous cows, respectively. The naïve Bayes algorithm, Bayesian network, and decision tree algorithms showed somewhat poorer classification performance. An information-based variable selection procedure identified herd average conception rate, incidence of ketosis, number of previous (failed) inseminations, days in milk at breeding, and mastitis as the most
Sun, Wenqing; Zheng, Bin; Qian, Wei
2017-10-01
This study aimed to analyze the ability of extracting automatically generated features using deep structured algorithms in lung nodule CT image diagnosis, and compare its performance with traditional computer aided diagnosis (CADx) systems using hand-crafted features. All of the 1018 cases were acquired from Lung Image Database Consortium (LIDC) public lung cancer database. The nodules were segmented according to four radiologists' markings, and 13,668 samples were generated by rotating every slice of nodule images. Three multichannel ROI based deep structured algorithms were designed and implemented in this study: convolutional neural network (CNN), deep belief network (DBN), and stacked denoising autoencoder (SDAE). For the comparison purpose, we also implemented a CADx system using hand-crafted features including density features, texture features and morphological features. The performance of every scheme was evaluated by using a 10-fold cross-validation method and an assessment index of the area under the receiver operating characteristic curve (AUC). The observed highest area under the curve (AUC) was 0.899±0.018 achieved by CNN, which was significantly higher than traditional CADx with the AUC=0.848±0.026. The results from DBN was also slightly higher than CADx, while SDAE was slightly lower. By visualizing the automatic generated features, we found some meaningful detectors like curvy stroke detectors from deep structured schemes. The study results showed the deep structured algorithms with automatically generated features can achieve desirable performance in lung nodule diagnosis. With well-tuned parameters and large enough dataset, the deep learning algorithms can have better performance than current popular CADx. We believe the deep learning algorithms with similar data preprocessing procedure can be used in other medical image analysis areas as well. Copyright © 2017. Published by Elsevier Ltd.
Limongelli, Carla; Sciarrone, Filippo; Temperini, Marco; Vaste, Giulia
2011-01-01
LS-Lab provides automatic support to comparison/evaluation of the Learning Object Sequences produced by different Curriculum Sequencing Algorithms. Through this framework a teacher can verify the correspondence between the behaviour of different sequencing algorithms and her pedagogical preferences. In fact the teacher can compare algorithms…
Ling, J.; Templeton, J.
2015-08-01
Reynolds Averaged Navier Stokes (RANS) models are widely used in industry to predict fluid flows, despite their acknowledged deficiencies. Not only do RANS models often produce inaccurate flow predictions, but there are very limited diagnostics available to assess RANS accuracy for a given flow configuration. If experimental or higher fidelity simulation results are not available for RANS validation, there is no reliable method to evaluate RANS accuracy. This paper explores the potential of utilizing machine learning algorithms to identify regions of high RANS uncertainty. Three different machine learning algorithms were evaluated: support vector machines, Adaboost decision trees, and random forests. The algorithms were trained on a database of canonical flow configurations for which validated direct numerical simulation or large eddy simulation results were available, and were used to classify RANS results on a point-by-point basis as having either high or low uncertainty, based on the breakdown of specific RANS modeling assumptions. Classifiers were developed for three different basic RANS eddy viscosity model assumptions: the isotropy of the eddy viscosity, the linearity of the Boussinesq hypothesis, and the non-negativity of the eddy viscosity. It is shown that these classifiers are able to generalize to flows substantially different from those on which they were trained. Feature selection techniques, model evaluation, and extrapolation detection are discussed in the context of turbulence modeling applications.
FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks.
Zhang, Zhen; Zhao, Dongbin; Gao, Junwei; Wang, Dongqing; Dai, Yujie
2017-06-01
In this paper, we propose a multiagent reinforcement learning algorithm dealing with fully cooperative tasks. The algorithm is called frequency of the maximum reward Q-learning (FMRQ). FMRQ aims to achieve one of the optimal Nash equilibria so as to optimize the performance index in multiagent systems. The frequency of obtaining the highest global immediate reward instead of immediate reward is used as the reinforcement signal. With FMRQ each agent does not need the observation of the other agents' actions and only shares its state and reward at each step. We validate FMRQ through case studies of repeated games: four cases of two-player two-action and one case of three-player two-action. It is demonstrated that FMRQ can converge to one of the optimal Nash equilibria in these cases. Moreover, comparison experiments on tasks with multiple states and finite steps are conducted. One is box-pushing and the other one is distributed sensor network problem. Experimental results show that the proposed algorithm outperforms others with higher performance.
Szantoi, Zoltan; Escobedo, Francisco J; Abd-Elrahman, Amr; Pearlstine, Leonard; Dewitt, Bon; Smith, Scot
2015-05-01
Mapping of wetlands (marsh vs. swamp vs. upland) is a common remote sensing application.Yet, discriminating between similar freshwater communities such as graminoid/sedge fromremotely sensed imagery is more difficult. Most of this activity has been performed using medium to low resolution imagery. There are only a few studies using highspatial resolutionimagery and machine learning image classification algorithms for mapping heterogeneouswetland plantcommunities. This study addresses this void by analyzing whether machine learning classifierssuch as decisiontrees (DT) and artificial neural networks (ANN) can accurately classify graminoid/sedgecommunities usinghigh resolution aerial imagery and image texture data in the Everglades National Park, Florida.In addition tospectral bands, the normalized difference vegetation index, and first- and second-order texturefeatures derivedfrom the near-infrared band were analyzed. Classifier accuracies were assessed using confusiontablesand the calculated kappa coefficients of the resulting maps. The results indicated that an ANN(multilayerperceptron based on backpropagation) algorithm produced a statistically significantly higheraccuracy(82.04%) than the DT (QUEST) algorithm (80.48%) or the maximum likelihood (80.56%)classifier (αtexture features.
Van Summeren, M. J. H.; Spliet, W. G. M.; Van Royen-Kerkhof, A.; Vermeer, C.; Lilien, M.; Kuis, W.; Schurgers, L. J.
Objectives. The aims of the present study were to investigate whether the calcification inhibitor matrix Gla protein (MGP) is expressed in muscle biopsies of patients with juvenile dermatomyositis (JDM), and whether different forms of MGP are differentially expressed in JDM patients with and without
Sokolov, Anton; Gengembre, Cyril; Dmitriev, Egor; Delbarre, Hervé
2017-04-01
The problem is considered of classification of local atmospheric meteorological events in the coastal area such as sea breezes, fogs and storms. The in-situ meteorological data as wind speed and direction, temperature, humidity and turbulence are used as predictors. Local atmospheric events of 2013-2014 were analysed manually to train classification algorithms in the coastal area of English Channel in Dunkirk (France). Then, ultrasonic anemometer data and LIDAR wind profiler data were used as predictors. A few algorithms were applied to determine meteorological events by local data such as a decision tree, the nearest neighbour classifier, a support vector machine. The comparison of classification algorithms was carried out, the most important predictors for each event type were determined. It was shown that in more than 80 percent of the cases machine learning algorithms detect the meteorological class correctly. We expect that this methodology could be applied also to classify events by climatological in-situ data or by modelling data. It allows estimating frequencies of each event in perspective of climate change.
Directory of Open Access Journals (Sweden)
Aiming Liu
2017-11-01
Full Text Available Motor Imagery (MI electroencephalography (EEG is widely studied for its non-invasiveness, easy availability, portability, and high temporal resolution. As for MI EEG signal processing, the high dimensions of features represent a research challenge. It is necessary to eliminate redundant features, which not only create an additional overhead of managing the space complexity, but also might include outliers, thereby reducing classification accuracy. The firefly algorithm (FA can adaptively select the best subset of features, and improve classification accuracy. However, the FA is easily entrapped in a local optimum. To solve this problem, this paper proposes a method of combining the firefly algorithm and learning automata (LA to optimize feature selection for motor imagery EEG. We employed a method of combining common spatial pattern (CSP and local characteristic-scale decomposition (LCD algorithms to obtain a high dimensional feature set, and classified it by using the spectral regression discriminant analysis (SRDA classifier. Both the fourth brain–computer interface competition data and real-time data acquired in our designed experiments were used to verify the validation of the proposed method. Compared with genetic and adaptive weight particle swarm optimization algorithms, the experimental results show that our proposed method effectively eliminates redundant features, and improves the classification accuracy of MI EEG signals. In addition, a real-time brain–computer interface system was implemented to verify the feasibility of our proposed methods being applied in practical brain–computer interface systems.
Predicting the Occurrence of Haze Events in Southeast Asia using Machine Learning Algorithms
Lee, H. H.; Chulakadabba, A.; Tonks, A.; Yang, Z.; Wang, C.
2017-12-01
Severe local- and regional-scale air pollution episodes typically originate from 1) high emissions of air pollutants, 2) poor dispersion conditions, and 3) trans-boundary pollutant transport. Biomass burning activities have become more frequent in Southeast Asia, especially in Sumatra, Borneo, and the mainland Southeast. Trans-boundary transport of biomass burning aerosols often lead to air quality problems in the region. Furthermore, particulate pollutants from human activities besides biomass burning also play an important role in the air quality of Southeast Asia. Singapore, for example, has a dynamic industrial sector including chemical, electric and metallurgic industries, and is the region's major petroleum-refining center. In addition, natural gas and oil power plants, waste incinerators, active port traffic, and a major regional airport further complicate Singapore's air quality issues. In this study, we compare five Machine Learning algorithms: k-Nearest Neighbors, Linear Support Vector Machine, Decision Tree, Random Forest and Artificial Neural Network, to identify haze patterns and determine variable importance. The algorithms were trained using local atmospheric data (i.e. months, atmospheric conditions, wind direction and relative humidity) from three observation stations in Singapore (Changi, Seletar and Paya Labar). We find that the algorithms reveal the associations in data within and between the stations, and provide in-depth interpretation of the haze sources. The algorithms also allow us to predict the probability of haze episodes in Singapore and to determine the correlation between this probability and atmospheric conditions.
Liu, Aiming; Chen, Kun; Liu, Quan; Ai, Qingsong; Xie, Yi; Chen, Anqi
2017-11-08
Motor Imagery (MI) electroencephalography (EEG) is widely studied for its non-invasiveness, easy availability, portability, and high temporal resolution. As for MI EEG signal processing, the high dimensions of features represent a research challenge. It is necessary to eliminate redundant features, which not only create an additional overhead of managing the space complexity, but also might include outliers, thereby reducing classification accuracy. The firefly algorithm (FA) can adaptively select the best subset of features, and improve classification accuracy. However, the FA is easily entrapped in a local optimum. To solve this problem, this paper proposes a method of combining the firefly algorithm and learning automata (LA) to optimize feature selection for motor imagery EEG. We employed a method of combining common spatial pattern (CSP) and local characteristic-scale decomposition (LCD) algorithms to obtain a high dimensional feature set, and classified it by using the spectral regression discriminant analysis (SRDA) classifier. Both the fourth brain-computer interface competition data and real-time data acquired in our designed experiments were used to verify the validation of the proposed method. Compared with genetic and adaptive weight particle swarm optimization algorithms, the experimental results show that our proposed method effectively eliminates redundant features, and improves the classification accuracy of MI EEG signals. In addition, a real-time brain-computer interface system was implemented to verify the feasibility of our proposed methods being applied in practical brain-computer interface systems.
Optimal design of planar slider-crank mechanism using teaching-learning-based optimization algorithm
International Nuclear Information System (INIS)
Chaudhary, Kailash; Chaudhary, Himanshu
2015-01-01
In this paper, a two stage optimization technique is presented for optimum design of planar slider-crank mechanism. The slider crank mechanism needs to be dynamically balanced to reduce vibrations and noise in the engine and to improve the vehicle performance. For dynamic balancing, minimization of the shaking force and the shaking moment is achieved by finding optimum mass distribution of crank and connecting rod using the equipemental system of point-masses in the first stage of the optimization. In the second stage, their shapes are synthesized systematically by closed parametric curve, i.e., cubic B-spline curve corresponding to the optimum inertial parameters found in the first stage. The multi-objective optimization problem to minimize both the shaking force and the shaking moment is solved using Teaching-learning-based optimization algorithm (TLBO) and its computational performance is compared with Genetic algorithm (GA).
Auto-SEIA: simultaneous optimization of image processing and machine learning algorithms
Negro Maggio, Valentina; Iocchi, Luca
2015-02-01
Object classification from images is an important task for machine vision and it is a crucial ingredient for many computer vision applications, ranging from security and surveillance to marketing. Image based object classification techniques properly integrate image processing and machine learning (i.e., classification) procedures. In this paper we present a system for automatic simultaneous optimization of algorithms and parameters for object classification from images. More specifically, the proposed system is able to process a dataset of labelled images and to return a best configuration of image processing and classification algorithms and of their parameters with respect to the accuracy of classification. Experiments with real public datasets are used to demonstrate the effectiveness of the developed system.
Optimal design of planar slider-crank mechanism using teaching-learning-based optimization algorithm
Energy Technology Data Exchange (ETDEWEB)
Chaudhary, Kailash; Chaudhary, Himanshu [Malaviya National Institute of Technology, Jaipur (Malaysia)
2015-11-15
In this paper, a two stage optimization technique is presented for optimum design of planar slider-crank mechanism. The slider crank mechanism needs to be dynamically balanced to reduce vibrations and noise in the engine and to improve the vehicle performance. For dynamic balancing, minimization of the shaking force and the shaking moment is achieved by finding optimum mass distribution of crank and connecting rod using the equipemental system of point-masses in the first stage of the optimization. In the second stage, their shapes are synthesized systematically by closed parametric curve, i.e., cubic B-spline curve corresponding to the optimum inertial parameters found in the first stage. The multi-objective optimization problem to minimize both the shaking force and the shaking moment is solved using Teaching-learning-based optimization algorithm (TLBO) and its computational performance is compared with Genetic algorithm (GA).
Discrete Teaching-learning-based optimization Algorithm for Traveling Salesman Problems
Directory of Open Access Journals (Sweden)
Wu Lehui
2017-01-01
Full Text Available In this paper, a discrete variant of TLBO (DTLBO is proposed for solving the traveling salesman problem (TSP. In the proposed method, an effective learner representation scheme is redefined based on the characteristics of TSP problem. Moreover, all learners are randomly divided into several sub-swarms with equal amounts of learners so as to increase the diversity of population and reduce the probability of being trapped in local optimum. In each sub-swarm, the new positions of learners in the teaching phase and the learning phase are generated by the crossover operation, the legality detection and mutation operation, and then the offspring learners are determined based on greedy selection. Finally, to verify the performance of the proposed algorithm, benchmark TSP problems are examined and the results indicate that DTLBO is effective compared with other algorithms used for TSP problems.
Machine learning based cloud mask algorithm driven by radiative transfer modeling
Chen, N.; Li, W.; Tanikawa, T.; Hori, M.; Shimada, R.; Stamnes, K. H.
2017-12-01
Cloud detection is a critically important first step required to derive many satellite data products. Traditional threshold based cloud mask algorithms require a complicated design process and fine tuning for each sensor, and have difficulty over snow/ice covered areas. With the advance of computational power and machine learning techniques, we have developed a new algorithm based on a neural network classifier driven by extensive radiative transfer modeling. Statistical validation results obtained by using collocated CALIOP and MODIS data show that its performance is consistent over different ecosystems and significantly better than the MODIS Cloud Mask (MOD35 C6) during the winter seasons over mid-latitude snow covered areas. Simulations using a reduced number of satellite channels also show satisfactory results, indicating its flexibility to be configured for different sensors.
Mundher Yaseen, Zaher; Abdulmohsin Afan, Haitham; Tran, Minh-Tung
2018-04-01
Scientifically evidenced that beam-column joints are a critical point in the reinforced concrete (RC) structure under the fluctuation loads effects. In this novel hybrid data-intelligence model developed to predict the joint shear behavior of exterior beam-column structure frame. The hybrid data-intelligence model is called genetic algorithm integrated with deep learning neural network model (GA-DLNN). The genetic algorithm is used as prior modelling phase for the input approximation whereas the DLNN predictive model is used for the prediction phase. To demonstrate this structural problem, experimental data is collected from the literature that defined the dimensional and specimens’ properties. The attained findings evidenced the efficitveness of the hybrid GA-DLNN in modelling beam-column joint shear problem. In addition, the accurate prediction achived with less input variables owing to the feasibility of the evolutionary phase.
Development of a Machine Learning Algorithm for the Surveillance of Autism Spectrum Disorder.
Directory of Open Access Journals (Sweden)
Matthew J Maenner
Full Text Available The Autism and Developmental Disabilities Monitoring (ADDM Network conducts population-based surveillance of autism spectrum disorder (ASD among 8-year old children in multiple US sites. To classify ASD, trained clinicians review developmental evaluations collected from multiple health and education sources to determine whether the child meets the ASD surveillance case criteria. The number of evaluations collected has dramatically increased since the year 2000, challenging the resources and timeliness of the surveillance system. We developed and evaluated a machine learning approach to classify case status in ADDM using words and phrases contained in children's developmental evaluations. We trained a random forest classifier using data from the 2008 Georgia ADDM site which included 1,162 children with 5,396 evaluations (601 children met ADDM ASD criteria using standard ADDM methods. The classifier used the words and phrases from the evaluations to predict ASD case status. We evaluated its performance on the 2010 Georgia ADDM surveillance data (1,450 children with 9,811 evaluations; 754 children met ADDM ASD criteria. We also estimated ASD prevalence using predictions from the classification algorithm. Overall, the machine learning approach predicted ASD case statuses that were 86.5% concordant with the clinician-determined case statuses (84.0% sensitivity, 89.4% predictive value positive. The area under the resulting receiver-operating characteristic curve was 0.932. Algorithm-derived ASD "prevalence" was 1.46% compared to the published (clinician-determined estimate of 1.55%. Using only the text contained in developmental evaluations, a machine learning algorithm was able to discriminate between children that do and do not meet ASD surveillance criteria at one surveillance site.
Nikitin, P. V.; Savinov, A. N.; Bazhenov, R. I.; Sivandaev, S. V.
2018-05-01
The article describes the method of identifying a person in distance learning systems based on a keyboard rhythm. An algorithm for the organization of access control is proposed, which implements authentication, identification and verification of a person using the keyboard rhythm. Authentication methods based on biometric personal parameters, including those based on the keyboard rhythm, due to the inexistence of biometric characteristics without a particular person, are able to provide an advanced accuracy and inability to refuse authorship and convenience for operators of automated systems, in comparison with other methods of conformity checking. Methods of permanent hidden keyboard monitoring allow detecting the substitution of a student and blocking the key system.
Secondary Structure Prediction of Protein using Resilient Back Propagation Learning Algorithm
Directory of Open Access Journals (Sweden)
Jyotshna Dongardive
2015-12-01
Full Text Available The paper proposes a neural network based approach to predict secondary structure of protein. It uses Multilayer Feed Forward Network (MLFN with resilient back propagation as the learning algorithm. Point Accepted Mutation (PAM is adopted as the encoding scheme and CB396 data set is used for the training and testing of the network. Overall accuracy of the network has been experimentally calculated with different window sizes for the sliding window scheme and by varying the number of units in the hidden layer. The best results were obtained with eleven as the window size and seven as the number of units in the hidden layer.
On the best learning algorithm for web services response time prediction
DEFF Research Database (Denmark)
Madsen, Henrik; Albu, Razvan-Daniel; Popentiu-Vladicescu, Florin
2013-01-01
In this article we will examine the effect of different learning algorithms, while training the MLP (Multilayer Perceptron) with the intention of predicting web services response time. Web services do not necessitate a user interface. This may seem contradictory to most people's concept of what...... an application is. A Web service is better imagined as an application "segment," or better as a program enabler. Performance is an important quality aspect of Web services because of their distributed nature. Predicting the response of web services during their operation is very important....
Learning-Based Precool Algorithms for Exploiting Foodstuff as Thermal Energy Reserve
DEFF Research Database (Denmark)
Vinther, Kasper; Rasmussen, Henrik; Izadi-Zamanabadi, Roozbeh
2015-01-01
Refrigeration is important to sustain high foodstuff quality and lifetime. Keeping the foodstuff within temperature thresholds in supermarkets is also important due to legislative requirements. Failure to do so can result in discarded foodstuff, a penalty fine to the shop owner, and health issues....... However, the refrigeration system might not be dimensioned to cope with hot summer days or performance degradation over time. Two learning-based algorithms are therefore proposed for thermostatically controlled loads, which precools the foodstuff in display cases in an anticipatory manner based on how...
A Learning Based Precool Algorithm for Utilization of Foodstuff as Thermal Energy Storage
DEFF Research Database (Denmark)
Vinther, Kasper; Rasmussen, Henrik; Izadi-Zamanabadi, Roozbeh
2013-01-01
Maintaining foodstuff within predefined temperature thresholds is important due to legislative requirements and to sustain high foodstuff quality. This is achieved using a refrigeration system. However, these systems might not be dimensioned for hot summer days or possible component performance...... degradation. A learning based algorithm is proposed in this paper, which precools the foodstuff in an anticipatory manner based on the saturation level in the system on recent days. The method is evaluated using a simulation model of a supermarket refrigeration system and simulations show that thermal energy...
Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression.
Sato, João R; Moll, Jorge; Green, Sophie; Deakin, John F W; Thomaz, Carlos E; Zahn, Roland
2015-08-30
Standard functional magnetic resonance imaging (fMRI) analyses cannot assess the potential of a neuroimaging signature as a biomarker to predict individual vulnerability to major depression (MD). Here, we use machine learning for the first time to address this question. Using a recently identified neural signature of guilt-selective functional disconnection, the classification algorithm was able to distinguish remitted MD from control participants with 78.3% accuracy. This demonstrates the high potential of our fMRI signature as a biomarker of MD vulnerability. Crown Copyright © 2015. Published by Elsevier Ireland Ltd. All rights reserved.
International Nuclear Information System (INIS)
Machado, Marcelo Dornellas
1999-04-01
Genetic algorithms are biologically motivated adaptive systems which have been used, with good results, for function optimization. In this work, a new learning mode, to be used by the Population-Based Incremental Learning (PBIL) algorithm, who combines mechanisms of standard genetic algorithm with simple competitive learning, has the aim to build a new evolutionary algorithm to be used in optimization of numerical problems and combinatorial problems. This new learning mode uses a variable learning rate during the optimization process, constituting a process know as proportional reward. The development of this new algorithm aims its application in the optimization of reload problem of PWR nuclear reactors. This problem can be interpreted as search of a load pattern to be used in the nucleus of the reactor in order to increase the useful life of the nuclear fuel. For the test, two classes of problems are used: numerical problems and combinatorial problem, the major interest relies on the last class. The results achieved with the tests indicate the applicability of the new learning mode, showing its potential as a developing tool in the solution of reload problem. (author)
A new learning algorithm for a fully connected neuro-fuzzy inference system.
Chen, C L Philip; Wang, Jing; Wang, Chi-Hsu; Chen, Long
2014-10-01
A traditional neuro-fuzzy system is transformed into an equivalent fully connected three layer neural network (NN), namely, the fully connected neuro-fuzzy inference systems (F-CONFIS). The F-CONFIS differs from traditional NNs by its dependent and repeated weights between input and hidden layers and can be considered as the variation of a kind of multilayer NN. Therefore, an efficient learning algorithm for the F-CONFIS to cope these repeated weights is derived. Furthermore, a dynamic learning rate is proposed for neuro-fuzzy systems via F-CONFIS where both premise (hidden) and consequent portions are considered. Several simulation results indicate that the proposed approach achieves much better accuracy and fast convergence.
Yan, Jingwen; Du, Lei; Kim, Sungeun; Risacher, Shannon L; Huang, Heng; Moore, Jason H; Saykin, Andrew J; Shen, Li
2014-09-01
Imaging genetics is an emerging field that studies the influence of genetic variation on brain structure and function. The major task is to examine the association between genetic markers such as single-nucleotide polymorphisms (SNPs) and quantitative traits (QTs) extracted from neuroimaging data. The complexity of these datasets has presented critical bioinformatics challenges that require new enabling tools. Sparse canonical correlation analysis (SCCA) is a bi-multivariate technique used in imaging genetics to identify complex multi-SNP-multi-QT associations. However, most of the existing SCCA algorithms are designed using the soft thresholding method, which assumes that the input features are independent from one another. This assumption clearly does not hold for the imaging genetic data. In this article, we propose a new knowledge-guided SCCA algorithm (KG-SCCA) to overcome this limitation as well as improve learning results by incorporating valuable prior knowledge. The proposed KG-SCCA method is able to model two types of prior knowledge: one as a group structure (e.g. linkage disequilibrium blocks among SNPs) and the other as a network structure (e.g. gene co-expression network among brain regions). The new model incorporates these prior structures by introducing new regularization terms to encourage weight similarity between grouped or connected features. A new algorithm is designed to solve the KG-SCCA model without imposing the independence constraint on the input features. We demonstrate the effectiveness of our algorithm with both synthetic and real data. For real data, using an Alzheimer's disease (AD) cohort, we examine the imaging genetic associations between all SNPs in the APOE gene (i.e. top AD gene) and amyloid deposition measures among cortical regions (i.e. a major AD hallmark). In comparison with a widely used SCCA implementation, our KG-SCCA algorithm produces not only improved cross-validation performances but also biologically meaningful
A deep learning method for lincRNA detection using auto-encoder algorithm.
Yu, Ning; Yu, Zeng; Pan, Yi
2017-12-06
RNA sequencing technique (RNA-seq) enables scientists to develop novel data-driven methods for discovering more unidentified lincRNAs. Meantime, knowledge-based technologies are experiencing a potential revolution ignited by the new deep learning methods. By scanning the newly found data set from RNA-seq, scientists have found that: (1) the expression of lincRNAs appears to be regulated, that is, the relevance exists along the DNA sequences; (2) lincRNAs contain some conversed patterns/motifs tethered together by non-conserved regions. The two evidences give the reasoning for adopting knowledge-based deep learning methods in lincRNA detection. Similar to coding region transcription, non-coding regions are split at transcriptional sites. However, regulatory RNAs rather than message RNAs are generated. That is, the transcribed RNAs participate the biological process as regulatory units instead of generating proteins. Identifying these transcriptional regions from non-coding regions is the first step towards lincRNA recognition. The auto-encoder method achieves 100% and 92.4% prediction accuracy on transcription sites over the putative data sets. The experimental results also show the excellent performance of predictive deep neural network on the lincRNA data sets compared with support vector machine and traditional neural network. In addition, it is validated through the newly discovered lincRNA data set and one unreported transcription site is found by feeding the whole annotated sequences through the deep learning machine, which indicates that deep learning method has the extensive ability for lincRNA prediction. The transcriptional sequences of lincRNAs are collected from the annotated human DNA genome data. Subsequently, a two-layer deep neural network is developed for the lincRNA detection, which adopts the auto-encoder algorithm and utilizes different encoding schemes to obtain the best performance over intergenic DNA sequence data. Driven by those newly
Machine learning algorithms for mode-of-action classification in toxicity assessment.
Zhang, Yile; Wong, Yau Shu; Deng, Jian; Anton, Cristina; Gabos, Stephan; Zhang, Weiping; Huang, Dorothy Yu; Jin, Can
2016-01-01
Real Time Cell Analysis (RTCA) technology is used to monitor cellular changes continuously over the entire exposure period. Combining with different testing concentrations, the profiles have potential in probing the mode of action (MOA) of the testing substances. In this paper, we present machine learning approaches for MOA assessment. Computational tools based on artificial neural network (ANN) and support vector machine (SVM) are developed to analyze the time-concentration response curves (TCRCs) of human cell lines responding to tested chemicals. The techniques are capable of learning data from given TCRCs with known MOA information and then making MOA classification for the unknown toxicity. A novel data processing step based on wavelet transform is introduced to extract important features from the original TCRC data. From the dose response curves, time interval leading to higher classification success rate can be selected as input to enhance the performance of the machine learning algorithm. This is particularly helpful when handling cases with limited and imbalanced data. The validation of the proposed method is demonstrated by the supervised learning algorithm applied to the exposure data of HepG2 cell line to 63 chemicals with 11 concentrations in each test case. Classification success rate in the range of 85 to 95 % are obtained using SVM for MOA classification with two clusters to cases up to four clusters. Wavelet transform is capable of capturing important features of TCRCs for MOA classification. The proposed SVM scheme incorporated with wavelet transform has a great potential for large scale MOA classification and high-through output chemical screening.
PEDLA: predicting enhancers with a deep learning-based algorithmic framework.
Liu, Feng; Li, Hao; Ren, Chao; Bo, Xiaochen; Shu, Wenjie
2016-06-22
Transcriptional enhancers are non-coding segments of DNA that play a central role in the spatiotemporal regulation of gene expression programs. However, systematically and precisely predicting enhancers remain a major challenge. Although existing methods have achieved some success in enhancer prediction, they still suffer from many issues. We developed a deep learning-based algorithmic framework named PEDLA (https://github.com/wenjiegroup/PEDLA), which can directly learn an enhancer predictor from massively heterogeneous data and generalize in ways that are mostly consistent across various cell types/tissues. We first trained PEDLA with 1,114-dimensional heterogeneous features in H1 cells, and demonstrated that PEDLA framework integrates diverse heterogeneous features and gives state-of-the-art performance relative to five existing methods for enhancer prediction. We further extended PEDLA to iteratively learn from 22 training cell types/tissues. Our results showed that PEDLA manifested superior performance consistency in both training and independent test sets. On average, PEDLA achieved 95.0% accuracy and a 96.8% geometric mean (GM) of sensitivity and specificity across 22 training cell types/tissues, as well as 95.7% accuracy and a 96.8% GM across 20 independent test cell types/tissues. Together, our work illustrates the power of harnessing state-of-the-art deep learning techniques to consistently identify regulatory elements at a genome-wide scale from massively heterogeneous data across diverse cell types/tissues.
Semi-supervised prediction of gene regulatory networks using machine learning algorithms.
Patel, Nihir; Wang, Jason T L
2015-10-01
Use of computational methods to predict gene regulatory networks (GRNs) from gene expression data is a challenging task. Many studies have been conducted using unsupervised methods to fulfill the task; however, such methods usually yield low prediction accuracies due to the lack of training data. In this article, we propose semi-supervised methods for GRN prediction by utilizing two machine learning algorithms, namely, support vector machines (SVM) and random forests (RF). The semi-supervised methods make use of unlabelled data for training. We investigated inductive and transductive learning approaches, both of which adopt an iterative procedure to obtain reliable negative training data from the unlabelled data. We then applied our semi-supervised methods to gene expression data of Escherichia coli and Saccharomyces cerevisiae, and evaluated the performance of our methods using the expression data. Our analysis indicated that the transductive learning approach outperformed the inductive learning approach for both organisms. However, there was no conclusive difference identified in the performance of SVM and RF. Experimental results also showed that the proposed semi-supervised methods performed better than existing supervised methods for both organisms.
Munir; Sutarno, H.; Aisyah, N. S.
2018-05-01
This research aims to find out how the development of interactive multimedia based on auditory, intellectually, and repetition can improve student learning outcomes. This interactive multimedia is developed through 5 stages. Analysis stages include the study of literature, questionnaire, interviews and observations. The design phase is done by the database design, flowchart, storyboards and repetition algorithm material while the development phase is done by the creation of web-based framework. Presentation material is adapted to the model of learning such as auditory, intellectually, repetition. Auditory points are obtained by recording the narrative material that presented by a variety of intellectual points. Multimedia as a product is validated by material and media experts. Implementation phase conducted on grade XI-TKJ2 SMKN 1 Garut. Based on index’s gain, an increasing of student learning outcomes in this study is 0.46 which is fair due to interest of student in using interactive multimedia. While the multimedia assessment earned 84.36% which is categorized as very well.
Application of Reinforcement Learning in Cognitive Radio Networks: Models and Algorithms
Directory of Open Access Journals (Sweden)
Kok-Lim Alvin Yau
2014-01-01
Full Text Available Cognitive radio (CR enables unlicensed users to exploit the underutilized spectrum in licensed spectrum whilst minimizing interference to licensed users. Reinforcement learning (RL, which is an artificial intelligence approach, has been applied to enable each unlicensed user to observe and carry out optimal actions for performance enhancement in a wide range of schemes in CR, such as dynamic channel selection and channel sensing. This paper presents new discussions of RL in the context of CR networks. It provides an extensive review on how most schemes have been approached using the traditional and enhanced RL algorithms through state, action, and reward representations. Examples of the enhancements on RL, which do not appear in the traditional RL approach, are rules and cooperative learning. This paper also reviews performance enhancements brought about by the RL algorithms and open issues. This paper aims to establish a foundation in order to spark new research interests in this area. Our discussion has been presented in a tutorial manner so that it is comprehensive to readers outside the specialty of RL and CR.
Directory of Open Access Journals (Sweden)
R. Jegadeeshwaran
2015-03-01
Full Text Available In automobile, brake system is an essential part responsible for control of the vehicle. Any failure in the brake system impacts the vehicle's motion. It will generate frequent catastrophic effects on the vehicle cum passenger's safety. Thus the brake system plays a vital role in an automobile and hence condition monitoring of the brake system is essential. Vibration based condition monitoring using machine learning techniques are gaining momentum. This study is one such attempt to perform the condition monitoring of a hydraulic brake system through vibration analysis. In this research, the performance of a Clonal Selection Classification Algorithm (CSCA for brake fault diagnosis has been reported. A hydraulic brake system test rig was fabricated. Under good and faulty conditions of a brake system, the vibration signals were acquired using a piezoelectric transducer. The statistical parameters were extracted from the vibration signal. The best feature set was identified for classification using attribute evaluator. The selected features were then classified using CSCA. The classification accuracy of such artificial intelligence technique has been compared with other machine learning approaches and discussed. The Clonal Selection Classification Algorithm performs better and gives the maximum classification accuracy (96% for the fault diagnosis of a hydraulic brake system.
Kryshchyshyn, Anna; Devinyak, Oleg; Kaminskyy, Danylo; Grellier, Philippe; Lesyk, Roman
2017-11-14
This paper presents novel QSAR models for the prediction of antitrypanosomal activity among thiazolidines and related heterocycles. The performance of four machine learning algorithms: Random Forest regression, Stochastic gradient boosting, Multivariate adaptive regression splines and Gaussian processes regression have been studied in order to reach better levels of predictivity. The results for Random Forest and Gaussian processes regression are comparable and outperform other studied methods. The preliminary descriptor selection with Boruta method improved the outcome of machine learning methods. The two novel QSAR-models developed with Random Forest and Gaussian processes regression algorithms have good predictive ability, which was proved by the external evaluation of the test set with corresponding Q 2 ext =0.812 and Q 2 ext =0.830. The obtained models can be used further for in silico screening of virtual libraries in the same chemical domain in order to find new antitrypanosomal agents. Thorough analysis of descriptors influence in the QSAR models and interpretation of their chemical meaning allows to highlight a number of structure-activity relationships. The presence of phenyl rings with electron-withdrawing atoms or groups in para-position, increased number of aromatic rings, high branching but short chains, high HOMO energy, and the introduction of 1-substituted 2-indolyl fragment into the molecular structure have been recognized as trypanocidal activity prerequisites. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.
Hatipoglu, Nuh; Bilgin, Gokhan
2017-10-01
In many computerized methods for cell detection, segmentation, and classification in digital histopathology that have recently emerged, the task of cell segmentation remains a chief problem for image processing in designing computer-aided diagnosis (CAD) systems. In research and diagnostic studies on cancer, pathologists can use CAD systems as second readers to analyze high-resolution histopathological images. Since cell detection and segmentation are critical for cancer grade assessments, cellular and extracellular structures should primarily be extracted from histopathological images. In response, we sought to identify a useful cell segmentation approach with histopathological images that uses not only prominent deep learning algorithms (i.e., convolutional neural networks, stacked autoencoders, and deep belief networks), but also spatial relationships, information of which is critical for achieving better cell segmentation results. To that end, we collected cellular and extracellular samples from histopathological images by windowing in small patches with various sizes. In experiments, the segmentation accuracies of the methods used improved as the window sizes increased due to the addition of local spatial and contextual information. Once we compared the effects of training sample size and influence of window size, results revealed that the deep learning algorithms, especially convolutional neural networks and partly stacked autoencoders, performed better than conventional methods in cell segmentation.
Short-Term Solar Forecasting Performance of Popular Machine Learning Algorithms: Preprint
Energy Technology Data Exchange (ETDEWEB)
Florita, Anthony R [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Elgindy, Tarek [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Hodge, Brian S [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Dobbs, Alex [National Renewable Energy Laboratory (NREL), Golden, CO (United States)
2017-10-03
A framework for assessing the performance of short-term solar forecasting is presented in conjunction with a range of numerical results using global horizontal irradiation (GHI) from the open-source Surface Radiation Budget (SURFRAD) data network. A suite of popular machine learning algorithms is compared according to a set of statistically distinct metrics and benchmarked against the persistence-of-cloudiness forecast and a cloud motion forecast. Results show significant improvement compared to the benchmarks with trade-offs among the machine learning algorithms depending on the desired error metric. Training inputs include time series observations of GHI for a history of years, historical weather and atmospheric measurements, and corresponding date and time stamps such that training sensitivities might be inferred. Prediction outputs are GHI forecasts for 1, 2, 3, and 4 hours ahead of the issue time, and they are made for every month of the year for 7 locations. Photovoltaic power and energy outputs can then be made using the solar forecasts to better understand power system impacts.
Xia, Youshen; Kamel, Mohamed S
2007-06-01
Identification of a general nonlinear noisy system viewed as an estimation of a predictor function is studied in this article. A measurement fusion method for the predictor function estimate is proposed. In the proposed scheme, observed data are first fused by using an optimal fusion technique, and then the optimal fused data are incorporated in a nonlinear function estimator based on a robust least squares support vector machine (LS-SVM). A cooperative learning algorithm is proposed to implement the proposed measurement fusion method. Compared with related identification methods, the proposed method can minimize both the approximation error and the noise error. The performance analysis shows that the proposed optimal measurement fusion function estimate has a smaller mean square error than the LS-SVM function estimate. Moreover, the proposed cooperative learning algorithm can converge globally to the optimal measurement fusion function estimate. Finally, the proposed measurement fusion method is applied to ARMA signal and spatial temporal signal modeling. Experimental results show that the proposed measurement fusion method can provide a more accurate model.
Open source machine-learning algorithms for the prediction of optimal cancer drug therapies.
Huang, Cai; Mezencev, Roman; McDonald, John F; Vannberg, Fredrik
2017-01-01
Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM) algorithm combined with a standard recursive feature elimination (RFE) approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60). The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be "drivers" of cancer onset/progression. Application of our models to publically available ovarian cancer (OC) patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm "open source", we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.
Directory of Open Access Journals (Sweden)
Ricardo Andres Pizarro
2016-12-01
Full Text Available High-resolution three-dimensional magnetic resonance imaging (3D-MRI is being increasingly used to delineate morphological changes underlying neuropsychiatric disorders. Unfortunately, artifacts frequently compromise the utility of 3D-MRI yielding irreproducible results, from both type I and type II errors. It is therefore critical to screen 3D-MRIs for artifacts before use. Currently, quality assessment involves slice-wise visual inspection of 3D-MRI volumes, a procedure that is both subjective and time consuming. Automating the quality rating of 3D-MRI could improve the efficiency and reproducibility of the procedure. The present study is one of the first efforts to apply a support vector machine (SVM algorithm in the quality assessment of structural brain images, using global and region of interest (ROI automated image quality features developed in-house. SVM is a supervised machine-learning algorithm that can predict the category of test datasets based on the knowledge acquired from a learning dataset. The performance (accuracy of the automated SVM approach was assessed, by comparing the SVM-predicted quality labels to investigator-determined quality labels. The accuracy for classifying 1457 3D-MRI volumes from our database using the SVM approach is around 80%. These results are promising and illustrate the possibility of using SVM as an automated quality assessment tool for 3D-MRI.
Pizarro, Ricardo A; Cheng, Xi; Barnett, Alan; Lemaitre, Herve; Verchinski, Beth A; Goldman, Aaron L; Xiao, Ena; Luo, Qian; Berman, Karen F; Callicott, Joseph H; Weinberger, Daniel R; Mattay, Venkata S
2016-01-01
High-resolution three-dimensional magnetic resonance imaging (3D-MRI) is being increasingly used to delineate morphological changes underlying neuropsychiatric disorders. Unfortunately, artifacts frequently compromise the utility of 3D-MRI yielding irreproducible results, from both type I and type II errors. It is therefore critical to screen 3D-MRIs for artifacts before use. Currently, quality assessment involves slice-wise visual inspection of 3D-MRI volumes, a procedure that is both subjective and time consuming. Automating the quality rating of 3D-MRI could improve the efficiency and reproducibility of the procedure. The present study is one of the first efforts to apply a support vector machine (SVM) algorithm in the quality assessment of structural brain images, using global and region of interest (ROI) automated image quality features developed in-house. SVM is a supervised machine-learning algorithm that can predict the category of test datasets based on the knowledge acquired from a learning dataset. The performance (accuracy) of the automated SVM approach was assessed, by comparing the SVM-predicted quality labels to investigator-determined quality labels. The accuracy for classifying 1457 3D-MRI volumes from our database using the SVM approach is around 80%. These results are promising and illustrate the possibility of using SVM as an automated quality assessment tool for 3D-MRI.
Open source machine-learning algorithms for the prediction of optimal cancer drug therapies.
Directory of Open Access Journals (Sweden)
Cai Huang
Full Text Available Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM algorithm combined with a standard recursive feature elimination (RFE approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60. The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be "drivers" of cancer onset/progression. Application of our models to publically available ovarian cancer (OC patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm "open source", we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.
Using Deep Learning Algorithm to Enhance Image-review Software for Surveillance Cameras
Energy Technology Data Exchange (ETDEWEB)
Cui, Yonggang
2018-05-07
We propose the development of proven deep learning algorithms to flag objects and events of interest in Next Generation Surveillance System (NGSS) surveillance to make IAEA image review more efficient. Video surveillance is one of the core monitoring technologies used by the IAEA Department of Safeguards when implementing safeguards at nuclear facilities worldwide. The current image review software GARS has limited automated functions, such as scene-change detection, black image detection and missing scene analysis, but struggles with highly cluttered backgrounds. A cutting-edge algorithm to be developed in this project will enable efficient and effective searches in images and video streams by identifying and tracking safeguards relevant objects and detect anomalies in their vicinity. In this project, we will develop the algorithm, test it with the IAEA surveillance cameras and data sets collected at simulated nuclear facilities at BNL and SNL, and implement it in a software program for potential integration into the IAEA’s IRAP (Integrated Review and Analysis Program).
Seghouane, Abd-Krim; Iqbal, Asif
2017-09-01
Sequential dictionary learning algorithms have been successfully applied to functional magnetic resonance imaging (fMRI) data analysis. fMRI data sets are, however, structured data matrices with the notions of temporal smoothness in the column direction. This prior information, which can be converted into a constraint of smoothness on the learned dictionary atoms, has seldomly been included in classical dictionary learning algorithms when applied to fMRI data analysis. In this paper, we tackle this problem by proposing two new sequential dictionary learning algorithms dedicated to fMRI data analysis by accounting for this prior information. These algorithms differ from the existing ones in their dictionary update stage. The steps of this stage are derived as a variant of the power method for computing the SVD. The proposed algorithms generate regularized dictionary atoms via the solution of a left regularized rank-one matrix approximation problem where temporal smoothness is enforced via regularization through basis expansion and sparse basis expansion in the dictionary update stage. Applications on synthetic data experiments and real fMRI data sets illustrating the performance of the proposed algorithms are provided.
Morita, Kenji; Jitsev, Jenia; Morrison, Abigail
2016-09-15
Value-based action selection has been suggested to be realized in the corticostriatal local circuits through competition among neural populations. In this article, we review theoretical and experimental studies that have constructed and verified this notion, and provide new perspectives on how the local-circuit selection mechanisms implement reinforcement learning (RL) algorithms and computations beyond them. The striatal neurons are mostly inhibitory, and lateral inhibition among them has been classically proposed to realize "Winner-Take-All (WTA)" selection of the maximum-valued action (i.e., 'max' operation). Although this view has been challenged by the revealed weakness, sparseness, and asymmetry of lateral inhibition, which suggest more complex dynamics, WTA-like competition could still occur on short time scales. Unlike the striatal circuit, the cortical circuit contains recurrent excitation, which may enable retention or temporal integration of information and probabilistic "soft-max" selection. The striatal "max" circuit and the cortical "soft-max" circuit might co-implement an RL algorithm called Q-learning; the cortical circuit might also similarly serve for other algorithms such as SARSA. In these implementations, the cortical circuit presumably sustains activity representing the executed action, which negatively impacts dopamine neurons so that they can calculate reward-prediction-error. Regarding the suggested more complex dynamics of striatal, as well as cortical, circuits on long time scales, which could be viewed as a sequence of short WTA fragments, computational roles remain open: such a sequence might represent (1) sequential state-action-state transitions, constituting replay or simulation of the internal model, (2) a single state/action by the whole trajectory, or (3) probabilistic sampling of state/action. Copyright © 2016. Published by Elsevier B.V.
Classification and authentication of unknown water samples using machine learning algorithms.
Kundu, Palash K; Panchariya, P C; Kundu, Madhusree
2011-07-01
This paper proposes the development of water sample classification and authentication, in real life which is based on machine learning algorithms. The proposed techniques used experimental measurements from a pulse voltametry method which is based on an electronic tongue (E-tongue) instrumentation system with silver and platinum electrodes. E-tongue include arrays of solid state ion sensors, transducers even of different types, data collectors and data analysis tools, all oriented to the classification of liquid samples and authentication of unknown liquid samples. The time series signal and the corresponding raw data represent the measurement from a multi-sensor system. The E-tongue system, implemented in a laboratory environment for 6 numbers of different ISI (Bureau of Indian standard) certified water samples (Aquafina, Bisleri, Kingfisher, Oasis, Dolphin, and McDowell) was the data source for developing two types of machine learning algorithms like classification and regression. A water data set consisting of 6 numbers of sample classes containing 4402 numbers of features were considered. A PCA (principal component analysis) based classification and authentication tool was developed in this study as the machine learning component of the E-tongue system. A proposed partial least squares (PLS) based classifier, which was dedicated as well; to authenticate a specific category of water sample evolved out as an integral part of the E-tongue instrumentation system. The developed PCA and PLS based E-tongue system emancipated an overall encouraging authentication percentage accuracy with their excellent performances for the aforesaid categories of water samples. Copyright © 2011 ISA. Published by Elsevier Ltd. All rights reserved.
International Nuclear Information System (INIS)
Lima, Alan M.M. de; Schirru, Roberto
2000-01-01
Genetic algorithms are biologically motivated adaptive systems which have been used, with good results, for function optimization. The purpose of this work is to introduce a new parallelization method to be applied to the Population-Based Incremental Learning (PBIL) algorithm. PBIL combines standard genetic algorithm mechanisms with simple competitive learning and has ben successfully used in combinatorial optimization problems. The development of this algorithm aims its application to the reload optimization of PWR nuclear reactors. Tests have been performed with combinatorial optimization problems similar to the reload problem. Results are compared to the serial PBIL ones, showing the new method's superiority and its viability as a tool for the nuclear core reload problem solution. (author)
Barua, Shaibal; Begum, Shahina; Ahmed, Mobyen Uddin
2015-01-01
Machine learning algorithms play an important role in computer science research. Recent advancement in sensor data collection in clinical sciences lead to a complex, heterogeneous data processing, and analysis for patient diagnosis and prognosis. Diagnosis and treatment of patients based on manual analysis of these sensor data are difficult and time consuming. Therefore, development of Knowledge-based systems to support clinicians in decision-making is important. However, it is necessary to perform experimental work to compare performances of different machine learning methods to help to select appropriate method for a specific characteristic of data sets. This paper compares classification performance of three popular machine learning methods i.e., case-based reasoning, neutral networks and support vector machine to diagnose stress of vehicle drivers using finger temperature and heart rate variability. The experimental results show that case-based reasoning outperforms other two methods in terms of classification accuracy. Case-based reasoning has achieved 80% and 86% accuracy to classify stress using finger temperature and heart rate variability. On contrary, both neural network and support vector machine have achieved less than 80% accuracy by using both physiological signals.
Directory of Open Access Journals (Sweden)
Deling Wang
2018-03-01
Full Text Available Breast cancer is one of the most common malignancies in women. Patient-derived tumor xenograft (PDX model is a cutting-edge approach for drug research on breast cancer. However, PDX still exhibits differences from original human tumors, thereby challenging the molecular understanding of tumorigenesis. In particular, gene expression changes after tissues are transplanted from human to mouse model. In this study, we propose a novel computational method by incorporating several machine learning algorithms, including Monte Carlo feature selection (MCFS, random forest (RF, and rough set-based rule learning, to identify genes with significant expression differences between PDX and original human tumors. First, 831 breast tumors, including 657 PDX and 174 human tumors, were collected. Based on MCFS and RF, 32 genes were then identified to be informative for the prediction of PDX and human tumors and can be used to construct a prediction model. The prediction model exhibits a Matthews coefficient correlation value of 0.777. Seven interpretable interactions within the informative gene were detected based on the rough set-based rule learning. Furthermore, the seven interpretable interactions can be well supported by previous experimental studies. Our study not only presents a method for identifying informative genes with differential expression but also provides insights into the mechanism through which gene expression changes after being transplanted from human tumor into mouse model. This work would be helpful for research and drug development for breast cancer.
Wang, Deling; Li, Jia-Rui; Zhang, Yu-Hang; Chen, Lei; Huang, Tao; Cai, Yu-Dong
2018-03-12
Breast cancer is one of the most common malignancies in women. Patient-derived tumor xenograft (PDX) model is a cutting-edge approach for drug research on breast cancer. However, PDX still exhibits differences from original human tumors, thereby challenging the molecular understanding of tumorigenesis. In particular, gene expression changes after tissues are transplanted from human to mouse model. In this study, we propose a novel computational method by incorporating several machine learning algorithms, including Monte Carlo feature selection (MCFS), random forest (RF), and rough set-based rule learning, to identify genes with significant expression differences between PDX and original human tumors. First, 831 breast tumors, including 657 PDX and 174 human tumors, were collected. Based on MCFS and RF, 32 genes were then identified to be informative for the prediction of PDX and human tumors and can be used to construct a prediction model. The prediction model exhibits a Matthews coefficient correlation value of 0.777. Seven interpretable interactions within the informative gene were detected based on the rough set-based rule learning. Furthermore, the seven interpretable interactions can be well supported by previous experimental studies. Our study not only presents a method for identifying informative genes with differential expression but also provides insights into the mechanism through which gene expression changes after being transplanted from human tumor into mouse model. This work would be helpful for research and drug development for breast cancer.
Skou, Søren T; Roos, Ewa M
2017-02-07
The uptake of evidence-based guidelines in clinical practice is suboptimal in osteoarthritis (OA) and other chronic diseases. Good Life with osteoArthritis in Denmark (GLA:D) was launched in 2013 with the aim of implementing guidelines for the treatment of knee and hip OA in clinical care nationwide. The purpose of this report was to evaluate the effects of the GLA:D intervention from 2013 to 2015, using data from the national GLA:D registry. Patients undergo education and supervised exercise delivered by trained physiotherapists. Outcomes evaluated at baseline, 3 and 12 months are pain intensity (0 to 100, best to worst), objective physical function (30-s chair-stand test and 40-m fast-paced walk test), physical activity (number of days per week being physically active for at least 30 min), quality of life (Knee injury and Osteoarthritis Outcome Score (KOOS) and the Hip disability and Osteoarthritis Outcome Score (HOOS) quality of life subscale, 0-100, worst to best), number of patients on painkillers and sick leave, and access to care according to guidelines. Data from 9,825 participants from the GLA:D registry were utilised in the analyses. It was demonstrated that GLA:D improved pain intensity and quality of life by 12.4 points and 5.4 points at 3 months, and 13.7 points and 9.4 points at 12 months, respectively. Furthermore, physical function and physical activity improved (only at 3 months), fewer patients took painkillers following the treatment, and fewer patients were on sick leave at 12 months following GLA:D compared with the year prior to GLA:D. GLA:D is offered in all five health care regions in Denmark via 286 active GLA:D units, but the uptake in the Danish municipalities is still low with only 20% of the municipalities offering GLA:D. Three years after its inception, GLA:D has been rolled out nationwide and has a significant impact not only on patient symptoms and physical function, but also on intake of painkillers and sick leave. The
Paegle, Jan; Baker, W. E.
1985-01-01
It is well-known that divergent wind estimates are much more dependent upon the analysis system than are estimates of the rotational wind. This conclusion is supported in recent analyses of FGGE SOP1 data produced by the Goddard Laboratory for Atmospheres (GLA), the Geophysical Fluid Dynamics Laboratory (GFDL) and the European Center for Medium Range Weather Forecasting (ECMWF). These analyses differ in the forecast models that are used for the four-dimensional assimilation, in the data rejection criteria, and, to a certain extent, in the data density. Because the final divergent wind is a product of both model constraints and observation, it is relevant to inquire how much of each goes into the final product. We presently investigate this question through a systematic analysis of tropical data that are sampled at different densities by the GLA GCM.
McIlvane, William J; Kledaras, Joanne B; Gerard, Christophe J; Wilde, Lorin; Smelson, David
2018-07-01
A few noteworthy exceptions notwithstanding, quantitative analyses of relational learning are most often simple descriptive measures of study outcomes. For example, studies of stimulus equivalence have made much progress using measures such as percentage consistent with equivalence relations, discrimination ratio, and response latency. Although procedures may have ad hoc variations, they remain fairly similar across studies. Comparison studies of training variables that lead to different outcomes are few. Yet to be developed are tools designed specifically for dynamic and/or parametric analyses of relational learning processes. This paper will focus on recent studies to develop (1) quality computer-based programmed instruction for supporting relational learning in children with autism spectrum disorders and intellectual disabilities and (2) formal algorithms that permit ongoing, dynamic assessment of learner performance and procedure changes to optimize instructional efficacy and efficiency. Because these algorithms have a strong basis in evidence and in theories of stimulus control, they may have utility also for basic and translational research. We present an overview of the research program, details of algorithm features, and summary results that illustrate their possible benefits. It also presents arguments that such algorithm development may encourage parametric research, help in integrating new research findings, and support in-depth quantitative analyses of stimulus control processes in relational learning. Such algorithms may also serve to model control of basic behavioral processes that is important to the design of effective programmed instruction for human learners with and without functional disabilities. Copyright © 2018 Elsevier B.V. All rights reserved.
Zheng, Wei; Yan, Xiaoyong; Zhao, Wei; Qian, Chengshan
2017-12-20
A novel large-scale multi-hop localization algorithm based on regularized extreme learning is proposed in this paper. The large-scale multi-hop localization problem is formulated as a learning problem. Unlike other similar localization algorithms, the proposed algorithm overcomes the shortcoming of the traditional algorithms which are only applicable to an isotropic network, therefore has a strong adaptability to the complex deployment environment. The proposed algorithm is composed of three stages: data acquisition, modeling and location estimation. In data acquisition stage, the training information between nodes of the given network is collected. In modeling stage, the model among the hop-counts and the physical distances between nodes is constructed using regularized extreme learning. In location estimation stage, each node finds its specific location in a distributed manner. Theoretical analysis and several experiments show that the proposed algorithm can adapt to the different topological environments with low computational cost. Furthermore, high accuracy can be achieved by this method without setting complex parameters.
Directory of Open Access Journals (Sweden)
Mojtaba Salehi
2013-03-01
Full Text Available In recent years, the explosion of learning materials in the web-based educational systems has caused difficulty of locating appropriate learning materials to learners. A personalized recommendation is an enabling mechanism to overcome information overload occurred in the new learning environments and deliver suitable materials to learners. Since users express their opinions based on some specific attributes of items, this paper proposes a hybrid recommender system for learning materials based on their attributes to improve the accuracy and quality of recommendation. The presented system has two main modules: explicit attribute-based recommender and implicit attribute-based recommender. In the first module, weights of implicit or latent attributes of materials for learner are considered as chromosomes in genetic algorithm then this algorithm optimizes the weights according to historical rating. Then, recommendation is generated by Nearest Neighborhood Algorithm (NNA using the optimized weight vectors implicit attributes that represent the opinions of learners. In the second, preference matrix (PM is introduced that can model the interests of learner based on explicit attributes of learning materials in a multidimensional information model. Then, a new similarity measure between PMs is introduced and recommendations are generated by NNA. The experimental results show that our proposed method outperforms current algorithms on accuracy measures and can alleviate some problems such as cold-start and sparsity.
Single-Iteration Learning Algorithm for Feed-Forward Neural Networks
Energy Technology Data Exchange (ETDEWEB)
Barhen, J.; Cogswell, R.; Protopopescu, V.
1999-07-31
A new methodology for neural learning is presented, whereby only a single iteration is required to train a feed-forward network with near-optimal results. To this aim, a virtual input layer is added to the multi-layer architecture. The virtual input layer is connected to the nominal input layer by a specird nonlinear transfer function, and to the fwst hidden layer by regular (linear) synapses. A sequence of alternating direction singular vrdue decompositions is then used to determine precisely the inter-layer synaptic weights. This algorithm exploits the known separability of the linear (inter-layer propagation) and nonlinear (neuron activation) aspects of information &ansfer within a neural network.
A new backpropagation learning algorithm for layered neural networks with nondifferentiable units.
Oohori, Takahumi; Naganuma, Hidenori; Watanabe, Kazuhisa
2007-05-01
We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance.
Directory of Open Access Journals (Sweden)
Xite Wang
2017-01-01
Full Text Available Outlier detection is an important data mining task, whose target is to find the abnormal or atypical objects from a given dataset. The techniques for detecting outliers have a lot of applications, such as credit card fraud detection and environment monitoring. Our previous work proposed the Cluster-Based (CB outlier and gave a centralized method using unsupervised extreme learning machines to compute CB outliers. In this paper, we propose a new distributed algorithm for the CB outlier detection (DACB. On the master node, we collect a small number of points from the slave nodes to obtain a threshold. On each slave node, we design a new filtering method that can use the threshold to efficiently speed up the computation. Furthermore, we also propose a ranking method to optimize the order of cluster scanning. At last, the effectiveness and efficiency of the proposed approaches are verified through a plenty of simulation experiments.
A learning algorithm for adaptive canonical correlation analysis of several data sets.
Vía, Javier; Santamaría, Ignacio; Pérez, Jesús
2007-01-01
Canonical correlation analysis (CCA) is a classical tool in statistical analysis to find the projections that maximize the correlation between two data sets. In this work we propose a generalization of CCA to several data sets, which is shown to be equivalent to the classical maximum variance (MAXVAR) generalization proposed by Kettenring. The reformulation of this generalization as a set of coupled least squares regression problems is exploited to develop a neural structure for CCA. In particular, the proposed CCA model is a two layer feedforward neural network with lateral connections in the output layer to achieve the simultaneous extraction of all the CCA eigenvectors through deflation. The CCA neural model is trained using a recursive least squares (RLS) algorithm. Finally, the convergence of the proposed learning rule is proved by means of stochastic approximation techniques and their performance is analyzed through simulations.
Soize, C.
2017-11-01
This paper deals with the optimal design of a titanium mesoscale implant in a cortical bone for which the apparent elasticity tensor is modeled by a non-Gaussian random field at mesoscale, which has been experimentally identified. The external applied forces are also random. The design parameters are geometrical dimensions related to the geometry of the implant. The stochastic elastostatic boundary value problem is discretized by the finite element method. The objective function and the constraints are related to normal, shear, and von Mises stresses inside the cortical bone. The constrained nonconvex optimization problem in presence of uncertainties is solved by using a probabilistic learning algorithm that allows for considerably reducing the numerical cost with respect to the classical approaches.
Directory of Open Access Journals (Sweden)
Mazyar Seraj
2014-10-01
Full Text Available This paper describes an experimental study of learning Dijkstra’s shortest path algorithm on mobile devices. The aim of the study is to investigate and compare the impacts of two different mobile screen user interfaces on students’ satisfaction for learning the technical subject. A mobile learning prototype was developed for learning Dijkstra’s shortest path algorithm on Apple iPhone 4 operated on iPhone operating system (iOS, and Acer Inconia Tab operated on an Android operating system. Thirty students, who are either currently studying or had previously studied Computer Networks, were recruited for the usability trial. At the end of each single session, students’ satisfaction interacting with the two mobile devices was measured using QUIS questionnaire. Although there is no significant difference in students’ satisfaction between the two different mobile screen interfaces, the subjective findings indicate that Acer Inconia Tab gained higher scores as compared to Apple iPhone 4.
Morello, Giuseppe; Morris, P. W.; Van Dyk, S. D.; Marston, A. P.; Mauerhan, J. C.
2018-01-01
We have investigated and applied machine-learning algorithms for infrared colour selection of Galactic Wolf-Rayet (WR) candidates. Objects taken from the Spitzer Galactic Legacy Infrared Midplane Survey Extraordinaire (GLIMPSE) catalogue of the infrared objects in the Galactic plane can be classified into different stellar populations based on the colours inferred from their broad-band photometric magnitudes [J, H and Ks from 2 Micron All Sky Survey (2MASS), and the four Spitzer/IRAC bands]. The algorithms tested in this pilot study are variants of the k-nearest neighbours approach, which is ideal for exploratory studies of classification problems where interrelations between variables and classes are complicated. The aims of this study are (1) to provide an automated tool to select reliable WR candidates and potentially other classes of objects, (2) to measure the efficiency of infrared colour selection at performing these tasks and (3) to lay the groundwork for statistically inferring the total number of WR stars in our Galaxy. We report the performance results obtained over a set of known objects and selected candidates for which we have carried out follow-up spectroscopic observations, and confirm the discovery of four new WR stars.
Ganguly, S.; Kumar, U.; Nemani, R. R.; Kalia, S.; Michaelis, A.
2017-12-01
In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS - national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91% was achieved, which is a 6% improvement in unmixing based classification relative to per-pixel based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.
Stoica, C; Camejo, J; Banciu, A; Nita-Lazar, M; Paun, I; Cristofor, S; Pacheco, O R; Guevara, M
2016-01-01
Environmental issues have a worldwide impact on water bodies, including the Danube Delta, the largest European wetland. The Water Framework Directive (2000/60/EC) implementation operates toward solving environmental issues from European and national level. As a consequence, the water quality and the biocenosis structure was altered, especially the composition of the macro invertebrate community which is closely related to habitat and substrate heterogeneity. This study aims to assess the ecological status of Southern Branch of the Danube Delta, Saint Gheorghe, using benthic fauna and a computational method as an alternative for monitoring the water quality in real time. The analysis of spatial and temporal variability of unicriterial and multicriterial indices were used to assess the current status of aquatic systems. In addition, chemical status was characterized. Coliform bacteria and several chemical parameters were used to feed machine-learning (ML) algorithms to simulate a real-time classification method. Overall, the assessment of the water bodies indicated a moderate ecological status based on the biological quality elements or a good ecological status based on chemical and ML algorithms criteria.
Das, Santanu; Srivastava, Ashok N.; Matthews, Bryan L.; Oza, Nikunj C.
2010-01-01
The world-wide aviation system is one of the most complex dynamical systems ever developed and is generating data at an extremely rapid rate. Most modern commercial aircraft record several hundred flight parameters including information from the guidance, navigation, and control systems, the avionics and propulsion systems, and the pilot inputs into the aircraft. These parameters may be continuous measurements or binary or categorical measurements recorded in one second intervals for the duration of the flight. Currently, most approaches to aviation safety are reactive, meaning that they are designed to react to an aviation safety incident or accident. In this paper, we discuss a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets. We pose a general anomaly detection problem which includes both discrete and continuous data streams, where we assume that the discrete streams have a causal influence on the continuous streams. We also assume that atypical sequence of events in the discrete streams can lead to off-nominal system performance. We discuss the application domain, novel algorithms, and also discuss results on real-world data sets. Our algorithm uncovers operationally significant events in high dimensional data streams in the aviation industry which are not detectable using state of the art methods
Matrix Gla Protein Polymorphisms are Associated with Coronary Artery Calcification in Men
Crosier, Michael D.; Booth, Sarah L.; Peter, Inga; Dawson-Hughes, Bess; Price, Paul A.; O’Donnell, Christopher J.; Hoffmann, Udo; Williamson, Matthew K.; Ordovas, Jose M.
2009-01-01
Summary Matrix Gla protein (MGP) is a key regulator of vascular calcification. Genetic variation at the MGP locus could modulate the development of coronary artery calcification (CAC). Our aim was to examine the cross-sectional association between MGP single nucleotide polymorphisms (SNPs) [rs1800802 (T-138C), rs1800801 (G-7A), and rs4236 (Ala102Thr)] and CAC. CAC was measured by multidetector computed tomography (MDCT), in older men and women of European descent, (n = 386; 60 to 80 y of age). Serum MGP was measured by radioimmunoassay. Linear, Tobit and Ordinal regression analyses all revealed that in men, homozygous carriers of the minor allele of rs1800802 , rs1800801 , or rs4236 (minor allele frequency: 21, 38, and 40%, respectively) were associated with a decreased quantity of CAC, relative to major allele carriers. This association was not found in women. Although genetic variation in MGP was associated with serum MGP concentrations, there were no associations between serum MGP and CAC. The results of this study suggest a role for MGP genetic variants in coronary atherosclerosis among men that is not reflected in serum MGP concentrations. PMID:19352064
The role of Matrix Gla Protein in ossification and recovery of the avian growth plate
Directory of Open Access Journals (Sweden)
Harel eDan
2012-07-01
Full Text Available ECM mineralization is an essential physiologic process in bone, teeth, and hypertrophic cartilage. Matrix Gla Protein (MGP, an inhibitor of mineralization, is expressed by chondrocytes and vascular smooth muscle cells to inhibit calcification of those soft tissues.Tibial Dyschondroplasia (TD, a skeletal abnormality apparent as a plug of non-vascularized, non-mineralized, white opaque cartilage in the tibial growth plate of avian species can serve as a good model for studying process and genes involved in matrix mineralization and calcification. In this work, we studied the involvement of MGP in the development of TD, as well as in the processes of spontaneous and induced recovery from this syndrome. First, we found that during normal bone development, MGP is expressed in specific time and locations, starting from wide spread expression in the yet un-ossified diaphysis during embryonic development, to specific expression in hypertrophic chondrocytes adjacent to the chondro-osseous junction and the secondary ossification center just prior to calcification. In addition, we show that MGP is not expressed in the impaired TD lesion, however when the lesion begins to heal, it strongly express MGP prior to its calcification. Moreover, we show that when calcification is inhibited, a gap is formed between the expression zones of MGP and BMP2 and that this gap is closed during the healing process. To conclude, we suggest that MGP, directly or through interaction with BMP2, plays a role as ossification regulator, rather then simple inhibitor that acts prior to ossification.
Matrix Gla Protein is Involved in Crystal Formation in Kidney of Hyperoxaluric Rats
Directory of Open Access Journals (Sweden)
Xiuli Lu
2013-02-01
Full Text Available Background: Matrix Gla protein (MGP is a molecular determinant regulating vascular calcification of the extracellular matrix. However, it is still unclear how MGP may be invovled in crystal formation in the kidney of hyperoxaluric rats. Methods: Male Sprague-Dawley rats were divided into the hyperoxaluric group and control group. Hyperoxaluric rats were administrated by 0.75% ethylene glycol (EG for up to 8 weeks. Renal MGP expression was detected by the standard avidin-biotin complex (ABC method. Renal crystal deposition was observed by a polarizing microscope. Total RNA and protein from the rat kidney tissue were extracted. The levels of MGP mRNA and protein expression were analyzed by the real-time polymerase chain reaction (RT-PCR and Western blot. Results: Hyperoxaluria was induced successfully in rats. The MGP was polarly distributed, on the apical membrane of renal tubular epithelial cells, and was found in the ascending thick limbs of Henle's loop (cTAL and the distal convoluted tubule (DCT in hyperoxaluric rats, its expression however, was present in the medullary collecting duct (MCD in stone-forming rats. Crystals with multilaminated structure formed in the injurious renal tubules with lack of MGP expression.MGP mRNA expression was significantly upregulated by the crystals' stimulations. Conclusion: Our results suggested that the MGP was involved in crystals formation by the continuous expression, distributing it polarly in the renal tubular cells and binding directly to the crystals.
D'Angelo, Gianni; Rampone, Salvatore
2014-01-01
The huge quantity of data produced in Biomedical research needs sophisticated algorithmic methodologies for its storage, analysis, and processing. High Performance Computing (HPC) appears as a magic bullet in this challenge. However, several hard to solve parallelization and load balancing problems arise in this context. Here we discuss the HPC-oriented implementation of a general purpose learning algorithm, originally conceived for DNA analysis and recently extended to treat uncertainty on data (U-BRAIN). The U-BRAIN algorithm is a learning algorithm that finds a Boolean formula in disjunctive normal form (DNF), of approximately minimum complexity, that is consistent with a set of data (instances) which may have missing bits. The conjunctive terms of the formula are computed in an iterative way by identifying, from the given data, a family of sets of conditions that must be satisfied by all the positive instances and violated by all the negative ones; such conditions allow the computation of a set of coefficients (relevances) for each attribute (literal), that form a probability distribution, allowing the selection of the term literals. The great versatility that characterizes it, makes U-BRAIN applicable in many of the fields in which there are data to be analyzed. However the memory and the execution time required by the running are of O(n(3)) and of O(n(5)) order, respectively, and so, the algorithm is unaffordable for huge data sets. We find mathematical and programming solutions able to lead us towards the implementation of the algorithm U-BRAIN on parallel computers. First we give a Dynamic Programming model of the U-BRAIN algorithm, then we minimize the representation of the relevances. When the data are of great size we are forced to use the mass memory, and depending on where the data are actually stored, the access times can be quite different. According to the evaluation of algorithmic efficiency based on the Disk Model, in order to reduce the costs of
Machine learning algorithms for the creation of clinical healthcare enterprise systems
Mandal, Indrajit
2017-10-01
Clinical recommender systems are increasingly becoming popular for improving modern healthcare systems. Enterprise systems are persuasively used for creating effective nurse care plans to provide nurse training, clinical recommendations and clinical quality control. A novel design of a reliable clinical recommender system based on multiple classifier system (MCS) is implemented. A hybrid machine learning (ML) ensemble based on random subspace method and random forest is presented. The performance accuracy and robustness of proposed enterprise architecture are quantitatively estimated to be above 99% and 97%, respectively (above 95% confidence interval). The study then extends to experimental analysis of the clinical recommender system with respect to the noisy data environment. The ranking of items in nurse care plan is demonstrated using machine learning algorithms (MLAs) to overcome the drawback of the traditional association rule method. The promising experimental results are compared against the sate-of-the-art approaches to highlight the advancement in recommendation technology. The proposed recommender system is experimentally validated using five benchmark clinical data to reinforce the research findings.
Directory of Open Access Journals (Sweden)
J. Bekker
2012-01-01
Full Text Available
ENGLISH ABSTRACT: The integration of the population-based incremental learning (PBIL algorithm with computer simulation shows how this particular combination can be applied to find good solutions to combinatorial optimisation problems. Two illustrative examples are used: the classical inventory problem of finding a reorder point and reorder quantity that minimises costs while achieving a required service level (a stochastic problem; and the signal timing of a complex traffic intersection. Any traffic control system must be designed to minimise the duration of interruptions at intersections while maximising traffic throughput. The duration of the phases of traffic lights is of primary importance in this regard.
AFRIKAANSE OPSOMMING: Die integrasie van die population-based incremental learning (PBIL algoritme met rekenaarsimulasie word bespreek, en daar word getoon hoe hierdie spesifieke kombinasie aangewend kan word om goeie oplossings vir kombinatoriese optimeringsprobleme te vind. Twee voorbeelde dien as illustrasie: die klassieke voorraadprobleem waarin ’n herbestelvlak en herbestelhoeveelheid bepaal moet word om koste te minimeer maar nogtans ’n vasgestelde diensvlak te handhaaf (’n stochastiese probleem; en die bepaling van die seintye van ’n komplekse verkeerskruising. Enige verkeerbeheerstelsel moet ontwerp word om die duur van die vloeionderbrekings by verkeerskruisings te minimeer en verkeerdeurset te maksimeer. Die tydsduur van die fases van verkeersligte is dus baie belangrik.
Tango, Fabio; Minin, Luca; Tesauri, Francesco; Montanari, Roberto
2010-03-01
This paper describes the field tests on a driving simulator carried out to validate the algorithms and the correlations of dynamic parameters, specifically driving task demand and drivers' distraction, able to predict drivers' intentions. These parameters belong to the driver's model developed by AIDE (Adaptive Integrated Driver-vehicle InterfacE) European Integrated Project. Drivers' behavioural data have been collected from the simulator tests to model and validate these parameters using machine learning techniques, specifically the adaptive neuro fuzzy inference systems (ANFIS) and the artificial neural network (ANN). Two models of task demand and distraction have been developed, one for each adopted technique. The paper provides an overview of the driver's model, the description of the task demand and distraction modelling and the tests conducted for the validation of these parameters. A test comparing predicted and expected outcomes of the modelled parameters for each machine learning technique has been carried out: for distraction, in particular, promising results (low prediction errors) have been obtained by adopting an artificial neural network.
Golla, Gowtham Kumar; Carlson, Jordan A; Huan, Jun; Kerr, Jacqueline; Mitchell, Tarrah; Borner, Kelsey
2016-10-01
Sedentary behavior of youth is an important determinant of health. However, better measures are needed to improve understanding of this relationship and the mechanisms at play, as well as to evaluate health promotion interventions. Wearable accelerometers are considered as the standard for assessing physical activity in research, but do not perform well for assessing posture (i.e., sitting vs. standing), a critical component of sedentary behavior. The machine learning algorithms that we propose for assessing sedentary behavior will allow us to re-examine existing accelerometer data to better understand the association between sedentary time and health in various populations. We collected two datasets, a laboratory-controlled dataset and a free-living dataset. We trained machine learning classifiers separately on each dataset and compared performance across datasets. The classifiers predict five postures: sit, stand, sit-stand, stand-sit, and stand\\walk. We compared a manually constructed Hidden Markov model (HMM) with an automated HMM from existing software. The manually constructed HMM gave more F1-Macro score on both datasets.
A Logical Deduction Based Clause Learning Algorithm for Boolean Satisfiability Problems
Directory of Open Access Journals (Sweden)
Qingshan Chen
2017-01-01
Full Text Available Clause learning is the key component of modern SAT solvers, while conflict analysis based on the implication graph is the mainstream technology to generate the learnt clauses. Whenever a clause in the clause database is falsified by the current variable assignments, the SAT solver will try to analyze the reason by using different cuts (i.e., the Unique Implication Points on the implication graph. Those schemes reflect only the conflict on the current search subspace, does not reflect the inherent conflict directly involved in the rest space. In this paper, we propose a new advanced clause learning algorithm based on the conflict analysis and the logical deduction, which reconstructs a linear logical deduction by analyzing the relationship of different decision variables between the backjumping level and the current decision level. The logical deduction result is then added into the clause database as a newly learnt clause. The resulting implementation in Minisat improves the state-of-the-art performance in SAT solving.
Biswas, Rahul; Blackburn, Lindy; Cao, Junwei; Essick, Reed; Hodge, Kari Alison; Katsavounidis, Erotokritos; Kim, Kyungmin; Kim, Young-Min; Le Bigot, Eric-Olivier; Lee, Chang-Hwan; Oh, John J.; Oh, Sang Hoon; Son, Edwin J.; Tao, Ye; Vaulin, Ruslan; Wang, Xiaoge
2013-09-01
The sensitivity of searches for astrophysical transients in data from the Laser Interferometer Gravitational-wave Observatory (LIGO) is generally limited by the presence of transient, non-Gaussian noise artifacts, which occur at a high enough rate such that accidental coincidence across multiple detectors is non-negligible. These “glitches” can easily be mistaken for transient gravitational-wave signals, and their robust identification and removal will help any search for astrophysical gravitational waves. We apply machine-learning algorithms (MLAs) to the problem, using data from auxiliary channels within the LIGO detectors that monitor degrees of freedom unaffected by astrophysical signals. Noise sources may produce artifacts in these auxiliary channels as well as the gravitational-wave channel. The number of auxiliary-channel parameters describing these disturbances may also be extremely large; high dimensionality is an area where MLAs are particularly well suited. We demonstrate the feasibility and applicability of three different MLAs: artificial neural networks, support vector machines, and random forests. These classifiers identify and remove a substantial fraction of the glitches present in two different data sets: four weeks of LIGO’s fourth science run and one week of LIGO’s sixth science run. We observe that all three algorithms agree on which events are glitches to within 10% for the sixth-science-run data, and support this by showing that the different optimization criteria used by each classifier generate the same decision surface, based on a likelihood-ratio statistic. Furthermore, we find that all classifiers obtain similar performance to the benchmark algorithm, the ordered veto list, which is optimized to detect pairwise correlations between transients in LIGO auxiliary channels and glitches in the gravitational-wave data. This suggests that most of the useful information currently extracted from the auxiliary channels is already described
Wu, Junfeng; Dai, Fang; Hu, Gang; Mou, Xuanqin
2018-04-18
Excessive radiation exposure in computed tomography (CT) scans increases the chance of developing cancer and has become a major clinical concern. Recently, statistical iterative reconstruction (SIR) with l0-norm dictionary learning regularization has been developed to reconstruct CT images from the low dose and few-view dataset in order to reduce radiation dose. Nonetheless, the sparse regularization term adopted in this approach is l0-norm, which cannot guarantee the global convergence of the proposed algorithm. To address this problem, in this study we introduced the l1-norm dictionary learning penalty into SIR framework for low dose CT image reconstruction, and developed an alternating minimization algorithm to minimize the associated objective function, which transforms CT image reconstruction problem into a sparse coding subproblem and an image updating subproblem. During the image updating process, an efficient model function approach based on balancing principle is applied to choose the regularization parameters. The proposed alternating minimization algorithm was evaluated first using real projection data of a sheep lung CT perfusion and then using numerical simulation based on sheep lung CT image and chest image. Both visual assessment and quantitative comparison using terms of root mean square error (RMSE) and structural similarity (SSIM) index demonstrated that the new image reconstruction algorithm yielded similar performance with l0-norm dictionary learning penalty and outperformed the conventional filtered backprojection (FBP) and total variation (TV) minimization algorithms.
Mustapha, Ibrahim; Mohd Ali, Borhanuddin; Rasid, Mohd Fadlee A; Sali, Aduwati; Mohamad, Hafizal
2015-08-13
It is well-known that clustering partitions network into logical groups of nodes in order to achieve energy efficiency and to enhance dynamic channel access in cognitive radio through cooperative sensing. While the topic of energy efficiency has been well investigated in conventional wireless sensor networks, the latter has not been extensively explored. In this paper, we propose a reinforcement learning-based spectrum-aware clustering algorithm that allows a member node to learn the energy and cooperative sensing costs for neighboring clusters to achieve an optimal solution. Each member node selects an optimal cluster that satisfies pairwise constraints, minimizes network energy consumption and enhances channel sensing performance through an exploration technique. We first model the network energy consumption and then determine the optimal number of clusters for the network. The problem of selecting an optimal cluster is formulated as a Markov Decision Process (MDP) in the algorithm and the obtained simulation results show convergence, learning and adaptability of the algorithm to dynamic environment towards achieving an optimal solution. Performance comparisons of our algorithm with the Groupwise Spectrum Aware (GWSA)-based algorithm in terms of Sum of Square Error (SSE), complexity, network energy consumption and probability of detection indicate improved performance from the proposed approach. The results further reveal that an energy savings of 9% and a significant Primary User (PU) detection improvement can be achieved with the proposed approach.
Amaral, Jorge L M; Lopes, Agnaldo J; Jansen, José M; Faria, Alvaro C D; Melo, Pedro L
2013-12-01
The purpose of this study was to develop an automatic classifier to increase the accuracy of the forced oscillation technique (FOT) for diagnosing early respiratory abnormalities in smoking patients. The data consisted of FOT parameters obtained from 56 volunteers, 28 healthy and 28 smokers with low tobacco consumption. Many supervised learning techniques were investigated, including logistic linear classifiers, k nearest neighbor (KNN), neural networks and support vector machines (SVM). To evaluate performance, the ROC curve of the most accurate parameter was established as baseline. To determine the best input features and classifier parameters, we used genetic algorithms and a 10-fold cross-validation using the average area under the ROC curve (AUC). In the first experiment, the original FOT parameters were used as input. We observed a significant improvement in accuracy (KNN=0.89 and SVM=0.87) compared with the baseline (0.77). The second experiment performed a feature selection on the original FOT parameters. This selection did not cause any significant improvement in accuracy, but it was useful in identifying more adequate FOT parameters. In the third experiment, we performed a feature selection on the cross products of the FOT parameters. This selection resulted in a further increase in AUC (KNN=SVM=0.91), which allows for high diagnostic accuracy. In conclusion, machine learning classifiers can help identify early smoking-induced respiratory alterations. The use of FOT cross products and the search for the best features and classifier parameters can markedly improve the performance of machine learning classifiers. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.
Directory of Open Access Journals (Sweden)
Zena M Hira
Full Text Available Microarray databases are a large source of genetic data, which, upon proper analysis, could enhance our understanding of biology and medicine. Many microarray experiments have been designed to investigate the genetic mechanisms of cancer, and analytical approaches have been applied in order to classify different types of cancer or distinguish between cancerous and non-cancerous tissue. However, microarrays are high-dimensional datasets with high levels of noise and this causes problems when using machine learning methods. A popular approach to this problem is to search for a set of features that will simplify the structure and to some degree remove the noise from the data. The most widely used approach to feature extraction is principal component analysis (PCA which assumes a multivariate Gaussian model of the data. More recently, non-linear methods have been investigated. Among these, manifold learning algorithms, for example Isomap, aim to project the data from a higher dimensional space onto a lower dimension one. We have proposed a priori manifold learning for finding a manifold in which a representative set of microarray data is fused with relevant data taken from the KEGG pathway database. Once the manifold has been constructed the raw microarray data is projected onto it and clustering and classification can take place. In contrast to earlier fusion based methods, the prior knowledge from the KEGG databases is not used in, and does not bias the classification process--it merely acts as an aid to find the best space in which to search the data. In our experiments we have found that using our new manifold method gives better classification results than using either PCA or conventional Isomap.
French, Robert M; Glady, Yannick; Thibaut, Jean-Pierre
2017-08-01
In recent years, eyetracking has begun to be used to study the dynamics of analogy making. Numerous scanpath-comparison algorithms and machine-learning techniques are available that can be applied to the raw eyetracking data. We show how scanpath-comparison algorithms, combined with multidimensional scaling and a classification algorithm, can be used to resolve an outstanding question in analogy making-namely, whether or not children's and adults' strategies in solving analogy problems are different. (They are.) We show which of these scanpath-comparison algorithms is best suited to the kinds of analogy problems that have formed the basis of much analogy-making research over the years. Furthermore, we use machine-learning classification algorithms to examine the item-to-item saccade vectors making up these scanpaths. We show which of these algorithms best predicts, from very early on in a trial, on the basis of the frequency of various item-to-item saccades, whether a child or an adult is doing the problem. This type of analysis can also be used to predict, on the basis of the item-to-item saccade dynamics in the first third of a trial, whether or not a problem will be solved correctly.
DEFF Research Database (Denmark)
Baira Ojeda, Ismael; Tolu, Silvia; Lund, Henrik Hautop
2017-01-01
Combining Fable robot, a modular robot, with a neuroinspired controller, we present the proof of principle of a system that can scale to several neurally controlled compliant modules. The motor control and learning of a robot module are carried out by a Unit Learning Machine (ULM) that embeds...... the Locally Weighted Projection Regression algorithm (LWPR) and a spiking cerebellar-like microcircuit. The LWPR guarantees both an optimized representation of the input space and the learning of the dynamic internal model (IM) of the robot. However, the cerebellar-like sub-circuit integrates LWPR input...
International Nuclear Information System (INIS)
Tanabe, Akira; Yamamoto, Toru; Shinfuku, Kimihiro; Nakamae, Takuji; Nishide, Fusayo.
1995-01-01
Previously a two-layered neural network model was developed to predict the relation between fissile enrichment of each fuel rod and local power distribution in a BWR fuel bundle. This model was obtained intuitively based on 33 patterns of training signals after an intensive survey of the models. Recently, a learning algorithm with forgetting was reported to simplify neural network models. It is an interesting subject what kind of model will be obtained if this algorithm is applied to the complex three-layered model which learns the same training signals. A three-layered model which is expanded to have direct connections between the 1st and the 3rd layer elements has been constructed and the learning method of normal back propagation was applied first to this model. The forgetting algorithm was then added to this learning process. The connections concerned with the 2nd layer elements disappeared and the 2nd layer has become unnecessary. It took a longer computing time by an order to learn the same training signals than the simple back propagation, but the two-layered model was obtained autonomously from the expanded three-layered model. (author)
Mizutani, Eiji; Demmel, James W
2003-01-01
This paper briefly introduces our numerical linear algebra approaches for solving structured nonlinear least squares problems arising from 'multiple-output' neural-network (NN) models. Our algorithms feature trust-region regularization, and exploit sparsity of either the 'block-angular' residual Jacobian matrix or the 'block-arrow' Gauss-Newton Hessian (or Fisher information matrix in statistical sense) depending on problem scale so as to render a large class of NN-learning algorithms 'efficient' in both memory and operation costs. Using a relatively large real-world nonlinear regression application, we shall explain algorithmic strengths and weaknesses, analyzing simulation results obtained by both direct and iterative trust-region algorithms with two distinct NN models: 'multilayer perceptrons' (MLP) and 'complementary mixtures of MLP-experts' (or neuro-fuzzy modular networks).
Li, Yang; Li, Guoqing; Wang, Zhenhao
2015-01-01
In order to overcome the problems of poor understandability of the pattern recognition-based transient stability assessment (PRTSA) methods, a new rule extraction method based on extreme learning machine (ELM) and an improved Ant-miner (IAM) algorithm is presented in this paper. First, the basic principles of ELM and Ant-miner algorithm are respectively introduced. Then, based on the selected optimal feature subset, an example sample set is generated by the trained ELM-based PRTSA model. And finally, a set of classification rules are obtained by IAM algorithm to replace the original ELM network. The novelty of this proposal is that transient stability rules are extracted from an example sample set generated by the trained ELM-based transient stability assessment model by using IAM algorithm. The effectiveness of the proposed method is shown by the application results on the New England 39-bus power system and a practical power system--the southern power system of Hebei province.
Graham, James; Ternovskiy, Igor V.
2013-06-01
We applied a two stage unsupervised hierarchical learning system to model complex dynamic surveillance and cyber space monitoring systems using a non-commercial version of the NeoAxis visualization software. The hierarchical scene learning and recognition approach is based on hierarchical expectation maximization, and was linked to a 3D graphics engine for validation of learning and classification results and understanding the human - autonomous system relationship. Scene recognition is performed by taking synthetically generated data and feeding it to a dynamic logic algorithm. The algorithm performs hierarchical recognition of the scene by first examining the features of the objects to determine which objects are present, and then determines the scene based on the objects present. This paper presents a framework within which low level data linked to higher-level visualization can provide support to a human operator and be evaluated in a detailed and systematic way.
Luo, Gang
2017-01-01
For user-friendliness, many software systems offer progress indicators for long-duration tasks. A typical progress indicator continuously estimates the remaining task execution time as well as the portion of the task that has been finished. Building a machine learning model often takes a long time, but no existing machine learning software supplies a non-trivial progress indicator. Similarly, running a data mining algorithm often takes a long time, but no existing data mining software provides a nontrivial progress indicator. In this article, we consider the problem of offering progress indicators for machine learning model building and data mining algorithm execution. We discuss the goals and challenges intrinsic to this problem. Then we describe an initial framework for implementing such progress indicators and two advanced, potential uses of them, with the goal of inspiring future research on this topic. PMID:29177022
Superior arm-movement decoding from cortex with a new, unsupervised-learning algorithm
Makin, Joseph G.; O'Doherty, Joseph E.; Cardoso, Mariana M. B.; Sabes, Philip N.
2018-04-01
Objective. The aim of this work is to improve the state of the art for motor-control with a brain-machine interface (BMI). BMIs use neurological recording devices and decoding algorithms to transform brain activity directly into real-time control of a machine, archetypically a robotic arm or a cursor. The standard procedure treats neural activity—vectors of spike counts in small temporal windows—as noisy observations of the kinematic state (position, velocity, acceleration) of the fingertip. Inferring the state from the observations then takes the form of a dynamical filter, typically some variant on Kalman’s (KF). The KF, however, although fairly robust in practice, is optimal only when the relationships between variables are linear and the noise is Gaussian, conditions usually violated in practice. Approach. To overcome these limitations we introduce a new filter, the ‘recurrent exponential-family harmonium’ (rEFH), that models the spike counts explicitly as Poisson-distributed, and allows for arbitrary nonlinear dynamics and observation models. Furthermore, the model underlying the filter is acquired through unsupervised learning, which allows temporal correlations in spike counts to be explained by latent dynamics that do not necessarily correspond to the kinematic state of the fingertip. Main results. We test the rEFH on offline reconstruction of the kinematics of reaches in the plane. The rEFH outperforms the standard, as well as three other state-of-the-art, decoders, across three monkeys, two different tasks, most kinematic variables, and a range of bin widths, amounts of training data, and numbers of neurons. Significance. Our algorithm establishes a new state of the art for offline decoding of reaches—in particular, for fingertip velocities, the variable used for control in most online decoders.
A New Tool for CME Arrival Time Prediction using Machine Learning Algorithms: CAT-PUMA
Liu, Jiajia; Ye, Yudong; Shen, Chenglong; Wang, Yuming; Erdélyi, Robert
2018-03-01
Coronal mass ejections (CMEs) are arguably the most violent eruptions in the solar system. CMEs can cause severe disturbances in interplanetary space and can even affect human activities in many aspects, causing damage to infrastructure and loss of revenue. Fast and accurate prediction of CME arrival time is vital to minimize the disruption that CMEs may cause when interacting with geospace. In this paper, we propose a new approach for partial-/full halo CME Arrival Time Prediction Using Machine learning Algorithms (CAT-PUMA). Via detailed analysis of the CME features and solar-wind parameters, we build a prediction engine taking advantage of 182 previously observed geo-effective partial-/full halo CMEs and using algorithms of the Support Vector Machine. We demonstrate that CAT-PUMA is accurate and fast. In particular, predictions made after applying CAT-PUMA to a test set unknown to the engine show a mean absolute prediction error of ∼5.9 hr within the CME arrival time, with 54% of the predictions having absolute errors less than 5.9 hr. Comparisons with other models reveal that CAT-PUMA has a more accurate prediction for 77% of the events investigated that can be carried out very quickly, i.e., within minutes of providing the necessary input parameters of a CME. A practical guide containing the CAT-PUMA engine and the source code of two examples are available in the Appendix, allowing the community to perform their own applications for prediction using CAT-PUMA.
Biswas, Rahul; Blackburn, Lindy L.; Cao, Junwei; Essick, Reed; Hodge, Kari Alison; Katsavounidis, Erotokritos; Kim, Kyungmin; Young-Min, Kim; Le Bigot, Eric-Olivier; Lee, Chang-Hwan;
2014-01-01
The sensitivity of searches for astrophysical transients in data from the Laser Interferometer Gravitationalwave Observatory (LIGO) is generally limited by the presence of transient, non-Gaussian noise artifacts, which occur at a high-enough rate such that accidental coincidence across multiple detectors is non-negligible. Furthermore, non-Gaussian noise artifacts typically dominate over the background contributed from stationary noise. These "glitches" can easily be confused for transient gravitational-wave signals, and their robust identification and removal will help any search for astrophysical gravitational-waves. We apply Machine Learning Algorithms (MLAs) to the problem, using data from auxiliary channels within the LIGO detectors that monitor degrees of freedom unaffected by astrophysical signals. Terrestrial noise sources may manifest characteristic disturbances in these auxiliary channels, inducing non-trivial correlations with glitches in the gravitational-wave data. The number of auxiliary-channel parameters describing these disturbances may also be extremely large; high dimensionality is an area where MLAs are particularly well-suited. We demonstrate the feasibility and applicability of three very different MLAs: Artificial Neural Networks, Support Vector Machines, and Random Forests. These classifiers identify and remove a substantial fraction of the glitches present in two very different data sets: four weeks of LIGO's fourth science run and one week of LIGO's sixth science run. We observe that all three algorithms agree on which events are glitches to within 10% for the sixth science run data, and support this by showing that the different optimization criteria used by each classifier generate the same decision surface, based on a likelihood-ratio statistic. Furthermore, we find that all classifiers obtain similar limiting performance, suggesting that most of the useful information currently contained in the auxiliary channel parameters we extract
Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm.
Han, Seung Seog; Kim, Myoung Shin; Lim, Woohyung; Park, Gyeong Hun; Park, Ilwoo; Chang, Sung Eun
2018-02-08
We tested the use of a deep learning algorithm to classify the clinical images of 12 skin diseases-basal cell carcinoma, squamous cell carcinoma, intraepithelial carcinoma, actinic keratosis, seborrheic keratosis, malignant melanoma, melanocytic nevus, lentigo, pyogenic granuloma, hemangioma, dermatofibroma, and wart. The convolutional neural network (Microsoft ResNet-152 model; Microsoft Research Asia, Beijing, China) was fine-tuned with images from the training portion of the Asan dataset, MED-NODE dataset, and atlas site images (19,398 images in total). The trained model was validated with the testing portion of the Asan, Hallym and Edinburgh datasets. With the Asan dataset, the area under the curve for the diagnosis of basal cell carcinoma, squamous cell carcinoma, intraepithelial carcinoma, and melanoma was 0.96 ± 0.01, 0.83 ± 0.01, 0.82 ± 0.02, and 0.96 ± 0.00, respectively. With the Edinburgh dataset, the area under the curve for the corresponding diseases was 0.90 ± 0.01, 0.91 ± 0.01, 0.83 ± 0.01, and 0.88 ± 0.01, respectively. With the Hallym dataset, the sensitivity for basal cell carcinoma diagnosis was 87.1% ± 6.0%. The tested algorithm performance with 480 Asan and Edinburgh images was comparable to that of 16 dermatologists. To improve the performance of convolutional neural network, additional images with a broader range of ages and ethnicities should be collected. Copyright © 2018 The Authors. Published by Elsevier Inc. All rights reserved.
Expression of uncarboxylated matrix Gla protein in ankylosing spondylitis and its significance
Directory of Open Access Journals (Sweden)
Han-qing HUANG
2013-07-01
Full Text Available Objective To investigate the serum level of uncarboxylated matrix Gla protein (ucMGP in ankylosing spondylitis (AS patients, and to evaluate its diagnostic value and the relation of ucMGP to inflammation and ossification process in AS. Methods Eight-two AS patients and 76 healthy controls were enrolled in this randomized controlled study. The clinical indices (age, gender, course of disease, disease activity, changes in radiographic studies, and indices of bone metabolism or inflammation, including erythrocyte sedimentation rate (ESR, C-reactive protein (CRP, osteocalcin (OC, and bone-specific alkaline phosphatase (BALP were evaluated or measured. The disease activity was assessed by Bath Ankylosing Spondylitis Disease Activity Index (BASDAI, and changes in radiographic pictures were evaluated according to the modified Stoke AS Spine Score (mSASSS, and serum level of ucMGP was measured by a competitive ELISA. The relationship between ucMGP and clinical indexes, radiographic scoring, indices in bone metabolism or inflammation was estimated by SPSS software, and the diagnostic value of ucMGP was analyzed by receiver operator characteristic (ROC curve. Results The levels of ESR and CRP in AS patients were higher than those in healthy controls, but the serum ucMGP was lower (2958±654nmol/L compared with healthy controls (4551±1036nmol/L, P0, r=－0.715, P1, r=－0.741, P10, r=－0.776, P<0.01; mSASSS <10, r=－0.297, P=0.028. Conclusion Serum ucMGP may serve as a diagnostic biomarker of AS and progression index of ossification, especially in late stage of AS.
Vitamin K-Dependent Carboxylation of Matrix Gla Protein Influences the Risk of Calciphylaxis.
Nigwekar, Sagar U; Bloch, Donald B; Nazarian, Rosalynn M; Vermeer, Cees; Booth, Sarah L; Xu, Dihua; Thadhani, Ravi I; Malhotra, Rajeev
2017-06-01
Matrix Gla protein (MGP) is a potent inhibitor of vascular calcification. The ability of MGP to inhibit calcification requires the activity of a vitamin K-dependent enzyme, which mediates MGP carboxylation. We investigated how MGP carboxylation influences the risk of calciphylaxis in adult patients receiving dialysis and examined the effects of vitamin K deficiency on MGP carboxylation. Our study included 20 patients receiving hemodialysis with calciphylaxis (cases) and 20 patients receiving hemodialysis without calciphylaxis (controls) matched for age, sex, race, and warfarin use. Cases had higher plasma levels of uncarboxylated MGP (ucMGP) and carboxylated MGP (cMGP) than controls. However, the fraction of total MGP that was carboxylated (relative cMGP concentration = cMGP/[cMGP + uncarboxylated MGP]) was lower in cases than in controls (0.58±0.02 versus 0.69±0.03, respectively; P =0.003). In patients not taking warfarin, cases had a similarly lower relative cMGP concentration. Each 0.1 unit reduction in relative cMGP concentration associated with a more than two-fold increase in calciphylaxis risk. Vitamin K deficiency associated with lower relative cMGP concentration in multivariable adjusted analyses ( β =-8.99; P =0.04). In conclusion, vitamin K deficiency-mediated reduction in relative cMGP concentration may have a role in the pathogenesis of calciphylaxis. Whether vitamin K supplementation can prevent and/or treat calciphylaxis requires further study. Copyright © 2017 by the American Society of Nephrology.
Magana-Mora, Arturo
2017-04-29
Machine-learning (ML) techniques have been widely applied to solve different problems in biology. However, biological data are large and complex, which often result in extremely intricate ML models. Frequently, these models may have a poor performance or may be computationally unfeasible. This study presents a set of novel computational methods and focuses on the application of genetic algorithms (GAs) for the simplification and optimization of ML models and their applications to biological problems. The dissertation addresses the following three challenges. The first is to develop a generalizable classification methodology able to systematically derive competitive models despite the complexity and nature of the data. Although several algorithms for the induction of classification models have been proposed, the algorithms are data dependent. Consequently, we developed OmniGA, a novel and generalizable framework that uses different classification models in a treeXlike decision structure, along with a parallel GA for the optimization of the OmniGA structure. Results show that OmniGA consistently outperformed existing commonly used classification models. The second challenge is the prediction of translation initiation sites (TIS) in plants genomic DNA. We performed a statistical analysis of the genomic DNA and proposed a new set of discriminant features for this problem. We developed a wrapper method based on GAs for selecting an optimal feature subset, which, in conjunction with a classification model, produced the most accurate framework for the recognition of TIS in plants. Finally, results demonstrate that despite the evolutionary distance between different plants, our approach successfully identified conserved genomic elements that may serve as the starting point for the development of a generic model for prediction of TIS in eukaryotic organisms. Finally, the third challenge is the accurate prediction of polyadenylation signals in human genomic DNA. To achieve
Short communication: Prediction of retention pay-off using a machine learning algorithm.
Shahinfar, Saleh; Kalantari, Afshin S; Cabrera, Victor; Weigel, Kent
2014-05-01
Replacement decisions have a major effect on dairy farm profitability. Dynamic programming (DP) has been widely studied to find the optimal replacement policies in dairy cattle. However, DP models are computationally intensive and might not be practical for daily decision making. Hence, the ability of applying machine learning on a prerun DP model to provide fast and accurate predictions of nonlinear and intercorrelated variables makes it an ideal methodology. Milk class (1 to 5), lactation number (1 to 9), month in milk (1 to 20), and month of pregnancy (0 to 9) were used to describe all cows in a herd in a DP model. Twenty-seven scenarios based on all combinations of 3 levels (base, 20% above, and 20% below) of milk production, milk price, and replacement cost were solved with the DP model, resulting in a data set of 122,716 records, each with a calculated retention pay-off (RPO). Then, a machine learning model tree algorithm was used to mimic the evaluated RPO with DP. The correlation coefficient factor was used to observe the concordance of RPO evaluated by DP and RPO predicted by the model tree. The obtained correlation coefficient was 0.991, with a corresponding value of 0.11 for relative absolute error. At least 100 instances were required per model constraint, resulting in 204 total equations (models). When these models were used for binary classification of positive and negative RPO, error rates were 1% false negatives and 9% false positives. Applying this trained model from simulated data for prediction of RPO for 102 actual replacement records from the University of Wisconsin-Madison dairy herd resulted in a 0.994 correlation with 0.10 relative absolute error rate. Overall results showed that model tree has a potential to be used in conjunction with DP to assist farmers in their replacement decisions. Copyright © 2014 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.
Assessing the Performance of a Machine Learning Algorithm in Identifying Bubbles in Dust Emission
Xu, Duo; Offner, Stella S. R.
2017-12-01
Stellar feedback created by radiation and winds from massive stars plays a significant role in both physical and chemical evolution of molecular clouds. This energy and momentum leaves an identifiable signature (“bubbles”) that affects the dynamics and structure of the cloud. Most bubble searches are performed “by eye,” which is usually time-consuming, subjective, and difficult to calibrate. Automatic classifications based on machine learning make it possible to perform systematic, quantifiable, and repeatable searches for bubbles. We employ a previously developed machine learning algorithm, Brut, and quantitatively evaluate its performance in identifying bubbles using synthetic dust observations. We adopt magnetohydrodynamics simulations, which model stellar winds launching within turbulent molecular clouds, as an input to generate synthetic images. We use a publicly available three-dimensional dust continuum Monte Carlo radiative transfer code, HYPERION, to generate synthetic images of bubbles in three Spitzer bands (4.5, 8, and 24 μm). We designate half of our synthetic bubbles as a training set, which we use to train Brut along with citizen-science data from the Milky Way Project (MWP). We then assess Brut’s accuracy using the remaining synthetic observations. We find that Brut’s performance after retraining increases significantly, and it is able to identify yellow bubbles, which are likely associated with B-type stars. Brut continues to perform well on previously identified high-score bubbles, and over 10% of the MWP bubbles are reclassified as high-confidence bubbles, which were previously marginal or ambiguous detections in the MWP data. We also investigate the influence of the size of the training set, dust model, evolutionary stage, and background noise on bubble identification.
Jiang, Guo-Qing; Xu, Jing; Wei, Jun
2018-04-01
Two algorithms based on machine learning neural networks are proposed—the shallow learning (S-L) and deep learning (D-L) algorithms—that can potentially be used in atmosphere-only typhoon forecast models to provide flow-dependent typhoon-induced sea surface temperature cooling (SSTC) for improving typhoon predictions. The major challenge of existing SSTC algorithms in forecast models is how to accurately predict SSTC induced by an upcoming typhoon, which requires information not only from historical data but more importantly also from the target typhoon itself. The S-L algorithm composes of a single layer of neurons with mixed atmospheric and oceanic factors. Such a structure is found to be unable to represent correctly the physical typhoon-ocean interaction. It tends to produce an unstable SSTC distribution, for which any perturbations may lead to changes in both SSTC pattern and strength. The D-L algorithm extends the neural network to a 4 × 5 neuron matrix with atmospheric and oceanic factors being separated in different layers of neurons, so that the machine learning can determine the roles of atmospheric and oceanic factors in shaping the SSTC. Therefore, it produces a stable crescent-shaped SSTC distribution, with its large-scale pattern determined mainly by atmospheric factors (e.g., winds) and small-scale features by oceanic factors (e.g., eddies). Sensitivity experiments reveal that the D-L algorithms improve maximum wind intensity errors by 60-70% for four case study simulations, compared to their atmosphere-only model runs.
A Pathological Brain Detection System based on Extreme Learning Machine Optimized by Bat Algorithm.
Lu, Siyuan; Qiu, Xin; Shi, Jianping; Li, Na; Lu, Zhi-Hai; Chen, Peng; Yang, Meng-Meng; Liu, Fang-Yuan; Jia, Wen-Juan; Zhang, Yudong
2017-01-01
It is beneficial to classify brain images as healthy or pathological automatically, because 3D brain images can generate so much information which is time consuming and tedious for manual analysis. Among various 3D brain imaging techniques, magnetic resonance (MR) imaging is the most suitable for brain, and it is now widely applied in hospitals, because it is helpful in the four ways of diagnosis, prognosis, pre-surgical, and postsurgical procedures. There are automatic detection methods; however they suffer from low accuracy. Therefore, we proposed a novel approach which employed 2D discrete wavelet transform (DWT), and calculated the entropies of the subbands as features. Then, a bat algorithm optimized extreme learning machine (BA-ELM) was trained to identify pathological brains from healthy controls. A 10x10-fold cross validation was performed to evaluate the out-of-sample performance. The method achieved a sensitivity of 99.04%, a specificity of 93.89%, and an overall accuracy of 98.33% over 132 MR brain images. The experimental results suggest that the proposed approach is accurate and robust in pathological brain detection. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.
A novel deep learning algorithm for incomplete face recognition: Low-rank-recovery network.
Zhao, Jianwei; Lv, Yongbiao; Zhou, Zhenghua; Cao, Feilong
2017-10-01
There have been a lot of methods to address the recognition of complete face images. However, in real applications, the images to be recognized are usually incomplete, and it is more difficult to realize such a recognition. In this paper, a novel convolution neural network frame, named a low-rank-recovery network (LRRNet), is proposed to conquer the difficulty effectively inspired by matrix completion and deep learning techniques. The proposed LRRNet first recovers the incomplete face images via an approach of matrix completion with the truncated nuclear norm regularization solution, and then extracts some low-rank parts of the recovered images as the filters. With these filters, some important features are obtained by means of the binaryzation and histogram algorithms. Finally, these features are classified with the classical support vector machines (SVMs). The proposed LRRNet method has high face recognition rate for the heavily corrupted images, especially for the images in the large databases. The proposed LRRNet performs well and efficiently for the images with heavily corrupted, especially in the case of large databases. Extensive experiments on several benchmark databases demonstrate that the proposed LRRNet performs better than some other excellent robust face recognition methods. Copyright © 2017 Elsevier Ltd. All rights reserved.
Generalizing and learning protein-DNA binding sequence representations by an evolutionary algorithm
Wong, Ka Chun
2011-02-05
Protein-DNA bindings are essential activities. Understanding them forms the basis for further deciphering of biological and genetic systems. In particular, the protein-DNA bindings between transcription factors (TFs) and transcription factor binding sites (TFBSs) play a central role in gene transcription. Comprehensive TF-TFBS binding sequence pairs have been found in a recent study. However, they are in one-to-one mappings which cannot fully reflect the many-to-many mappings within the bindings. An evolutionary algorithm is proposed to learn generalized representations (many-to-many mappings) from the TF-TFBS binding sequence pairs (one-to-one mappings). The generalized pairs are shown to be more meaningful than the original TF-TFBS binding sequence pairs. Some representative examples have been analyzed in this study. In particular, it shows that the TF-TFBS binding sequence pairs are not presumably in one-to-one mappings. They can also exhibit many-to-many mappings. The proposed method can help us extract such many-to-many information from the one-to-one TF-TFBS binding sequence pairs found in the previous study, providing further knowledge in understanding the bindings between TFs and TFBSs. © 2011 Springer-Verlag.
Generalizing and learning protein-DNA binding sequence representations by an evolutionary algorithm
Wong, Ka Chun; Peng, Chengbin; Wong, Manhon; Leung, Kwongsak
2011-01-01
Protein-DNA bindings are essential activities. Understanding them forms the basis for further deciphering of biological and genetic systems. In particular, the protein-DNA bindings between transcription factors (TFs) and transcription factor binding sites (TFBSs) play a central role in gene transcription. Comprehensive TF-TFBS binding sequence pairs have been found in a recent study. However, they are in one-to-one mappings which cannot fully reflect the many-to-many mappings within the bindings. An evolutionary algorithm is proposed to learn generalized representations (many-to-many mappings) from the TF-TFBS binding sequence pairs (one-to-one mappings). The generalized pairs are shown to be more meaningful than the original TF-TFBS binding sequence pairs. Some representative examples have been analyzed in this study. In particular, it shows that the TF-TFBS binding sequence pairs are not presumably in one-to-one mappings. They can also exhibit many-to-many mappings. The proposed method can help us extract such many-to-many information from the one-to-one TF-TFBS binding sequence pairs found in the previous study, providing further knowledge in understanding the bindings between TFs and TFBSs. © 2011 Springer-Verlag.
Wei, Jun; Jiang, Guo-Qing; Liu, Xin
2017-09-01
This study proposed three algorithms that can potentially be used to provide sea surface temperature (SST) conditions for typhoon prediction models. Different from traditional data assimilation approaches, which provide prescribed initial/boundary conditions, our proposed algorithms aim to resolve a flow-dependent SST feedback between growing typhoons and oceans in the future time. Two of these algorithms are based on linear temperature equations (TE-based), and the other is based on an innovative technique involving machine learning (ML-based). The algorithms are then implemented into a Weather Research and Forecasting model for the simulation of typhoon to assess their effectiveness, and the results show significant improvement in simulated storm intensities by including ocean cooling feedback. The TE-based algorithm I considers wind-induced ocean vertical mixing and upwelling processes only, and thus obtained a synoptic and relatively smooth sea surface temperature cooling. The TE-based algorithm II incorporates not only typhoon winds but also ocean information, and thus resolves more cooling features. The ML-based algorithm is based on a neural network, consisting of multiple layers of input variables and neurons, and produces the best estimate of the cooling structure, in terms of its amplitude and position. Sensitivity analysis indicated that the typhoon-induced ocean cooling is a nonlinear process involving interactions of multiple atmospheric and oceanic variables. Therefore, with an appropriate selection of input variables and neuron sizes, the ML-based algorithm appears to be more efficient in prognosing the typhoon-induced ocean cooling and in predicting typhoon intensity than those algorithms based on linear regression methods.
Niny Rydzewskiej "Ludzie z węgla" i Zyty Oryszyn "Ocalenie Atlantydy": próba lektury palimpsestowej
Kraskowska, Ewa
2014-01-01
This article presents a parallel (“palipmsest”) reading of two novels set in post−war Wałbrzych: Ludzie z węgla (People of Coal) by Nina Rydzewska and Ocalenie Atlantydy (Atlantis Rescued) by Zyta Oryszyn. The former was published in 1951 and follows the doctrine of socialist realism,and the latter appeared in print in 2013, as the last one of the author’s novel cycle started in 1981. Extremely different in form and worldview, these two novels share their chronotope, and the aim of this study...
DEFF Research Database (Denmark)
Kamby, C; Egsmose, C; Söletormos, G
1993-01-01
Serum bone Gla protein (S-BGP), a marker of bone metabolism, was measured in 60 patients included in a staging programme for recurrent breast cancer. Other diagnostic procedures comprised S-alkaline phosphatase (S-AP), bone scan (B-scan), bilateral iliac crest bone marrow biopsies, and radiological...... bone survey. The sites of recurrence were bone (61%), bone marrow (46%), soft tissue (52%), lung (13%), pleura (11%), liver (4%), and brain (2%). Radiology and bone biopsy served as key diagnoses as to the presence or absence of bone metastases. The diagnostic efficiency of B-scan and S-AP was greater...
Li, Qiang; Wang, Zhi; Le, Yansi; Sun, Chonghui; Song, Xiaojia; Wu, Chongqing
2016-10-01
Neuromorphic engineering has a wide range of applications in the fields of machine learning, pattern recognition, adaptive control, etc. Photonics, characterized by its high speed, wide bandwidth, low power consumption and massive parallelism, is an ideal way to realize ultrafast spiking neural networks (SNNs). Synaptic plasticity is believed to be critical for learning, memory and development in neural circuits. Experimental results have shown that changes of synapse are highly dependent on the relative timing of pre- and postsynaptic spikes. Synaptic plasticity in which presynaptic spikes preceding postsynaptic spikes results in strengthening, while the opposite timing results in weakening is called antisymmetric spike-timing-dependent plasticity (STDP) learning rule. And synaptic plasticity has the opposite effect under the same conditions is called antisymmetric anti-STDP learning rule. We proposed and experimentally demonstrated an optical implementation of neural learning algorithms, which can achieve both of antisymmetric STDP and anti-STDP learning rule, based on the cross-gain modulation (XGM) within a single semiconductor optical amplifier (SOA). The weight and height of the potentitation and depression window can be controlled by adjusting the injection current of the SOA, to mimic the biological antisymmetric STDP and anti-STDP learning rule more realistically. As the injection current increases, the width of depression and potentitation window decreases and height increases, due to the decreasing of recovery time and increasing of gain under a stronger injection current. Based on the demonstrated optical STDP circuit, ultrafast learning in optical SNNs can be realized.
Lee, Jae-Hong; Kim, Do-Hyung; Jeong, Seong-Nyum; Choi, Seong-Ho
2018-04-01
The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.
Directory of Open Access Journals (Sweden)
Marco Scutari
2017-03-01
Full Text Available It is well known in the literature that the problem of learning the structure of Bayesian networks is very hard to tackle: Its computational complexity is super-exponential in the number of nodes in the worst case and polynomial in most real-world scenarios. Efficient implementations of score-based structure learning benefit from past and current research in optimization theory, which can be adapted to the task by using the network score as the objective function to maximize. This is not true for approaches based on conditional independence tests, called constraint-based learning algorithms. The only optimization in widespread use, backtracking, leverages the symmetries implied by the definitions of neighborhood and Markov blanket. In this paper we illustrate how backtracking is implemented in recent versions of the bnlearn R package, and how it degrades the stability of Bayesian network structure learning for little gain in terms of speed. As an alternative, we describe a software architecture and framework that can be used to parallelize constraint-based structure learning algorithms (also implemented in bnlearn and we demonstrate its performance using four reference networks and two real-world data sets from genetics and systems biology. We show that on modern multi-core or multiprocessor hardware parallel implementations are preferable over backtracking, which was developed when single-processor machines were the norm.
Sweeney, Elizabeth M.; Vogelstein, Joshua T.; Cuzzocreo, Jennifer L.; Calabresi, Peter A.; Reich, Daniel S.; Crainiceanu, Ciprian M.; Shinohara, Russell T.
2014-01-01
Machine learning is a popular method for mining and analyzing large collections of medical data. We focus on a particular problem from medical research, supervised multiple sclerosis (MS) lesion segmentation in structural magnetic resonance imaging (MRI). We examine the extent to which the choice of machine learning or classification algorithm and feature extraction function impacts the performance of lesion segmentation methods. As quantitative measures derived from structural MRI are important clinical tools for research into the pathophysiology and natural history of MS, the development of automated lesion segmentation methods is an active research field. Yet, little is known about what drives performance of these methods. We evaluate the performance of automated MS lesion segmentation methods, which consist of a supervised classification algorithm composed with a feature extraction function. These feature extraction functions act on the observed T1-weighted (T1-w), T2-weighted (T2-w) and fluid-attenuated inversion recovery (FLAIR) MRI voxel intensities. Each MRI study has a manual lesion segmentation that we use to train and validate the supervised classification algorithms. Our main finding is that the differences in predictive performance are due more to differences in the feature vectors, rather than the machine learning or classification algorithms. Features that incorporate information from neighboring voxels in the brain were found to increase performance substantially. For lesion segmentation, we conclude that it is better to use simple, interpretable, and fast algorithms, such as logistic regression, linear discriminant analysis, and quadratic discriminant analysis, and to develop the features to improve performance. PMID:24781953
Ehteshami Bejnordi, Babak; Veta, Mitko; Johannes van Diest, Paul; van Ginneken, Bram; Karssemeijer, Nico; Litjens, Geert; van der Laak, Jeroen A W M; Hermsen, Meyke; Manson, Quirine F; Balkenhol, Maschenka; Geessink, Oscar; Stathonikos, Nikolaos; van Dijk, Marcory Crf; Bult, Peter; Beca, Francisco; Beck, Andrew H; Wang, Dayong; Khosla, Aditya; Gargeya, Rishab; Irshad, Humayun; Zhong, Aoxiao; Dou, Qi; Li, Quanzheng; Chen, Hao; Lin, Huang-Jing; Heng, Pheng-Ann; Haß, Christian; Bruni, Elia; Wong, Quincy; Halici, Ugur; Öner, Mustafa Ümit; Cetin-Atalay, Rengul; Berseth, Matt; Khvatkov, Vitali; Vylegzhanin, Alexei; Kraus, Oren; Shaban, Muhammad; Rajpoot, Nasir; Awan, Ruqayya; Sirinukunwattana, Korsuk; Qaiser, Talha; Tsang, Yee-Wah; Tellez, David; Annuscheit, Jonas; Hufnagl, Peter; Valkonen, Mira; Kartasalo, Kimmo; Latonen, Leena; Ruusuvuori, Pekka; Liimatainen, Kaisa; Albarqouni, Shadi; Mungal, Bharti; George, Ami; Demirci, Stefanie; Navab, Nassir; Watanabe, Seiryo; Seno, Shigeto; Takenaka, Yoichi; Matsuda, Hideo; Ahmady Phoulady, Hady; Kovalev, Vassili; Kalinovsky, Alexander; Liauchuk, Vitali; Bueno, Gloria; Fernandez-Carrobles, M Milagro; Serrano, Ismael; Deniz, Oscar; Racoceanu, Daniel; Venâncio, Rui
2017-12-12
Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image
Olivera, André Rodrigues; Roesler, Valter; Iochpe, Cirano; Schmidt, Maria Inês; Vigo, Álvaro; Barreto, Sandhi Maria; Duncan, Bruce Bartholow
2017-01-01
Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. The best models were created using artificial neural networks and logistic regression. -These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.
Baptista, Miguel Viana; Ferreira, Susana; Pinho-E-Melo, Teresa; Carvalho, Marta; Cruz, Vítor T; Carmona, Cátia; Silva, Fernando A; Tuna, Assunção; Rodrigues, Miguel; Ferreira, Carla; Pinto, Ana A N; Leitão, André; Gabriel, João Paulo; Calado, Sofia; Oliveira, João Paulo; Ferro, José M
2010-03-01
Fabry disease is an X-linked monogenic disorder caused by mutations in the GLA gene. Recent data suggest that stroke in young adults may be associated with Fabry disease. We aimed to ascertain the prevalence of this disorder among young adult patients with stroke in Portugal by GLA genotyping. During 1 year, all patients aged 18 to 55 years with first-ever stroke, who were admitted into any of 12 neurology hospital departments in Portugal, were prospectively enrolled (n=625). Ischemic stroke was classified according to Trial of Org 10172 in Acute Stroke Treatment criteria. Alpha-galactosidase activity was further assayed in all patients with GLA mutations. Four hundred ninety-three patients (mean age, 45.4 years; 61% male) underwent genetic analyses: 364 with ischemic stroke, 89 with intracerebral hemorrhage, 26 with subarachnoid hemorrhage, and 14 with cerebral venous thrombosis. Twelve patients had missense GLA mutations: 9 with ischemic stroke (p.R118C: n=4; p.D313Y: n=5), including 5 patients with an identified cause of stroke (cardiac embolism: n=2; small vessel disease: n=2; other cause: n=1), 2 with intracerebral hemorrhage (p.R118C: n=1; p.D313Y: n=1), and one with cerebral venous thrombosis (p.R118C: n=1). Leukocyte alpha-galactosidase activity was subnormal in the hemizygous males and subnormal or low-normal in the heterozygous females. Estimated prevalence of missense GLA mutations was 2.4% (95% CI, 1.3% to 4.1%). Despite a low diagnostic yield, screening for GLA mutations should probably be considered in different types of stroke. Restricting investigation to patients with cryptogenic stroke may underestimate the true prevalence of Fabry disease in young patients with stroke.
Cha, Seung Bin; Kim, Woo Sik; Kim, Jong-Seok; Kim, Hongmin; Kwon, Kee Woong; Han, Seung Jung; Cho, Sang-Nae; Coler, Rhea N; Reed, Steven G; Shin, Sung Jae
2016-04-27
The majority of tuberculosis (TB) vaccine candidates advanced to clinical trials have been evaluated preclinically using laboratory-adapted strains. However, it has been proposed that challenge with clinical isolates in preclinical vaccine testing could provide further and more practical validation. Here, we tested the ID93/GLA-SE TB vaccine candidate against the clinical Mycobacterium tuberculosis (Mtb) strain K (Mtb K) belonging to the Beijing family, the most prevalent Mtb strain in South Korea. Mice immunized with ID93/GLA-SE exhibited a significant reduction in bacteria and reduced lung inflammation against Mtb K when compared to non-immunized controls. In addition, we analyzed the immune responses in the lungs of ID93/GLA-SE-immunized mice, and showed that ID93/GLA-SE was able to elicit sustained Th1-biased immune responses including antigen-specific multifunctional CD4(+) T cell co-producing IFN-γ, TNF-α, and IL-2 as well as a high magnitude of IFN-γ response for up to 10 weeks post-challenge. Notably, further investigation of T cell subsets in the lung following challenge showed remarkable generation of CD8(+) central memory T cells by ID93/GLA-SE-immunization. Our findings showed that ID93/GLA-SE vaccine confers a high level of robust protection against the hypervirulent Mtb Beijing infection which was characterized by pulmonary Th1-polarized T-cell immune responses. These findings may also provide relevant information for potential utility of this vaccine candidate in East-Asian countries where the Beijing genotype is highly prevalent. Copyright © 2016 Elsevier Ltd. All rights reserved.
Directory of Open Access Journals (Sweden)
Xuanyu Wang
2017-12-01
Full Text Available Terrestrial latent heat flux (LE is a key component of the global terrestrial water, energy, and carbon exchanges. Accurate estimation of LE from moderate resolution imaging spectroradiometer (MODIS data remains a major challenge. In this study, we estimated the daily LE for different plant functional types (PFTs across North America using three machine learning algorithms: artificial neural network (ANN; support vector machines (SVM; and, multivariate adaptive regression spline (MARS driven by MODIS and Modern Era Retrospective Analysis for Research and Applications (MERRA meteorology data. These three predictive algorithms, which were trained and validated using observed LE over the period 2000–2007, all proved to be accurate. However, ANN outperformed the other two algorithms for the majority of the tested configurations for most PFTs and was the only method that arrived at 80% precision for LE estimation. We also applied three machine learning algorithms for MODIS data and MERRA meteorology to map the average annual terrestrial LE of North America during 2002–2004 using a spatial resolution of 0.05°, which proved to be useful for estimating the long-term LE over North America.
Machine Learning Algorithms For Predicting the Instability Timescales of Compact Planetary Systems
Tamayo, Daniel; Ali-Dib, Mohamad; Cloutier, Ryan; Huang, Chelsea; Van Laerhoven, Christa L.; Leblanc, Rejean; Menou, Kristen; Murray, Norman; Obertas, Alysa; Paradise, Adiv; Petrovich, Cristobal; Rachkov, Aleksandar; Rein, Hanno; Silburt, Ari; Tacik, Nick; Valencia, Diana
2016-10-01
The Kepler mission has uncovered hundreds of compact multi-planet systems. The dynamical pathways to instability in these compact systems and their associated timescales are not well understood theoretically. However, long-term stability is often used as a constraint to narrow down the space of orbital solutions from the transit data. This requires a large suite of N-body integrations that can each take several weeks to complete. This computational bottleneck is therefore an important limitation in our ability to characterize compact multi-planet systems.From suites of numerical simulations, previous studies have fit simple scaling relations between the instability timescale and various system parameters. However, the numerically simulated systems can deviate strongly from these empirical fits.We present a new approach to the problem using machine learning algorithms that have enjoyed success across a broad range of high-dimensional industry applications. In particular, we have generated large training sets of direct N-body integrations of synthetic compact planetary systems to train several regression models (support vector machine, gradient boost) that predict the instability timescale. We find that ensembling these models predicts the instability timescale of planetary systems better than previous approaches using the simple scaling relations mentioned above.Finally, we will discuss how these models provide a powerful tool for not only understanding the current Kepler multi-planet sample, but also for characterizing and shaping the radial-velocity follow-up strategies of multi-planet systems from the upcoming Transiting Exoplanet Survey Satellite (TESS) mission, given its shorter observation baselines.
Chung, Seok Won; Han, Seung Seog; Lee, Ji Whan; Oh, Kyung-Soo; Kim, Na Ra; Yoon, Jong Pil; Kim, Joon Yub; Moon, Sung Hoon; Kwon, Jieun; Lee, Hyo-Jin; Noh, Young-Min; Kim, Youngjun
2018-03-26
Background and purpose - We aimed to evaluate the ability of artificial intelligence (a deep learning algorithm) to detect and classify proximal humerus fractures using plain anteroposterior shoulder radiographs. Patients and methods - 1,891 images (1 image per person) of normal shoulders (n = 515) and 4 proximal humerus fracture types (greater tuberosity, 346; surgical neck, 514; 3-part, 269; 4-part, 247) classified by 3 specialists were evaluated. We trained a deep convolutional neural network (CNN) after augmentation of a training dataset. The ability of the CNN, as measured by top-1 accuracy, area under receiver operating characteristics curve (AUC), sensitivity/specificity, and Youden index, in comparison with humans (28 general physicians, 11 general orthopedists, and 19 orthopedists specialized in the shoulder) to detect and classify proximal humerus fractures was evaluated. Results - The CNN showed a high performance of 96% top-1 accuracy, 1.00 AUC, 0.99/0.97 sensitivity/specificity, and 0.97 Youden index for distinguishing normal shoulders from proximal humerus fractures. In addition, the CNN showed promising results with 65-86% top-1 accuracy, 0.90-0.98 AUC, 0.88/0.83-0.97/0.94 sensitivity/specificity, and 0.71-0.90 Youden index for classifying fracture type. When compared with the human groups, the CNN showed superior performance to that of general physicians and orthopedists, similar performance to orthopedists specialized in the shoulder, and the superior performance of the CNN was more marked in complex 3- and 4-part fractures. Interpretation - The use of artificial intelligence can accurately detect and classify proximal humerus fractures on plain shoulder AP radiographs. Further studies are necessary to determine the feasibility of applying artificial intelligence in the clinic and whether its use could improve care and outcomes compared with current orthopedic assessments.
Directory of Open Access Journals (Sweden)
Majid Nazeer
2017-11-01
Full Text Available Coastal waters are one of the most vulnerable resources that require effective monitoring programs. One of the key factors for effective coastal monitoring is the use of remote sensing technologies that significantly capture the spatiotemporal variability of coastal waters. Optical properties of coastal waters are strongly linked to components, such as colored dissolved organic matter (CDOM, chlorophyll-a (Chl-a, and suspended solids (SS concentrations, which are essential for the survival of a coastal ecosystem and usually independent of each other. Thus, developing effective remote sensing models to estimate these important water components based on optical properties of coastal waters is mandatory for a successful coastal monitoring program. This study attempted to evaluate the performance of empirical predictive models (EPM and neural networks (NN-based algorithms to estimate Chl-a and SS concentrations, in the coastal area of Hong Kong. Remotely-sensed data over a 13-year period was used to develop regional and local models to estimate Chl-a and SS over the entire Hong Kong waters and for each water class within the study area, respectively. The accuracy of regional models derived from EPM and NN in estimating Chl-a and SS was 83%, 93%, 78%, and 97%, respectively, whereas the accuracy of local models in estimating Chl-a and SS ranged from 60–94% and 81–94%, respectively. Both the regional and local NN models exhibited a higher performance than those models derived from empirical analysis. Thus, this study suggests using machine learning methods (i.e., NN for the more accurate and efficient routine monitoring of coastal water quality parameters (i.e., Chl-a and SS concentrations over the complex coastal area of Hong Kong and other similar coastal environments.
Gulshan, Varun; Peng, Lily; Coram, Marc; Stumpe, Martin C; Wu, Derek; Narayanaswamy, Arunachalam; Venugopalan, Subhashini; Widner, Kasumi; Madams, Tom; Cuadros, Jorge; Kim, Ramasamy; Raman, Rajiv; Nelson, Philip C; Mega, Jessica L; Webster, Dale R
2016-12-13
Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation. To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs. A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015. The resultant algorithm was validated in January and February 2016 using 2 separate data sets, both graded by at least 7 US board-certified ophthalmologists with high intragrader consistency. Deep learning-trained algorithm. The sensitivity and specificity of the algorithm for detecting referable diabetic retinopathy (RDR), defined as moderate and worse diabetic retinopathy, referable diabetic macular edema, or both, were generated based on the reference standard of the majority decision of the ophthalmologist panel. The algorithm was evaluated at 2 operating points selected from the development set, one selected for high specificity and another for high sensitivity. The EyePACS-1 data set consisted of 9963 images from 4997 patients (mean age, 54.4 years; 62.2% women; prevalence of RDR, 683/8878 fully gradable images [7.8%]); the Messidor-2 data set had 1748 images from 874 patients (mean age, 57.6 years; 42.6% women; prevalence of RDR, 254/1745 fully gradable images [14.6%]). For detecting RDR, the algorithm had an area under the receiver operating curve of 0.991 (95% CI, 0.988-0.993) for EyePACS-1 and 0
Sengupta, Partho P; Huang, Yen-Min; Bansal, Manish; Ashrafi, Ali; Fisher, Matt; Shameer, Khader; Gall, Walt; Dudley, Joel T
2016-06-01
Associating a patient's profile with the memories of prototypical patients built through previous repeat clinical experience is a key process in clinical judgment. We hypothesized that a similar process using a cognitive computing tool would be well suited for learning and recalling multidimensional attributes of speckle tracking echocardiography data sets derived from patients with known constrictive pericarditis and restrictive cardiomyopathy. Clinical and echocardiographic data of 50 patients with constrictive pericarditis and 44 with restrictive cardiomyopathy were used for developing an associative memory classifier-based machine-learning algorithm. The speckle tracking echocardiography data were normalized in reference to 47 controls with no structural heart disease, and the diagnostic area under the receiver operating characteristic curve of the associative memory classifier was evaluated for differentiating constrictive pericarditis from restrictive cardiomyopathy. Using only speckle tracking echocardiography variables, associative memory classifier achieved a diagnostic area under the curve of 89.2%, which improved to 96.2% with addition of 4 echocardiographic variables. In comparison, the area under the curve of early diastolic mitral annular velocity and left ventricular longitudinal strain were 82.1% and 63.7%, respectively. Furthermore, the associative memory classifier demonstrated greater accuracy and shorter learning curves than other machine-learning approaches, with accuracy asymptotically approaching 90% after a training fraction of 0.3 and remaining flat at higher training fractions. This study demonstrates feasibility of a cognitive machine-learning approach for learning and recalling patterns observed during echocardiographic evaluations. Incorporation of machine-learning algorithms in cardiac imaging may aid standardized assessments and support the quality of interpretations, particularly for novice readers with limited experience. © 2016
Sengupta, Partho P.; Huang, Yen-Min; Bansal, Manish; Ashrafi, Ali; Fisher, Matt; Shameer, Khader; Gall, Walt; Dudley, Joel T
2016-01-01
Background Associating a patient’s profile with the memories of prototypical patients built through previous repeat clinical experience is a key process in clinical judgment. We hypothesized that a similar process using a cognitive computing tool would be well suited for learning and recalling multidimensional attributes of speckle tracking echocardiography (STE) data sets derived from patients with known constrictive pericarditis (CP) and restrictive cardiomyopathy (RCM). Methods and Results Clinical and echocardiographic data of 50 patients with CP and 44 with RCM were used for developing an associative memory classifier (AMC) based machine learning algorithm. The STE data was normalized in reference to 47 controls with no structural heart disease, and the diagnostic area under the receiver operating characteristic curve (AUC) of the AMC was evaluated for differentiating CP from RCM. Using only STE variables, AMC achieved a diagnostic AUC of 89·2%, which improved to 96·2% with addition of 4 echocardiographic variables. In comparison, the AUC of early diastolic mitral annular velocity and left ventricular longitudinal strain were 82.1% and 63·7%, respectively. Furthermore, AMC demonstrated greater accuracy and shorter learning curves than other machine learning approaches with accuracy asymptotically approaching 90% after a training fraction of 0·3 and remaining flat at higher training fractions. Conclusions This study demonstrates feasibility of a cognitive machine learning approach for learning and recalling patterns observed during echocardiographic evaluations. Incorporation of machine learning algorithms in cardiac imaging may aid standardized assessments and support the quality of interpretations, particularly for novice readers with limited experience. PMID:27266599
Xu, Yue; Wang, Yan-Hui; Liu, Tian-Qi; Zhang, Hui; Zhang, He; Li, Jie
2018-03-31
α-Galactosidases are widely used in many fields. It is necessary to improve the production of enzymes through microbiological processes. The aim of this study was to construct recombinant Aspergillus niger strains with high α-galactosidase production. Two recombinant A. niger strains were constructed: AB and AGB. The recombinant AB strain contained the α-galactosidase aglB gene from A. niger with its native AglB signal peptide regulated by the glucoamylase promoter. In the AGB recombinant strain, the AglB signal peptide was replaced with the glucoamylase (GlaA) signal peptide. The extracellular maximum α-galactosidase activity of the AGB strain was 215.7 U/ml and that of the AB strain was 9.8 U/mL. The optimal conditions for α-galactosidase were pH 3.5 and 35 °C. The GlaA signal peptide substantially increased the yield of secreted α-galactosidase in A. niger. This recombinant strain holds great potential for industrial applications.
Directory of Open Access Journals (Sweden)
Chien-Hung Huang
2015-01-01
Full Text Available Many proteins are known to be associated with cancer diseases. It is quite often that their precise functional role in disease pathogenesis remains unclear. A strategy to gain a better understanding of the function of these proteins is to make use of a combination of different aspects of proteomics data types. In this study, we extended Aragues’s method by employing the protein-protein interaction (PPI data, domain-domain interaction (DDI data, weighted domain frequency score (DFS, and cancer linker degree (CLD data to predict cancer proteins. Performances were benchmarked based on three kinds of experiments as follows: (I using individual algorithm, (II combining algorithms, and (III combining the same classification types of algorithms. When compared with Aragues’s method, our proposed methods, that is, machine learning algorithm and voting with the majority, are significantly superior in all seven performance measures. We demonstrated the accuracy of the proposed method on two independent datasets. The best algorithm can achieve a hit ratio of 89.4% and 72.8% for lung cancer dataset and lung cancer microarray study, respectively. It is anticipated that the current research could help understand disease mechanisms and diagnosis.
Watson, Robert A
2014-08-01
To test the hypothesis that machine learning algorithms increase the predictive power to classify surgical expertise using surgeons' hand motion patterns. In 2012 at the University of North Carolina at Chapel Hill, 14 surgical attendings and 10 first- and second-year surgical residents each performed two bench model venous anastomoses. During the simulated tasks, the participants wore an inertial measurement unit on the dorsum of their dominant (right) hand to capture their hand motion patterns. The pattern from each bench model task performed was preprocessed into a symbolic time series and labeled as expert (attending) or novice (resident). The labeled hand motion patterns were processed and used to train a Support Vector Machine (SVM) classification algorithm. The trained algorithm was then tested for discriminative/predictive power against unlabeled (blinded) hand motion patterns from tasks not used in the training. The Lempel-Ziv (LZ) complexity metric was also measured from each hand motion pattern, with an optimal threshold calculated to separately classify the patterns. The LZ metric classified unlabeled (blinded) hand motion patterns into expert and novice groups with an accuracy of 70% (sensitivity 64%, specificity 80%). The SVM algorithm had an accuracy of 83% (sensitivity 86%, specificity 80%). The results confirmed the hypothesis. The SVM algorithm increased the predictive power to classify blinded surgical hand motion patterns into expert versus novice groups. With further development, the system used in this study could become a viable tool for low-cost, objective assessment of procedural proficiency in a competency-based curriculum.
2017-01-01
Background Machine learning techniques may be an effective and efficient way to classify open-text reports on doctor’s activity for the purposes of quality assurance, safety, and continuing professional development. Objective The objective of the study was to evaluate the accuracy of machine learning algorithms trained to classify open-text reports of doctor performance and to assess the potential for classifications to identify significant differences in doctors’ professional performance in the United Kingdom. Methods We used 1636 open-text comments (34,283 words) relating to the performance of 548 doctors collected from a survey of clinicians’ colleagues using the General Medical Council Colleague Questionnaire (GMC-CQ). We coded 77.75% (1272/1636) of the comments into 5 global themes (innovation, interpersonal skills, popularity, professionalism, and respect) using a qualitative framework. We trained 8 machine learning algorithms to classify comments and assessed their performance using several training samples. We evaluated doctor performance using the GMC-CQ and compared scores between doctors with different classifications using t tests. Results Individual algorithm performance was high (range F score=.68 to .83). Interrater agreement between the algorithms and the human coder was highest for codes relating to “popular” (recall=.97), “innovator” (recall=.98), and “respected” (recall=.87) codes and was lower for the “interpersonal” (recall=.80) and “professional” (recall=.82) codes. A 10-fold cross-validation demonstrated similar performance in each analysis. When combined together into an ensemble of multiple algorithms, mean human-computer interrater agreement was .88. Comments that were classified as “respected,” “professional,” and “interpersonal” related to higher doctor scores on the GMC-CQ compared with comments that were not classified (P.05). Conclusions Machine learning algorithms can classify open-text feedback
Gibbons, Chris; Richards, Suzanne; Valderas, Jose Maria; Campbell, John
2017-03-15
Machine learning techniques may be an effective and efficient way to classify open-text reports on doctor's activity for the purposes of quality assurance, safety, and continuing professional development. The objective of the study was to evaluate the accuracy of machine learning algorithms trained to classify open-text reports of doctor performance and to assess the potential for classifications to identify significant differences in doctors' professional performance in the United Kingdom. We used 1636 open-text comments (34,283 words) relating to the performance of 548 doctors collected from a survey of clinicians' colleagues using the General Medical Council Colleague Questionnaire (GMC-CQ). We coded 77.75% (1272/1636) of the comments into 5 global themes (innovation, interpersonal skills, popularity, professionalism, and respect) using a qualitative framework. We trained 8 machine learning algorithms to classify comments and assessed their performance using several training samples. We evaluated doctor performance using the GMC-CQ and compared scores between doctors with different classifications using t tests. Individual algorithm performance was high (range F score=.68 to .83). Interrater agreement between the algorithms and the human coder was highest for codes relating to "popular" (recall=.97), "innovator" (recall=.98), and "respected" (recall=.87) codes and was lower for the "interpersonal" (recall=.80) and "professional" (recall=.82) codes. A 10-fold cross-validation demonstrated similar performance in each analysis. When combined together into an ensemble of multiple algorithms, mean human-computer interrater agreement was .88. Comments that were classified as "respected," "professional," and "interpersonal" related to higher doctor scores on the GMC-CQ compared with comments that were not classified (P.05). Machine learning algorithms can classify open-text feedback of doctor performance into multiple themes derived by human raters with high
Energy Technology Data Exchange (ETDEWEB)
Lee, Youngrok [Iowa State Univ., Ames, IA (United States)
2013-05-15
Heterogeneity exists on a data set when samples from di erent classes are merged into the data set. Finite mixture models can be used to represent a survival time distribution on heterogeneous patient group by the proportions of each class and by the survival time distribution within each class as well. The heterogeneous data set cannot be explicitly decomposed to homogeneous subgroups unless all the samples are precisely labeled by their origin classes; such impossibility of decomposition is a barrier to overcome for estimating nite mixture models. The expectation-maximization (EM) algorithm has been used to obtain maximum likelihood estimates of nite mixture models by soft-decomposition of heterogeneous samples without labels for a subset or the entire set of data. In medical surveillance databases we can find partially labeled data, that is, while not completely unlabeled there is only imprecise information about class values. In this study we propose new EM algorithms that take advantages of using such partial labels, and thus incorporate more information than traditional EM algorithms. We particularly propose four variants of the EM algorithm named EM-OCML, EM-PCML, EM-HCML and EM-CPCML, each of which assumes a specific mechanism of missing class values. We conducted a simulation study on exponential survival trees with five classes and showed that the advantages of incorporating substantial amount of partially labeled data can be highly signi cant. We also showed model selection based on AIC values fairly works to select the best proposed algorithm on each specific data set. A case study on a real-world data set of gastric cancer provided by Surveillance, Epidemiology and End Results (SEER) program showed a superiority of EM-CPCML to not only the other proposed EM algorithms but also conventional supervised, unsupervised and semi-supervised learning algorithms.
Heidari, Morteza; Zargari Khuzani, Abolfazl; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qian, Wei; Zheng, Bin
2018-03-01
Both conventional and deep machine learning has been used to develop decision-support tools applied in medical imaging informatics. In order to take advantages of both conventional and deep learning approach, this study aims to investigate feasibility of applying a locally preserving projection (LPP) based feature regeneration algorithm to build a new machine learning classifier model to predict short-term breast cancer risk. First, a computer-aided image processing scheme was used to segment and quantify breast fibro-glandular tissue volume. Next, initially computed 44 image features related to the bilateral mammographic tissue density asymmetry were extracted. Then, an LLP-based feature combination method was applied to regenerate a new operational feature vector using a maximal variance approach. Last, a k-nearest neighborhood (KNN) algorithm based machine learning classifier using the LPP-generated new feature vectors was developed to predict breast cancer risk. A testing dataset involving negative mammograms acquired from 500 women was used. Among them, 250 were positive and 250 remained negative in the next subsequent mammography screening. Applying to this dataset, LLP-generated feature vector reduced the number of features from 44 to 4. Using a leave-onecase-out validation method, area under ROC curve produced by the KNN classifier significantly increased from 0.62 to 0.68 (p breast cancer detected in the next subsequent mammography screening.
Berthon, Beatrice; Marshall, Christopher; Evans, Mererid; Spezi, Emiliano
2016-07-07
Accurate and reliable tumour delineation on positron emission tomography (PET) is crucial for radiotherapy treatment planning. PET automatic segmentation (PET-AS) eliminates intra- and interobserver variability, but there is currently no consensus on the optimal method to use, as different algorithms appear to perform better for different types of tumours. This work aimed to develop a predictive segmentation model, trained to automatically select and apply the best PET-AS method, according to the tumour characteristics. ATLAAS, the automatic decision tree-based learning algorithm for advanced segmentation is based on supervised machine learning using decision trees. The model includes nine PET-AS methods and was trained on a 100 PET scans with known true contour. A decision tree was built for each PET-AS algorithm to predict its accuracy, quantified using the Dice similarity coefficient (DSC), according to the tumour volume, tumour peak to background SUV ratio and a regional texture metric. The performance of ATLAAS was evaluated for 85 PET scans obtained from fillable and printed subresolution sandwich phantoms. ATLAAS showed excellent accuracy across a wide range of phantom data and predicted the best or near-best segmentation algorithm in 93% of cases. ATLAAS outperformed all single PET-AS methods on fillable phantom data with a DSC of 0.881, while the DSC for H&N phantom data was 0.819. DSCs higher than 0.650 were achieved in all cases. ATLAAS is an advanced automatic image segmentation algorithm based on decision tree predictive modelling, which can be trained on images with known true contour, to predict the best PET-AS method when the true contour is unknown. ATLAAS provides robust and accurate image segmentation with potential applications to radiation oncology.
Algorithm Animations for Teaching and Learning the Main Ideas of Basic Sortings
Végh, Ladislav; Stoffová, Veronika
2017-01-01
Algorithms are hard to understand for novice computer science students because they dynamically modify values of elements of abstract data structures. Animations can help to understand algorithms, since they connect abstract concepts to real life objects and situations. In the past 30-35 years, there have been conducted many experiments in the…
Heidari, Morteza; Zargari Khuzani, Abolfazl; Hollingsworth, Alan B.; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qiu, Yuchen; Liu, Hong; Zheng, Bin
2018-02-01
In order to automatically identify a set of effective mammographic image features and build an optimal breast cancer risk stratification model, this study aims to investigate advantages of applying a machine learning approach embedded with a locally preserving projection (LPP) based feature combination and regeneration algorithm to predict short-term breast cancer risk. A dataset involving negative mammograms acquired from 500 women was assembled. This dataset was divided into two age-matched classes of 250 high risk cases in which cancer was detected in the next subsequent mammography screening and 250 low risk cases, which remained negative. First, a computer-aided image processing scheme was applied to segment fibro-glandular tissue depicted on mammograms and initially compute 44 features related to the bilateral asymmetry of mammographic tissue density distribution between left and right breasts. Next, a multi-feature fusion based machine learning classifier was built to predict the risk of cancer detection in the next mammography screening. A leave-one-case-out (LOCO) cross-validation method was applied to train and test the machine learning classifier embedded with a LLP algorithm, which generated a new operational vector with 4 features using a maximal variance approach in each LOCO process. Results showed a 9.7% increase in risk prediction accuracy when using this LPP-embedded machine learning approach. An increased trend of adjusted odds ratios was also detected in which odds ratios increased from 1.0 to 11.2. This study demonstrated that applying the LPP algorithm effectively reduced feature dimensionality, and yielded higher and potentially more robust performance in predicting short-term breast cancer risk.
Ceylan Koydemir, Hatice; Feng, Steve; Liang, Kyle; Nadkarni, Rohan; Benien, Parul; Ozcan, Aydogan
2017-06-01
Giardia lamblia is a waterborne parasite that affects millions of people every year worldwide, causing a diarrheal illness known as giardiasis. Timely detection of the presence of the cysts of this parasite in drinking water is important to prevent the spread of the disease, especially in resource-limited settings. Here we provide extended experimental testing and evaluation of the performance and repeatability of a field-portable and cost-effective microscopy platform for automated detection and counting of Giardia cysts in water samples, including tap water, non-potable water, and pond water. This compact platform is based on our previous work, and is composed of a smartphone-based fluorescence microscope, a disposable sample processing cassette, and a custom-developed smartphone application. Our mobile phone microscope has a large field of view of 0.8 cm2 and weighs only 180 g, excluding the phone. A custom-developed smartphone application provides a user-friendly graphical interface, guiding the users to capture a fluorescence image of the sample filter membrane and analyze it automatically at our servers using an image processing algorithm and training data, consisting of >30,000 images of cysts and >100,000 images of other fluorescent particles that are captured, including, e.g. dust. The total time that it takes from sample preparation to automated cyst counting is less than an hour for each 10 ml of water sample that is tested. We compared the sensitivity and the specificity of our platform using multiple supervised classification models, including support vector machines and nearest neighbors, and demonstrated that a bootstrap aggregating (i.e. bagging) approach using raw image file format provides the best performance for automated detection of Giardia cysts. We evaluated the performance of this machine learning enabled pathogen detection device with water samples taken from different sources (e.g. tap water, non-potable water, pond water) and achieved a
Ceylan Koydemir, Hatice
2017-06-14
Giardia lamblia is a waterborne parasite that affects millions of people every year worldwide, causing a diarrheal illness known as giardiasis. Timely detection of the presence of the cysts of this parasite in drinking water is important to prevent the spread of the disease, especially in resource-limited settings. Here we provide extended experimental testing and evaluation of the performance and repeatability of a field-portable and cost-effective microscopy platform for automated detection and counting of Giardia cysts in water samples, including tap water, non-potable water, and pond water. This compact platform is based on our previous work, and is composed of a smartphone-based fluorescence microscope, a disposable sample processing cassette, and a custom-developed smartphone application. Our mobile phone microscope has a large field of view of ~0.8 cm2 and weighs only ~180 g, excluding the phone. A custom-developed smartphone application provides a user-friendly graphical interface, guiding the users to capture a fluorescence image of the sample filter membrane and analyze it automatically at our servers using an image processing algorithm and training data, consisting of >30,000 images of cysts and >100,000 images of other fluorescent particles that are captured, including, e.g. dust. The total time that it takes from sample preparation to automated cyst counting is less than an hour for each 10 ml of water sample that is tested. We compared the sensitivity and the specificity of our platform using multiple supervised classification models, including support vector machines and nearest neighbors, and demonstrated that a bootstrap aggregating (i.e. bagging) approach using raw image file format provides the best performance for automated detection of Giardia cysts. We evaluated the performance of this machine learning enabled pathogen detection device with water samples taken from different sources (e.g. tap water, non-potable water, pond water) and achieved
Directory of Open Access Journals (Sweden)
Ceylan Koydemir Hatice
2017-06-01
Full Text Available Giardia lamblia is a waterborne parasite that affects millions of people every year worldwide, causing a diarrheal illness known as giardiasis. Timely detection of the presence of the cysts of this parasite in drinking water is important to prevent the spread of the disease, especially in resource-limited settings. Here we provide extended experimental testing and evaluation of the performance and repeatability of a field-portable and cost-effective microscopy platform for automated detection and counting of Giardia cysts in water samples, including tap water, non-potable water, and pond water. This compact platform is based on our previous work, and is composed of a smartphone-based fluorescence microscope, a disposable sample processing cassette, and a custom-developed smartphone application. Our mobile phone microscope has a large field of view of ~0.8 cm2 and weighs only ~180 g, excluding the phone. A custom-developed smartphone application provides a user-friendly graphical interface, guiding the users to capture a fluorescence image of the sample filter membrane and analyze it automatically at our servers using an image processing algorithm and training data, consisting of >30,000 images of cysts and >100,000 images of other fluorescent particles that are captured, including, e.g. dust. The total time that it takes from sample preparation to automated cyst counting is less than an hour for each 10 ml of water sample that is tested. We compared the sensitivity and the specificity of our platform using multiple supervised classification models, including support vector machines and nearest neighbors, and demonstrated that a bootstrap aggregating (i.e. bagging approach using raw image file format provides the best performance for automated detection of Giardia cysts. We evaluated the performance of this machine learning enabled pathogen detection device with water samples taken from different sources (e.g. tap water, non-potable water, pond
Ceylan Koydemir, Hatice; Feng, Steve; Liang, Kyle; Nadkarni, Rohan; Benien, Parul; Ozcan, Aydogan
2017-01-01
Giardia lamblia is a waterborne parasite that affects millions of people every year worldwide, causing a diarrheal illness known as giardiasis. Timely detection of the presence of the cysts of this parasite in drinking water is important to prevent the spread of the disease, especially in resource-limited settings. Here we provide extended experimental testing and evaluation of the performance and repeatability of a field-portable and cost-effective microscopy platform for automated detection and counting of Giardia cysts in water samples, including tap water, non-potable water, and pond water. This compact platform is based on our previous work, and is composed of a smartphone-based fluorescence microscope, a disposable sample processing cassette, and a custom-developed smartphone application. Our mobile phone microscope has a large field of view of ~0.8 cm2 and weighs only ~180 g, excluding the phone. A custom-developed smartphone application provides a user-friendly graphical interface, guiding the users to capture a fluorescence image of the sample filter membrane and analyze it automatically at our servers using an image processing algorithm and training data, consisting of >30,000 images of cysts and >100,000 images of other fluorescent particles that are captured, including, e.g. dust. The total time that it takes from sample preparation to automated cyst counting is less than an hour for each 10 ml of water sample that is tested. We compared the sensitivity and the specificity of our platform using multiple supervised classification models, including support vector machines and nearest neighbors, and demonstrated that a bootstrap aggregating (i.e. bagging) approach using raw image file format provides the best performance for automated detection of Giardia cysts. We evaluated the performance of this machine learning enabled pathogen detection device with water samples taken from different sources (e.g. tap water, non-potable water, pond water) and achieved
SOLAR FLARE PREDICTION USING SDO/HMI VECTOR MAGNETIC FIELD DATA WITH A MACHINE-LEARNING ALGORITHM
International Nuclear Information System (INIS)
Bobra, M. G.; Couvidat, S.
2015-01-01
We attempt to forecast M- and X-class solar flares using a machine-learning algorithm, called support vector machine (SVM), and four years of data from the Solar Dynamics Observatory's Helioseismic and Magnetic Imager, the first instrument to continuously map the full-disk photospheric vector magnetic field from space. Most flare forecasting efforts described in the literature use either line-of-sight magnetograms or a relatively small number of ground-based vector magnetograms. This is the first time a large data set of vector magnetograms has been used to forecast solar flares. We build a catalog of flaring and non-flaring active regions sampled from a database of 2071 active regions, comprised of 1.5 million active region patches of vector magnetic field data, and characterize each active region by 25 parameters. We then train and test the machine-learning algorithm and we estimate its performances using forecast verification metrics with an emphasis on the true skill statistic (TSS). We obtain relatively high TSS scores and overall predictive abilities. We surmise that this is partly due to fine-tuning the SVM for this purpose and also to an advantageous set of features that can only be calculated from vector magnetic field data. We also apply a feature selection algorithm to determine which of our 25 features are useful for discriminating between flaring and non-flaring active regions and conclude that only a handful are needed for good predictive abilities
Schneider, Laura P.; Schoonderwoerd, Antoinet J.; Moutaftsi, Magdalini; Howard, Randall F.; Reed, Steven G.; de Jong, Esther C.; Teunissen, Marcel B. M.
2012-01-01
The natural TLR4 agonist lipopolysaccharide (LPS) has notable adjuvant activity. However, it is not useful as a vaccine adjuvant due to its toxicity. Glucopyranosyl lipid A (GLA) is a synthetic derivative of the lipid A tail of LPS with limited cytotoxicity, but strong potential to induce immune
Zune, Q.; Delepierre, A.; Gofflot, S.; Bauwens, J.; Twizere, J.C.; Punt, P.J.; Francis, F.; Toye, D.; Bawin, T.; Delvigne, F.
2015-01-01
Fungal biofilm is known to promote the excretion of secondary metabolites in accordance with solid-staterelated physiological mechanisms. This work is based on the comparative analysis of classical submerged fermentation with a fungal biofilmreactor for the production of a Gla::green fluorescent
Squiers, John J.; Li, Weizhi; King, Darlene R.; Mo, Weirong; Zhang, Xu; Lu, Yang; Sellke, Eric W.; Fan, Wensheng; DiMaio, J. Michael; Thatcher, Jeffrey E.
2016-03-01
The clinical judgment of expert burn surgeons is currently the standard on which diagnostic and therapeutic decisionmaking regarding burn injuries is based. Multispectral imaging (MSI) has the potential to increase the accuracy of burn depth assessment and the intraoperative identification of viable wound bed during surgical debridement of burn injuries. A highly accurate classification model must be developed using machine-learning techniques in order to translate MSI data into clinically-relevant information. An animal burn model was developed to build an MSI training database and to study the burn tissue classification ability of several models trained via common machine-learning algorithms. The algorithms tested, from least to most complex, were: K-nearest neighbors (KNN), decision tree (DT), linear discriminant analysis (LDA), weighted linear discriminant analysis (W-LDA), quadratic discriminant analysis (QDA), ensemble linear discriminant analysis (EN-LDA), ensemble K-nearest neighbors (EN-KNN), and ensemble decision tree (EN-DT). After the ground-truth database of six tissue types (healthy skin, wound bed, blood, hyperemia, partial injury, full injury) was generated by histopathological analysis, we used 10-fold cross validation to compare the algorithms' performances based on their accuracies in classifying data against the ground truth, and each algorithm was tested 100 times. The mean test accuracy of the algorithms were KNN 68.3%, DT 61.5%, LDA 70.5%, W-LDA 68.1%, QDA 68.9%, EN-LDA 56.8%, EN-KNN 49.7%, and EN-DT 36.5%. LDA had the highest test accuracy, reflecting the bias-variance tradeoff over the range of complexities inherent to the algorithms tested. Several algorithms were able to match the current standard in burn tissue classification, the clinical judgment of expert burn surgeons. These results will guide further development of an MSI burn tissue classification system. Given that there are few surgeons and facilities specializing in burn care
Directory of Open Access Journals (Sweden)
Yang Li
Full Text Available In order to overcome the problems of poor understandability of the pattern recognition-based transient stability assessment (PRTSA methods, a new rule extraction method based on extreme learning machine (ELM and an improved Ant-miner (IAM algorithm is presented in this paper. First, the basic principles of ELM and Ant-miner algorithm are respectively introduced. Then, based on the selected optimal feature subset, an example sample set is generated by the trained ELM-based PRTSA model. And finally, a set of classification rules are obtained by IAM algorithm to replace the original ELM network. The novelty of this proposal is that transient stability rules are extracted from an example sample set generated by the trained ELM-based transient stability assessment model by using IAM algorithm. The effectiveness of the proposed method is shown by the application results on the New England 39-bus power system and a practical power system--the southern power system of Hebei province.
Tatjewski, Marcin; Kierczak, Marcin; Plewczynski, Dariusz
2017-01-01
Here, we present two perspectives on the task of predicting post translational modifications (PTMs) from local sequence fragments using machine learning algorithms. The first is the description of the fundamental steps required to construct a PTM predictor from the very beginning. These steps include data gathering, feature extraction, or machine-learning classifier selection. The second part of our work contains the detailed discussion of more advanced problems which are encountered in PTM prediction task. Probably the most challenging issues which we have covered here are: (1) how to address the training data class imbalance problem (we also present statistics describing the problem); (2) how to properly set up cross-validation folds with an approach which takes into account the homology of protein data records, to address this problem we present our folds-over-clusters algorithm; and (3) how to efficiently reach for new sources of learning features. Presented techniques and notes resulted from intense studies in the field, performed by our and other groups, and can be useful both for researchers beginning in the field of PTM prediction and for those who want to extend the repertoire of their research techniques.
Directory of Open Access Journals (Sweden)
HU Gensheng
2018-03-01
Full Text Available Ground object information of remote sensing images covered with thin clouds is obscure. An information recovery algorithm for ground objects in thin cloud images is proposed by fusing guide filter and transfer learning. Firstly, multi-resolution decomposition of thin cloud target images and cloud-free guidance images is performed by using multi-directional nonsubsampled dual-tree complex wavelet transform. Then the decomposed low frequency subbands are processed by using support vector guided filter and transfer learning respectively. The decomposed high frequency subbands are enhanced by using modified Laine enhancement function. The low frequency subbands output by guided filter and those predicted by transfer learning model are fused by the method of selection and weighting based on regional energy. Finally, the enhanced high frequency subbands and the fused low frequency subbands are reconstructed by using inverse multi-directional nonsubsampled dual-tree complex wavelet transform to obtain the ground object information recovery images. Experimental results of Landsat-8 OLI multispectral images show that, support vector guided filter can effectively preserve the detail information of the target images, domain adaptive transfer learning can effectively extend the range of available multi-source and multi-temporal remote sensing images, and good effects for ground object information recover are obtained by fusing guide filter and transfer learning to remove thin cloud on the remote sensing images.
Learning Mobility: Adaptive Control Algorithms for the Novel Unmanned Ground Vehicle (NUGV)
National Research Council Canada - National Science Library
Blackburn, Mike
2003-01-01
Mobility is a serious limiting factor in the usefulness of unmanned ground vehicles, This paper contains a description of our approach to develop control algorithms for the Novel Unmanned Ground Vehicle (NUGV...
A Fast Logdet Divergence Based Metric Learning Algorithm for Large Data Sets Classification
Directory of Open Access Journals (Sweden)
Jiangyuan Mei
2014-01-01
the basis of classifiers, for example, the k-nearest neighbors classifier. Experiments on benchmark data sets demonstrate that the proposed algorithm compares favorably with the state-of-the-art methods.
Li, Ming; Miao, Chunyan; Leung, Cyril
2015-12-04
Coverage control is one of the most fundamental issues in directional sensor networks. In this paper, the coverage optimization problem in a directional sensor network is formulated as a multi-objective optimization problem. It takes into account the coverage rate of the network, the number of working sensor nodes and the connectivity of the network. The coverage problem considered in this paper is characterized by the geographical irregularity of the sensed events and heterogeneity of the sensor nodes in terms of sensing radius, field of angle and communication radius. To solve this multi-objective problem, we introduce a learning automata-based coral reef algorithm for adaptive parameter selection and use a novel Tchebycheff decomposition method to decompose the multi-objective problem into a single-objective problem. Simulation results show the consistent superiority of the proposed algorithm over alternative approaches.
Directory of Open Access Journals (Sweden)
B. Thamaraikannan
2014-01-01
Full Text Available This paper studies in detail the background and implementation of a teaching-learning based optimization (TLBO algorithm with differential operator for optimization task of a few mechanical components, which are essential for most of the mechanical engineering applications. Like most of the other heuristic techniques, TLBO is also a population-based method and uses a population of solutions to proceed to the global solution. A differential operator is incorporated into the TLBO for effective search of better solutions. To validate the effectiveness of the proposed method, three typical optimization problems are considered in this research: firstly, to optimize the weight in a belt-pulley drive, secondly, to optimize the volume in a closed coil helical spring, and finally to optimize the weight in a hollow shaft. have been demonstrated. Simulation result on the optimization (mechanical components problems reveals the ability of the proposed methodology to find better optimal solutions compared to other optimization algorithms.
Chen, C P; Wan, J Z
1999-01-01
A fast learning algorithm is proposed to find an optimal weights of the flat neural networks (especially, the functional-link network). Although the flat networks are used for nonlinear function approximation, they can be formulated as linear systems. Thus, the weights of the networks can be solved easily using a linear least-square method. This formulation makes it easier to update the weights instantly for both a new added pattern and a new added enhancement node. A dynamic stepwise updating algorithm is proposed to update the weights of the system on-the-fly. The model is tested on several time-series data including an infrared laser data set, a chaotic time-series, a monthly flour price data set, and a nonlinear system identification problem. The simulation results are compared to existing models in which more complex architectures and more costly training are needed. The results indicate that the proposed model is very attractive to real-time processes.
Hosfelt, Diane Duros
2015-01-01
Threats from the internet, particularly malicious software (i.e., malware) often use cryptographic algorithms to disguise their actions and even to take control of a victim's system (as in the case of ransomware). Malware and other threats proliferate too quickly for the time-consuming traditional methods of binary analysis to be effective. By automating detection and classification of cryptographic algorithms, we can speed program analysis and more efficiently combat malware. This thesis wil...
A Machine Learning Regression scheme to design a FR-Image Quality Assessment Algorithm
Charrier , Christophe; Lezoray , Olivier; Lebrun , Gilles
2012-01-01
International audience; A crucial step in image compression is the evaluation of its performance, and more precisely available ways to measure the quality of compressed images. In this paper, a machine learning expert, providing a quality score is proposed. This quality measure is based on a learned classification process in order to respect that of human observers. The proposed method namely Machine Learning-based Image Quality Measurment (MLIQM) first classifies the quality using multi Supp...
Delahanty, Ryan J; Kaufman, David; Jones, Spencer S
2018-06-01
Risk adjustment algorithms for ICU mortality are necessary for measuring and improving ICU performance. Existing risk adjustment algorithms are not widely adopted. Key barriers to adoption include licensing and implementation costs as well as labor costs associated with human-intensive data collection. Widespread adoption of electronic health records makes automated risk adjustment feasible. Using modern machine learning methods and open source tools, we developed and evaluated a retrospective risk adjustment algorithm for in-hospital mortality among ICU patients. The Risk of Inpatient Death score can be fully automated and is reliant upon data elements that are generated in the course of usual hospital processes. One hundred thirty-one ICUs in 53 hospitals operated by Tenet Healthcare. A cohort of 237,173 ICU patients discharged between January 2014 and December 2016. The data were randomly split into training (36 hospitals), and validation (17 hospitals) data sets. Feature selection and model training were carried out using the training set while the discrimination, calibration, and accuracy of the model were assessed in the validation data set. Model discrimination was evaluated based on the area under receiver operating characteristic curve; accuracy and calibration were assessed via adjusted Brier scores and visual analysis of calibration curves. Seventeen features, including a mix of clinical and administrative data elements, were retained in the final model. The Risk of Inpatient Death score demonstrated excellent discrimination (area under receiver operating characteristic curve = 0.94) and calibration (adjusted Brier score = 52.8%) in the validation dataset; these results compare favorably to the published performance statistics for the most commonly used mortality risk adjustment algorithms. Low adoption of ICU mortality risk adjustment algorithms impedes progress toward increasing the value of the healthcare delivered in ICUs. The Risk of Inpatient Death
Directory of Open Access Journals (Sweden)
Paul Y Boxma
Full Text Available Vitamin K is essential for activation of γ-carboxyglutamate (Gla-proteins including the vascular calcification inhibitor matrix Gla-protein (MGP. Insufficient vitamin K intake leads to production of uncarboxylated, mostly inactive proteins and contributes to an increased cardiovascular risk. In kidney transplant recipients, cardiovascular risk is high but vitamin K intake and status have not been defined. We investigated dietary vitamin K intake, vascular vitamin K status and its determinants in kidney transplant recipients. We estimated vitamin K intake in a cohort of kidney transplant recipients (n = 60 with stable renal function (creatinine clearance 61 [42-77] (median [interquartile range] ml/min, who were 75 [35-188] months after transplantation, using three-day food records and food frequency questionnaires. Vascular vitamin K status was assessed by measuring plasma desphospho-uncarboxylated MGP (dp-ucMGP. Total vitamin K intake was below the recommended level in 50% of patients. Lower vitamin K intake was associated with less consumption of green vegetables (33 vs 40 g/d, p = 0.06 and increased dp-ucMGP levels (621 vs 852 pmol/L, p500 pmol/L in 80% of patients. Multivariate regression identified creatinine clearance, coumarin use, body mass index, high sensitivity-CRP and sodium excretion as independent determinants of dp-ucMGP levels. In a considerable part of the kidney transplant population, vitamin K intake is too low for maximal carboxylation of vascular MGP. The high dp-ucMGP levels may result in an increased risk for arterial calcification. Whether increasing vitamin K intake may have health benefits for kidney transplant recipients should be addressed by future studies.
Boxma, Paul Y; van den Berg, Else; Geleijnse, Johanna M; Laverman, Gozewijn D; Schurgers, Leon J; Vermeer, Cees; Kema, Ido P; Muskiet, Frits A; Navis, Gerjan; Bakker, Stephan J L; de Borst, Martin H
2012-01-01
Vitamin K is essential for activation of γ-carboxyglutamate (Gla)-proteins including the vascular calcification inhibitor matrix Gla-protein (MGP). Insufficient vitamin K intake leads to production of uncarboxylated, mostly inactive proteins and contributes to an increased cardiovascular risk. In kidney transplant recipients, cardiovascular risk is high but vitamin K intake and status have not been defined. We investigated dietary vitamin K intake, vascular vitamin K status and its determinants in kidney transplant recipients. We estimated vitamin K intake in a cohort of kidney transplant recipients (n = 60) with stable renal function (creatinine clearance 61 [42-77] (median [interquartile range]) ml/min), who were 75 [35-188] months after transplantation, using three-day food records and food frequency questionnaires. Vascular vitamin K status was assessed by measuring plasma desphospho-uncarboxylated MGP (dp-ucMGP). Total vitamin K intake was below the recommended level in 50% of patients. Lower vitamin K intake was associated with less consumption of green vegetables (33 vs 40 g/d, p = 0.06) and increased dp-ucMGP levels (621 vs 852 pmol/L, p500 pmol/L) in 80% of patients. Multivariate regression identified creatinine clearance, coumarin use, body mass index, high sensitivity-CRP and sodium excretion as independent determinants of dp-ucMGP levels. In a considerable part of the kidney transplant population, vitamin K intake is too low for maximal carboxylation of vascular MGP. The high dp-ucMGP levels may result in an increased risk for arterial calcification. Whether increasing vitamin K intake may have health benefits for kidney transplant recipients should be addressed by future studies.
Guo, Zhan; Yan, Xuefeng
2018-04-01
Different operating conditions of p-xylene oxidation have different influences on the product, purified terephthalic acid. It is necessary to obtain the optimal combination of reaction conditions to ensure the quality of the products, cut down on consumption and increase revenues. A multi-objective differential evolution (MODE) algorithm co-evolved with the population-based incremental learning (PBIL) algorithm, called PBMODE, is proposed. The PBMODE algorithm was designed as a co-evolutionary system. Each individual has its own parameter individual, which is co-evolved by PBIL. PBIL uses statistical analysis to build a model based on the corresponding symbiotic individuals of the superior original individuals during the main evolutionary process. The results of simulations and statistical analysis indicate that the overall performance of the PBMODE algorithm is better than that of the compared algorithms and it can be used to optimize the operating conditions of the p-xylene oxidation process effectively and efficiently.
Directory of Open Access Journals (Sweden)
Rabindra Kumar Sahu
2016-03-01
Full Text Available This paper presents the design and analysis of Proportional-Integral-Double Derivative (PIDD controller for Automatic Generation Control (AGC of multi-area power systems with diverse energy sources using Teaching Learning Based Optimization (TLBO algorithm. At first, a two-area reheat thermal power system with appropriate Generation Rate Constraint (GRC is considered. The design problem is formulated as an optimization problem and TLBO is employed to optimize the parameters of the PIDD controller. The superiority of the proposed TLBO based PIDD controller has been demonstrated by comparing the results with recently published optimization technique such as hybrid Firefly Algorithm and Pattern Search (hFA-PS, Firefly Algorithm (FA, Bacteria Foraging Optimization Algorithm (BFOA, Genetic Algorithm (GA and conventional Ziegler Nichols (ZN for the same interconnected power system. Also, the proposed approach has been extended to two-area power system with diverse sources of generation like thermal, hydro, wind and diesel units. The system model includes boiler dynamics, GRC and Governor Dead Band (GDB non-linearity. It is observed from simulation results that the performance of the proposed approach provides better dynamic responses by comparing the results with recently published in the literature. Further, the study is extended to a three unequal-area thermal power system with different controllers in each area and the results are compared with published FA optimized PID controller for the same system under study. Finally, sensitivity analysis is performed by varying the system parameters and operating load conditions in the range of ±25% from their nominal values to test the robustness.
van Hasselt, H.P.
2011-01-01
A key aspect of artificial intelligence is the ability to learn from experience. If examples of correct solutions exist, supervised learning techniques can be used to predict what the correct solution will be for future observations. However, often such examples are not readily available. The field
HyDR-MI : A hybrid algorithm to reduce dimensionality in multiple instance learning
Zafra, A.; Pechenizkiy, M.; Ventura, S.
2013-01-01
Feature selection techniques have been successfully applied in many applications for making supervised learning more effective and efficient. These techniques have been widely used and studied in traditional supervised learning settings, where each instance is expected to have a label. In multiple
Directory of Open Access Journals (Sweden)
Abdelali Slimani
2018-01-01
Full Text Available learning analytics is an emerging discipline focused on the measurement, collection, analysis and reporting of learner interaction data through the E-learning contents. Serious game provides a potential source for relevant educational user data; it can propose an interactive environment for training and offer an effective learning process. This paper presents methods and approaches of educational data mining such as EM and K-Means to discuss the learning analytics through serious games, and then we provide an analysis of the player experience data collected from the educational game “ELISA” used to teach students of biology the immunological technique for determination of ANTI-HIV antibodies. Finally, we propose critically evaluation of our results including the limitations of our study and making suggestions for future research that links learning analytics and serious gaming.
An affective computing algorithm based on temperament type in E－Learning
Directory of Open Access Journals (Sweden)
WANG Biyun
2013-02-01
Full Text Available This paper extracts five emotional features according to the emotions that may affect in learning,and introduces psychological theory to generate emotional susceptibility matrix and to draw personalized emotion vector by different learners' temperament type vectors,which all reflect the emotional state of the learners more realistically.This paper also recommends learners of different emotions and emotional intensity to learn the knowledge of different levels of difficulty,making learning more humane.Temperament type is a temperament doctrine evolved based on the Hippocratic humoral theory and can be a good expression of human personality foundation.Temperament type has been introduced into affective computing in the E－Learning in this paper so that computer can be better on the classification of the learner's personality and learning state and realistically be individualized.
Directory of Open Access Journals (Sweden)
K. Shahverdi
2016-02-01
Full Text Available Introduction: Nowadays considering water shortage and weak management in agricultural water sector and for optimal uses of water, irrigation networks performance need to be improveed. Recently, intelligent management of water conveyance and delivery, and better control technologies have been considered for improving the performance of irrigation networks and their operation. For this affair, providing of mathematical model of automatic control system and related structures, which connected with hydrodynamic models, is necessary. The main objective of this research, is development of mathematical model of RL upstream control algorithm inside ICSS hydrodynamic model as a subroutine. Materials and Methods: In the learning systems, a set of state-action rules called classifiers compete to control the system based on the system's receipt from the environment. One could be identified five main elements of the RL: an agent, an environment, a policy, a reward function, and a simulator. The learner (decision-maker is called the agent. The thing it interacts with, comprising everything outside the agent, is called the environment. The agent selects an action based on existing state in the environment. When the agent takes an action and performs on environment, the environment goes new state and reward is assigned based on it. The agent and the environment continually interact to maximize the reward. The policy is a set of state-action pair, which have higher rewards. It defines the agent's behavior and says which action must be taken in which state. The reward function defines the goal in a RL problem. The reward function defines what the good and bad events are for the agent. The higher the reward, the better the action. The simulator provides environment information. In irrigation canals, the agent is the check structures. The action and state are the check structures adjustment and the water depth, respectively. The environment comprises the hydraulic
Osler, James Edward
2016-01-01
This paper provides a novel instructional methodology that is a unique E-Learning engineered "4A Metric Algorithm" designed to conceptually address the four main challenges faced by 21st century students, who are tempted to cheat in a myriad of higher education settings (face to face, hybrid, and online). The algorithmic online…
In vitro molecular machine learning algorithm via symmetric internal loops of DNA.
Lee, Ji-Hoon; Lee, Seung Hwan; Baek, Christina; Chun, Hyosun; Ryu, Je-Hwan; Kim, Jin-Woo; Deaton, Russell; Zhang, Byoung-Tak
2017-08-01
Programmable biomolecules, such as DNA strands, deoxyribozymes, and restriction enzymes, have been used to solve computational problems, construct large-scale logic circuits, and program simple molecular games. Although studies have shown the potential of molecular computing, the capability of computational learning with DNA molecules, i.e., molecular machine learning, has yet to be experimentally verified. Here, we present a novel molecular learning in vitro model in which symmetric internal loops of double-stranded DNA are exploited to measure the differences between training instances, thus enabling the molecules to learn from small errors. The model was evaluated on a data set of twenty dialogue sentences obtained from the television shows Friends and Prison Break. The wet DNA-computing experiments confirmed that the molecular learning machine was able to generalize the dialogue patterns of each show and successfully identify the show from which the sentences originated. The molecular machine learning model described here opens the way for solving machine learning problems in computer science and biology using in vitro molecular computing with the data encoded in DNA molecules. Copyright © 2017. Published by Elsevier B.V.
Directory of Open Access Journals (Sweden)
R. Ghiasi
2017-09-01
Full Text Available Utilizing surrogate models based on artificial intelligence methods for detecting structural damages has attracted the attention of many researchers in recent decades. In this study, a new kernel based on Littlewood-Paley Wavelet (LPW is proposed for Extreme Learning Machine (ELM algorithm to improve the accuracy of detecting multiple damages in structural systems. ELM is used as metamodel (surrogate model of exact finite element analysis of structures in order to efficiently reduce the computational cost through updating process. In the proposed two-step method, first a damage index, based on Frequency Response Function (FRF of the structure, is used to identify the location of damages. In the second step, the severity of damages in identified elements is detected using ELM. In order to evaluate the efficacy of ELM, the results obtained from the proposed kernel were compared with other kernels proposed for ELM as well as Least Square Support Vector Machine algorithm. The solved numerical problems indicated that ELM algorithm accuracy in detecting structural damages is increased drastically in case of using LPW kernel.
DEFF Research Database (Denmark)
Endelt, Benny Ørtoft; Volk, Wolfram
2013-01-01
, there is a number of obstacles which need to be addressed before an industrial implementation is possible, e.g. the proposed control algorithms are often limited by the ability to sample process data with both sufficient accuracy and robustness - this lack of robust sampling technologies is one of the main barriers...
An E-Learning Environment for Algorithmic: Toward an Active Construction of Skills
Babori, Abdelghani; Fassi, Hicham Fihri; Hariri, Abdellah; Bideq, Mustapha
2016-01-01
Assimilating an algorithmic course is a persistent problem for many undergraduate students. The major problem faced by students is the lack of problem solving ability and flexibility. Therefore, students are generally passive, unmotivated and unable to mobilize all the acquired knowledge (loops, test, variables, etc.) to deal with new encountered…
Artificial Neural Network Approach in Laboratory Test Reporting: Learning Algorithms.
Demirci, Ferhat; Akan, Pinar; Kume, Tuncay; Sisman, Ali Riza; Erbayraktar, Zubeyde; Sevinc, Suleyman
2016-08-01
In the field of laboratory medicine, minimizing errors and establishing standardization is only possible by predefined processes. The aim of this study was to build an experimental decision algorithm model open to improvement that would efficiently and rapidly evaluate the results of biochemical tests with critical values by evaluating multiple factors concurrently. The experimental model was built by Weka software (Weka, Waikato, New Zealand) based on the artificial neural network method. Data were received from Dokuz Eylül University Central Laboratory. "Training sets" were developed for our experimental model to teach the evaluation criteria. After training the system, "test sets" developed for different conditions were used to statistically assess the validity of the model. After developing the decision algorithm with three iterations of training, no result was verified that was refused by the laboratory specialist. The sensitivity of the model was 91% and specificity was 100%. The estimated κ score was 0.950. This is the first study based on an artificial neural network to build an experimental assessment and decision algorithm model. By integrating our trained algorithm model into a laboratory information system, it may be possible to reduce employees' workload without compromising patient safety. © American Society for Clinical Pathology, 2016. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
Study Navigator: An Algorithmically Generated Aid for Learning from Electronic Textbooks
Agrawal, Rakesh; Gollapudi, Sreenivas; Kannan, Anitha; Kenthapadi, Krishnaram
2014-01-01
We present "study navigator," an algorithmically-generated aid for enhancing the experience of studying from electronic textbooks. The study navigator for a section of the book consists of helpful "concept references" for understanding this section. Each concept reference is a pair consisting of a concept phrase explained…
P.A.N. Bosman (Peter); J.A. La Poutré (Han); D. Thierens (Dirk)
2007-01-01
htmlabstractThe focus of this paper is on how to design evolutionary algorithms (EAs) for solving stochastic dynamic optimization problems online, i.e. as time goes by. For a proper design, the EA must not only be capable of tracking shifting optima, it must also take into account the future
International Nuclear Information System (INIS)
Taraglio, S.; Massaioli, F.
1995-08-01
A parallel implementation of a library to build and train Multi Layer Perceptrons via the Back Propagation algorithm is presented. The target machine is the SIMD massively parallel supercomputer Quadrics. Performance measures are provided on three different machines with different number of processors, for two network examples. A sample source code is given
National Research Council Canada - National Science Library
Qi, Yuan
2000-01-01
In this thesis, we propose two new machine learning schemes, a subband-based Independent Component Analysis scheme and a hybrid Independent Component Analysis/Support Vector Machine scheme, and apply...
Directory of Open Access Journals (Sweden)
Uttam Kumar
2017-10-01
Full Text Available Land cover (LC refers to the physical and biological cover present over the Earth’s surface in terms of the natural environment such as vegetation, water, bare soil, etc. Most LC features occur at finer spatial scales compared to the resolution of primary remote sensing satellites. Therefore, observed data are a mixture of spectral signatures of two or more LC features resulting in mixed pixels. One solution to the mixed pixel problem is the use of subpixel learning algorithms to disintegrate the pixel spectrum into its constituent spectra. Despite the popularity and existing research conducted on the topic, the most appropriate approach is still under debate. As an attempt to address this question, we compared the performance of several subpixel learning algorithms based on least squares, sparse regression, signal–subspace and geometrical methods. Analysis of the results obtained through computer-simulated and Landsat data indicated that fully constrained least squares (FCLS outperformed the other techniques. Further, FCLS was used to unmix global Web-Enabled Landsat Data to obtain abundances of substrate (S, vegetation (V and dark object (D classes. Due to the sheer nature of data and computational needs, we leveraged the NASA Earth Exchange (NEX high-performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into four classes, namely forest, farmland, water and urban areas (in conjunction with nighttime lights data over California, USA using a random forest classifier. Validation of these LC maps with the National Land Cover Database 2011 products and North American Forest Dynamics static forest map shows a 6% improvement in unmixing-based classification relative to per-pixel classification. As such, abundance maps continue to offer a useful alternative to high-spatial-resolution classified maps for forest inventory analysis, multi
Gatos, Ilias; Tsantis, Stavros; Spiliopoulos, Stavros; Karnabatidis, Dimitris; Theotokas, Ioannis; Zoumpoulis, Pavlos; Loupas, Thanasis; Hazle, John D; Kagadis, George C
2017-09-01
The purpose of the present study was to employ a computer-aided diagnosis system that classifies chronic liver disease (CLD) using ultrasound shear wave elastography (SWE) imaging, with a stiffness value-clustering and machine-learning algorithm. A clinical data set of 126 patients (56 healthy controls, 70 with CLD) was analyzed. First, an RGB-to-stiffness inverse mapping technique was employed. A five-cluster segmentation was then performed associating corresponding different-color regions with certain stiffness value ranges acquired from the SWE manufacturer-provided color bar. Subsequently, 35 features (7 for each cluster), indicative of physical characteristics existing within the SWE image, were extracted. A stepwise regression analysis toward feature reduction was used to derive a reduced feature subset that was fed into the support vector machine classification algorithm to classify CLD from healthy cases. The highest accuracy in classification of healthy to CLD subject discrimination from the support vector machine model was 87.3% with sensitivity and specificity values of 93.5% and 81.2%, respectively. Receiver operating characteristic curve analysis gave an area under the curve value of 0.87 (confidence interval: 0.77-0.92). A machine-learning algorithm that quantifies color information in terms of stiffness values from SWE images and discriminates CLD from healthy cases is introduced. New objective parameters and criteria for CLD diagnosis employing SWE images provided by the present study can be considered an important step toward color-based interpretation, and could assist radiologists' diagnostic performance on a daily basis after being installed in a PC and employed retrospectively, immediately after the examination. Copyright © 2017 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.
Ruske, Simon; Topping, David O.; Foot, Virginia E.; Kaye, Paul H.; Stanley, Warren R.; Crawford, Ian; Morse, Andrew P.; Gallagher, Martin W.
2017-03-01
Characterisation of bioaerosols has important implications within environment and public health sectors. Recent developments in ultraviolet light-induced fluorescence (UV-LIF) detectors such as the Wideband Integrated Bioaerosol Spectrometer (WIBS) and the newly introduced Multiparameter Bioaerosol Spectrometer (MBS) have allowed for the real-time collection of fluorescence, size and morphology measurements for the purpose of discriminating between bacteria, fungal spores and pollen.This new generation of instruments has enabled ever larger data sets to be compiled with the aim of studying more complex environments. In real world data sets, particularly those from an urban environment, the population may be dominated by non-biological fluorescent interferents, bringing into question the accuracy of measurements of quantities such as concentrations. It is therefore imperative that we validate the performance of different algorithms which can be used for the task of classification.For unsupervised learning we tested hierarchical agglomerative clustering with various different linkages. For supervised learning, 11 methods were tested, including decision trees, ensemble methods (random forests, gradient boosting and AdaBoost), two implementations for support vector machines (libsvm and liblinear) and Gaussian methods (Gaussian naïve Bayesian, quadratic and linear discriminant analysis, the k-nearest neighbours algorithm and artificial neural networks).The methods were applied to two different data sets produced using the new MBS, which provides multichannel UV-LIF fluorescence signatures for single airborne biological particles. The first data set contained mixed PSLs and the second contained a variety of laboratory-generated aerosol.Clustering in general performs slightly worse than the supervised learning methods, correctly classifying, at best, only 67. 6 and 91. 1 % for the two data sets respectively. For supervised learning the gradient boosting algorithm was
International Nuclear Information System (INIS)
Nicolae, A; Lu, L; Morton, G; Chung, H; Helou, J; Al Hanaqta, M; Loblaw, A; Ravi, A; Heath, E
2016-01-01
Purpose: A novel, automated, algorithm for permanent prostate brachytherapy (PPB) treatment planning has been developed. The novel approach uses machine-learning (ML), a form of artificial intelligence, to substantially decrease planning time while simultaneously retaining the clinical intuition of plans created by radiation oncologists. This study seeks to compare the ML algorithm against expert-planned PPB plans to evaluate the equivalency of dosimetric and clinical plan quality. Methods: Plan features were computed from historical high-quality PPB treatments (N = 100) and stored in a relational database (RDB). The ML algorithm matched new PPB features to a highly similar case in the RDB; this initial plan configuration was then further optimized using a stochastic search algorithm. PPB pre-plans (N = 30) generated using the ML algorithm were compared to plan variants created by an expert dosimetrist (RT), and radiation oncologist (MD). Planning time and pre-plan dosimetry were evaluated using a one-way Student’s t-test and ANOVA, respectively (significance level = 0.05). Clinical implant quality was evaluated by expert PPB radiation oncologists as part of a qualitative study. Results: Average planning time was 0.44 ± 0.42 min compared to 17.88 ± 8.76 min for the ML algorithm and RT, respectively, a significant advantage [t(9), p = 0.01]. A post-hoc ANOVA [F(2,87) = 6.59, p = 0.002] using Tukey-Kramer criteria showed a significantly lower mean prostate V150% for the ML plans (52.9%) compared to the RT (57.3%), and MD (56.2%) plans. Preliminary qualitative study results indicate comparable clinical implant quality between RT and ML plans with a trend towards preference for ML plans. Conclusion: PPB pre-treatment plans highly comparable to those of an expert radiation oncologist can be created using a novel ML planning model. The use of an ML-based planning approach is expected to translate into improved PPB accessibility and plan uniformity.
Energy Technology Data Exchange (ETDEWEB)
Nicolae, A [Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, ON (Canada); Department of Physics, Ryerson University, Toronto, ON (Canada); Lu, L; Morton, G; Chung, H; Helou, J; Al Hanaqta, M; Loblaw, A; Ravi, A [Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, ON (Canada); Heath, E [Carleton Laboratory for Radiotherapy Physics, Carleton University, Ottawa, ON, CA (Canada)
2016-06-15
Purpose: A novel, automated, algorithm for permanent prostate brachytherapy (PPB) treatment planning has been developed. The novel approach uses machine-learning (ML), a form of artificial intelligence, to substantially decrease planning time while simultaneously retaining the clinical intuition of plans created by radiation oncologists. This study seeks to compare the ML algorithm against expert-planned PPB plans to evaluate the equivalency of dosimetric and clinical plan quality. Methods: Plan features were computed from historical high-quality PPB treatments (N = 100) and stored in a relational database (RDB). The ML algorithm matched new PPB features to a highly similar case in the RDB; this initial plan configuration was then further optimized using a stochastic search algorithm. PPB pre-plans (N = 30) generated using the ML algorithm were compared to plan variants created by an expert dosimetrist (RT), and radiation oncologist (MD). Planning time and pre-plan dosimetry were evaluated using a one-way Student’s t-test and ANOVA, respectively (significance level = 0.05). Clinical implant quality was evaluated by expert PPB radiation oncologists as part of a qualitative study. Results: Average planning time was 0.44 ± 0.42 min compared to 17.88 ± 8.76 min for the ML algorithm and RT, respectively, a significant advantage [t(9), p = 0.01]. A post-hoc ANOVA [F(2,87) = 6.59, p = 0.002] using Tukey-Kramer criteria showed a significantly lower mean prostate V150% for the ML plans (52.9%) compared to the RT (57.3%), and MD (56.2%) plans. Preliminary qualitative study results indicate comparable clinical implant quality between RT and ML plans with a trend towards preference for ML plans. Conclusion: PPB pre-treatment plans highly comparable to those of an expert radiation oncologist can be created using a novel ML planning model. The use of an ML-based planning approach is expected to translate into improved PPB accessibility and plan uniformity.
Fergus, Paul; Hussain, Abir; Al-Jumeily, Dhiya; Huang, De-Shuang; Bouguila, Nizar
2017-07-06
Visual inspection of cardiotocography traces by obstetricians and midwives is the gold standard for monitoring the wellbeing of the foetus during antenatal care. However, inter- and intra-observer variability is high with only a 30% positive predictive value for the classification of pathological outcomes. This has a significant negative impact on the perinatal foetus and often results in cardio-pulmonary arrest, brain and vital organ damage, cerebral palsy, hearing, visual and cognitive defects and in severe cases, death. This paper shows that using machine learning and foetal heart rate signals provides direct information about the foetal state and helps to filter the subjective opinions of medical practitioners when used as a decision support tool. The primary aim is to provide a proof-of-concept that demonstrates how machine learning can be used to objectively determine when medical intervention, such as caesarean section, is required and help avoid preventable perinatal deaths. This is evidenced using an open dataset that comprises 506 controls (normal virginal deliveries) and 46 cases (caesarean due to pH ≤ 7.20-acidosis, n = 18; pH > 7.20 and pH machine-learning algorithms are trained, and validated, using binary classifier performance measures. The findings show that deep learning classification achieves sensitivity = 94%, specificity = 91%, Area under the curve = 99%, F-score = 100%, and mean square error = 1%. The results demonstrate that machine learning significantly improves the efficiency for the detection of caesarean section and normal vaginal deliveries using foetal heart rate signals compared with obstetrician and midwife predictions and systems reported in previous studies.
Rose, R.; Aizenman, H.; Mei, E.; Choudhury, N.
2013-12-01
High School students interested in the STEM fields benefit most when actively participating, so I created a series of learning modules on how to analyze complex systems using machine-learning that give automated feedback to students. The automated feedbacks give timely responses that will encourage the students to continue testing and enhancing their programs. I have designed my modules to take the tactical learning approach in conveying the concepts behind correlation, linear regression, and vector distance based classification and clustering. On successful completion of these modules, students will learn how to calculate linear regression, Pearson's correlation, and apply classification and clustering techniques to a dataset. Working on these modules will allow the students to take back to the classroom what they've learned and then apply it to the Earth Science curriculum. During my research this summer, we applied these lessons to analyzing river deltas; we looked at trends in the different variables over time, looked for similarities in NDVI, precipitation, inundation, runoff and discharge, and attempted to predict floods based on the precipitation, waves mean, area of discharge, NDVI, and inundation.
A novel structure-aware sparse learning algorithm for brain imaging genetics.
Du, Lei; Jingwen, Yan; Kim, Sungeun; Risacher, Shannon L; Huang, Heng; Inlow, Mark; Moore, Jason H; Saykin, Andrew J; Shen, Li
2014-01-01
Brain imaging genetics is an emergent research field where the association between genetic variations such as single nucleotide polymorphisms (SNPs) and neuroimaging quantitative traits (QTs) is evaluated. Sparse canonical correlation analysis (SCCA) is a bi-multivariate analysis method that has the potential to reveal complex multi-SNP-multi-QT associations. Most existing SCCA algorithms are designed using the soft threshold strategy, which assumes that the features in the data are independent from each other. This independence assumption usually does not hold in imaging genetic data, and thus inevitably limits the capability of yielding optimal solutions. We propose a novel structure-aware SCCA (denoted as S2CCA) algorithm to not only eliminate the independence assumption for the input data, but also incorporate group-like structure in the model. Empirical comparison with a widely used SCCA implementation, on both simulated and real imaging genetic data, demonstrated that S2CCA could yield improved prediction performance and biologically meaningful findings.
Multi–GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL
Directory of Open Access Journals (Sweden)
Jan Masek
2016-06-01
Full Text Available Using modern Graphic Processing Units (GPUs becomes very useful for computing complex and time consuming processes. GPUs provide high–performance computation capabilities with a good price. This paper deals with a multi–GPU OpenCL and CUDA implementations of k–Nearest Neighbor (k–NN algorithm. This work compares performances of OpenCLand CUDA implementations where each of them is suitable for different number of used attributes. The proposed CUDA algorithm achieves acceleration up to 880x in comparison witha single thread CPU version. The common k-NN was modified to be faster when the lower number of k neighbors is set. The performance of algorithm was verified with two GPUs dual-core NVIDIA GeForce GTX 690 and CPU Intel Core i7 3770 with 4.1 GHz frequency. The results of speed up were measured for one GPU, two GPUs, three and four GPUs. We performed several tests with data sets containing up to 4 million elements with various number of attributes.
Serag, Ahmed; Blesa, Manuel; Moore, Emma J; Pataky, Rozalia; Sparrow, Sarah A; Wilkinson, A G; Macnaught, Gillian; Semple, Scott I; Boardman, James P
2016-03-24
Accurate whole-brain segmentation, or brain extraction, of magnetic resonance imaging (MRI) is a critical first step in most neuroimage analysis pipelines. The majority of brain extraction algorithms have been developed and evaluated for adult data and their validity for neonatal brain extraction, which presents age-specific challenges for this task, has not been established. We developed a novel method for brain extraction of multi-modal neonatal brain MR images, named ALFA (Accurate Learning with Few Atlases). The method uses a new sparsity-based atlas selection strategy that requires a very limited number of atlases 'uniformly' distributed in the low-dimensional data space, combined with a machine learning based label fusion technique. The performance of the method for brain extraction from multi-modal data of 50 newborns is evaluated and compared with results obtained using eleven publicly available brain extraction methods. ALFA outperformed the eleven compared methods providing robust and accurate brain extraction results across different modalities. As ALFA can learn from partially labelled datasets, it can be used to segment large-scale datasets efficiently. ALFA could also be applied to other imaging modalities and other stages across the life course.
Predicting incomplete gene microarray data with the use of supervised learning algorithms
CSIR Research Space (South Africa)
Twala, B
2010-10-01
Full Text Available that prediction using supervised learning can be improved in probabilistic terms given incomplete microarray data. This imputation approach is based on the a priori probability of each value determined from the instances at that node of a decision tree (PDT...
Yue, Lei; Guan, Zailin; Saif, Ullah; Zhang, Fei; Wang, Hao
2016-01-01
Group scheduling is significant for efficient and cost effective production system. However, there exist setup times between the groups, which require to decrease it by sequencing groups in an efficient way. Current research is focused on a sequence dependent group scheduling problem with an aim to minimize the makespan in addition to minimize the total weighted tardiness simultaneously. In most of the production scheduling problems, the processing time of jobs is assumed as fixed. However, the actual processing time of jobs may be reduced due to "learning effect". The integration of sequence dependent group scheduling problem with learning effects has been rarely considered in literature. Therefore, current research considers a single machine group scheduling problem with sequence dependent setup times and learning effects simultaneously. A novel hybrid Pareto artificial bee colony algorithm (HPABC) with some steps of genetic algorithm is proposed for current problem to get Pareto solutions. Furthermore, five different sizes of test problems (small, small medium, medium, large medium, large) are tested using proposed HPABC. Taguchi method is used to tune the effective parameters of the proposed HPABC for each problem category. The performance of HPABC is compared with three famous multi objective optimization algorithms, improved strength Pareto evolutionary algorithm (SPEA2), non-dominated sorting genetic algorithm II (NSGAII) and particle swarm optimization algorithm (PSO). Results indicate that HPABC outperforms SPEA2, NSGAII and PSO and gives better Pareto optimal solutions in terms of diversity and quality for almost all the instances of the different sizes of problems.
Squillaro, Tiziana; Antonucci, Ivana; Alessio, Nicola; Esposito, Anna; Cipollaro, Marilena; Melone, Mariarosa Anna Beatrice; Peluso, Gianfranco; Stuppia, Liborio; Galderisi, Umberto
2017-12-01
Lysosomal storage disorders (LDS) comprise a group of rare multisystemic diseases resulting from inherited gene mutations that impair lysosomal homeostasis. The most common LSDs, Gaucher disease (GD), and Fabry disease (FD) are caused by deficiencies in the lysosomal glucocerebrosidase (GBA) and alpha-galactosidase A (GLA) enzymes, respectively. Given the systemic nature of enzyme deficiency, we hypothesized that the stem cell compartment of GD and FD patients might be also affected. Among stem cells, mesenchymal stem cells (MSCs) are a commonly investigated population given their role in hematopoiesis and the homeostatic maintenance of many organs and tissues. Since the impairment of MSC functions could pose profound consequences on body physiology, we evaluated whether GBA and GLA silencing could affect the biology of MSCs isolated from bone marrow and amniotic fluid. Those cell populations were chosen given the former's key role in organ physiology and the latter's intriguing potential as an alternative stem cell model for human genetic disease. Our results revealed that GBA and GLA deficiencies prompted cell cycle arrest along with the impairment of autophagic flux and an increase of apoptotic and senescent cell percentages. Moreover, an increase in ataxia-telangiectasia-mutated staining 1 hr after oxidative stress induction and a return to basal level at 48 hr, along with persistent gamma-H2AX staining, indicated that MSCs properly activated DNA repair signaling, though some damages remained unrepaired. Our data therefore suggest that MSCs with reduced GBA or GLA activity are prone to apoptosis and senescence due to impaired autophagy and DNA repair capacity. © 2017 Wiley Periodicals, Inc.
Energy Technology Data Exchange (ETDEWEB)
Nicolae, Alexandru [Department of Physics, Ryerson University, Toronto, Ontario (Canada); Department of Medical Physics, Odette Cancer Center, Sunnybrook Health Sciences Centre, Toronto, Ontario (Canada); Morton, Gerard; Chung, Hans; Loblaw, Andrew [Department of Radiation Oncology, Odette Cancer Center, Sunnybrook Health Sciences Centre, Toronto, Ontario (Canada); Jain, Suneil; Mitchell, Darren [Department of Clinical Oncology, The Northern Ireland Cancer Centre, Belfast City Hospital, Antrim, Northern Ireland (United Kingdom); Lu, Lin [Department of Radiation Therapy, Odette Cancer Center, Sunnybrook Health Sciences Centre, Toronto, Ontario (Canada); Helou, Joelle; Al-Hanaqta, Motasem [Department of Radiation Oncology, Odette Cancer Center, Sunnybrook Health Sciences Centre, Toronto, Ontario (Canada); Heath, Emily [Department of Physics, Carleton University, Ottawa, Ontario (Canada); Ravi, Ananth, E-mail: ananth.ravi@sunnybrook.ca [Department of Medical Physics, Odette Cancer Center, Sunnybrook Health Sciences Centre, Toronto, Ontario (Canada)
2017-03-15
Purpose: This work presents the application of a machine learning (ML) algorithm to automatically generate high-quality, prostate low-dose-rate (LDR) brachytherapy treatment plans. The ML algorithm can mimic characteristics of preoperative treatment plans deemed clinically acceptable by brachytherapists. The planning efficiency, dosimetry, and quality (as assessed by experts) of preoperative plans generated with an ML planning approach was retrospectively evaluated in this study. Methods and Materials: Preimplantation and postimplantation treatment plans were extracted from 100 high-quality LDR treatments and stored within a training database. The ML training algorithm matches similar features from a new LDR case to those within the training database to rapidly obtain an initial seed distribution; plans were then further fine-tuned using stochastic optimization. Preimplantation treatment plans generated by the ML algorithm were compared with brachytherapist (BT) treatment plans in terms of planning time (Wilcoxon rank sum, α = 0.05) and dosimetry (1-way analysis of variance, α = 0.05). Qualitative preimplantation plan quality was evaluated by expert LDR radiation oncologists using a Likert scale questionnaire. Results: The average planning time for the ML approach was 0.84 ± 0.57 minutes, compared with 17.88 ± 8.76 minutes for the expert planner (P=.020). Preimplantation plans were dosimetrically equivalent to the BT plans; the average prostate V150% was 4% lower for ML plans (P=.002), although the difference was not clinically significant. Respondents ranked the ML-generated plans as equivalent to expert BT treatment plans in terms of target coverage, normal tissue avoidance, implant confidence, and the need for plan modifications. Respondents had difficulty differentiating between plans generated by a human or those generated by the ML algorithm. Conclusions: Prostate LDR preimplantation treatment plans that have equivalent quality to plans created
International Nuclear Information System (INIS)
Nicolae, Alexandru; Morton, Gerard; Chung, Hans; Loblaw, Andrew; Jain, Suneil; Mitchell, Darren; Lu, Lin; Helou, Joelle; Al-Hanaqta, Motasem; Heath, Emily; Ravi, Ananth
2017-01-01
Purpose: This work presents the application of a machine learning (ML) algorithm to automatically generate high-quality, prostate low-dose-rate (LDR) brachytherapy treatment plans. The ML algorithm can mimic characteristics of preoperative treatment plans deemed clinically acceptable by brachytherapists. The planning efficiency, dosimetry, and quality (as assessed by experts) of preoperative plans generated with an ML planning approach was retrospectively evaluated in this study. Methods and Materials: Preimplantation and postimplantation treatment plans were extracted from 100 high-quality LDR treatments and stored within a training database. The ML training algorithm matches similar features from a new LDR case to those within the training database to rapidly obtain an initial seed distribution; plans were then further fine-tuned using stochastic optimization. Preimplantation treatment plans generated by the ML algorithm were compared with brachytherapist (BT) treatment plans in terms of planning time (Wilcoxon rank sum, α = 0.05) and dosimetry (1-way analysis of variance, α = 0.05). Qualitative preimplantation plan quality was evaluated by expert LDR radiation oncologists using a Likert scale questionnaire. Results: The average planning time for the ML approach was 0.84 ± 0.57 minutes, compared with 17.88 ± 8.76 minutes for the expert planner (P=.020). Preimplantation plans were dosimetrically equivalent to the BT plans; the average prostate V150% was 4% lower for ML plans (P=.002), although the difference was not clinically significant. Respondents ranked the ML-generated plans as equivalent to expert BT treatment plans in terms of target coverage, normal tissue avoidance, implant confidence, and the need for plan modifications. Respondents had difficulty differentiating between plans generated by a human or those generated by the ML algorithm. Conclusions: Prostate LDR preimplantation treatment plans that have equivalent quality to plans created
Taylor, Jonathan Christopher; Fenner, John Wesley
2017-11-29
Semi-quantification methods are well established in the clinic for assisted reporting of (I123) Ioflupane images. Arguably, these are limited diagnostic tools. Recent research has demonstrated the potential for improved classification performance offered by machine learning algorithms. A direct comparison between methods is required to establish whether a move towards widespread clinical adoption of machine learning algorithms is justified. This study compared three machine learning algorithms with that of a range of semi-quantification methods, using the Parkinson's Progression Markers Initiative (PPMI) research database and a locally derived clinical database for validation. Machine learning algorithms were based on support vector machine classifiers with three different sets of features: Voxel intensities Principal components of image voxel intensities Striatal binding radios from the putamen and caudate. Semi-quantification methods were based on striatal binding ratios (SBRs) from both putamina, with and without consideration of the caudates. Normal limits for the SBRs were defined through four different methods: Minimum of age-matched controls Mean minus 1/1.5/2 standard deviations from age-matched controls Linear regression of normal patient data against age (minus 1/1.5/2 standard errors) Selection of the optimum operating point on the receiver operator characteristic curve from normal and abnormal training data Each machine learning and semi-quantification technique was evaluated with stratified, nested 10-fold cross-validation, repeated 10 times. The mean accuracy of the semi-quantitative methods for classification of local data into Parkinsonian and non-Parkinsonian groups varied from 0.78 to 0.87, contrasting with 0.89 to 0.95 for classifying PPMI data into healthy controls and Parkinson's disease groups. The machine learning algorithms gave mean accuracies between 0.88 to 0.92 and 0.95 to 0.97 for local and PPMI data respectively. Classification
Directory of Open Access Journals (Sweden)
Carla S. B. Viegas
2014-01-01
Full Text Available Gla-rich protein (GRP was described in sturgeon as a new vitamin-K-dependent protein (VKDP with a high density of Gla residues and associated with ectopic calcifications in humans. Although VKDPs function has been related with γ-carboxylation, the Gla status of GRP in humans is still unknown. Here, we investigated the expression of recently identified GRP spliced transcripts, the γ-carboxylation status, and its association with ectopic calcifications, in skin basal cell and breast carcinomas. GRP-F1 was identified as the predominant splice variant expressed in healthy and cancer tissues. Patterns of γ-carboxylated GRP (cGRP/undercarboxylated GRP (ucGRP accumulation in healthy and cancer tissues were determined by immunohistochemistry, using newly developed conformation-specific antibodies. Both GRP protein forms were found colocalized in healthy tissues, while ucGRP was the predominant form associated with tumor cells. Both cGRP and ucGRP found at sites of microcalcifications were shown to have in vitro calcium mineral-binding capacity. The decreased levels of cGRP and predominance of ucGRP in tumor cells suggest that GRP may represent a new target for the anticancer potential of vitamin K. Also, the direct interaction of cGRP and ucGRP with BCP crystals provides a possible mechanism explaining GRP association with pathological mineralization.
Mishra, Aashwin; Iaccarino, Gianluca
2017-11-01
In spite of their deficiencies, RANS models represent the workhorse for industrial investigations into turbulent flows. In this context, it is essential to provide diagnostic measures to assess the quality of RANS predictions. To this end, the primary step is to identify feature importances amongst massive sets of potentially descriptive and discriminative flow features. This aids the physical interpretability of the resultant discrepancy model and its extensibility to similar problems. Recent investigations have utilized approaches such as Random Forests, Support Vector Machines and the Least Absolute Shrinkage and Selection Operator for feature selection. With examples, we exhibit how such methods may not be suitable for turbulent flow datasets. The underlying rationale, such as the correlation bias and the required conditions for the success of penalized algorithms, are discussed with illustrative examples. Finally, we provide alternate approaches using convex combinations of regularized regression approaches and randomized sub-sampling in combination with feature selection algorithms, to infer model structure from data. This research was supported by the Defense Advanced Research Projects Agency under the Enabling Quantification of Uncertainty in Physical Systems (EQUiPS) project (technical monitor: Dr Fariba Fahroo).
Karthick, P A; Ghosh, Diptasree Maitra; Ramakrishnan, S
2018-02-01
Surface electromyography (sEMG) based muscle fatigue research is widely preferred in sports science and occupational/rehabilitation studies due to its noninvasiveness. However, these signals are complex, multicomponent and highly nonstationary with large inter-subject variations, particularly during dynamic contractions. Hence, time-frequency based machine learning methodologies can improve the design of automated system for these signals. In this work, the analysis based on high-resolution time-frequency methods, namely, Stockwell transform (S-transform), B-distribution (BD) and extended modified B-distribution (EMBD) are proposed to differentiate the dynamic muscle nonfatigue and fatigue conditions. The nonfatigue and fatigue segments of sEMG signals recorded from the biceps brachii of 52 healthy volunteers are preprocessed and subjected to S-transform, BD and EMBD. Twelve features are extracted from each method and prominent features are selected using genetic algorithm (GA) and binary particle swarm optimization (BPSO). Five machine learning algorithms, namely, naïve Bayes, support vector machine (SVM) of polynomial and radial basis kernel, random forest and rotation forests are used for the classification. The results show that all the proposed time-frequency distributions (TFDs) are able to show the nonstationary variations of sEMG signals. Most of the features exhibit statistically significant difference in the muscle fatigue and nonfatigue conditions. The maximum number of features (66%) is reduced by GA and BPSO for EMBD and BD-TFD respectively. The combination of EMBD- polynomial kernel based SVM is found to be most accurate (91% accuracy) in classifying the conditions with the features selected using GA. The proposed methods are found to be capable of handling the nonstationary and multicomponent variations of sEMG signals recorded in dynamic fatiguing contractions. Particularly, the combination of EMBD- polynomial kernel based SVM could be used to
Performance Comparison of Two Reinforcement Learning Algorithms for Small Mobile Robots
Czech Academy of Sciences Publication Activity Database
Neruda, Roman; Slušný, Stanislav
2009-01-01
Roč. 2, č. 1 (2009), s. 59-68 ISSN 2005-4297 R&D Projects: GA MŠk(CZ) 1M0567 Grant - others:GA UK(CZ) 7637/2007 Institutional research plan: CEZ:AV0Z10300504 Keywords : reinforcement learning * mobile robots * inteligent agents Subject RIV: IN - Informatics, Computer Science http://www.sersc.org/journals/IJCA/vol2_no1/7.pdf
From Genetics to Genetic Algorithms
Indian Academy of Sciences (India)
Genetic algorithms (GAs) are computational optimisation schemes with an ... The algorithms solve optimisation problems ..... Genetic Algorithms in Search, Optimisation and Machine. Learning, Addison-Wesley Publishing Company, Inc. 1989.
Zhang, Xu; Foderaro, Greg; Henriquez, Craig; Ferrari, Silvia
2018-03-01
Recent developments in neural stimulation and recording technologies are providing scientists with the ability of recording and controlling the activity of individual neurons in vitro or in vivo, with very high spatial and temporal resolution. Tools such as optogenetics, for example, are having a significant impact in the neuroscience field by delivering optical firing control with the precision and spatiotemporal resolution required for investigating information processing and plasticity in biological brains. While a number of training algorithms have been developed to date for spiking neural network (SNN) models of biological neuronal circuits, exiting methods rely on learning rules that adjust the synaptic strengths (or weights) directly, in order to obtain the desired network-level (or functional-level) performance. As such, they are not applicable to modifying plasticity in biological neuronal circuits, in which synaptic strengths only change as a result of pre- and post-synaptic neuron firings or biological mechanisms beyond our control. This paper presents a weight-free training algorithm that relies solely on adjusting the spatiotemporal delivery of neuron firings in order to optimize the network performance. The proposed weight-free algorithm does not require any knowledge of the SNN model or its plasticity mechanisms. As a result, this training approach is potentially realizable in vitro or in vivo via neural stimulation and recording technologies, such as optogenetics and multielectrode arrays, and could be utilized to control plasticity at multiple scales of biological neuronal circuits. The approach is demonstrated by training SNNs with hundreds of units to control a virtual insect navigating in an unknown environment.
Directory of Open Access Journals (Sweden)
Meihong Wu
2016-01-01
Full Text Available Measuring stride variability and dynamics in children is useful for the quantitative study of gait maturation and neuromotor development in childhood and adolescence. In this paper, we computed the sample entropy (SampEn and average stride interval (ASI parameters to quantify the stride series of 50 gender-matched children participants in three age groups. We also normalized the SampEn and ASI values by leg length and body mass for each participant, respectively. Results show that the original and normalized SampEn values consistently decrease over the significance level of the Mann-Whitney U test (p<0.01 in children of 3–14 years old, which indicates the stride irregularity has been significantly ameliorated with the body growth. The original and normalized ASI values are also significantly changing when comparing between any two groups of young (aged 3–5 years, middle (aged 6–8 years, and elder (aged 10–14 years children. Such results suggest that healthy children may better modulate their gait cadence rhythm with the development of their musculoskeletal and neurological systems. In addition, the AdaBoost.M2 and Bagging algorithms were used to effectively distinguish the children’s gait patterns. These ensemble learning algorithms both provided excellent gait classification results in terms of overall accuracy (≥90%, recall (≥0.8, and precision (≥0.8077.
Directory of Open Access Journals (Sweden)
Chao Yang
2016-01-01
Full Text Available The artificial bee colony (ABC algorithm is a recently introduced optimization method in the research field of swarm intelligence. This paper presents an improved ABC algorithm named as OGABC based on opposition-based learning (OBL and global best search equation to overcome the shortcomings of the slow convergence rate and sinking into local optima in the process of inversion of atmospheric duct. Taking the inversion of the surface duct using refractivity from clutter (RFC technique as an example to validate the performance of the proposed OGABC, the inversion results are compared with those of the modified invasive weed optimization (MIWO and ABC. The radar sea clutter power calculated by parabolic equation method using the simulated and measured refractivity profile is utilized to carry out the inversion of the surface duct, respectively. The comparative investigation results indicate that the performance of OGABC is superior to that of MIWO and ABC in terms of stability, accuracy, and convergence rate during the process of inversion.
Pham, Lien T. H.; Brabyn, Lars
2017-06-01
Mangrove forests are well-known for their provision of ecosystem services and capacity to reduce carbon dioxide concentrations in the atmosphere. Mapping and quantifying mangrove biomass is useful for the effective management of these forests and maximizing their ecosystem service performance. The objectives of this research were to model, map, and analyse the biomass change between 2000 and 2011 of mangrove forests in the Cangio region in Vietnam. SPOT 4 and 5 images were used in conjunction with object-based image analysis and machine learning algorithms. The study area included natural and planted mangroves of diverse species. After image preparation, three different mangrove associations were identified using two levels of image segmentation followed by a Support Vector Machine classifier and a range of spectral, texture and GIS information for classification. The overall classification accuracy for the 2000 and 2011 images were 77.1% and 82.9%, respectively. Random Forest regression algorithms were then used for modelling and mapping biomass. The model that integrated spectral, vegetation association type, texture, and vegetation indices obtained the highest accuracy (R2adj = 0.73). Among the different variables, vegetation association type was the most important variable identified by the Random Forest model. Based on the biomass maps generated from the Random Forest, total biomass in the Cangio mangrove forest increased by 820,136 tons over this period, although this change varied between the three different mangrove associations.
Cavaco, Sofia; Viegas, Carla S B; Rafael, Marta S; Ramos, Acácio; Magalhães, Joana; Blanco, Francisco J; Vermeer, Cees; Simes, Dina C
2016-03-01
Osteoarthritis (OA) is a whole-joint disease characterized by articular cartilage loss, tissue inflammation, abnormal bone formation and extracellular matrix (ECM) mineralization. Disease-modifying treatments are not yet available and a better understanding of osteoarthritis pathophysiology should lead to the discovery of more effective treatments. Gla-rich protein (GRP) has been proposed to act as a mineralization inhibitor and was recently shown to be associated with OA in vivo. Here, we further investigated the association of GRP with OA mineralization-inflammation processes. Using a synoviocyte and chondrocyte OA cell system, we showed that GRP expression was up-regulated following cell differentiation throughout ECM calcification, and that inflammatory stimulation with IL-1β results in an increased expression of COX2 and MMP13 and up-regulation of GRP. Importantly, while treatment of articular cells with γ-carboxylated GRP inhibited ECM calcification, treatment with either GRP or GRP-coated basic calcium phosphate (BCP) crystals resulted in the down-regulation of inflammatory cytokines and mediators of inflammation, independently of its γ-carboxylation status. Our results strengthen the calcification inhibitory function of GRP and strongly suggest GRP as a novel anti-inflammatory agent, with potential beneficial effects on the main processes responsible for osteoarthritis progression. In conclusion, GRP is a strong candidate target to develop new therapeutic approaches.
JACoW Model learning algorithms for anomaly detection in CERN control systems
Tilaro, Filippo; Gonzalez-Berges, Manuel; Roshchin, Mikhail; Varela, Fernando
2018-01-01
The CERN automation infrastructure consists of over 600 heterogeneous industrial control systems with around 45 million deployed sensors, actuators and control objects. Therefore, it is evident that the monitoring of such huge system represents a challenging and complex task. This paper describes three different mathematical approaches that have been designed and developed to detect anomalies in any of the CERN control systems. Specifically, one of these algorithms is purely based on expert knowledge; the other two mine the historical generated data to create a simple model of the system; this model is then used to detect faulty sensors measurements. The presented methods can be categorized as dynamic unsupervised anomaly detection; “dynamic” since the behaviour of the system and the evolution of its attributes are observed and changing in time. They are “unsupervised” because we are trying to predict faulty events without examples in the data history. So, the described strategies involve monitoring t...
Doheny, Dana; Srinivasan, Ram; Pagant, Silvere; Chen, Brenden; Yasuda, Makiko; Desnick, Robert J
2018-04-01
Fabry Disease (FD), an X linked lysosomal storage disease due to pathogenic α-galactosidase A ( GLA ) mutations, results in two major subtypes, the early-onset Type 1 'Classic' and the Type 2 'Later-Onset' phenotypes. To identify previously unrecognised patients, investigators screened cardiac, renal and stroke clinics by enzyme assays. However, some screening studies did not perform confirmatory GLA mutation analyses, and many included recently recognised 'benign/likely-benign' variants, thereby inflating prevalence estimates. Online databases were searched for all FD screening studies in high-risk clinics (1995-2017). Studies reporting GLA mutations were re-analysed for pathogenic mutations, sex and phenotype. Phenotype-specific and sex-specific prevalence rates were determined. Of 67 studies, 63 that screened 51363patients (33943M and 17420F) and provided GLA mutations were reanalysed for disease-causing mutations. Of reported GLA mutations, benign variants occurred in 47.9% of males and 74.1% of females. The following were the revised prevalence estimates: among 36820 (23954M and 12866F) haemodialysis screenees, 0.21% males and 0.15% females; among 3074 (2031M and 1043F) renal transplant screenees, 0.25% males and no females; among 5491 (4054M and 1437F) cardiac screenees, 0.94% males and 0.90% females; and among 5978 (3904M and 2074F) stroke screenees, 0.13% males and 0.14% females. Among male and female screenees with pathogenic mutations, the type 1 Classic phenotype was predominant (~60%), except more male cardiac patients (75%) had type 2 Later-Onset phenotype. Compared with previous findings, reanalysis of 63 studies increased the screenee numbers (~3.4-fold), eliminated 20 benign/likely benign variants, and provided more accurate sex-specific and phenotype-specific prevalence estimates, ranging from ~0.13% of stroke to ~0.9% of cardiac male or female screenees. © Article author(s) (or their employer(s) unless otherwise stated in the text of the article
CERN. Geneva
2018-01-01
Particle identification (PID) plays a crucial role in LHCb analyses. Combining information from LHCb subdetectors allows one to distinguish between various species of long-lived charged and neutral particles. PID performance directly affects the sensitivity of most LHCb measurements. Advanced multivariate approaches are used at LHCb to obtain the best PID performance and control systematic uncertainties. This talk highlights recent developments in PID that use innovative machine learning techniques, as well as novel data-driven approaches which ensure that PID performance is well reproduced in simulation.
Data Mining Learning Models and Algorithms on a Scada System Data Repository
Directory of Open Access Journals (Sweden)
Mircea Rîşteiu
2010-06-01
Full Text Available This paper presents three data mining techniques applied
on a SCADA system data repository: NaÄ³ve Bayes, k-Nearest Neighbor and Decision Trees. A conclusion that k-Nearest Neighbor is a suitable method to classify the large amount of data considered is made finally according to the mining result and its reasonable explanation. The experiments are built on the training data set and evaluated using the new test set with machine learning tool WEKA.
Czech Academy of Sciences Publication Activity Database
Djordjilović, V.; Chiogna, M.; Vomlel, Jiří
2017-01-01
Roč. 88, č. 1 (2017), s. 602-613 ISSN 0888-613X R&D Projects: GA ČR(CZ) GA16-12010S Institutional support: RVO:67985556 Keywords : Bayesian networks * Structure learning * Reverse engineering * Gene networks Subject RIV: JD - Computer Applications, Robotics OBOR OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) Impact factor: 2.845, year: 2016 http://library.utia.cas.cz/separaty/2017/MTR/vomlel-0477168.pdf