active learning algorithms: Topics by Science.gov

Sample records for active learning algorithms

Active Learning Using Hint Information.

PubMed

Li, Chun-Liang; Ferng, Chun-Sung; Lin, Hsuan-Tien

2015-08-01

The abundance of real-world data and limited labeling budget calls for active learning, an important learning paradigm for reducing human labeling efforts. Many recently developed active learning algorithms consider both uncertainty and representativeness when making querying decisions. However, exploiting representativeness with uncertainty concurrently usually requires tackling sophisticated and challenging learning tasks, such as clustering. In this letter, we propose a new active learning framework, called hinted sampling, which takes both uncertainty and representativeness into account in a simpler way. We design a novel active learning algorithm within the hinted sampling framework with an extended support vector machine. Experimental results validate that the novel active learning algorithm can result in a better and more stable performance than that achieved by state-of-the-art algorithms. We also show that the hinted sampling framework allows improving another active learning algorithm designed from the transductive support vector machine.
Active learning for clinical text classification: is it better than random sampling?

PubMed

Figueroa, Rosa L; Zeng-Treitler, Qing; Ngo, Long H; Goryachev, Sergey; Wiechmann, Eduardo P

2012-01-01

This study explores active learning algorithms as a way to reduce the requirements for large training sets in medical text classification tasks. Three existing active learning algorithms (distance-based (DIST), diversity-based (DIV), and a combination of both (CMB)) were used to classify text from five datasets. The performance of these algorithms was compared to that of passive learning on the five datasets. We then conducted a novel investigation of the interaction between dataset characteristics and the performance results. Classification accuracy and area under receiver operating characteristics (ROC) curves for each algorithm at different sample sizes were generated. The performance of active learning algorithms was compared with that of passive learning using a weighted mean of paired differences. To determine why the performance varies on different datasets, we measured the diversity and uncertainty of each dataset using relative entropy and correlated the results with the performance differences. The DIST and CMB algorithms performed better than passive learning. With a statistical significance level set at 0.05, DIST outperformed passive learning in all five datasets, while CMB was found to be better than passive learning in four datasets. We found strong correlations between the dataset diversity and the DIV performance, as well as the dataset uncertainty and the performance of the DIST algorithm. For medical text classification, appropriate active learning algorithms can yield performance comparable to that of passive learning with considerably smaller training sets. In particular, our results suggest that DIV performs better on data with higher diversity and DIST on data with lower uncertainty.
Active learning for clinical text classification: is it better than random sampling?

PubMed Central

Figueroa, Rosa L; Ngo, Long H; Goryachev, Sergey; Wiechmann, Eduardo P

2012-01-01

Objective This study explores active learning algorithms as a way to reduce the requirements for large training sets in medical text classification tasks. Design Three existing active learning algorithms (distance-based (DIST), diversity-based (DIV), and a combination of both (CMB)) were used to classify text from five datasets. The performance of these algorithms was compared to that of passive learning on the five datasets. We then conducted a novel investigation of the interaction between dataset characteristics and the performance results. Measurements Classification accuracy and area under receiver operating characteristics (ROC) curves for each algorithm at different sample sizes were generated. The performance of active learning algorithms was compared with that of passive learning using a weighted mean of paired differences. To determine why the performance varies on different datasets, we measured the diversity and uncertainty of each dataset using relative entropy and correlated the results with the performance differences. Results The DIST and CMB algorithms performed better than passive learning. With a statistical significance level set at 0.05, DIST outperformed passive learning in all five datasets, while CMB was found to be better than passive learning in four datasets. We found strong correlations between the dataset diversity and the DIV performance, as well as the dataset uncertainty and the performance of the DIST algorithm. Conclusion For medical text classification, appropriate active learning algorithms can yield performance comparable to that of passive learning with considerably smaller training sets. In particular, our results suggest that DIV performs better on data with higher diversity and DIST on data with lower uncertainty. PMID:22707743
DOE Office of Scientific and Technical Information (OSTI.GOV)

Jamieson, Kevin; Davis, IV, Warren L.

Active learning methods automatically adapt data collection by selecting the most informative samples in order to accelerate machine learning. Because of this, real-world testing and comparing active learning algorithms requires collecting new datasets (adaptively), rather than simply applying algorithms to benchmark datasets, as is the norm in (passive) machine learning research. To facilitate the development, testing and deployment of active learning for real applications, we have built an open-source software system for large-scale active learning research and experimentation. The system, called NEXT, provides a unique platform for realworld, reproducible active learning research. This paper details the challenges of building themore » system and demonstrates its capabilities with several experiments. The results show how experimentation can help expose strengths and weaknesses of active learning algorithms, in sometimes unexpected and enlightening ways.« less
Collegial Activity Learning between Heterogeneous Sensors.

PubMed

Feuz, Kyle D; Cook, Diane J

2017-11-01

Activity recognition algorithms have matured and become more ubiquitous in recent years. However, these algorithms are typically customized for a particular sensor platform. In this paper we introduce PECO, a Personalized activity ECOsystem, that transfers learned activity information seamlessly between sensor platforms in real time so that any available sensor can continue to track activities without requiring its own extensive labeled training data. We introduce a multi-view transfer learning algorithm that facilitates this information handoff between sensor platforms and provide theoretical performance bounds for the algorithm. In addition, we empirically evaluate PECO using datasets that utilize heterogeneous sensor platforms to perform activity recognition. These results indicate that not only can activity recognition algorithms transfer important information to new sensor platforms, but any number of platforms can work together as colleagues to boost performance.
An Educational System for Learning Search Algorithms and Automatically Assessing Student Performance

ERIC Educational Resources Information Center

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…
A developmental approach to learning causal models for cyber security

NASA Astrophysics Data System (ADS)

Mugan, Jonathan

2013-05-01

To keep pace with our adversaries, we must expand the scope of machine learning and reasoning to address the breadth of possible attacks. One approach is to employ an algorithm to learn a set of causal models that describes the entire cyber network and each host end node. Such a learning algorithm would run continuously on the system and monitor activity in real time. With a set of causal models, the algorithm could anticipate novel attacks, take actions to thwart them, and predict the second-order effects flood of information, and the algorithm would have to determine which streams of that flood were relevant in which situations. This paper will present the results of efforts toward the application of a developmental learning algorithm to the problem of cyber security. The algorithm is modeled on the principles of human developmental learning and is designed to allow an agent to learn about the computer system in which it resides through active exploration. Children are flexible learners who acquire knowledge by actively exploring their environment and making predictions about what they will find,1, 2 and our algorithm is inspired by the work of the developmental psychologist Jean Piaget.3 Piaget described how children construct knowledge in stages and learn new concepts on top of those they already know. Developmental learning allows our algorithm to focus on subsets of the environment that are most helpful for learning given its current knowledge. In experiments, the algorithm was able to learn the conditions for file exfiltration and use that knowledge to protect sensitive files.
Fast Back-Propagation Learning Using Steep Activation Functions and Automatic Weight

Treesearch

Tai-Hoon Cho; Richard W. Conners; Philip A. Araman

1992-01-01

In this paper, several back-propagation (BP) learning speed-up algorithms that employ the Ã£gainÃ¤ parameter, i.e., steepness of the activation function, are examined. Simulations will show that increasing the gain seemingly increases the speed of convergence and that these algorithms can converge faster than the standard BP learning algorithm on some problems. However,...
Learning Behavior Characterization with Multi-Feature, Hierarchical Activity Sequences

ERIC Educational Resources Information Center

Ye, Cheng; Segedy, James R.; Kinnebrew, John S.; Biswas, Gautam

2015-01-01

This paper discusses Multi-Feature Hierarchical Sequential Pattern Mining, MFH-SPAM, a novel algorithm that efficiently extracts patterns from students' learning activity sequences. This algorithm extends an existing sequential pattern mining algorithm by dynamically selecting the level of specificity for hierarchically-defined features…
Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity.

PubMed

Kim, Hui Kwon; Min, Seonwoo; Song, Myungjae; Jung, Soobin; Choi, Jae Woo; Kim, Younggwang; Lee, Sangeun; Yoon, Sungroh; Kim, Hyongbum Henry

2018-03-01

We present two algorithms to predict the activity of AsCpf1 guide RNAs. Indel frequencies for 15,000 target sequences were used in a deep-learning framework based on a convolutional neural network to train Seq-deepCpf1. We then incorporated chromatin accessibility information to create the better-performing DeepCpf1 algorithm for cell lines for which such information is available and show that both algorithms outperform previous machine learning algorithms on our own and published data sets.
Automatic Earthquake Detection by Active Learning

NASA Astrophysics Data System (ADS)

Bergen, K.; Beroza, G. C.

2017-12-01

In recent years, advances in machine learning have transformed fields such as image recognition, natural language processing and recommender systems. Many of these performance gains have relied on the availability of large, labeled data sets to train high-accuracy models; labeled data sets are those for which each sample includes a target class label, such as waveforms tagged as either earthquakes or noise. Earthquake seismologists are increasingly leveraging machine learning and data mining techniques to detect and analyze weak earthquake signals in large seismic data sets. One of the challenges in applying machine learning to seismic data sets is the limited labeled data problem; learning algorithms need to be given examples of earthquake waveforms, but the number of known events, taken from earthquake catalogs, may be insufficient to build an accurate detector. Furthermore, earthquake catalogs are known to be incomplete, resulting in training data that may be biased towards larger events and contain inaccurate labels. This challenge is compounded by the class imbalance problem; the events of interest, earthquakes, are infrequent relative to noise in continuous data sets, and many learning algorithms perform poorly on rare classes. In this work, we investigate the use of active learning for automatic earthquake detection. Active learning is a type of semi-supervised machine learning that uses a human-in-the-loop approach to strategically supplement a small initial training set. The learning algorithm incorporates domain expertise through interaction between a human expert and the algorithm, with the algorithm actively posing queries to the user to improve detection performance. We demonstrate the potential of active machine learning to improve earthquake detection performance with limited available training data.
Using human brain activity to guide machine learning.

PubMed

Fong, Ruth C; Scheirer, Walter J; Cox, David D

2018-03-29

Machine learning is a field of computer science that builds algorithms that learn. In many cases, machine learning algorithms are used to recreate a human ability like adding a caption to a photo, driving a car, or playing a game. While the human brain has long served as a source of inspiration for machine learning, little effort has been made to directly use data collected from working brains as a guide for machine learning algorithms. Here we demonstrate a new paradigm of "neurally-weighted" machine learning, which takes fMRI measurements of human brain activity from subjects viewing images, and infuses these data into the training process of an object recognition learning algorithm to make it more consistent with the human brain. After training, these neurally-weighted classifiers are able to classify images without requiring any additional neural data. We show that our neural-weighting approach can lead to large performance gains when used with traditional machine vision features, as well as to significant improvements with already high-performing convolutional neural network features. The effectiveness of this approach points to a path forward for a new class of hybrid machine learning algorithms which take both inspiration and direct constraints from neuronal data.
Performance of thigh-mounted triaxial accelerometer algorithms in objective quantification of sedentary behaviour and physical activity in older adults

PubMed Central

Verschueren, Sabine M. P.; Degens, Hans; Morse, Christopher I.; Onambélé, Gladys L.

2017-01-01

Accurate monitoring of sedentary behaviour and physical activity is key to investigate their exact role in healthy ageing. To date, accelerometers using cut-off point models are most preferred for this, however, machine learning seems a highly promising future alternative. Hence, the current study compared between cut-off point and machine learning algorithms, for optimal quantification of sedentary behaviour and physical activity intensities in the elderly. Thus, in a heterogeneous sample of forty participants (aged ≥60 years, 50% female) energy expenditure during laboratory-based activities (ranging from sedentary behaviour through to moderate-to-vigorous physical activity) was estimated by indirect calorimetry, whilst wearing triaxial thigh-mounted accelerometers. Three cut-off point algorithms and a Random Forest machine learning model were developed and cross-validated using the collected data. Detailed analyses were performed to check algorithm robustness, and examine and benchmark both overall and participant-specific balanced accuracies. This revealed that the four models can at least be used to confidently monitor sedentary behaviour and moderate-to-vigorous physical activity. Nevertheless, the machine learning algorithm outperformed the cut-off point models by being robust for all individual’s physiological and non-physiological characteristics and showing more performance of an acceptable level over the whole range of physical activity intensities. Therefore, we propose that Random Forest machine learning may be optimal for objective assessment of sedentary behaviour and physical activity in older adults using thigh-mounted triaxial accelerometry. PMID:29155839
Performance of thigh-mounted triaxial accelerometer algorithms in objective quantification of sedentary behaviour and physical activity in older adults.

PubMed

Wullems, Jorgen A; Verschueren, Sabine M P; Degens, Hans; Morse, Christopher I; Onambélé, Gladys L

2017-01-01

Accurate monitoring of sedentary behaviour and physical activity is key to investigate their exact role in healthy ageing. To date, accelerometers using cut-off point models are most preferred for this, however, machine learning seems a highly promising future alternative. Hence, the current study compared between cut-off point and machine learning algorithms, for optimal quantification of sedentary behaviour and physical activity intensities in the elderly. Thus, in a heterogeneous sample of forty participants (aged ≥60 years, 50% female) energy expenditure during laboratory-based activities (ranging from sedentary behaviour through to moderate-to-vigorous physical activity) was estimated by indirect calorimetry, whilst wearing triaxial thigh-mounted accelerometers. Three cut-off point algorithms and a Random Forest machine learning model were developed and cross-validated using the collected data. Detailed analyses were performed to check algorithm robustness, and examine and benchmark both overall and participant-specific balanced accuracies. This revealed that the four models can at least be used to confidently monitor sedentary behaviour and moderate-to-vigorous physical activity. Nevertheless, the machine learning algorithm outperformed the cut-off point models by being robust for all individual's physiological and non-physiological characteristics and showing more performance of an acceptable level over the whole range of physical activity intensities. Therefore, we propose that Random Forest machine learning may be optimal for objective assessment of sedentary behaviour and physical activity in older adults using thigh-mounted triaxial accelerometry.
Machine learning of molecular properties: Locality and active learning

NASA Astrophysics Data System (ADS)

Gubaev, Konstantin; Podryabinkin, Evgeny V.; Shapeev, Alexander V.

2018-06-01

In recent years, the machine learning techniques have shown great potent1ial in various problems from a multitude of disciplines, including materials design and drug discovery. The high computational speed on the one hand and the accuracy comparable to that of density functional theory on another hand make machine learning algorithms efficient for high-throughput screening through chemical and configurational space. However, the machine learning algorithms available in the literature require large training datasets to reach the chemical accuracy and also show large errors for the so-called outliers—the out-of-sample molecules, not well-represented in the training set. In the present paper, we propose a new machine learning algorithm for predicting molecular properties that addresses these two issues: it is based on a local model of interatomic interactions providing high accuracy when trained on relatively small training sets and an active learning algorithm of optimally choosing the training set that significantly reduces the errors for the outliers. We compare our model to the other state-of-the-art algorithms from the literature on the widely used benchmark tests.
Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms.

PubMed

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.
Using Active Learning for Speeding up Calibration in Simulation Models.

PubMed

Cevik, Mucahit; Ergun, Mehmet Ali; Stout, Natasha K; Trentham-Dietz, Amy; Craven, Mark; Alagoz, Oguzhan

2016-07-01

Most cancer simulation models include unobservable parameters that determine disease onset and tumor growth. These parameters play an important role in matching key outcomes such as cancer incidence and mortality, and their values are typically estimated via a lengthy calibration procedure, which involves evaluating a large number of combinations of parameter values via simulation. The objective of this study is to demonstrate how machine learning approaches can be used to accelerate the calibration process by reducing the number of parameter combinations that are actually evaluated. Active learning is a popular machine learning method that enables a learning algorithm such as artificial neural networks to interactively choose which parameter combinations to evaluate. We developed an active learning algorithm to expedite the calibration process. Our algorithm determines the parameter combinations that are more likely to produce desired outputs and therefore reduces the number of simulation runs performed during calibration. We demonstrate our method using the previously developed University of Wisconsin breast cancer simulation model (UWBCS). In a recent study, calibration of the UWBCS required the evaluation of 378 000 input parameter combinations to build a race-specific model, and only 69 of these combinations produced results that closely matched observed data. By using the active learning algorithm in conjunction with standard calibration methods, we identify all 69 parameter combinations by evaluating only 5620 of the 378 000 combinations. Machine learning methods hold potential in guiding model developers in the selection of more promising parameter combinations and hence speeding up the calibration process. Applying our machine learning algorithm to one model shows that evaluating only 1.49% of all parameter combinations would be sufficient for the calibration. © The Author(s) 2015.
Using Active Learning for Speeding up Calibration in Simulation Models

PubMed Central

Cevik, Mucahit; Ali Ergun, Mehmet; Stout, Natasha K.; Trentham-Dietz, Amy; Craven, Mark; Alagoz, Oguzhan

2015-01-01

Background Most cancer simulation models include unobservable parameters that determine the disease onset and tumor growth. These parameters play an important role in matching key outcomes such as cancer incidence and mortality and their values are typically estimated via lengthy calibration procedure, which involves evaluating large number of combinations of parameter values via simulation. The objective of this study is to demonstrate how machine learning approaches can be used to accelerate the calibration process by reducing the number of parameter combinations that are actually evaluated. Methods Active learning is a popular machine learning method that enables a learning algorithm such as artificial neural networks to interactively choose which parameter combinations to evaluate. We develop an active learning algorithm to expedite the calibration process. Our algorithm determines the parameter combinations that are more likely to produce desired outputs, therefore reduces the number of simulation runs performed during calibration. We demonstrate our method using previously developed University of Wisconsin Breast Cancer Simulation Model (UWBCS). Results In a recent study, calibration of the UWBCS required the evaluation of 378,000 input parameter combinations to build a race-specific model and only 69 of these combinations produced results that closely matched observed data. By using the active learning algorithm in conjunction with standard calibration methods, we identify all 69 parameter combinations by evaluating only 5620 of the 378,000 combinations. Conclusion Machine learning methods hold potential in guiding model developers in the selection of more promising parameter combinations and hence speeding up the calibration process. Applying our machine learning algorithm to one model shows that evaluating only 1.49% of all parameter combinations would be sufficient for the calibration. PMID:26471190
Active Learning with Irrelevant Examples

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri; Mazzoni, Dominic

2009-01-01

An improved active learning method has been devised for training data classifiers. One example of a data classifier is the algorithm used by the United States Postal Service since the 1960s to recognize scans of handwritten digits for processing zip codes. Active learning algorithms enable rapid training with minimal investment of time on the part of human experts to provide training examples consisting of correctly classified (labeled) input data. They function by identifying which examples would be most profitable for a human expert to label. The goal is to maximize classifier accuracy while minimizing the number of examples the expert must label. Although there are several well-established methods for active learning, they may not operate well when irrelevant examples are present in the data set. That is, they may select an item for labeling that the expert simply cannot assign to any of the valid classes. In the context of classifying handwritten digits, the irrelevant items may include stray marks, smudges, and mis-scans. Querying the expert about these items results in wasted time or erroneous labels, if the expert is forced to assign the item to one of the valid classes. In contrast, the new algorithm provides a specific mechanism for avoiding querying the irrelevant items. This algorithm has two components: an active learner (which could be a conventional active learning algorithm) and a relevance classifier. The combination of these components yields a method, denoted Relevance Bias, that enables the active learner to avoid querying irrelevant data so as to increase its learning rate and efficiency when irrelevant items are present. The algorithm collects irrelevant data in a set of rejected examples, then trains the relevance classifier to distinguish between labeled (relevant) training examples and the rejected ones. The active learner combines its ranking of the items with the probability that they are relevant to yield a final decision about which item to present to the expert for labeling. Experiments on several data sets have demonstrated that the Relevance Bias approach significantly decreases the number of irrelevant items queried and also accelerates learning speed.
[Purity Detection Model Update of Maize Seeds Based on Active Learning].

PubMed

Tang, Jin-ya; Huang, Min; Zhu, Qi-bing

2015-08-01

Seed purity reflects the degree of seed varieties in typical consistent characteristics, so it is great important to improve the reliability and accuracy of seed purity detection to guarantee the quality of seeds. Hyperspectral imaging can reflect the internal and external characteristics of seeds at the same time, which has been widely used in nondestructive detection of agricultural products. The essence of nondestructive detection of agricultural products using hyperspectral imaging technique is to establish the mathematical model between the spectral information and the quality of agricultural products. Since the spectral information is easily affected by the sample growth environment, the stability and generalization of model would weaken when the test samples harvested from different origin and year. Active learning algorithm was investigated to add representative samples to expand the sample space for the original model, so as to implement the rapid update of the model's ability. Random selection (RS) and Kennard-Stone algorithm (KS) were performed to compare the model update effect with active learning algorithm. The experimental results indicated that in the division of different proportion of sample set (1:1, 3:1, 4:1), the updated purity detection model for maize seeds from 2010 year which was added 40 samples selected by active learning algorithm from 2011 year increased the prediction accuracy for 2011 new samples from 47%, 33.75%, 49% to 98.89%, 98.33%, 98.33%. For the updated purity detection model of 2011 year, its prediction accuracy for 2010 new samples increased by 50.83%, 54.58%, 53.75% to 94.57%, 94.02%, 94.57% after adding 56 new samples from 2010 year. Meanwhile the effect of model updated by active learning algorithm was better than that of RS and KS. Therefore, the update for purity detection model of maize seeds is feasible by active learning algorithm.

Assessing the quality of activities in a smart environment.

PubMed

Cook, Diane J; Schmitter-Edgecombe, M

2009-01-01

Pervasive computing technology can provide valuable health monitoring and assistance technology to help individuals live independent lives in their own homes. As a critical part of this technology, our objective is to design software algorithms that recognize and assess the consistency of activities of daily living that individuals perform in their own homes. We have designed algorithms that automatically learn Markov models for each class of activity. These models are used to recognize activities that are performed in a smart home and to identify errors and inconsistencies in the performed activity. We validate our approach using data collected from 60 volunteers who performed a series of activities in our smart apartment testbed. The results indicate that the algorithms correctly label the activities and successfully assess the completeness and consistency of the performed task. Our results indicate that activity recognition and assessment can be automated using machine learning algorithms and smart home technology. These algorithms will be useful for automating remote health monitoring and interventions.
Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms

PubMed Central

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel. PMID:24795875
Evaluation of a Didactic Method for the Active Learning of Greedy Algorithms

ERIC Educational Resources Information Center

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…
Applying active learning to supervised word sense disambiguation in MEDLINE.

PubMed

Chen, Yukun; Cao, Hongxin; Mei, Qiaozhu; Zheng, Kai; Xu, Hua

2013-01-01

This study was to assess whether active learning strategies can be integrated with supervised word sense disambiguation (WSD) methods, thus reducing the number of annotated samples, while keeping or improving the quality of disambiguation models. We developed support vector machine (SVM) classifiers to disambiguate 197 ambiguous terms and abbreviations in the MSH WSD collection. Three different uncertainty sampling-based active learning algorithms were implemented with the SVM classifiers and were compared with a passive learner (PL) based on random sampling. For each ambiguous term and each learning algorithm, a learning curve that plots the accuracy computed from the test set as a function of the number of annotated samples used in the model was generated. The area under the learning curve (ALC) was used as the primary metric for evaluation. Our experiments demonstrated that active learners (ALs) significantly outperformed the PL, showing better performance for 177 out of 197 (89.8%) WSD tasks. Further analysis showed that to achieve an average accuracy of 90%, the PL needed 38 annotated samples, while the ALs needed only 24, a 37% reduction in annotation effort. Moreover, we analyzed cases where active learning algorithms did not achieve superior performance and identified three causes: (1) poor models in the early learning stage; (2) easy WSD cases; and (3) difficult WSD cases, which provide useful insight for future improvements. This study demonstrated that integrating active learning strategies with supervised WSD methods could effectively reduce annotation cost and improve the disambiguation models.
Applying active learning to supervised word sense disambiguation in MEDLINE

PubMed Central

Chen, Yukun; Cao, Hongxin; Mei, Qiaozhu; Zheng, Kai; Xu, Hua

2013-01-01

Objectives This study was to assess whether active learning strategies can be integrated with supervised word sense disambiguation (WSD) methods, thus reducing the number of annotated samples, while keeping or improving the quality of disambiguation models. Methods We developed support vector machine (SVM) classifiers to disambiguate 197 ambiguous terms and abbreviations in the MSH WSD collection. Three different uncertainty sampling-based active learning algorithms were implemented with the SVM classifiers and were compared with a passive learner (PL) based on random sampling. For each ambiguous term and each learning algorithm, a learning curve that plots the accuracy computed from the test set as a function of the number of annotated samples used in the model was generated. The area under the learning curve (ALC) was used as the primary metric for evaluation. Results Our experiments demonstrated that active learners (ALs) significantly outperformed the PL, showing better performance for 177 out of 197 (89.8%) WSD tasks. Further analysis showed that to achieve an average accuracy of 90%, the PL needed 38 annotated samples, while the ALs needed only 24, a 37% reduction in annotation effort. Moreover, we analyzed cases where active learning algorithms did not achieve superior performance and identified three causes: (1) poor models in the early learning stage; (2) easy WSD cases; and (3) difficult WSD cases, which provide useful insight for future improvements. Conclusions This study demonstrated that integrating active learning strategies with supervised WSD methods could effectively reduce annotation cost and improve the disambiguation models. PMID:23364851
Recommending Learning Activities in Social Network Using Data Mining Algorithms

ERIC Educational Resources Information Center

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…
A fast and accurate online sequential learning algorithm for feedforward networks.

PubMed

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.
Active learning in the presence of unlabelable examples

NASA Technical Reports Server (NTRS)

Mazzoni, Dominic; Wagstaff, Kiri

2004-01-01

We propose a new active learning framework where the expert labeler is allowed to decline to label any example. This may be necessary because the true label is unknown or because the example belongs to a class that is not part of the real training problem. We show that within this framework, popular active learning algorithms (such as Simple) may perform worse than random selection because they make so many queries to the unlabelable class. We present a method by which any active learning algorithm can be modified to avoid unlabelable examples by training a second classifier to distinguish between the labelable and unlabelable classes. We also demonstrate the effectiveness of the method on two benchmark data sets and a real-world problem.
Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control

NASA Technical Reports Server (NTRS)

Bernstein, Daniel S.; Zilberstein, Shlomo

2003-01-01

Weakly-coupled Markov decision processes can be decomposed into subprocesses that interact only through a small set of bottleneck states. We study a hierarchical reinforcement learning algorithm designed to take advantage of this particular type of decomposability. To test our algorithm, we use a decision-making problem faced by autonomous planetary rovers. In this problem, a Mars rover must decide which activities to perform and when to traverse between science sites in order to make the best use of its limited resources. In our experiments, the hierarchical algorithm performs better than Q-learning in the early stages of learning, but unlike Q-learning it converges to a suboptimal policy. This suggests that it may be advantageous to use the hierarchical algorithm when training time is limited.
Automated assessment of cognitive health using smart home technologies.

PubMed

Dawadi, Prafulla N; Cook, Diane J; Schmitter-Edgecombe, Maureen; Parsey, Carolyn

2013-01-01

The goal of this work is to develop intelligent systems to monitor the wellbeing of individuals in their home environments. This paper introduces a machine learning-based method to automatically predict activity quality in smart homes and automatically assess cognitive health based on activity quality. This paper describes an automated framework to extract set of features from smart home sensors data that reflects the activity performance or ability of an individual to complete an activity which can be input to machine learning algorithms. Output from learning algorithms including principal component analysis, support vector machine, and logistic regression algorithms are used to quantify activity quality for a complex set of smart home activities and predict cognitive health of participants. Smart home activity data was gathered from volunteer participants (n=263) who performed a complex set of activities in our smart home testbed. We compare our automated activity quality prediction and cognitive health prediction with direct observation scores and health assessment obtained from neuropsychologists. With all samples included, we obtained statistically significant correlation (r=0.54) between direct observation scores and predicted activity quality. Similarly, using a support vector machine classifier, we obtained reasonable classification accuracy (area under the ROC curve=0.80, g-mean=0.73) in classifying participants into two different cognitive classes, dementia and cognitive healthy. The results suggest that it is possible to automatically quantify the task quality of smart home activities and perform limited assessment of the cognitive health of individual if smart home activities are properly chosen and learning algorithms are appropriately trained.
Automated Assessment of Cognitive Health Using Smart Home Technologies

PubMed Central

Dawadi, Prafulla N.; Cook, Diane J.; Schmitter-Edgecombe, Maureen; Parsey, Carolyn

2014-01-01

BACKGROUND The goal of this work is to develop intelligent systems to monitor the well being of individuals in their home environments. OBJECTIVE This paper introduces a machine learning-based method to automatically predict activity quality in smart homes and automatically assess cognitive health based on activity quality. METHODS This paper describes an automated framework to extract set of features from smart home sensors data that reflects the activity performance or ability of an individual to complete an activity which can be input to machine learning algorithms. Output from learning algorithms including principal component analysis, support vector machine, and logistic regression algorithms are used to quantify activity quality for a complex set of smart home activities and predict cognitive health of participants. RESULTS Smart home activity data was gathered from volunteer participants (n=263) who performed a complex set of activities in our smart home testbed. We compare our automated activity quality prediction and cognitive health prediction with direct observation scores and health assessment obtained from neuropsychologists. With all samples included, we obtained statistically significant correlation (r=0.54) between direct observation scores and predicted activity quality. Similarly, using a support vector machine classifier, we obtained reasonable classification accuracy (area under the ROC curve = 0.80, g-mean = 0.73) in classifying participants into two different cognitive classes, dementia and cognitive healthy. CONCLUSIONS The results suggest that it is possible to automatically quantify the task quality of smart home activities and perform limited assessment of the cognitive health of individual if smart home activities are properly chosen and learning algorithms are appropriately trained. PMID:23949177
Feature combination networks for the interpretation of statistical machine learning models: application to Ames mutagenicity.

PubMed

Webb, Samuel J; Hanser, Thierry; Howlin, Brendan; Krause, Paul; Vessey, Jonathan D

2014-03-25

A new algorithm has been developed to enable the interpretation of black box models. The developed algorithm is agnostic to learning algorithm and open to all structural based descriptors such as fragments, keys and hashed fingerprints. The algorithm has provided meaningful interpretation of Ames mutagenicity predictions from both random forest and support vector machine models built on a variety of structural fingerprints.A fragmentation algorithm is utilised to investigate the model's behaviour on specific substructures present in the query. An output is formulated summarising causes of activation and deactivation. The algorithm is able to identify multiple causes of activation or deactivation in addition to identifying localised deactivations where the prediction for the query is active overall. No loss in performance is seen as there is no change in the prediction; the interpretation is produced directly on the model's behaviour for the specific query. Models have been built using multiple learning algorithms including support vector machine and random forest. The models were built on public Ames mutagenicity data and a variety of fingerprint descriptors were used. These models produced a good performance in both internal and external validation with accuracies around 82%. The models were used to evaluate the interpretation algorithm. Interpretation was revealed that links closely with understood mechanisms for Ames mutagenicity. This methodology allows for a greater utilisation of the predictions made by black box models and can expedite further study based on the output for a (quantitative) structure activity model. Additionally the algorithm could be utilised for chemical dataset investigation and knowledge extraction/human SAR development.
Anomaly detection using temporal data mining in a smart home environment.

PubMed

Jakkula, V; Cook, D J

2008-01-01

To many people, home is a sanctuary. With the maturing of smart home technologies, many people with cognitive and physical disabilities can lead independent lives in their own homes for extended periods of time. In this paper, we investigate the design of machine learning algorithms that support this goal. We hypothesize that machine learning algorithms can be designed to automatically learn models of resident behavior in a smart home, and that the results can be used to perform automated health monitoring and to detect anomalies. Specifically, our algorithms draw upon the temporal nature of sensor data collected in a smart home to build a model of expected activities and to detect unexpected, and possibly health-critical, events in the home. We validate our algorithms using synthetic data and real activity data collected from volunteers in an automated smart environment. The results from our experiments support our hypothesis that a model can be learned from observed smart home data and used to report anomalies, as they occur, in a smart home.
Learning Extended Finite State Machines

NASA Technical Reports Server (NTRS)

Cassel, Sofia; Howar, Falk; Jonsson, Bengt; Steffen, Bernhard

2014-01-01

We present an active learning algorithm for inferring extended finite state machines (EFSM)s, combining data flow and control behavior. Key to our learning technique is a novel learning model based on so-called tree queries. The learning algorithm uses the tree queries to infer symbolic data constraints on parameters, e.g., sequence numbers, time stamps, identifiers, or even simple arithmetic. We describe sufficient conditions for the properties that the symbolic constraints provided by a tree query in general must have to be usable in our learning model. We have evaluated our algorithm in a black-box scenario, where tree queries are realized through (black-box) testing. Our case studies include connection establishment in TCP and a priority queue from the Java Class Library.
A semi-learning algorithm for noise rejection: an fNIRS study on ADHD children

NASA Astrophysics Data System (ADS)

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
Active semi-supervised learning method with hybrid deep belief networks.

PubMed

Zhou, Shusen; Chen, Qingcai; Wang, Xiaolong

2014-01-01

In this paper, we develop a novel semi-supervised learning algorithm called active hybrid deep belief networks (AHD), to address the semi-supervised sentiment classification problem with deep learning. First, we construct the previous several hidden layers using restricted Boltzmann machines (RBM), which can reduce the dimension and abstract the information of the reviews quickly. Second, we construct the following hidden layers using convolutional restricted Boltzmann machines (CRBM), which can abstract the information of reviews effectively. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. Finally, active learning method is combined based on the proposed deep architecture. We did several experiments on five sentiment classification datasets, and show that AHD is competitive with previous semi-supervised learning algorithm. Experiments are also conducted to verify the effectiveness of our proposed method with different number of labeled reviews and unlabeled reviews respectively.
A Low-Tech, Hands-On Approach To Teaching Sorting Algorithms to Working Students.

ERIC Educational Resources Information Center

Dios, R.; Geller, J.

1998-01-01

Focuses on identifying the educational effects of "activity oriented" instructional techniques. Examines which instructional methods produce enhanced learning and comprehension. Discusses the problem of learning "sorting algorithms," a major topic in every Computer Science curriculum. Presents a low-tech, hands-on teaching method for sorting…
The UXO Classification Demonstration at San Luis Obispo, CA

DTIC Science & Technology

2010-09-01

Set ................................45 2.17.2 Active Learning Training and Test Set ..........................................47 2.17.3 Extended...optimized algorithm by applying it to only the unlabeled data in the test set. 2.17.2 Active Learning Training and Test Set SIG also used active ... learning [12]. Active learning , an alternative approach for constructing a training set, is used in conjunction with either supervised or semi
An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity

PubMed Central

Whittington, James C. R.; Bogacz, Rafal

2017-01-01

To efficiently learn from feedback, cortical networks need to update synaptic weights on multiple levels of cortical hierarchy. An effective and well-known algorithm for computing such changes in synaptic weights is the error backpropagation algorithm. However, in this algorithm, the change in synaptic weights is a complex function of weights and activities of neurons not directly connected with the synapse being modified, whereas the changes in biological synapses are determined only by the activity of presynaptic and postsynaptic neurons. Several models have been proposed that approximate the backpropagation algorithm with local synaptic plasticity, but these models require complex external control over the network or relatively complex plasticity rules. Here we show that a network developed in the predictive coding framework can efficiently perform supervised learning fully autonomously, employing only simple local Hebbian plasticity. Furthermore, for certain parameters, the weight change in the predictive coding model converges to that of the backpropagation algorithm. This suggests that it is possible for cortical networks with simple Hebbian synaptic plasticity to implement efficient learning algorithms in which synapses in areas on multiple levels of hierarchy are modified to minimize the error on the output. PMID:28333583
An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity.

PubMed

Whittington, James C R; Bogacz, Rafal

2017-05-01

To efficiently learn from feedback, cortical networks need to update synaptic weights on multiple levels of cortical hierarchy. An effective and well-known algorithm for computing such changes in synaptic weights is the error backpropagation algorithm. However, in this algorithm, the change in synaptic weights is a complex function of weights and activities of neurons not directly connected with the synapse being modified, whereas the changes in biological synapses are determined only by the activity of presynaptic and postsynaptic neurons. Several models have been proposed that approximate the backpropagation algorithm with local synaptic plasticity, but these models require complex external control over the network or relatively complex plasticity rules. Here we show that a network developed in the predictive coding framework can efficiently perform supervised learning fully autonomously, employing only simple local Hebbian plasticity. Furthermore, for certain parameters, the weight change in the predictive coding model converges to that of the backpropagation algorithm. This suggests that it is possible for cortical networks with simple Hebbian synaptic plasticity to implement efficient learning algorithms in which synapses in areas on multiple levels of hierarchy are modified to minimize the error on the output.

11.2 YIP Human In the Loop Statistical RelationalLearners

DTIC Science & Technology

2017-10-23

learning formalisms including inverse reinforcement learning [4] and statistical relational learning [7, 5, 8]. We have also applied our algorithms in...one introduced for label preferences. 4 Figure 2: Active Advice Seeking for Inverse Reinforcement Learning. active advice seeking is in selecting the...learning tasks. 1.2.1 Sequential Decision-Making Our previous work on advice for inverse reinforcement learning (IRL) defined advice as action
Exploiting Secondary Sources for Unsupervised Record Linkage

DTIC Science & Technology

2004-01-01

paper, we present an extension to Apollo’s active learning component to Report Documentation Page Form ApprovedOMB No. 0704-0188 Public reporting...Sources address the issue of user involvement. Using secondary sources, a system can autonomously answer questions posed by its active learning component...over, we present how Apollo utilizes the identified sec- ondary sources in an unsupervised active learning pro- cess. Apollo’s learning algorithm
Performance of Activity Classification Algorithms in Free-living Older Adults

PubMed Central

Sasaki, Jeffer Eidi; Hickey, Amanda; Staudenmayer, John; John, Dinesh; Kent, Jane A.; Freedson, Patty S.

2015-01-01

Purpose To compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults. Methods Thirty-five older adults (21F and 14M ; 70.8 ± 4.9 y) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (dominant hip, wrist, and ankle). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore the GT3X+ in free-living settings and were directly observed for 2-3 hours. Time- and frequency- domain features from acceleration signals of each monitor were used to train Random Forest (RF) and Support Vector Machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on lab data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20 s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique. Results Overall classification accuracy rates for the algorithms developed from lab data were between 49% (wrist) to 55% (ankle) for the SVMLab algorithms, and 49% (wrist) to 54% (ankle) for RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively. Conclusion Our algorithms developed on free-living accelerometer data were more accurate in classifying activity type in free-living older adults than our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine-learning algorithms in older adults. PMID:26673129
Performance of Activity Classification Algorithms in Free-Living Older Adults.

PubMed

Sasaki, Jeffer Eidi; Hickey, Amanda M; Staudenmayer, John W; John, Dinesh; Kent, Jane A; Freedson, Patty S

2016-05-01

The objective of this study is to compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults. Thirty-five older adults (21 females and 14 males, 70.8 ± 4.9 yr) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (in the dominant hip, wrist, and ankle; ActiGraph, LLC, Pensacola, FL). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore GT3X+ in free-living settings and were directly observed for 2-3 h. Time- and frequency-domain features from acceleration signals of each monitor were used to train random forest (RF) and support vector machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on laboratory data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20-s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique. Overall classification accuracy rates for the algorithms developed from laboratory data were between 49% (wrist) and 55% (ankle) for the SVMLab algorithms and 49% (wrist) to 54% (ankle) for the RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively. Our algorithms developed on free-living accelerometer data were more accurate in classifying the activity type in free-living older adults than those on our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine learning algorithms in older adults.
Estimation of State Transition Probabilities: A Neural Network Model

NASA Astrophysics Data System (ADS)

Saito, Hiroshi; Takiyama, Ken; Okada, Masato

2015-12-01

Humans and animals can predict future states on the basis of acquired knowledge. This prediction of the state transition is important for choosing the best action, and the prediction is only possible if the state transition probability has already been learned. However, how our brains learn the state transition probability is unknown. Here, we propose a simple algorithm for estimating the state transition probability by utilizing the state prediction error. We analytically and numerically confirmed that our algorithm is able to learn the probability completely with an appropriate learning rate. Furthermore, our learning rule reproduced experimentally reported psychometric functions and neural activities in the lateral intraparietal area in a decision-making task. Thus, our algorithm might describe the manner in which our brains learn state transition probabilities and predict future states.
Effect of Algorithms' Multiple Representations in the Context of Programming Education

ERIC Educational Resources Information Center

Siozou, Stefania; Tselios, Nikolaos; Komis, Vassilis

2008-01-01

Purpose: The purpose of this paper is to compare the effect of different representations while teaching basic algorithmic concepts to novice programmers. Design/methodology/approach: A learning activity was designed and mediated with two conceptually different learning environments, each one used by a different group. The first group used the…
Active learning: learning a motor skill without a coach.

PubMed

Huang, Vincent S; Shadmehr, Reza; Diedrichsen, Jörn

2008-08-01

When we learn a new skill (e.g., golf) without a coach, we are "active learners": we have to choose the specific components of the task on which to train (e.g., iron, driver, putter, etc.). What guides our selection of the training sequence? How do choices that people make compare with choices made by machine learning algorithms that attempt to optimize performance? We asked subjects to learn the novel dynamics of a robotic tool while moving it in four directions. They were instructed to choose their practice directions to maximize their performance in subsequent tests. We found that their choices were strongly influenced by motor errors: subjects tended to immediately repeat an action if that action had produced a large error. This strategy was correlated with better performance on test trials. However, even when participants performed perfectly on a movement, they did not avoid repeating that movement. The probability of repeating an action did not drop below chance even when no errors were observed. This behavior led to suboptimal performance. It also violated a strong prediction of current machine learning algorithms, which solve the active learning problem by choosing a training sequence that will maximally reduce the learner's uncertainty about the task. While we show that these algorithms do not provide an adequate description of human behavior, our results suggest ways to improve human motor learning by helping people choose an optimal training sequence.
Making predictions in a changing world-inference, uncertainty, and learning.

PubMed

O'Reilly, Jill X

2013-01-01

To function effectively, brains need to make predictions about their environment based on past experience, i.e., they need to learn about their environment. The algorithms by which learning occurs are of interest to neuroscientists, both in their own right (because they exist in the brain) and as a tool to model participants' incomplete knowledge of task parameters and hence, to better understand their behavior. This review focusses on a particular challenge for learning algorithms-how to match the rate at which they learn to the rate of change in the environment, so that they use as much observed data as possible whilst disregarding irrelevant, old observations. To do this algorithms must evaluate whether the environment is changing. We discuss the concepts of likelihood, priors and transition functions, and how these relate to change detection. We review expected and estimation uncertainty, and how these relate to change detection and learning rate. Finally, we consider the neural correlates of uncertainty and learning. We argue that the neural correlates of uncertainty bear a resemblance to neural systems that are active when agents actively explore their environments, suggesting that the mechanisms by which the rate of learning is set may be subject to top down control (in circumstances when agents actively seek new information) as well as bottom up control (by observations that imply change in the environment).
Trans-algorithmic nature of learning in biological systems.

PubMed

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.
Exploring Representativeness and Informativeness for Active Learning.

PubMed

Du, Bo; Wang, Zengmao; Zhang, Lefei; Zhang, Liangpei; Liu, Wei; Shen, Jialie; Tao, Dacheng

2017-01-01

How can we find a general way to choose the most suitable samples for training a classifier? Even with very limited prior information? Active learning, which can be regarded as an iterative optimization procedure, plays a key role to construct a refined training set to improve the classification performance in a variety of applications, such as text analysis, image recognition, social network modeling, etc. Although combining representativeness and informativeness of samples has been proven promising for active sampling, state-of-the-art methods perform well under certain data structures. Then can we find a way to fuse the two active sampling criteria without any assumption on data? This paper proposes a general active learning framework that effectively fuses the two criteria. Inspired by a two-sample discrepancy problem, triple measures are elaborately designed to guarantee that the query samples not only possess the representativeness of the unlabeled data but also reveal the diversity of the labeled data. Any appropriate similarity measure can be employed to construct the triple measures. Meanwhile, an uncertain measure is leveraged to generate the informativeness criterion, which can be carried out in different ways. Rooted in this framework, a practical active learning algorithm is proposed, which exploits a radial basis function together with the estimated probabilities to construct the triple measures and a modified best-versus-second-best strategy to construct the uncertain measure, respectively. Experimental results on benchmark datasets demonstrate that our algorithm consistently achieves superior performance over the state-of-the-art active learning algorithms.
Applying Active Learning to Assertion Classification of Concepts in Clinical Text

PubMed Central

Chen, Yukun; Mani, Subramani; Xu, Hua

2012-01-01

Supervised machine learning methods for clinical natural language processing (NLP) research require a large number of annotated samples, which are very expensive to build because of the involvement of physicians. Active learning, an approach that actively samples from a large pool, provides an alternative solution. Its major goal in classification is to reduce the annotation effort while maintaining the quality of the predictive model. However, few studies have investigated its uses in clinical NLP. This paper reports an application of active learning to a clinical text classification task: to determine the assertion status of clinical concepts. The annotated corpus for the assertion classification task in the 2010 i2b2/VA Clinical NLP Challenge was used in this study. We implemented several existing and newly developed active learning algorithms and assessed their uses. The outcome is reported in the global ALC score, based on the Area under the average Learning Curve of the AUC (Area Under the Curve) score. Results showed that when the same number of annotated samples was used, active learning strategies could generate better classification models (best ALC – 0.7715) than the passive learning method (random sampling) (ALC – 0.7411). Moreover, to achieve the same classification performance, active learning strategies required fewer samples than the random sampling method. For example, to achieve an AUC of 0.79, the random sampling method used 32 samples, while our best active learning algorithm required only 12 samples, a reduction of 62.5% in manual annotation effort. PMID:22127105
Competitive learning with pairwise constraints.

PubMed

Covões, Thiago F; Hruschka, Eduardo R; Ghosh, Joydeep

2013-01-01

Constrained clustering has been an active research topic since the last decade. Most studies focus on batch-mode algorithms. This brief introduces two algorithms for on-line constrained learning, named on-line linear constrained vector quantization error (O-LCVQE) and constrained rival penalized competitive learning (C-RPCL). The former is a variant of the LCVQE algorithm for on-line settings, whereas the latter is an adaptation of the (on-line) RPCL algorithm to deal with constrained clustering. The accuracy results--in terms of the normalized mutual information (NMI)--from experiments with nine datasets show that the partitions induced by O-LCVQE are competitive with those found by the (batch-mode) LCVQE. Compared with this formidable baseline algorithm, it is surprising that C-RPCL can provide better partitions (in terms of the NMI) for most of the datasets. Also, experiments on a large dataset show that on-line algorithms for constrained clustering can significantly reduce the computational time.
Sequential and Mixed Genetic Algorithm and Learning Automata (SGALA, MGALA) for Feature Selection in QSAR

PubMed Central

MotieGhader, Habib; Gharaghani, Sajjad; Masoudi-Sobhanzadeh, Yosef; Masoudi-Nejad, Ali

2017-01-01

Feature selection is of great importance in Quantitative Structure-Activity Relationship (QSAR) analysis. This problem has been solved using some meta-heuristic algorithms such as GA, PSO, ACO and so on. In this work two novel hybrid meta-heuristic algorithms i.e. Sequential GA and LA (SGALA) and Mixed GA and LA (MGALA), which are based on Genetic algorithm and learning automata for QSAR feature selection are proposed. SGALA algorithm uses advantages of Genetic algorithm and Learning Automata sequentially and the MGALA algorithm uses advantages of Genetic Algorithm and Learning Automata simultaneously. We applied our proposed algorithms to select the minimum possible number of features from three different datasets and also we observed that the MGALA and SGALA algorithms had the best outcome independently and in average compared to other feature selection algorithms. Through comparison of our proposed algorithms, we deduced that the rate of convergence to optimal result in MGALA and SGALA algorithms were better than the rate of GA, ACO, PSO and LA algorithms. In the end, the results of GA, ACO, PSO, LA, SGALA, and MGALA algorithms were applied as the input of LS-SVR model and the results from LS-SVR models showed that the LS-SVR model had more predictive ability with the input from SGALA and MGALA algorithms than the input from all other mentioned algorithms. Therefore, the results have corroborated that not only is the predictive efficiency of proposed algorithms better, but their rate of convergence is also superior to the all other mentioned algorithms. PMID:28979308
Sequential and Mixed Genetic Algorithm and Learning Automata (SGALA, MGALA) for Feature Selection in QSAR.

PubMed

MotieGhader, Habib; Gharaghani, Sajjad; Masoudi-Sobhanzadeh, Yosef; Masoudi-Nejad, Ali

2017-01-01

Feature selection is of great importance in Quantitative Structure-Activity Relationship (QSAR) analysis. This problem has been solved using some meta-heuristic algorithms such as GA, PSO, ACO and so on. In this work two novel hybrid meta-heuristic algorithms i.e. Sequential GA and LA (SGALA) and Mixed GA and LA (MGALA), which are based on Genetic algorithm and learning automata for QSAR feature selection are proposed. SGALA algorithm uses advantages of Genetic algorithm and Learning Automata sequentially and the MGALA algorithm uses advantages of Genetic Algorithm and Learning Automata simultaneously. We applied our proposed algorithms to select the minimum possible number of features from three different datasets and also we observed that the MGALA and SGALA algorithms had the best outcome independently and in average compared to other feature selection algorithms. Through comparison of our proposed algorithms, we deduced that the rate of convergence to optimal result in MGALA and SGALA algorithms were better than the rate of GA, ACO, PSO and LA algorithms. In the end, the results of GA, ACO, PSO, LA, SGALA, and MGALA algorithms were applied as the input of LS-SVR model and the results from LS-SVR models showed that the LS-SVR model had more predictive ability with the input from SGALA and MGALA algorithms than the input from all other mentioned algorithms. Therefore, the results have corroborated that not only is the predictive efficiency of proposed algorithms better, but their rate of convergence is also superior to the all other mentioned algorithms.
Ensemble Methods for Classification of Physical Activities from Wrist Accelerometry.

PubMed

Chowdhury, Alok Kumar; Tjondronegoro, Dian; Chandran, Vinod; Trost, Stewart G

2017-09-01

To investigate whether the use of ensemble learning algorithms improve physical activity recognition accuracy compared to the single classifier algorithms, and to compare the classification accuracy achieved by three conventional ensemble machine learning methods (bagging, boosting, random forest) and a custom ensemble model comprising four algorithms commonly used for activity recognition (binary decision tree, k nearest neighbor, support vector machine, and neural network). The study used three independent data sets that included wrist-worn accelerometer data. For each data set, a four-step classification framework consisting of data preprocessing, feature extraction, normalization and feature selection, and classifier training and testing was implemented. For the custom ensemble, decisions from the single classifiers were aggregated using three decision fusion methods: weighted majority vote, naïve Bayes combination, and behavior knowledge space combination. Classifiers were cross-validated using leave-one subject out cross-validation and compared on the basis of average F1 scores. In all three data sets, ensemble learning methods consistently outperformed the individual classifiers. Among the conventional ensemble methods, random forest models provided consistently high activity recognition; however, the custom ensemble model using weighted majority voting demonstrated the highest classification accuracy in two of the three data sets. Combining multiple individual classifiers using conventional or custom ensemble learning methods can improve activity recognition accuracy from wrist-worn accelerometer data.
Brain-Inspired Constructive Learning Algorithms with Evolutionally Additive Nonlinear Neurons

NASA Astrophysics Data System (ADS)

Fang, Le-Heng; Lin, Wei; Luo, Qiang

In this article, inspired partially by the physiological evidence of brain’s growth and development, we developed a new type of constructive learning algorithm with evolutionally additive nonlinear neurons. The new algorithms have remarkable ability in effective regression and accurate classification. In particular, the algorithms are able to sustain a certain reduction of the loss function when the dynamics of the trained network are bogged down in the vicinity of the local minima. The algorithm augments the neural network by adding only a few connections as well as neurons whose activation functions are nonlinear, nonmonotonic, and self-adapted to the dynamics of the loss functions. Indeed, we analytically demonstrate the reduction dynamics of the algorithm for different problems, and further modify the algorithms so as to obtain an improved generalization capability for the augmented neural networks. Finally, through comparing with the classical algorithm and architecture for neural network construction, we show that our constructive learning algorithms as well as their modified versions have better performances, such as faster training speed and smaller network size, on several representative benchmark datasets including the MNIST dataset for handwriting digits.
Optimizing the learning rate for adaptive estimation of neural encoding models

PubMed Central

2018-01-01

Closed-loop neurotechnologies often need to adaptively learn an encoding model that relates the neural activity to the brain state, and is used for brain state decoding. The speed and accuracy of adaptive learning algorithms are critically affected by the learning rate, which dictates how fast model parameters are updated based on new observations. Despite the importance of the learning rate, currently an analytical approach for its selection is largely lacking and existing signal processing methods vastly tune it empirically or heuristically. Here, we develop a novel analytical calibration algorithm for optimal selection of the learning rate in adaptive Bayesian filters. We formulate the problem through a fundamental trade-off that learning rate introduces between the steady-state error and the convergence time of the estimated model parameters. We derive explicit functions that predict the effect of learning rate on error and convergence time. Using these functions, our calibration algorithm can keep the steady-state parameter error covariance smaller than a desired upper-bound while minimizing the convergence time, or keep the convergence time faster than a desired value while minimizing the error. We derive the algorithm both for discrete-valued spikes modeled as point processes nonlinearly dependent on the brain state, and for continuous-valued neural recordings modeled as Gaussian processes linearly dependent on the brain state. Using extensive closed-loop simulations, we show that the analytical solution of the calibration algorithm accurately predicts the effect of learning rate on parameter error and convergence time. Moreover, the calibration algorithm allows for fast and accurate learning of the encoding model and for fast convergence of decoding to accurate performance. Finally, larger learning rates result in inaccurate encoding models and decoders, and smaller learning rates delay their convergence. The calibration algorithm provides a novel analytical approach to predictably achieve a desired level of error and convergence time in adaptive learning, with application to closed-loop neurotechnologies and other signal processing domains. PMID:29813069
Optimizing the learning rate for adaptive estimation of neural encoding models.

PubMed

Hsieh, Han-Lin; Shanechi, Maryam M

2018-05-01

Closed-loop neurotechnologies often need to adaptively learn an encoding model that relates the neural activity to the brain state, and is used for brain state decoding. The speed and accuracy of adaptive learning algorithms are critically affected by the learning rate, which dictates how fast model parameters are updated based on new observations. Despite the importance of the learning rate, currently an analytical approach for its selection is largely lacking and existing signal processing methods vastly tune it empirically or heuristically. Here, we develop a novel analytical calibration algorithm for optimal selection of the learning rate in adaptive Bayesian filters. We formulate the problem through a fundamental trade-off that learning rate introduces between the steady-state error and the convergence time of the estimated model parameters. We derive explicit functions that predict the effect of learning rate on error and convergence time. Using these functions, our calibration algorithm can keep the steady-state parameter error covariance smaller than a desired upper-bound while minimizing the convergence time, or keep the convergence time faster than a desired value while minimizing the error. We derive the algorithm both for discrete-valued spikes modeled as point processes nonlinearly dependent on the brain state, and for continuous-valued neural recordings modeled as Gaussian processes linearly dependent on the brain state. Using extensive closed-loop simulations, we show that the analytical solution of the calibration algorithm accurately predicts the effect of learning rate on parameter error and convergence time. Moreover, the calibration algorithm allows for fast and accurate learning of the encoding model and for fast convergence of decoding to accurate performance. Finally, larger learning rates result in inaccurate encoding models and decoders, and smaller learning rates delay their convergence. The calibration algorithm provides a novel analytical approach to predictably achieve a desired level of error and convergence time in adaptive learning, with application to closed-loop neurotechnologies and other signal processing domains.
Predicting Solar Activity Using Machine-Learning Methods

NASA Astrophysics Data System (ADS)

Bobra, M.

2017-12-01

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

PubMed

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.

Flow Navigation by Smart Microswimmers via Reinforcement Learning

NASA Astrophysics Data System (ADS)

Colabrese, Simona; Biferale, Luca; Celani, Antonio; Gustavsson, Kristian

2017-11-01

We have numerically modeled active particles which are able to acquire some limited knowledge of the fluid environment from simple mechanical cues and exert a control on their preferred steering direction. We show that those swimmers can learn effective strategies just by experience, using a reinforcement learning algorithm. As an example, we focus on smart gravitactic swimmers. These are active particles whose task is to reach the highest altitude within some time horizon, exploiting the underlying flow whenever possible. The reinforcement learning algorithm allows particles to learn effective strategies even in difficult situations when, in the absence of control, they would end up being trapped by flow structures. These strategies are highly nontrivial and cannot be easily guessed in advance. This work paves the way towards the engineering of smart microswimmers that solve difficult navigation problems. ERC AdG NewTURB 339032.
Magnified gradient function with deterministic weight modification in adaptive learning.

PubMed

Ng, Sin-Chun; Cheung, Chi-Chung; Leung, Shu-Hung

2004-11-01

This paper presents two novel approaches, backpropagation (BP) with magnified gradient function (MGFPROP) and deterministic weight modification (DWM), to speed up the convergence rate and improve the global convergence capability of the standard BP learning algorithm. The purpose of MGFPROP is to increase the convergence rate by magnifying the gradient function of the activation function, while the main objective of DWM is to reduce the system error by changing the weights of a multilayered feedforward neural network in a deterministic way. Simulation results show that the performance of the above two approaches is better than BP and other modified BP algorithms for a number of learning problems. Moreover, the integration of the above two approaches forming a new algorithm called MDPROP, can further improve the performance of MGFPROP and DWM. From our simulation results, the MDPROP algorithm always outperforms BP and other modified BP algorithms in terms of convergence rate and global convergence capability.
Methods for reducing interference in the Complementary Learning Systems model: oscillating inhibition and autonomous memory rehearsal.

PubMed

Norman, Kenneth A; Newman, Ehren L; Perotte, Adler J

2005-11-01

The stability-plasticity problem (i.e. how the brain incorporates new information into its model of the world, while at the same time preserving existing knowledge) has been at the forefront of computational memory research for several decades. In this paper, we critically evaluate how well the Complementary Learning Systems theory of hippocampo-cortical interactions addresses the stability-plasticity problem. We identify two major challenges for the model: Finding a learning algorithm for cortex and hippocampus that enacts selective strengthening of weak memories, and selective punishment of competing memories; and preventing catastrophic forgetting in the case of non-stationary environments (i.e. when items are temporarily removed from the training set). We then discuss potential solutions to these problems: First, we describe a recently developed learning algorithm that leverages neural oscillations to find weak parts of memories (so they can be strengthened) and strong competitors (so they can be punished), and we show how this algorithm outperforms other learning algorithms (CPCA Hebbian learning and Leabra at memorizing overlapping patterns. Second, we describe how autonomous re-activation of memories (separately in cortex and hippocampus) during REM sleep, coupled with the oscillating learning algorithm, can reduce the rate of forgetting of input patterns that are no longer present in the environment. We then present a simple demonstration of how this process can prevent catastrophic interference in an AB-AC learning paradigm.
Summary of Progress on SIG Ft. Ord ESTCP DemVal

DTIC Science & Technology

2007-04-01

We report on progress under an ESTCP demonstration plan dedicated to demonstrating active learning - based UXO detection on an actual former UXO site...Ft. Ord), using EMI data. In addition to describing the details of the active - learning algorithm, we discuss techniques that were required when...terms of two dipole-moment magnitudes and two resonant frequencies. Information-theoretic active learning is then conducted on all anomalies to
An Imperfect Dopaminergic Error Signal Can Drive Temporal-Difference Learning

PubMed Central

Potjans, Wiebke; Diesmann, Markus; Morrison, Abigail

2011-01-01

An open problem in the field of computational neuroscience is how to link synaptic plasticity to system-level learning. A promising framework in this context is temporal-difference (TD) learning. Experimental evidence that supports the hypothesis that the mammalian brain performs temporal-difference learning includes the resemblance of the phasic activity of the midbrain dopaminergic neurons to the TD error and the discovery that cortico-striatal synaptic plasticity is modulated by dopamine. However, as the phasic dopaminergic signal does not reproduce all the properties of the theoretical TD error, it is unclear whether it is capable of driving behavior adaptation in complex tasks. Here, we present a spiking temporal-difference learning model based on the actor-critic architecture. The model dynamically generates a dopaminergic signal with realistic firing rates and exploits this signal to modulate the plasticity of synapses as a third factor. The predictions of our proposed plasticity dynamics are in good agreement with experimental results with respect to dopamine, pre- and post-synaptic activity. An analytical mapping from the parameters of our proposed plasticity dynamics to those of the classical discrete-time TD algorithm reveals that the biological constraints of the dopaminergic signal entail a modified TD algorithm with self-adapting learning parameters and an adapting offset. We show that the neuronal network is able to learn a task with sparse positive rewards as fast as the corresponding classical discrete-time TD algorithm. However, the performance of the neuronal network is impaired with respect to the traditional algorithm on a task with both positive and negative rewards and breaks down entirely on a task with purely negative rewards. Our model demonstrates that the asymmetry of a realistic dopaminergic signal enables TD learning when learning is driven by positive rewards but not when driven by negative rewards. PMID:21589888
Adaptive structured dictionary learning for image fusion based on group-sparse-representation

NASA Astrophysics Data System (ADS)

Yang, Jiajie; Sun, Bin; Luo, Chengwei; Wu, Yuzhong; Xu, Limei

2018-04-01

Dictionary learning is the key process of sparse representation which is one of the most widely used image representation theories in image fusion. The existing dictionary learning method does not use the group structure information and the sparse coefficients well. In this paper, we propose a new adaptive structured dictionary learning algorithm and a l1-norm maximum fusion rule that innovatively utilizes grouped sparse coefficients to merge the images. In the dictionary learning algorithm, we do not need prior knowledge about any group structure of the dictionary. By using the characteristics of the dictionary in expressing the signal, our algorithm can automatically find the desired potential structure information that hidden in the dictionary. The fusion rule takes the physical meaning of the group structure dictionary, and makes activity-level judgement on the structure information when the images are being merged. Therefore, the fused image can retain more significant information. Comparisons have been made with several state-of-the-art dictionary learning methods and fusion rules. The experimental results demonstrate that, the dictionary learning algorithm and the fusion rule both outperform others in terms of several objective evaluation metrics.
Periodic activation function and a modified learning algorithm for the multivalued neuron.

PubMed

Aizenberg, Igor

2010-12-01

In this paper, we consider a new periodic activation function for the multivalued neuron (MVN). The MVN is a neuron with complex-valued weights and inputs/output, which are located on the unit circle. Although the MVN outperforms many other neurons and MVN-based neural networks have shown their high potential, the MVN still has a limited capability of learning highly nonlinear functions. A periodic activation function, which is introduced in this paper, makes it possible to learn nonlinearly separable problems and non-threshold multiple-valued functions using a single multivalued neuron. We call this neuron a multivalued neuron with a periodic activation function (MVN-P). The MVN-Ps functionality is much higher than that of the regular MVN. The MVN-P is more efficient in solving various classification problems. A learning algorithm based on the error-correction rule for the MVN-P is also presented. It is shown that a single MVN-P can easily learn and solve those benchmark classification problems that were considered unsolvable using a single neuron. It is also shown that a universal binary neuron, which can learn nonlinearly separable Boolean functions, and a regular MVN are particular cases of the MVN-P.
Neuroprosthetic Decoder Training as Imitation Learning.

PubMed

Merel, Josh; Carlson, David; Paninski, Liam; Cunningham, John P

2016-05-01

Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user's intention is not directly observable, recent methods have demonstrated value in training the decoder against a surrogate for the user's intended movement. Here we show that training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available. Specifically, we describe how a generic imitation learning meta-algorithm, dataset aggregation (DAgger), can be adapted to train a generic brain-computer interface. By deriving existing learning algorithms for brain-computer interfaces in this framework, we provide a novel analysis of regret (an important metric of learning efficacy) for brain-computer interfaces. This analysis allows us to characterize the space of algorithmic variants and bounds on their regret rates. Existing approaches for decoder learning have been performed in the cursor control setting, but the available design principles for these decoders are such that it has been impossible to scale them to naturalistic settings. Leveraging our findings, we then offer an algorithm that combines imitation learning with optimal control, which should allow for training of arbitrary effectors for which optimal control can generate goal-oriented control. We demonstrate this novel and general BCI algorithm with simulated neuroprosthetic control of a 26 degree-of-freedom model of an arm, a sophisticated and realistic end effector.
Minimizing Statistical Bias with Queries.

DTIC Science & Technology

1995-09-14

method for optimally selecting these points would o er enormous savings in time and money. An active learning system will typically attempt to select data...research in active learning assumes that the sec- ond term of Equation 2 is approximately zero, that is, that the learner is unbiased. If this is the case...outperforms the variance- minimizing algorithm and random exploration. and e ective strategy for active learning . I have given empirical evidence that, with
Asynchronous Gossip for Averaging and Spectral Ranking

NASA Astrophysics Data System (ADS)

Borkar, Vivek S.; Makhijani, Rahul; Sundaresan, Rajesh

2014-08-01

We consider two variants of the classical gossip algorithm. The first variant is a version of asynchronous stochastic approximation. We highlight a fundamental difficulty associated with the classical asynchronous gossip scheme, viz., that it may not converge to a desired average, and suggest an alternative scheme based on reinforcement learning that has guaranteed convergence to the desired average. We then discuss a potential application to a wireless network setting with simultaneous link activation constraints. The second variant is a gossip algorithm for distributed computation of the Perron-Frobenius eigenvector of a nonnegative matrix. While the first variant draws upon a reinforcement learning algorithm for an average cost controlled Markov decision problem, the second variant draws upon a reinforcement learning algorithm for risk-sensitive control. We then discuss potential applications of the second variant to ranking schemes, reputation networks, and principal component analysis.
Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms

NASA Astrophysics Data System (ADS)

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.
Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms

DOE Office of Scientific and Technical Information (OSTI.GOV)

Nishizuka, N.; Kubo, Y.; Den, M.

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 neutralmore » 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.« less
Personalized Physical Activity Coaching: A Machine Learning Approach

PubMed Central

Dijkhuis, Talko B.; van Ittersum, Miriam W.; Velthuijsen, Hugo

2018-01-01

Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant’s progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time. PMID:29463052
Automated isotope identification algorithm using artificial neural networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kamuda, Mark; Stinnett, Jacob; Sullivan, Clair

There is a need to develop an algorithm that can determine the relative activities of radio-isotopes in a large dataset of low-resolution gamma-ray spectra that contains a mixture of many radio-isotopes. Low-resolution gamma-ray spectra that contain mixtures of radio-isotopes often exhibit feature over-lap, requiring algorithms that can analyze these features when overlap occurs. While machine learning and pattern recognition algorithms have shown promise for the problem of radio-isotope identification, their ability to identify and quantify mixtures of radio-isotopes has not been studied. Because machine learning algorithms use abstract features of the spectrum, such as the shape of overlapping peaks andmore » Compton continuum, they are a natural choice for analyzing radio-isotope mixtures. An artificial neural network (ANN) has be trained to calculate the relative activities of 32 radio-isotopes in a spectrum. Furthermore, the ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target radio-isotopes. In this paper we present our initial algorithms based on an ANN and evaluate them against a series measured and simulated spectra.« less
Automated isotope identification algorithm using artificial neural networks

DOE PAGES

Kamuda, Mark; Stinnett, Jacob; Sullivan, Clair

2017-04-12

There is a need to develop an algorithm that can determine the relative activities of radio-isotopes in a large dataset of low-resolution gamma-ray spectra that contains a mixture of many radio-isotopes. Low-resolution gamma-ray spectra that contain mixtures of radio-isotopes often exhibit feature over-lap, requiring algorithms that can analyze these features when overlap occurs. While machine learning and pattern recognition algorithms have shown promise for the problem of radio-isotope identification, their ability to identify and quantify mixtures of radio-isotopes has not been studied. Because machine learning algorithms use abstract features of the spectrum, such as the shape of overlapping peaks andmore » Compton continuum, they are a natural choice for analyzing radio-isotope mixtures. An artificial neural network (ANN) has be trained to calculate the relative activities of 32 radio-isotopes in a spectrum. Furthermore, the ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target radio-isotopes. In this paper we present our initial algorithms based on an ANN and evaluate them against a series measured and simulated spectra.« less
AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment

PubMed Central

2011-01-01

Background Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. Results This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. Conclusions AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of highly accurate QSAR models fulfilling regulatory requirements. PMID:21798025
AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment.

PubMed

Stålring, Jonna C; Carlsson, Lars A; Almeida, Pedro; Boyer, Scott

2011-07-28

Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of highly accurate QSAR models fulfilling regulatory requirements.
SOLAR FLARE PREDICTION USING SDO/HMI VECTOR MAGNETIC FIELD DATA WITH A MACHINE-LEARNING ALGORITHM

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bobra, M. G.; Couvidat, S., E-mail: couvidat@stanford.edu

2015-01-10

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 databasemore » 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.« less
Flow Navigation by Smart Microswimmers via Reinforcement Learning

NASA Astrophysics Data System (ADS)

Colabrese, Simona; Gustavsson, Kristian; Celani, Antonio; Biferale, Luca

2017-04-01

Smart active particles can acquire some limited knowledge of the fluid environment from simple mechanical cues and exert a control on their preferred steering direction. Their goal is to learn the best way to navigate by exploiting the underlying flow whenever possible. As an example, we focus our attention on smart gravitactic swimmers. These are active particles whose task is to reach the highest altitude within some time horizon, given the constraints enforced by fluid mechanics. By means of numerical experiments, we show that swimmers indeed learn nearly optimal strategies just by experience. A reinforcement learning algorithm allows particles to learn effective strategies even in difficult situations when, in the absence of control, they would end up being trapped by flow structures. These strategies are highly nontrivial and cannot be easily guessed in advance. This Letter illustrates the potential of reinforcement learning algorithms to model adaptive behavior in complex flows and paves the way towards the engineering of smart microswimmers that solve difficult navigation problems.
Fall detection algorithms for real-world falls harvested from lumbar sensors in the elderly population: a machine learning approach.

PubMed

Bourke, Alan K; Klenk, Jochen; Schwickert, Lars; Aminian, Kamiar; Ihlen, Espen A F; Mellone, Sabato; Helbostad, Jorunn L; Chiari, Lorenzo; Becker, Clemens

2016-08-01

Automatic fall detection will promote independent living and reduce the consequences of falls in the elderly by ensuring people can confidently live safely at home for linger. In laboratory studies inertial sensor technology has been shown capable of distinguishing falls from normal activities. However less than 7% of fall-detection algorithm studies have used fall data recorded from elderly people in real life. The FARSEEING project has compiled a database of real life falls from elderly people, to gain new knowledge about fall events and to develop fall detection algorithms to combat the problems associated with falls. We have extracted 12 different kinematic, temporal and kinetic related features from a data-set of 89 real-world falls and 368 activities of daily living. Using the extracted features we applied machine learning techniques and produced a selection of algorithms based on different feature combinations. The best algorithm employs 10 different features and produced a sensitivity of 0.88 and a specificity of 0.87 in classifying falls correctly. This algorithm can be used distinguish real-world falls from normal activities of daily living in a sensor consisting of a tri-axial accelerometer and tri-axial gyroscope located at L5.

Neuroprosthetic Decoder Training as Imitation Learning

PubMed Central

Merel, Josh; Paninski, Liam; Cunningham, John P.

2016-01-01

Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user’s intention is not directly observable, recent methods have demonstrated value in training the decoder against a surrogate for the user’s intended movement. Here we show that training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available. Specifically, we describe how a generic imitation learning meta-algorithm, dataset aggregation (DAgger), can be adapted to train a generic brain-computer interface. By deriving existing learning algorithms for brain-computer interfaces in this framework, we provide a novel analysis of regret (an important metric of learning efficacy) for brain-computer interfaces. This analysis allows us to characterize the space of algorithmic variants and bounds on their regret rates. Existing approaches for decoder learning have been performed in the cursor control setting, but the available design principles for these decoders are such that it has been impossible to scale them to naturalistic settings. Leveraging our findings, we then offer an algorithm that combines imitation learning with optimal control, which should allow for training of arbitrary effectors for which optimal control can generate goal-oriented control. We demonstrate this novel and general BCI algorithm with simulated neuroprosthetic control of a 26 degree-of-freedom model of an arm, a sophisticated and realistic end effector. PMID:27191387
Using machine learning algorithms to guide rehabilitation planning for home care clients.

PubMed

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.
Beyond the "c" and the "x": Learning with algorithms in massive open online courses (MOOCs)

NASA Astrophysics Data System (ADS)

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 discourse around the use of algorithms in MOOC education and beyond.
A Random Forest-based ensemble method for activity recognition.

PubMed

Feng, Zengtao; Mo, Lingfei; Li, Meng

2015-01-01

This paper presents a multi-sensor ensemble approach to human physical activity (PA) recognition, using random forest. We designed an ensemble learning algorithm, which integrates several independent Random Forest classifiers based on different sensor feature sets to build a more stable, more accurate and faster classifier for human activity recognition. To evaluate the algorithm, PA data collected from the PAMAP (Physical Activity Monitoring for Aging People), which is a standard, publicly available database, was utilized to train and test. The experimental results show that the algorithm is able to correctly recognize 19 PA types with an accuracy of 93.44%, while the training is faster than others. The ensemble classifier system based on the RF (Random Forest) algorithm can achieve high recognition accuracy and fast calculation.
Active Semi-Supervised Community Detection Based on Must-Link and Cannot-Link Constraints

PubMed Central

Cheng, Jianjun; Leng, Mingwei; Li, Longjie; Zhou, Hanhai; Chen, Xiaoyun

2014-01-01

Community structure detection is of great importance because it can help in discovering the relationship between the function and the topology structure of a network. Many community detection algorithms have been proposed, but how to incorporate the prior knowledge in the detection process remains a challenging problem. In this paper, we propose a semi-supervised community detection algorithm, which makes full utilization of the must-link and cannot-link constraints to guide the process of community detection and thereby extracts high-quality community structures from networks. To acquire the high-quality must-link and cannot-link constraints, we also propose a semi-supervised component generation algorithm based on active learning, which actively selects nodes with maximum utility for the proposed semi-supervised community detection algorithm step by step, and then generates the must-link and cannot-link constraints by accessing a noiseless oracle. Extensive experiments were carried out, and the experimental results show that the introduction of active learning into the problem of community detection makes a success. Our proposed method can extract high-quality community structures from networks, and significantly outperforms other comparison methods. PMID:25329660
SortNet: learning to rank by a neural preference function.

PubMed

Rigutini, Leonardo; Papini, Tiziano; Maggini, Marco; Scarselli, Franco

2011-09-01

Relevance ranking consists in sorting a set of objects with respect to a given criterion. However, in personalized retrieval systems, the relevance criteria may usually vary among different users and may not be predefined. In this case, ranking algorithms that adapt their behavior from users' feedbacks must be devised. Two main approaches are proposed in the literature for learning to rank: the use of a scoring function, learned by examples, that evaluates a feature-based representation of each object yielding an absolute relevance score, a pairwise approach, where a preference function is learned to determine the object that has to be ranked first in a given pair. In this paper, we present a preference learning method for learning to rank. A neural network, the comparative neural network (CmpNN), is trained from examples to approximate the comparison function for a pair of objects. The CmpNN adopts a particular architecture designed to implement the symmetries naturally present in a preference function. The learned preference function can be embedded as the comparator into a classical sorting algorithm to provide a global ranking of a set of objects. To improve the ranking performances, an active-learning procedure is devised, that aims at selecting the most informative patterns in the training set. The proposed algorithm is evaluated on the LETOR dataset showing promising performances in comparison with other state-of-the-art algorithms.
Adaptive Batch Mode Active Learning.

PubMed

Chakraborty, Shayok; Balasubramanian, Vineeth; Panchanathan, Sethuraman

2015-08-01

Active learning techniques have gained popularity to reduce human effort in labeling data instances for inducing a classifier. When faced with large amounts of unlabeled data, such algorithms automatically identify the exemplar and representative instances to be selected for manual annotation. More recently, there have been attempts toward a batch mode form of active learning, where a batch of data points is simultaneously selected from an unlabeled set. Real-world applications require adaptive approaches for batch selection in active learning, depending on the complexity of the data stream in question. However, the existing work in this field has primarily focused on static or heuristic batch size selection. In this paper, we propose two novel optimization-based frameworks for adaptive batch mode active learning (BMAL), where the batch size as well as the selection criteria are combined in a single formulation. We exploit gradient-descent-based optimization strategies as well as properties of submodular functions to derive the adaptive BMAL algorithms. The solution procedures have the same computational complexity as existing state-of-the-art static BMAL techniques. Our empirical results on the widely used VidTIMIT and the mobile biometric (MOBIO) data sets portray the efficacy of the proposed frameworks and also certify the potential of these approaches in being used for real-world biometric recognition applications.
Simultaneous vibration control and energy harvesting using actor-critic based reinforcement learning

NASA Astrophysics Data System (ADS)

Loong, Cheng Ning; Chang, C. C.; Dimitrakopoulos, Elias G.

2018-03-01

Mitigating excessive vibration of civil engineering structures using various types of devices has been a conspicuous research topic in the past few decades. Some devices, such as electromagnetic transducers, which have a capability of exerting control forces while simultaneously harvesting energy, have been proposed recently. These devices make possible a self-regenerative system that can semi-actively mitigate structural vibration without the need of external energy. Integrating mechanical, electrical components, and control algorithms, these devices open up a new research domain that needs to be addressed. In this study, the feasibility of using an actor-critic based reinforcement learning control algorithm for simultaneous vibration control and energy harvesting for a civil engineering structure is investigated. The actor-critic based reinforcement learning control algorithm is a real-time, model-free adaptive technique that can adjust the controller parameters based on observations and reward signals without knowing the system characteristics. It is suitable for the control of a partially known nonlinear system with uncertain parameters. The feasibility of implementing this algorithm on a building structure equipped with an electromagnetic damper will be investigated in this study. Issues related to the modelling of learning algorithm, initialization and convergence will be presented and discussed.
ANALYTiC: An Active Learning System for Trajectory Classification.

PubMed

Soares Junior, Amilcar; Renso, Chiara; Matwin, Stan

2017-01-01

The increasing availability and use of positioning devices has resulted in large volumes of trajectory data. However, semantic annotations for such data are typically added by domain experts, which is a time-consuming task. Machine-learning algorithms can help infer semantic annotations from trajectory data by learning from sets of labeled data. Specifically, active learning approaches can minimize the set of trajectories to be annotated while preserving good performance measures. The ANALYTiC web-based interactive tool visually guides users through this annotation process.
Decoding the encoding of functional brain networks: An fMRI classification comparison of non-negative matrix factorization (NMF), independent component analysis (ICA), and sparse coding algorithms.

PubMed

Xie, Jianwen; Douglas, Pamela K; Wu, Ying Nian; Brody, Arthur L; Anderson, Ariana E

2017-04-15

Brain networks in fMRI are typically identified using spatial independent component analysis (ICA), yet other mathematical constraints provide alternate biologically-plausible frameworks for generating brain networks. Non-negative matrix factorization (NMF) would suppress negative BOLD signal by enforcing positivity. Spatial sparse coding algorithms (L1 Regularized Learning and K-SVD) would impose local specialization and a discouragement of multitasking, where the total observed activity in a single voxel originates from a restricted number of possible brain networks. The assumptions of independence, positivity, and sparsity to encode task-related brain networks are compared; the resulting brain networks within scan for different constraints are used as basis functions to encode observed functional activity. These encodings are then decoded using machine learning, by using the time series weights to predict within scan whether a subject is viewing a video, listening to an audio cue, or at rest, in 304 fMRI scans from 51 subjects. The sparse coding algorithm of L1 Regularized Learning outperformed 4 variations of ICA (p<0.001) for predicting the task being performed within each scan using artifact-cleaned components. The NMF algorithms, which suppressed negative BOLD signal, had the poorest accuracy compared to the ICA and sparse coding algorithms. Holding constant the effect of the extraction algorithm, encodings using sparser spatial networks (containing more zero-valued voxels) had higher classification accuracy (p<0.001). Lower classification accuracy occurred when the extracted spatial maps contained more CSF regions (p<0.001). The success of sparse coding algorithms suggests that algorithms which enforce sparsity, discourage multitasking, and promote local specialization may capture better the underlying source processes than those which allow inexhaustible local processes such as ICA. Negative BOLD signal may capture task-related activations. Copyright © 2017 Elsevier B.V. All rights reserved.
Virtual screening by a new Clustering-based Weighted Similarity Extreme Learning Machine approach

PubMed Central

Kudisthalert, Wasu

2018-01-01

Machine learning techniques are becoming popular in virtual screening tasks. One of the powerful machine learning algorithms is Extreme Learning Machine (ELM) which has been applied to many applications and has recently been applied to virtual screening. We propose the Weighted Similarity ELM (WS-ELM) which is based on a single layer feed-forward neural network in a conjunction of 16 different similarity coefficients as activation function in the hidden layer. It is known that the performance of conventional ELM is not robust due to random weight selection in the hidden layer. Thus, we propose a Clustering-based WS-ELM (CWS-ELM) that deterministically assigns weights by utilising clustering algorithms i.e. k-means clustering and support vector clustering. The experiments were conducted on one of the most challenging datasets–Maximum Unbiased Validation Dataset–which contains 17 activity classes carefully selected from PubChem. The proposed algorithms were then compared with other machine learning techniques such as support vector machine, random forest, and similarity searching. The results show that CWS-ELM in conjunction with support vector clustering yields the best performance when utilised together with Sokal/Sneath(1) coefficient. Furthermore, ECFP_6 fingerprint presents the best results in our framework compared to the other types of fingerprints, namely ECFP_4, FCFP_4, and FCFP_6. PMID:29652912
Active flow separation control by a position-based iterative learning control algorithm with experimental validation

NASA Astrophysics Data System (ADS)

Cai, Zhonglun; Chen, Peng; Angland, David; Zhang, Xin

2014-03-01

A novel iterative learning control (ILC) algorithm was developed and applied to an active flow control problem. The technique uses pulsed air jets to delay flow separation on a two-element high-lift wing. The ILC algorithm uses position-based pressure measurements to update the actuation. The method was experimentally tested on a wing model in a 0.9 m × 0.6 m low-speed wind tunnel at the University of Southampton. Compressed air and fast switching solenoid valves were used as actuators to excite the flow, and the pressure distribution around the chord of the wing was measured as a feedback control signal for the ILC controller. Experimental results showed that the actuation was able to delay the separation and increase the lift by approximately 10%-15%. By using the ILC algorithm, the controller was able to find the optimum control input and maintain the improvement despite sudden changes of the separation position.
Active Learning by Querying Informative and Representative Examples.

PubMed

Huang, Sheng-Jun; Jin, Rong; Zhou, Zhi-Hua

2014-10-01

Active learning reduces the labeling cost by iteratively selecting the most valuable data to query their labels. It has attracted a lot of interests given the abundance of unlabeled data and the high cost of labeling. Most active learning approaches select either informative or representative unlabeled instances to query their labels, which could significantly limit their performance. Although several active learning algorithms were proposed to combine the two query selection criteria, they are usually ad hoc in finding unlabeled instances that are both informative and representative. We address this limitation by developing a principled approach, termed QUIRE, based on the min-max view of active learning. The proposed approach provides a systematic way for measuring and combining the informativeness and representativeness of an unlabeled instance. Further, by incorporating the correlation among labels, we extend the QUIRE approach to multi-label learning by actively querying instance-label pairs. Extensive experimental results show that the proposed QUIRE approach outperforms several state-of-the-art active learning approaches in both single-label and multi-label learning.
Bidirectional Active Learning: A Two-Way Exploration Into Unlabeled and Labeled Data Set.

PubMed

Zhang, Xiao-Yu; Wang, Shupeng; Yun, Xiaochun

2015-12-01

In practical machine learning applications, human instruction is indispensable for model construction. To utilize the precious labeling effort effectively, active learning queries the user with selective sampling in an interactive way. Traditional active learning techniques merely focus on the unlabeled data set under a unidirectional exploration framework and suffer from model deterioration in the presence of noise. To address this problem, this paper proposes a novel bidirectional active learning algorithm that explores into both unlabeled and labeled data sets simultaneously in a two-way process. For the acquisition of new knowledge, forward learning queries the most informative instances from unlabeled data set. For the introspection of learned knowledge, backward learning detects the most suspiciously unreliable instances within the labeled data set. Under the two-way exploration framework, the generalization ability of the learning model can be greatly improved, which is demonstrated by the encouraging experimental results.
The algorithm for duration acceleration of repetitive projects considering the learning effect

NASA Astrophysics Data System (ADS)

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.
Active Learning with Irrelevant Examples

NASA Technical Reports Server (NTRS)

Mazzoni, Dominic; Wagstaff, Kiri L.; Burl, Michael

2006-01-01

Active learning algorithms attempt to accelerate the learning process by requesting labels for the most informative items first. In real-world problems, however, there may exist unlabeled items that are irrelevant to the user's classification goals. Queries about these points slow down learning because they provide no information about the problem of interest. We have observed that when irrelevant items are present, active learning can perform worse than random selection, requiring more time (queries) to achieve the same level of accuracy. Therefore, we propose a novel approach, Relevance Bias, in which the active learner combines its default selection heuristic with the output of a simultaneously trained relevance classifier to favor items that are likely to be both informative and relevant. In our experiments on a real-world problem and two benchmark datasets, the Relevance Bias approach significantly improved the learning rate of three different active learning approaches.
Using Machine Learning for Advanced Anomaly Detection and Classification

NASA Astrophysics Data System (ADS)

Lane, B.; Poole, M.; Camp, M.; Murray-Krezan, J.

2016-09-01

Machine Learning (ML) techniques have successfully been used in a wide variety of applications to automatically detect and potentially classify changes in activity, or a series of activities by utilizing large amounts data, sometimes even seemingly-unrelated data. The amount of data being collected, processed, and stored in the Space Situational Awareness (SSA) domain has grown at an exponential rate and is now better suited for ML. This paper describes development of advanced algorithms to deliver significant improvements in characterization of deep space objects and indication and warning (I&W) using a global network of telescopes that are collecting photometric data on a multitude of space-based objects. The Phase II Air Force Research Laboratory (AFRL) Small Business Innovative Research (SBIR) project Autonomous Characterization Algorithms for Change Detection and Characterization (ACDC), contracted to ExoAnalytic Solutions Inc. is providing the ability to detect and identify photometric signature changes due to potential space object changes (e.g. stability, tumble rate, aspect ratio), and correlate observed changes to potential behavioral changes using a variety of techniques, including supervised learning. Furthermore, these algorithms run in real-time on data being collected and processed by the ExoAnalytic Space Operations Center (EspOC), providing timely alerts and warnings while dynamically creating collection requirements to the EspOC for the algorithms that generate higher fidelity I&W. This paper will discuss the recently implemented ACDC algorithms, including the general design approach and results to date. The usage of supervised algorithms, such as Support Vector Machines, Neural Networks, k-Nearest Neighbors, etc., and unsupervised algorithms, for example k-means, Principle Component Analysis, Hierarchical Clustering, etc., and the implementations of these algorithms is explored. Results of applying these algorithms to EspOC data both in an off-line "pattern of life" analysis as well as using the algorithms on-line in real-time, meaning as data is collected, will be presented. Finally, future work in applying ML for SSA will be discussed.
Learning polynomial feedforward neural networks by genetic programming and backpropagation.

PubMed

Nikolaev, N Y; Iba, H

2003-01-01

This paper presents an approach to learning polynomial feedforward neural networks (PFNNs). The approach suggests, first, finding the polynomial network structure by means of a population-based search technique relying on the genetic programming paradigm, and second, further adjustment of the best discovered network weights by an especially derived backpropagation algorithm for higher order networks with polynomial activation functions. These two stages of the PFNN learning process enable us to identify networks with good training as well as generalization performance. Empirical results show that this approach finds PFNN which outperform considerably some previous constructive polynomial network algorithms on processing benchmark time series.
Automated activity-aware prompting for activity initiation.

PubMed

Holder, Lawrence B; Cook, Diane J

2013-01-01

Performing daily activities without assistance is important to maintaining an independent functional lifestyle. As a result, automated activity prompting systems can potentially extend the period of time that adults can age in place. In this paper we introduce AP, an algorithm to automate activity prompting based on smart home technology. AP learns prompt rules based on the time when activities are typically performed as well as the relationship between activities that normally occur in a sequence. We evaluate the AP algorithm based on smart home datasets and demonstrate its ability to operate within a physical smart environment.
Learning Multirobot Hose Transportation and Deployment by Distributed Round-Robin Q-Learning.

PubMed

Fernandez-Gauna, Borja; Etxeberria-Agiriano, Ismael; Graña, Manuel

2015-01-01

Multi-Agent Reinforcement Learning (MARL) algorithms face two main difficulties: the curse of dimensionality, and environment non-stationarity due to the independent learning processes carried out by the agents concurrently. In this paper we formalize and prove the convergence of a Distributed Round Robin Q-learning (D-RR-QL) algorithm for cooperative systems. The computational complexity of this algorithm increases linearly with the number of agents. Moreover, it eliminates environment non sta tionarity by carrying a round-robin scheduling of the action selection and execution. That this learning scheme allows the implementation of Modular State-Action Vetoes (MSAV) in cooperative multi-agent systems, which speeds up learning convergence in over-constrained systems by vetoing state-action pairs which lead to undesired termination states (UTS) in the relevant state-action subspace. Each agent's local state-action value function learning is an independent process, including the MSAV policies. Coordination of locally optimal policies to obtain the global optimal joint policy is achieved by a greedy selection procedure using message passing. We show that D-RR-QL improves over state-of-the-art approaches, such as Distributed Q-Learning, Team Q-Learning and Coordinated Reinforcement Learning in a paradigmatic Linked Multi-Component Robotic System (L-MCRS) control problem: the hose transportation task. L-MCRS are over-constrained systems with many UTS induced by the interaction of the passive linking element and the active mobile robots.

Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning

NASA Astrophysics Data System (ADS)

Debats, Stephanie Renee

Smallholder farms dominate in many parts of the world, including Sub-Saharan Africa. These systems are characterized by small, heterogeneous, and often indistinct field patterns, requiring a specialized methodology to map agricultural landcover. In this thesis, we developed a benchmark labeled data set of high-resolution satellite imagery of agricultural fields in South Africa. We presented a new approach to mapping agricultural fields, based on efficient extraction of a vast set of simple, highly correlated, and interdependent features, followed by a random forest classifier. The algorithm achieved similar high performance across agricultural types, including spectrally indistinct smallholder fields, and demonstrated the ability to generalize across large geographic areas. In sensitivity analyses, we determined multi-temporal images provided greater performance gains than the addition of multi-spectral bands. We also demonstrated how active learning can be incorporated in the algorithm to create smaller, more efficient training data sets, which reduced computational resources, minimized the need for humans to hand-label data, and boosted performance. We designed a patch-based uncertainty metric to drive the active learning framework, based on the regular grid of a crowdsourcing platform, and demonstrated how subject matter experts can be replaced with fleets of crowdsourcing workers. Our active learning algorithm achieved similar performance as an algorithm trained with randomly selected data, but with 62% less data samples. This thesis furthers the goal of providing accurate agricultural landcover maps, at a scale that is relevant for the dominant smallholder class. Accurate maps are crucial for monitoring and promoting agricultural production. Furthermore, improved agricultural landcover maps will aid a host of other applications, including landcover change assessments, cadastral surveys to strengthen smallholder land rights, and constraints for crop modeling and famine prediction.
Learning Setting-Generalized Activity Models for Smart Spaces

PubMed Central

Cook, Diane J.

2011-01-01

The data mining and pervasive computing technologies found in smart homes offer unprecedented opportunities for providing context-aware services, including health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to provide these services, smart environment algorithms need to recognize and track activities that people normally perform as part of their daily routines. However, activity recognition has typically involved gathering and labeling large amounts of data in each setting to learn a model for activities in that setting. We hypothesize that generalized models can be learned for common activities that span multiple environment settings and resident types. We describe our approach to learning these models and demonstrate the approach using eleven CASAS datasets collected in seven environments. PMID:21461133
Oscillatory neural network for pattern recognition: trajectory based classification and supervised learning.

PubMed

Miller, Vonda H; Jansen, Ben H

2008-12-01

Computer algorithms that match human performance in recognizing written text or spoken conversation remain elusive. The reasons why the human brain far exceeds any existing recognition scheme to date in the ability to generalize and to extract invariant characteristics relevant to category matching are not clear. However, it has been postulated that the dynamic distribution of brain activity (spatiotemporal activation patterns) is the mechanism by which stimuli are encoded and matched to categories. This research focuses on supervised learning using a trajectory based distance metric for category discrimination in an oscillatory neural network model. Classification is accomplished using a trajectory based distance metric. Since the distance metric is differentiable, a supervised learning algorithm based on gradient descent is demonstrated. Classification of spatiotemporal frequency transitions and their relation to a priori assessed categories is shown along with the improved classification results after supervised training. The results indicate that this spatiotemporal representation of stimuli and the associated distance metric is useful for simple pattern recognition tasks and that supervised learning improves classification results.
A new simple /spl infin/OH neuron model as a biologically plausible principal component analyzer.

PubMed

Jankovic, M V

2003-01-01

A new approach to unsupervised learning in a single-layer neural network is discussed. An algorithm for unsupervised learning based upon the Hebbian learning rule is presented. A simple neuron model is analyzed. A dynamic neural model, which contains both feed-forward and feedback connections between the input and the output, has been adopted. The, proposed learning algorithm could be more correctly named self-supervised rather than unsupervised. The solution proposed here is a modified Hebbian rule, in which the modification of the synaptic strength is proportional not to pre- and postsynaptic activity, but instead to the presynaptic and averaged value of postsynaptic activity. It is shown that the model neuron tends to extract the principal component from a stationary input vector sequence. Usually accepted additional decaying terms for the stabilization of the original Hebbian rule are avoided. Implementation of the basic Hebbian scheme would not lead to unrealistic growth of the synaptic strengths, thanks to the adopted network structure.
Evaluation of multilayer perceptron algorithms for an analysis of network flow data

NASA Astrophysics Data System (ADS)

Bieniasz, Jedrzej; Rawski, Mariusz; Skowron, Krzysztof; Trzepiński, Mateusz

2016-09-01

The volume of exchanged information through IP networks is larger than ever and still growing. It creates a space for both benign and malicious activities. The second one raises awareness on security network devices, as well as network infrastructure and a system as a whole. One of the basic tools to prevent cyber attacks is Network Instrusion Detection System (NIDS). NIDS could be realized as a signature-based detector or an anomaly-based one. In the last few years the emphasis has been placed on the latter type, because of the possibility of applying smart and intelligent solutions. An ideal NIDS of next generation should be composed of self-learning algorithms that could react on known and unknown malicious network activities respectively. In this paper we evaluated a machine learning approach for detection of anomalies in IP network data represented as NetFlow records. We considered Multilayer Perceptron (MLP) as the classifier and we used two types of learning algorithms - Backpropagation (BP) and Particle Swarm Optimization (PSO). This paper includes a comprehensive survey on determining the most optimal MLP learning algorithm for the classification problem in application to network flow data. The performance, training time and convergence of BP and PSO methods were compared. The results show that PSO algorithm implemented by the authors outperformed other solutions if accuracy of classifications is considered. The major disadvantage of PSO is training time, which could be not acceptable for larger data sets or in real network applications. At the end we compared some key findings with the results from the other papers to show that in all cases results from this study outperformed them.
Automated Detection of Epileptic Biomarkers in Resting-State Interictal MEG Data

PubMed Central

Soriano, Miguel C.; Niso, Guiomar; Clements, Jillian; Ortín, Silvia; Carrasco, Sira; Gudín, María; Mirasso, Claudio R.; Pereda, Ernesto

2017-01-01

Certain differences between brain networks of healthy and epilectic subjects have been reported even during the interictal activity, in which no epileptic seizures occur. Here, magnetoencephalography (MEG) data recorded in the resting state is used to discriminate between healthy subjects and patients with either idiopathic generalized epilepsy or frontal focal epilepsy. Signal features extracted from interictal periods without any epileptiform activity are used to train a machine learning algorithm to draw a diagnosis. This is potentially relevant to patients without frequent or easily detectable spikes. To analyze the data, we use an up-to-date machine learning algorithm and explore the benefits of including different features obtained from the MEG data as inputs to the algorithm. We find that the relative power spectral density of the MEG time-series is sufficient to distinguish between healthy and epileptic subjects with a high prediction accuracy. We also find that a combination of features such as the phase-locked value and the relative power spectral density allow to discriminate generalized and focal epilepsy, when these features are calculated over a filtered version of the signals in certain frequency bands. Machine learning algorithms are currently being applied to the analysis and classification of brain signals. It is, however, less evident to identify the proper features of these signals that are prone to be used in such machine learning algorithms. Here, we evaluate the influence of the input feature selection on a clinical scenario to distinguish between healthy and epileptic subjects. Our results indicate that such distinction is possible with a high accuracy (86%), allowing the discrimination between idiopathic generalized and frontal focal epilepsy types. PMID:28713260
Efficient Grammar Induction Algorithm with Parse Forests from Real Corpora

NASA Astrophysics Data System (ADS)

Kurihara, Kenichi; Kameya, Yoshitaka; Sato, Taisuke

The task of inducing grammar structures has received a great deal of attention. The reasons why researchers have studied are different; to use grammar induction as the first stage in building large treebanks or to make up better language models. However, grammar induction has inherent computational complexity. To overcome it, some grammar induction algorithms add new production rules incrementally. They refine the grammar while keeping their computational complexity low. In this paper, we propose a new efficient grammar induction algorithm. Although our algorithm is similar to algorithms which learn a grammar incrementally, our algorithm uses the graphical EM algorithm instead of the Inside-Outside algorithm. We report results of learning experiments in terms of learning speeds. The results show that our algorithm learns a grammar in constant time regardless of the size of the grammar. Since our algorithm decreases syntactic ambiguities in each step, our algorithm reduces required time for learning. This constant-time learning considerably affects learning time for larger grammars. We also reports results of evaluation of criteria to choose nonterminals. Our algorithm refines a grammar based on a nonterminal in each step. Since there can be several criteria to decide which nonterminal is the best, we evaluate them by learning experiments.
Perceptually Guided Photo Retargeting.

PubMed

Xia, Yingjie; Zhang, Luming; Hong, Richang; Nie, Liqiang; Yan, Yan; Shao, Ling

2016-04-22

We propose perceptually guided photo retargeting, which shrinks a photo by simulating a human's process of sequentially perceiving visually/semantically important regions in a photo. In particular, we first project the local features (graphlets in this paper) onto a semantic space, wherein visual cues such as global spatial layout and rough geometric context are exploited. Thereafter, a sparsity-constrained learning algorithm is derived to select semantically representative graphlets of a photo, and the selecting process can be interpreted by a path which simulates how a human actively perceives semantics in a photo. Furthermore, we learn the prior distribution of such active graphlet paths (AGPs) from training photos that are marked as esthetically pleasing by multiple users. The learned priors enforce the corresponding AGP of a retargeted photo to be maximally similar to those from the training photos. On top of the retargeting model, we further design an online learning scheme to incrementally update the model with new photos that are esthetically pleasing. The online update module makes the algorithm less dependent on the number and contents of the initial training data. Experimental results show that: 1) the proposed AGP is over 90% consistent with human gaze shifting path, as verified by the eye-tracking data, and 2) the retargeting algorithm outperforms its competitors significantly, as AGP is more indicative of photo esthetics than conventional saliency maps.
Efficient model learning methods for actor-critic control.

PubMed

Grondman, Ivo; Vaandrager, Maarten; Buşoniu, Lucian; Babuska, Robert; Schuitema, Erik

2012-06-01

We propose two new actor-critic algorithms for reinforcement learning. Both algorithms use local linear regression (LLR) to learn approximations of the functions involved. A crucial feature of the algorithms is that they also learn a process model, and this, in combination with LLR, provides an efficient policy update for faster learning. The first algorithm uses a novel model-based update rule for the actor parameters. The second algorithm does not use an explicit actor but learns a reference model which represents a desired behavior, from which desired control actions can be calculated using the inverse of the learned process model. The two novel methods and a standard actor-critic algorithm are applied to the pendulum swing-up problem, in which the novel methods achieve faster learning than the standard algorithm.
A relational learning approach to Structure-Activity Relationships in drug design toxicity studies.

PubMed

Camacho, Rui; Pereira, Max; Costa, Vítor Santos; Fonseca, Nuno A; Adriano, Carlos; Simões, Carlos J V; Brito, Rui M M

2011-09-16

It has been recognized that the development of new therapeutic drugs is a complex and expensive process. A large number of factors affect the activity in vivo of putative candidate molecules and the propensity for causing adverse and toxic effects is recognized as one of the major hurdles behind the current "target-rich, lead-poor" scenario. Structure-Activity Relationship (SAR) studies, using relational Machine Learning (ML) algorithms, have already been shown to be very useful in the complex process of rational drug design. Despite the ML successes, human expertise is still of the utmost importance in the drug development process. An iterative process and tight integration between the models developed by ML algorithms and the know-how of medicinal chemistry experts would be a very useful symbiotic approach. In this paper we describe a software tool that achieves that goal--iLogCHEM. The tool allows the use of Relational Learners in the task of identifying molecules or molecular fragments with potential to produce toxic effects, and thus help in stream-lining drug design in silico. It also allows the expert to guide the search for useful molecules without the need to know the details of the algorithms used. The models produced by the algorithms may be visualized using a graphical interface, that is of common use amongst researchers in structural biology and medicinal chemistry. The graphical interface enables the expert to provide feedback to the learning system. The developed tool has also facilities to handle the similarity bias typical of large chemical databases. For that purpose the user can filter out similar compounds when assembling a data set. Additionally, we propose ways of providing background knowledge for Relational Learners using the results of Graph Mining algorithms. Copyright 2011 The Author(s). Published by Journal of Integrative Bioinformatics.
Incorporating Duration Information in Activity Recognition

NASA Astrophysics Data System (ADS)

Chaurasia, Priyanka; Scotney, Bryan; McClean, Sally; Zhang, Shuai; Nugent, Chris

Activity recognition has become a key issue in smart home environments. The problem involves learning high level activities from low level sensor data. Activity recognition can depend on several variables; one such variable is duration of engagement with sensorised items or duration of intervals between sensor activations that can provide useful information about personal behaviour. In this paper a probabilistic learning algorithm is proposed that incorporates episode, time and duration information to determine inhabitant identity and the activity being undertaken from low level sensor data. Our results verify that incorporating duration information consistently improves the accuracy.
Shape-driven 3D segmentation using spherical wavelets.

PubMed

Nain, Delphine; Haker, Steven; Bobick, Aaron; Tannenbaum, Allen

2006-01-01

This paper presents a novel active surface segmentation algorithm using a multiscale shape representation and prior. We define a parametric model of a surface using spherical wavelet functions and learn a prior probability distribution over the wavelet coefficients to model shape variations at different scales and spatial locations in a training set. Based on this representation, we derive a parametric active surface evolution using the multiscale prior coefficients as parameters for our optimization procedure to naturally include the prior in the segmentation framework. Additionally, the optimization method can be applied in a coarse-to-fine manner. We apply our algorithm to the segmentation of brain caudate nucleus, of interest in the study of schizophrenia. Our validation shows our algorithm is computationally efficient and outperforms the Active Shape Model algorithm by capturing finer shape details.
Active learning methods for interactive image retrieval.

PubMed

Gosselin, Philippe Henri; Cord, Matthieu

2008-07-01

Active learning methods have been considered with increased interest in the statistical learning community. Initially developed within a classification framework, a lot of extensions are now being proposed to handle multimedia applications. This paper provides algorithms within a statistical framework to extend active learning for online content-based image retrieval (CBIR). The classification framework is presented with experiments to compare several powerful classification techniques in this information retrieval context. Focusing on interactive methods, active learning strategy is then described. The limitations of this approach for CBIR are emphasized before presenting our new active selection process RETIN. First, as any active method is sensitive to the boundary estimation between classes, the RETIN strategy carries out a boundary correction to make the retrieval process more robust. Second, the criterion of generalization error to optimize the active learning selection is modified to better represent the CBIR objective of database ranking. Third, a batch processing of images is proposed. Our strategy leads to a fast and efficient active learning scheme to retrieve sets of online images (query concept). Experiments on large databases show that the RETIN method performs well in comparison to several other active strategies.
Classifying BCI signals from novice users with extreme learning machine

NASA Astrophysics Data System (ADS)

Rodríguez-Bermúdez, Germán; Bueno-Crespo, Andrés; José Martinez-Albaladejo, F.

2017-07-01

Brain computer interface (BCI) allows to control external devices only with the electrical activity of the brain. In order to improve the system, several approaches have been proposed. However it is usual to test algorithms with standard BCI signals from experts users or from repositories available on Internet. In this work, extreme learning machine (ELM) has been tested with signals from 5 novel users to compare with standard classification algorithms. Experimental results show that ELM is a suitable method to classify electroencephalogram signals from novice users.
An E-Learning Environment for Algorithmic: Toward an Active Construction of Skills

ERIC Educational Resources Information Center

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…
Predicting Student Grades in Learning Management Systems with Multiple Instance Genetic Programming

ERIC Educational Resources Information Center

Zafra, Amelia; Ventura, Sebastian

2009-01-01

The ability to predict a student's performance could be useful in a great number of different ways associated with university-level learning. In this paper, a grammar guided genetic programming algorithm, G3P-MI, has been applied to predict if the student will fail or pass a certain course and identifies activities to promote learning in a…
Extreme Trust Region Policy Optimization for Active Object Recognition.

PubMed

Liu, Huaping; Wu, Yupei; Sun, Fuchun; Huaping Liu; Yupei Wu; Fuchun Sun; Sun, Fuchun; Liu, Huaping; Wu, Yupei

2018-06-01

In this brief, we develop a deep reinforcement learning method to actively recognize objects by choosing a sequence of actions for an active camera that helps to discriminate between the objects. The method is realized using trust region policy optimization, in which the policy is realized by an extreme learning machine and, therefore, leads to efficient optimization algorithm. The experimental results on the publicly available data set show the advantages of the developed extreme trust region optimization method.
Minimization of annotation work: diagnosis of mammographic masses via active learning

NASA Astrophysics Data System (ADS)

Zhao, Yu; Zhang, Jingyang; Xie, Hongzhi; Zhang, Shuyang; Gu, Lixu

2018-06-01

The prerequisite for establishing an effective prediction system for mammographic diagnosis is the annotation of each mammographic image. The manual annotation work is time-consuming and laborious, which becomes a great hindrance for researchers. In this article, we propose a novel active learning algorithm that can adequately address this problem, leading to the minimization of the labeling costs on the premise of guaranteed performance. Our proposed method is different from the existing active learning methods designed for the general problem as it is specifically designed for mammographic images. Through its modified discriminant functions and improved sample query criteria, the proposed method can fully utilize the pairing of mammographic images and select the most valuable images from both the mediolateral and craniocaudal views. Moreover, in order to extend active learning to the ordinal regression problem, which has no precedent in existing studies, but is essential for mammographic diagnosis (mammographic diagnosis is not only a classification task, but also an ordinal regression task for predicting an ordinal variable, viz. the malignancy risk of lesions), multiple sample query criteria need to be taken into consideration simultaneously. We formulate it as a criteria integration problem and further present an algorithm based on self-adaptive weighted rank aggregation to achieve a good solution. The efficacy of the proposed method was demonstrated on thousands of mammographic images from the digital database for screening mammography. The labeling costs of obtaining optimal performance in the classification and ordinal regression task respectively fell to 33.8 and 19.8 percent of their original costs. The proposed method also generated 1228 wins, 369 ties and 47 losses for the classification task, and 1933 wins, 258 ties and 185 losses for the ordinal regression task compared to the other state-of-the-art active learning algorithms. By taking the particularities of mammographic images, the proposed AL method can indeed reduce the manual annotation work to a great extent without sacrificing the performance of the prediction system for mammographic diagnosis.
Minimization of annotation work: diagnosis of mammographic masses via active learning.

PubMed

Zhao, Yu; Zhang, Jingyang; Xie, Hongzhi; Zhang, Shuyang; Gu, Lixu

2018-05-22

The prerequisite for establishing an effective prediction system for mammographic diagnosis is the annotation of each mammographic image. The manual annotation work is time-consuming and laborious, which becomes a great hindrance for researchers. In this article, we propose a novel active learning algorithm that can adequately address this problem, leading to the minimization of the labeling costs on the premise of guaranteed performance. Our proposed method is different from the existing active learning methods designed for the general problem as it is specifically designed for mammographic images. Through its modified discriminant functions and improved sample query criteria, the proposed method can fully utilize the pairing of mammographic images and select the most valuable images from both the mediolateral and craniocaudal views. Moreover, in order to extend active learning to the ordinal regression problem, which has no precedent in existing studies, but is essential for mammographic diagnosis (mammographic diagnosis is not only a classification task, but also an ordinal regression task for predicting an ordinal variable, viz. the malignancy risk of lesions), multiple sample query criteria need to be taken into consideration simultaneously. We formulate it as a criteria integration problem and further present an algorithm based on self-adaptive weighted rank aggregation to achieve a good solution. The efficacy of the proposed method was demonstrated on thousands of mammographic images from the digital database for screening mammography. The labeling costs of obtaining optimal performance in the classification and ordinal regression task respectively fell to 33.8 and 19.8 percent of their original costs. The proposed method also generated 1228 wins, 369 ties and 47 losses for the classification task, and 1933 wins, 258 ties and 185 losses for the ordinal regression task compared to the other state-of-the-art active learning algorithms. By taking the particularities of mammographic images, the proposed AL method can indeed reduce the manual annotation work to a great extent without sacrificing the performance of the prediction system for mammographic diagnosis.
Learning patterns of life from intelligence analyst chat

NASA Astrophysics Data System (ADS)

Schneider, Michael K.; Alford, Mark; Babko-Malaya, Olga; Blasch, Erik; Chen, Lingji; Crespi, Valentino; HandUber, Jason; Haney, Phil; Nagy, Jim; Richman, Mike; Von Pless, Gregory; Zhu, Howie; Rhodes, Bradley J.

2016-05-01

Our Multi-INT Data Association Tool (MIDAT) learns patterns of life (POL) of a geographical area from video analyst observations called out in textual reporting. Typical approaches to learning POLs from video make use of computer vision algorithms to extract locations in space and time of various activities. Such approaches are subject to the detection and tracking performance of the video processing algorithms. Numerous examples of human analysts monitoring live video streams annotating or "calling out" relevant entities and activities exist, such as security analysis, crime-scene forensics, news reports, and sports commentary. This user description typically corresponds with textual capture, such as chat. Although the purpose of these text products is primarily to describe events as they happen, organizations typically archive the reports for extended periods. This archive provides a basis to build POLs. Such POLs are useful for diagnosis to assess activities in an area based on historical context, and for consumers of products, who gain an understanding of historical patterns. MIDAT combines natural language processing, multi-hypothesis tracking, and Multi-INT Activity Pattern Learning and Exploitation (MAPLE) technologies in an end-to-end lab prototype that processes textual products produced by video analysts, infers POLs, and highlights anomalies relative to those POLs with links to "tracks" of related activities performed by the same entity. MIDAT technologies perform well, achieving, for example, a 90% F1-value on extracting activities from the textual reports.

SemiBoost: boosting for semi-supervised learning.

PubMed

Mallapragada, Pavan Kumar; Jin, Rong; Jain, Anil K; Liu, Yi

2009-11-01

Semi-supervised learning has attracted a significant amount of attention in pattern recognition and machine learning. Most previous studies have focused on designing special algorithms to effectively exploit the unlabeled data in conjunction with labeled data. Our goal is to improve the classification accuracy of any given supervised learning algorithm by using the available unlabeled examples. We call this as the Semi-supervised improvement problem, to distinguish the proposed approach from the existing approaches. We design a metasemi-supervised learning algorithm that wraps around the underlying supervised algorithm and improves its performance using unlabeled data. This problem is particularly important when we need to train a supervised learning algorithm with a limited number of labeled examples and a multitude of unlabeled examples. We present a boosting framework for semi-supervised learning, termed as SemiBoost. The key advantages of the proposed semi-supervised learning approach are: 1) performance improvement of any supervised learning algorithm with a multitude of unlabeled data, 2) efficient computation by the iterative boosting algorithm, and 3) exploiting both manifold and cluster assumption in training classification models. An empirical study on 16 different data sets and text categorization demonstrates that the proposed framework improves the performance of several commonly used supervised learning algorithms, given a large number of unlabeled examples. We also show that the performance of the proposed algorithm, SemiBoost, is comparable to the state-of-the-art semi-supervised learning algorithms.
Teaching and Learning Activity Sequencing System using Distributed Genetic Algorithms

NASA Astrophysics Data System (ADS)

Matsui, Tatsunori; Ishikawa, Tomotake; Okamoto, Toshio

The purpose of this study is development of a supporting system for teacher's design of lesson plan. Especially design of lesson plan which relates to the new subject "Information Study" is supported. In this study, we developed a system which generates teaching and learning activity sequences by interlinking lesson's activities corresponding to the various conditions according to the user's input. Because user's input is multiple information, there will be caused contradiction which the system should solve. This multiobjective optimization problem is resolved by Distributed Genetic Algorithms, in which some fitness functions are defined with reference models on lesson, thinking and teaching style. From results of various experiments, effectivity and validity of the proposed methods and reference models were verified; on the other hand, some future works on reference models and evaluation functions were also pointed out.
Scene recognition based on integrating active learning with dictionary learning

NASA Astrophysics Data System (ADS)

Wang, Chengxi; Yin, Xueyan; Yang, Lin; Gong, Chengrong; Zheng, Caixia; Yi, Yugen

2018-04-01

Scene recognition is a significant topic in the field of computer vision. Most of the existing scene recognition models require a large amount of labeled training samples to achieve a good performance. However, labeling image manually is a time consuming task and often unrealistic in practice. In order to gain satisfying recognition results when labeled samples are insufficient, this paper proposed a scene recognition algorithm named Integrating Active Learning and Dictionary Leaning (IALDL). IALDL adopts projective dictionary pair learning (DPL) as classifier and introduces active learning mechanism into DPL for improving its performance. When constructing sampling criterion in active learning, IALDL considers both the uncertainty and representativeness as the sampling criteria to effectively select the useful unlabeled samples from a given sample set for expanding the training dataset. Experiment results on three standard databases demonstrate the feasibility and validity of the proposed IALDL.
Development of cyberblog-based intelligent tutorial system to improve students learning ability algorithm

NASA Astrophysics Data System (ADS)

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.
Noise-enhanced clustering and competitive learning algorithms.

PubMed

Osoba, Osonde; Kosko, Bart

2013-01-01

Noise can provably speed up convergence in many centroid-based clustering algorithms. This includes the popular k-means clustering algorithm. The clustering noise benefit follows from the general noise benefit for the expectation-maximization algorithm because many clustering algorithms are special cases of the expectation-maximization algorithm. Simulations show that noise also speeds up convergence in stochastic unsupervised competitive learning, supervised competitive learning, and differential competitive learning. Copyright © 2012 Elsevier Ltd. All rights reserved.
Q-Learning-Based Adjustable Fixed-Phase Quantum Grover Search Algorithm

NASA Astrophysics Data System (ADS)

Guo, Ying; Shi, Wensha; Wang, Yijun; Hu, Jiankun

2017-02-01

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.
Active subspace: toward scalable low-rank learning.

PubMed

Liu, Guangcan; Yan, Shuicheng

2012-12-01

We address the scalability issues in low-rank matrix learning problems. Usually these problems resort to solving nuclear norm regularized optimization problems (NNROPs), which often suffer from high computational complexities if based on existing solvers, especially in large-scale settings. Based on the fact that the optimal solution matrix to an NNROP is often low rank, we revisit the classic mechanism of low-rank matrix factorization, based on which we present an active subspace algorithm for efficiently solving NNROPs by transforming large-scale NNROPs into small-scale problems. The transformation is achieved by factorizing the large solution matrix into the product of a small orthonormal matrix (active subspace) and another small matrix. Although such a transformation generally leads to nonconvex problems, we show that a suboptimal solution can be found by the augmented Lagrange alternating direction method. For the robust PCA (RPCA) (Candès, Li, Ma, & Wright, 2009 ) problem, a typical example of NNROPs, theoretical results verify the suboptimality of the solution produced by our algorithm. For the general NNROPs, we empirically show that our algorithm significantly reduces the computational complexity without loss of optimality.
Modification Of Learning Rate With Lvq Model Improvement In Learning Backpropagation

NASA Astrophysics Data System (ADS)

Tata Hardinata, Jaya; Zarlis, Muhammad; Budhiarti Nababan, Erna; Hartama, Dedy; Sembiring, Rahmat W.

2017-12-01

One type of artificial neural network is a backpropagation, This algorithm trained with the network architecture used during the training as well as providing the correct output to insert a similar but not the same with the architecture in use at training.The selection of appropriate parameters also affects the outcome, value of learning rate is one of the parameters which influence the process of training, Learning rate affects the speed of learning process on the network architecture.If the learning rate is set too large, then the algorithm will become unstable and otherwise the algorithm will converge in a very long period of time.So this study was made to determine the value of learning rate on the backpropagation algorithm. LVQ models of learning rate is one of the models used in the determination of the value of the learning rate of the algorithm LVQ.By modifying this LVQ model to be applied to the backpropagation algorithm. From the experimental results known to modify the learning rate LVQ models were applied to the backpropagation algorithm learning process becomes faster (epoch less).
Predicting the survival of diabetes using neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Data mining techniques at the present time are used in predicting diseases of health care industries. Neural Network is one among the prevailing method in data mining techniques of an intelligent field for predicting diseases in health care industries. This paper presents a study on the prediction of the survival of diabetes diseases using different learning algorithms from the supervised learning algorithms of neural network. Three learning algorithms are considered in this study: (i) The levenberg-marquardt learning algorithm (ii) The Bayesian regulation learning algorithm and (iii) The scaled conjugate gradient learning algorithm. The network is trained using the Pima Indian Diabetes Dataset with the help of MATLAB R2014(a) software. The performance of each algorithm is further discussed through regression analysis. The prediction accuracy of the best algorithm is further computed to validate the accurate prediction
User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm.

PubMed

Bourobou, Serge Thomas Mickala; Yoo, Younghwan

2015-05-21

This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home.
Shape-Driven 3D Segmentation Using Spherical Wavelets

PubMed Central

Nain, Delphine; Haker, Steven; Bobick, Aaron; Tannenbaum, Allen

2013-01-01

This paper presents a novel active surface segmentation algorithm using a multiscale shape representation and prior. We define a parametric model of a surface using spherical wavelet functions and learn a prior probability distribution over the wavelet coefficients to model shape variations at different scales and spatial locations in a training set. Based on this representation, we derive a parametric active surface evolution using the multiscale prior coefficients as parameters for our optimization procedure to naturally include the prior in the segmentation framework. Additionally, the optimization method can be applied in a coarse-to-fine manner. We apply our algorithm to the segmentation of brain caudate nucleus, of interest in the study of schizophrenia. Our validation shows our algorithm is computationally efficient and outperforms the Active Shape Model algorithm by capturing finer shape details. PMID:17354875
Learning to Control Advanced Life Support Systems

NASA Technical Reports Server (NTRS)

Subramanian, Devika

2004-01-01

Advanced life support systems have many interacting processes and limited resources. Controlling and optimizing advanced life support systems presents unique challenges. In particular, advanced life support systems are nonlinear coupled dynamical systems and it is difficult for humans to take all interactions into account to design an effective control strategy. In this project. we developed several reinforcement learning controllers that actively explore the space of possible control strategies, guided by rewards from a user specified long term objective function. We evaluated these controllers using a discrete event simulation of an advanced life support system. This simulation, called BioSim, designed by Nasa scientists David Kortenkamp and Scott Bell has multiple, interacting life support modules including crew, food production, air revitalization, water recovery, solid waste incineration and power. They are implemented in a consumer/producer relationship in which certain modules produce resources that are consumed by other modules. Stores hold resources between modules. Control of this simulation is via adjusting flows of resources between modules and into/out of stores. We developed adaptive algorithms that control the flow of resources in BioSim. Our learning algorithms discovered several ingenious strategies for maximizing mission length by controlling the air and water recycling systems as well as crop planting schedules. By exploiting non-linearities in the overall system dynamics, the learned controllers easily out- performed controllers written by human experts. In sum, we accomplished three goals. We (1) developed foundations for learning models of coupled dynamical systems by active exploration of the state space, (2) developed and tested algorithms that learn to efficiently control air and water recycling processes as well as crop scheduling in Biosim, and (3) developed an understanding of the role machine learning in designing control systems for advanced life support.
Discriminative structural approaches for enzyme active-site prediction.

PubMed

Kato, Tsuyoshi; Nagano, Nozomi

2011-02-15

Predicting enzyme active-sites in proteins is an important issue not only for protein sciences but also for a variety of practical applications such as drug design. Because enzyme reaction mechanisms are based on the local structures of enzyme active-sites, various template-based methods that compare local structures in proteins have been developed to date. In comparing such local sites, a simple measurement, RMSD, has been used so far. This paper introduces new machine learning algorithms that refine the similarity/deviation for comparison of local structures. The similarity/deviation is applied to two types of applications, single template analysis and multiple template analysis. In the single template analysis, a single template is used as a query to search proteins for active sites, whereas a protein structure is examined as a query to discover the possible active-sites using a set of templates in the multiple template analysis. This paper experimentally illustrates that the machine learning algorithms effectively improve the similarity/deviation measurements for both the analyses.
The Behavioral and Neural Mechanisms Underlying the Tracking of Expertise

PubMed Central

Boorman, Erie D.; O’Doherty, John P.; Adolphs, Ralph; Rangel, Antonio

2013-01-01

Summary Evaluating the abilities of others is fundamental for successful economic and social behavior. We investigated the computational and neurobiological basis of ability tracking by designing an fMRI task that required participants to use and update estimates of both people and algorithms’ expertise through observation of their predictions. Behaviorally, we find a model-based algorithm characterized subject predictions better than several alternative models. Notably, when the agent’s prediction was concordant rather than discordant with the subject’s own likely prediction, participants credited people more than algorithms for correct predictions and penalized them less for incorrect predictions. Neurally, many components of the mentalizing network—medial prefrontal cortex, anterior cingulate gyrus, temporoparietal junction, and precuneus—represented or updated expertise beliefs about both people and algorithms. Moreover, activity in lateral orbitofrontal and medial prefrontal cortex reflected behavioral differences in learning about people and algorithms. These findings provide basic insights into the neural basis of social learning. PMID:24360551
Designing algorithm visualization on mobile platform: The proposed guidelines

NASA Astrophysics Data System (ADS)

Supli, A. A.; Shiratuddin, N.

2017-09-01

This paper entails an ongoing study about the design guidelines of algorithm visualization (AV) on mobile platform, helping students learning data structures and algorithm (DSA) subject effectively. Our previous review indicated that design guidelines of AV on mobile platform are still few. Mostly, previous guidelines of AV are developed for AV on desktop and website platform. In fact, mobile learning has been proved to enhance engagement in learning circumstances, and thus effect student's performance. In addition, the researchers highly recommend including UI design and Interactivity in designing effective AV system. However, the discussions of these two aspects in previous AV design guidelines are not comprehensive. The UI design in this paper describes the arrangement of AV features in mobile environment, whereas interactivity is about the active learning strategy features based on learning experiences (how to engage learners). Thus, this study main objective is to propose design guidelines of AV on mobile platform (AVOMP) that entails comprehensively UI design and interactivity aspects. These guidelines are developed through content analysis and comparative analysis from various related studies. These guidelines are useful for AV designers to help them constructing AVOMP for various topics on DSA.
Using an improved association rules mining optimization algorithm in web-based mobile-learning system

NASA Astrophysics Data System (ADS)

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.
A Human Activity Recognition System Using Skeleton Data from RGBD Sensors.

PubMed

Cippitelli, Enea; Gasparrini, Samuele; Gambi, Ennio; Spinsante, Susanna

2016-01-01

The aim of Active and Assisted Living is to develop tools to promote the ageing in place of elderly people, and human activity recognition algorithms can help to monitor aged people in home environments. Different types of sensors can be used to address this task and the RGBD sensors, especially the ones used for gaming, are cost-effective and provide much information about the environment. This work aims to propose an activity recognition algorithm exploiting skeleton data extracted by RGBD sensors. The system is based on the extraction of key poses to compose a feature vector, and a multiclass Support Vector Machine to perform classification. Computation and association of key poses are carried out using a clustering algorithm, without the need of a learning algorithm. The proposed approach is evaluated on five publicly available datasets for activity recognition, showing promising results especially when applied for the recognition of AAL related actions. Finally, the current applicability of this solution in AAL scenarios and the future improvements needed are discussed.
Fast Adapting Ensemble: A New Algorithm for Mining Data Streams with Concept Drift

PubMed Central

Ortíz Díaz, Agustín; Ramos-Jiménez, Gonzalo; Frías Blanco, Isvani; Caballero Mota, Yailé; Morales-Bueno, Rafael

2015-01-01

The treatment of large data streams in the presence of concept drifts is one of the main challenges in the field of data mining, particularly when the algorithms have to deal with concepts that disappear and then reappear. This paper presents a new algorithm, called Fast Adapting Ensemble (FAE), which adapts very quickly to both abrupt and gradual concept drifts, and has been specifically designed to deal with recurring concepts. FAE processes the learning examples in blocks of the same size, but it does not have to wait for the batch to be complete in order to adapt its base classification mechanism. FAE incorporates a drift detector to improve the handling of abrupt concept drifts and stores a set of inactive classifiers that represent old concepts, which are activated very quickly when these concepts reappear. We compare our new algorithm with various well-known learning algorithms, taking into account, common benchmark datasets. The experiments show promising results from the proposed algorithm (regarding accuracy and runtime), handling different types of concept drifts. PMID:25879051
A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms

PubMed Central

Yang, Changju; Kim, Hyongsuk; Adhikari, Shyam Prasad; Chua, Leon O.

2016-01-01

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems. PMID:28025566
The applications of machine learning algorithms in the modeling of estrogen-like chemicals.

PubMed

Liu, Huanxiang; Yao, Xiaojun; Gramatica, Paola

2009-06-01

Increasing concern is being shown by the scientific community, government regulators, and the public about endocrine-disrupting chemicals that, in the environment, are adversely affecting human and wildlife health through a variety of mechanisms, mainly estrogen receptor-mediated mechanisms of toxicity. Because of the large number of such chemicals in the environment, there is a great need for an effective means of rapidly assessing endocrine-disrupting activity in the toxicology assessment process. When faced with the challenging task of screening large libraries of molecules for biological activity, the benefits of computational predictive models based on quantitative structure-activity relationships to identify possible estrogens become immediately obvious. Recently, in order to improve the accuracy of prediction, some machine learning techniques were introduced to build more effective predictive models. In this review we will focus our attention on some recent advances in the use of these methods in modeling estrogen-like chemicals. The advantages and disadvantages of the machine learning algorithms used in solving this problem, the importance of the validation and performance assessment of the built models as well as their applicability domains will be discussed.

A Comparison of Supervised Machine Learning Algorithms and Feature Vectors for MS Lesion Segmentation Using Multimodal Structural MRI

PubMed Central

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
A comparison of supervised machine learning algorithms and feature vectors for MS lesion segmentation using multimodal structural MRI.

PubMed

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.
A meta-cognitive learning algorithm for a Fully Complex-valued Relaxation Network.

PubMed

Savitha, R; Suresh, S; Sundararajan, N

2012-08-01

This paper presents a meta-cognitive learning algorithm for a single hidden layer complex-valued neural network called "Meta-cognitive Fully Complex-valued Relaxation Network (McFCRN)". McFCRN has two components: a cognitive component and a meta-cognitive component. A Fully Complex-valued Relaxation Network (FCRN) with a fully complex-valued Gaussian like activation function (sech) in the hidden layer and an exponential activation function in the output layer forms the cognitive component. The meta-cognitive component contains a self-regulatory learning mechanism which controls the learning ability of FCRN by deciding what-to-learn, when-to-learn and how-to-learn from a sequence of training data. The input parameters of cognitive components are chosen randomly and the output parameters are estimated by minimizing a logarithmic error function. The problem of explicit minimization of magnitude and phase errors in the logarithmic error function is converted to system of linear equations and output parameters of FCRN are computed analytically. McFCRN starts with zero hidden neuron and builds the number of neurons required to approximate the target function. The meta-cognitive component selects the best learning strategy for FCRN to acquire the knowledge from training data and also adapts the learning strategies to implement best human learning components. Performance studies on a function approximation and real-valued classification problems show that proposed McFCRN performs better than the existing results reported in the literature. Copyright © 2012 Elsevier Ltd. All rights reserved.
Predicting the Occurrence of Haze Events in Southeast Asia using Machine Learning Algorithms

NASA Astrophysics Data System (ADS)

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.
Rapid classification of hippocampal replay content for real-time applications

PubMed Central

Liu, Daniel F.; Karlsson, Mattias P.; Frank, Loren M.; Eden, Uri T.

2016-01-01

Sharp-wave ripple (SWR) events in the hippocampus replay millisecond-timescale patterns of place cell activity related to the past experience of an animal. Interrupting SWR events leads to learning and memory impairments, but how the specific patterns of place cell spiking seen during SWRs contribute to learning and memory remains unclear. A deeper understanding of this issue will require the ability to manipulate SWR events based on their content. Accurate real-time decoding of SWR replay events requires new algorithms that are able to estimate replay content and the associated uncertainty, along with software and hardware that can execute these algorithms for biological interventions on a millisecond timescale. Here we develop an efficient estimation algorithm to categorize the content of replay from multiunit spiking activity. Specifically, we apply real-time decoding methods to each SWR event and then compute the posterior probability of the replay feature. We illustrate this approach by classifying SWR events from data recorded in the hippocampus of a rat performing a spatial memory task into four categories: whether they represent outbound or inbound trajectories and whether the activity is replayed forward or backward in time. We show that our algorithm can classify the majority of SWR events in a recording epoch within 20 ms of the replay onset with high certainty, which makes the algorithm suitable for a real-time implementation with short latencies to incorporate into content-based feedback experiments. PMID:27535369
Identifying physical activity type in manual wheelchair users with spinal cord injury by means of accelerometers.

PubMed

García-Massó, X; Serra-Añó, P; Gonzalez, L M; Ye-Lin, Y; Prats-Boluda, G; Garcia-Casado, J

2015-10-01

This was a cross-sectional study. The main objective of this study was to develop and test classification algorithms based on machine learning using accelerometers to identify the activity type performed by manual wheelchair users with spinal cord injury (SCI). The study was conducted in the Physical Therapy department and the Physical Education and Sports department of the University of Valencia. A total of 20 volunteers were asked to perform 10 physical activities, lying down, body transfers, moving items, mopping, working on a computer, watching TV, arm-ergometer exercises, passive propulsion, slow propulsion and fast propulsion, while fitted with four accelerometers placed on both wrists, chest and waist. The activities were grouped into five categories: sedentary, locomotion, housework, body transfers and moderate physical activity. Different machine learning algorithms were used to develop individual and group activity classifiers from the acceleration data for different combinations of number and position of the accelerometers. We found that although the accuracy of the classifiers for individual activities was moderate (55-72%), with higher values for a greater number of accelerometers, grouped activities were correctly classified in a high percentage of cases (83.2-93.6%). With only two accelerometers and the quadratic discriminant analysis algorithm we achieved a reasonably accurate group activity recognition system (>90%). Such a system with the minimum of intervention would be a valuable tool for studying physical activity in individuals with SCI.
Superior Generalization Capability of Hardware-Learing Algorithm Developed for Self-Learning Neuron-MOS Neural Networks

NASA Astrophysics Data System (ADS)

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.
Learning control system design based on 2-D theory - An application to parallel link manipulator

NASA Technical Reports Server (NTRS)

Geng, Z.; Carroll, R. L.; Lee, J. D.; Haynes, L. H.

1990-01-01

An approach to iterative learning control system design based on two-dimensional system theory is presented. A two-dimensional model for the iterative learning control system which reveals the connections between learning control systems and two-dimensional system theory is established. A learning control algorithm is proposed, and the convergence of learning using this algorithm is guaranteed by two-dimensional stability. The learning algorithm is applied successfully to the trajectory tracking control problem for a parallel link robot manipulator. The excellent performance of this learning algorithm is demonstrated by the computer simulation results.
When drug discovery meets web search: Learning to Rank for ligand-based virtual screening.

PubMed

Zhang, Wei; Ji, Lijuan; Chen, Yanan; Tang, Kailin; Wang, Haiping; Zhu, Ruixin; Jia, Wei; Cao, Zhiwei; Liu, Qi

2015-01-01

The rapid increase in the emergence of novel chemical substances presents a substantial demands for more sophisticated computational methodologies for drug discovery. In this study, the idea of Learning to Rank in web search was presented in drug virtual screening, which has the following unique capabilities of 1). Applicable of identifying compounds on novel targets when there is not enough training data available for these targets, and 2). Integration of heterogeneous data when compound affinities are measured in different platforms. A standard pipeline was designed to carry out Learning to Rank in virtual screening. Six Learning to Rank algorithms were investigated based on two public datasets collected from Binding Database and the newly-published Community Structure-Activity Resource benchmark dataset. The results have demonstrated that Learning to rank is an efficient computational strategy for drug virtual screening, particularly due to its novel use in cross-target virtual screening and heterogeneous data integration. To the best of our knowledge, we have introduced here the first application of Learning to Rank in virtual screening. The experiment workflow and algorithm assessment designed in this study will provide a standard protocol for other similar studies. All the datasets as well as the implementations of Learning to Rank algorithms are available at http://www.tongji.edu.cn/~qiliu/lor_vs.html. Graphical AbstractThe analogy between web search and ligand-based drug discovery.
Automated condition-invariable neurite segmentation and synapse classification using textural analysis-based machine-learning algorithms

PubMed Central

Kandaswamy, Umasankar; Rotman, Ziv; Watt, Dana; Schillebeeckx, Ian; Cavalli, Valeria; Klyachko, Vitaly

2013-01-01

High-resolution live-cell imaging studies of neuronal structure and function are characterized by large variability in image acquisition conditions due to background and sample variations as well as low signal-to-noise ratio. The lack of automated image analysis tools that can be generalized for varying image acquisition conditions represents one of the main challenges in the field of biomedical image analysis. Specifically, segmentation of the axonal/dendritic arborizations in brightfield or fluorescence imaging studies is extremely labor-intensive and still performed mostly manually. Here we describe a fully automated machine-learning approach based on textural analysis algorithms for segmenting neuronal arborizations in high-resolution brightfield images of live cultured neurons. We compare performance of our algorithm to manual segmentation and show that it combines 90% accuracy, with similarly high levels of specificity and sensitivity. Moreover, the algorithm maintains high performance levels under a wide range of image acquisition conditions indicating that it is largely condition-invariable. We further describe an application of this algorithm to fully automated synapse localization and classification in fluorescence imaging studies based on synaptic activity. Textural analysis-based machine-learning approach thus offers a high performance condition-invariable tool for automated neurite segmentation. PMID:23261652
Active machine learning-driven experimentation to determine compound effects on protein patterns.

PubMed

Naik, Armaghan W; Kangas, Joshua D; Sullivan, Devin P; Murphy, Robert F

2016-02-03

High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance.
Reinforcement active learning in the vibrissae system: optimal object localization.

PubMed

Gordon, Goren; Dorfman, Nimrod; Ahissar, Ehud

2013-01-01

Rats move their whiskers to acquire information about their environment. It has been observed that they palpate novel objects and objects they are required to localize in space. We analyze whisker-based object localization using two complementary paradigms, namely, active learning and intrinsic-reward reinforcement learning. Active learning algorithms select the next training samples according to the hypothesized solution in order to better discriminate between correct and incorrect labels. Intrinsic-reward reinforcement learning uses prediction errors as the reward to an actor-critic design, such that behavior converges to the one that optimizes the learning process. We show that in the context of object localization, the two paradigms result in palpation whisking as their respective optimal solution. These results suggest that rats may employ principles of active learning and/or intrinsic reward in tactile exploration and can guide future research to seek the underlying neuronal mechanisms that implement them. Furthermore, these paradigms are easily transferable to biomimetic whisker-based artificial sensors and can improve the active exploration of their environment. Copyright © 2012 Elsevier Ltd. All rights reserved.
Discrete-Time Deterministic $Q$ -Learning: A Novel Convergence Analysis.

PubMed

Wei, Qinglai; Lewis, Frank L; Sun, Qiuye; Yan, Pengfei; Song, Ruizhuo

2017-05-01

In this paper, a novel discrete-time deterministic Q -learning algorithm is developed. In each iteration of the developed Q -learning algorithm, the iterative Q function is updated for all the state and control spaces, instead of updating for a single state and a single control in traditional Q -learning algorithm. A new convergence criterion is established to guarantee that the iterative Q function converges to the optimum, where the convergence criterion of the learning rates for traditional Q -learning algorithms is simplified. During the convergence analysis, the upper and lower bounds of the iterative Q function are analyzed to obtain the convergence criterion, instead of analyzing the iterative Q function itself. For convenience of analysis, the convergence properties for undiscounted case of the deterministic Q -learning algorithm are first developed. Then, considering the discounted factor, the convergence criterion for the discounted case is established. Neural networks are used to approximate the iterative Q function and compute the iterative control law, respectively, for facilitating the implementation of the deterministic Q -learning algorithm. Finally, simulation results and comparisons are given to illustrate the performance of the developed algorithm.
Generalization in Adaptation to Stable and Unstable Dynamics

PubMed Central

Kadiallah, Abdelhamid; Franklin, David W.; Burdet, Etienne

2012-01-01

Humans skillfully manipulate objects and tools despite the inherent instability. In order to succeed at these tasks, the sensorimotor control system must build an internal representation of both the force and mechanical impedance. As it is not practical to either learn or store motor commands for every possible future action, the sensorimotor control system generalizes a control strategy for a range of movements based on learning performed over a set of movements. Here, we introduce a computational model for this learning and generalization, which specifies how to learn feedforward muscle activity in a function of the state space. Specifically, by incorporating co-activation as a function of error into the feedback command, we are able to derive an algorithm from a gradient descent minimization of motion error and effort, subject to maintaining a stability margin. This algorithm can be used to learn to coordinate any of a variety of motor primitives such as force fields, muscle synergies, physical models or artificial neural networks. This model for human learning and generalization is able to adapt to both stable and unstable dynamics, and provides a controller for generating efficient adaptive motor behavior in robots. Simulation results exhibit predictions consistent with all experiments on learning of novel dynamics requiring adaptation of force and impedance, and enable us to re-examine some of the previous interpretations of experiments on generalization. PMID:23056191
Active Player Modeling in the Iterated Prisoner's Dilemma

PubMed Central

Park, Hyunsoo; Kim, Kyung-Joong

2016-01-01

The iterated prisoner's dilemma (IPD) is well known within the domain of game theory. Although it is relatively simple, it can also elucidate important problems related to cooperation and trust. Generally, players can predict their opponents' actions when they are able to build a precise model of their behavior based on their game playing experience. However, it is difficult to make such predictions based on a limited number of games. The creation of a precise model requires the use of not only an appropriate learning algorithm and framework but also a good dataset. Active learning approaches have recently been introduced to machine learning communities. The approach can usually produce informative datasets with relatively little effort. Therefore, we have proposed an active modeling technique to predict the behavior of IPD players. The proposed method can model the opponent player's behavior while taking advantage of interactive game environments. This experiment used twelve representative types of players as opponents, and an observer used an active modeling algorithm to model these opponents. This observer actively collected data and modeled the opponent's behavior online. Most of our data showed that the observer was able to build, through direct actions, a more accurate model of an opponent's behavior than when the data were collected through random actions. PMID:26989405
Active Player Modeling in the Iterated Prisoner's Dilemma.

PubMed

Park, Hyunsoo; Kim, Kyung-Joong

2016-01-01

The iterated prisoner's dilemma (IPD) is well known within the domain of game theory. Although it is relatively simple, it can also elucidate important problems related to cooperation and trust. Generally, players can predict their opponents' actions when they are able to build a precise model of their behavior based on their game playing experience. However, it is difficult to make such predictions based on a limited number of games. The creation of a precise model requires the use of not only an appropriate learning algorithm and framework but also a good dataset. Active learning approaches have recently been introduced to machine learning communities. The approach can usually produce informative datasets with relatively little effort. Therefore, we have proposed an active modeling technique to predict the behavior of IPD players. The proposed method can model the opponent player's behavior while taking advantage of interactive game environments. This experiment used twelve representative types of players as opponents, and an observer used an active modeling algorithm to model these opponents. This observer actively collected data and modeled the opponent's behavior online. Most of our data showed that the observer was able to build, through direct actions, a more accurate model of an opponent's behavior than when the data were collected through random actions.
Predictive Model of Linear Antimicrobial Peptides Active against Gram-Negative Bacteria.

PubMed

Vishnepolsky, Boris; Gabrielian, Andrei; Rosenthal, Alex; Hurt, Darrell E; Tartakovsky, Michael; Managadze, Grigol; Grigolava, Maya; Makhatadze, George I; Pirtskhalava, Malak

2018-05-29

Antimicrobial peptides (AMPs) have been identified as a potential new class of anti-infectives for drug development. There are a lot of computational methods that try to predict AMPs. Most of them can only predict if a peptide will show any antimicrobial potency, but to the best of our knowledge, there are no tools which can predict antimicrobial potency against particular strains. Here we present a predictive model of linear AMPs being active against particular Gram-negative strains relying on a semi-supervised machine-learning approach with a density-based clustering algorithm. The algorithm can well distinguish peptides active against particular strains from others which may also be active but not against the considered strain. The available AMP prediction tools cannot carry out this task. The prediction tool based on the algorithm suggested herein is available on https://dbaasp.org.
A Methodology for the Hybridization Based in Active Components: The Case of cGA and Scatter Search.

PubMed

Villagra, Andrea; Alba, Enrique; Leguizamón, Guillermo

2016-01-01

This work presents the results of a new methodology for hybridizing metaheuristics. By first locating the active components (parts) of one algorithm and then inserting them into second one, we can build efficient and accurate optimization, search, and learning algorithms. This gives a concrete way of constructing new techniques that contrasts the spread ad hoc way of hybridizing. In this paper, the enhanced algorithm is a Cellular Genetic Algorithm (cGA) which has been successfully used in the past to find solutions to such hard optimization problems. In order to extend and corroborate the use of active components as an emerging hybridization methodology, we propose here the use of active components taken from Scatter Search (SS) to improve cGA. The results obtained over a varied set of benchmarks are highly satisfactory in efficacy and efficiency when compared with a standard cGA. Moreover, the proposed hybrid approach (i.e., cGA+SS) has shown encouraging results with regard to earlier applications of our methodology.
A study on the performance comparison of metaheuristic algorithms on the learning of neural networks

NASA Astrophysics Data System (ADS)

Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline

2017-08-01

The learning or training process of neural networks entails the task of finding the most optimal set of parameters, which includes translation vectors, dilation parameter, synaptic weights, and bias terms. Apart from the traditional gradient descent-based methods, metaheuristic methods can also be used for this learning purpose. Since the inception of genetic algorithm half a century ago, the last decade witnessed the explosion of a variety of novel metaheuristic algorithms, such as harmony search algorithm, bat algorithm, and whale optimization algorithm. Despite the proof of the no free lunch theorem in the discipline of optimization, a survey in the literature of machine learning gives contrasting results. Some researchers report that certain metaheuristic algorithms are superior to the others, whereas some others argue that different metaheuristic algorithms give comparable performance. As such, this paper aims to investigate if a certain metaheuristic algorithm will outperform the other algorithms. In this work, three metaheuristic algorithms, namely genetic algorithms, particle swarm optimization, and harmony search algorithm are considered. The algorithms are incorporated in the learning of neural networks and their classification results on the benchmark UCI machine learning data sets are compared. It is found that all three metaheuristic algorithms give similar and comparable performance, as captured in the average overall classification accuracy. The results corroborate the findings reported in the works done by previous researchers. Several recommendations are given, which include the need of statistical analysis to verify the results and further theoretical works to support the obtained empirical results.
User Activity Recognition in Smart Homes Using Pattern Clustering Applied to Temporal ANN Algorithm

PubMed Central

Bourobou, Serge Thomas Mickala; Yoo, Younghwan

2015-01-01

This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen’s temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home. PMID:26007738

Machine learning methods in chemoinformatics

PubMed Central

Mitchell, John B O

2014-01-01

Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure–activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers. WIREs Comput Mol Sci 2014, 4:468–481. How to cite this article: WIREs Comput Mol Sci 2014, 4:468–481. doi:10.1002/wcms.1183 PMID:25285160
Classifying spatially heterogeneous wetland communities using machine learning algorithms and spectral and textural features.

PubMed

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 (α<0.05). Findings show that using multiple window sizes provided the best results. First-ordertexture featuresalso provided computational advantages and results that were not significantly different fromthose usingsecond-order texture features.
Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling.

PubMed

Keshtkaran, Mohammad Reza; Yang, Zhi

2017-06-01

Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.
Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling

NASA Astrophysics Data System (ADS)

Keshtkaran, Mohammad Reza; Yang, Zhi

2017-06-01

Objective. Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. Approach. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Main results. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. Significance. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.
A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework

DOE PAGES

Zhu, Feng; Aziz, H. M. Abdul; Qian, Xinwu; ...

2015-01-31

Our study develops a novel reinforcement learning algorithm for the challenging coordinated signal control problem. Traffic signals are modeled as intelligent agents interacting with the stochastic traffic environment. The model is built on the framework of coordinated reinforcement learning. The Junction Tree Algorithm (JTA) based reinforcement learning is proposed to obtain an exact inference of the best joint actions for all the coordinated intersections. Moreover, the algorithm is implemented and tested with a network containing 18 signalized intersections in VISSIM. Finally, our results show that the JTA based algorithm outperforms independent learning (Q-learning), real-time adaptive learning, and fixed timing plansmore » in terms of average delay, number of stops, and vehicular emissions at the network level.« less
MODIS Science Algorithms and Data Systems Lessons Learned

NASA Technical Reports Server (NTRS)

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.
Protein-ligand docking using fitness learning-based artificial bee colony with proximity stimuli.

PubMed

Uehara, Shota; Fujimoto, Kazuhiro J; Tanaka, Shigenori

2015-07-07

Protein-ligand docking is an optimization problem, which aims to identify the binding pose of a ligand with the lowest energy in the active site of a target protein. In this study, we employed a novel optimization algorithm called fitness learning-based artificial bee colony with proximity stimuli (FlABCps) for docking. Simulation results revealed that FlABCps improved the success rate of docking, compared to four state-of-the-art algorithms. The present results also showed superior docking performance of FlABCps, in particular for dealing with highly flexible ligands and proteins with a wide and shallow binding pocket.
Guided Discovery, Visualization, and Technology Applied to the New Curriculum for Secondary Mathematics.

ERIC Educational Resources Information Center

Smith, Karan B.

1996-01-01

Presents activities which highlight major concepts of linear programming. Demonstrates how technology allows students to solve linear programming problems using exploration prior to learning algorithmic methods. (DDR)
An analysis dictionary learning algorithm under a noisy data model with orthogonality constraint.

PubMed

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.
Ask-the-expert: Active Learning Based Knowledge Discovery Using the Expert

NASA Technical Reports Server (NTRS)

Das, Kamalika; Avrekh, Ilya; Matthews, Bryan; Sharma, Manali; Oza, Nikunj

2017-01-01

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the backend. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.
Ask-the-Expert: Active Learning Based Knowledge Discovery Using the Expert

NASA Technical Reports Server (NTRS)

Das, Kamalika

2017-01-01

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the back end. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.
Human Activity Recognition from Body Sensor Data using Deep Learning.

PubMed

Hassan, Mohammad Mehedi; Huda, Shamsul; Uddin, Md Zia; Almogren, Ahmad; Alrubaian, Majed

2018-04-16

In recent years, human activity recognition from body sensor data or wearable sensor data has become a considerable research attention from academia and health industry. This research can be useful for various e-health applications such as monitoring elderly and physical impaired people at Smart home to improve their rehabilitation processes. However, it is not easy to accurately and automatically recognize physical human activity through wearable sensors due to the complexity and variety of body activities. In this paper, we address the human activity recognition problem as a classification problem using wearable body sensor data. In particular, we propose to utilize a Deep Belief Network (DBN) model for successful human activity recognition. First, we extract the important initial features from the raw body sensor data. Then, a kernel principal component analysis (KPCA) and linear discriminant analysis (LDA) are performed to further process the features and make them more robust to be useful for fast activity recognition. Finally, the DBN is trained by these features. Various experiments were performed on a real-world wearable sensor dataset to verify the effectiveness of the deep learning algorithm. The results show that the proposed DBN outperformed other algorithms and achieves satisfactory activity recognition performance.
A Semisupervised Support Vector Machines Algorithm for BCI Systems

PubMed Central

Qin, Jianzhao; Li, Yuanqing; Sun, Wei

2007-01-01

As an emerging technology, brain-computer interfaces (BCIs) bring us new communication interfaces which translate brain activities into control signals for devices like computers, robots, and so forth. In this study, we propose a semisupervised support vector machine (SVM) algorithm for brain-computer interface (BCI) systems, aiming at reducing the time-consuming training process. In this algorithm, we apply a semisupervised SVM for translating the features extracted from the electrical recordings of brain into control signals. This SVM classifier is built from a small labeled data set and a large unlabeled data set. Meanwhile, to reduce the time for training semisupervised SVM, we propose a batch-mode incremental learning method, which can also be easily applied to the online BCI systems. Additionally, it is suggested in many studies that common spatial pattern (CSP) is very effective in discriminating two different brain states. However, CSP needs a sufficient labeled data set. In order to overcome the drawback of CSP, we suggest a two-stage feature extraction method for the semisupervised learning algorithm. We apply our algorithm to two BCI experimental data sets. The offline data analysis results demonstrate the effectiveness of our algorithm. PMID:18368141
Machine Learning Methods for Attack Detection in the Smart Grid.

PubMed

Ozay, Mete; Esnaola, Inaki; Yarman Vural, Fatos Tunay; Kulkarni, Sanjeev R; Poor, H Vincent

2016-08-01

Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semisupervised) are employed with decision- and feature-level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than attack detection algorithms that employ state vector estimation methods in the proposed attack detection framework.
A Locality-Constrained and Label Embedding Dictionary Learning Algorithm for Image Classification.

PubMed

Zhengming Li; Zhihui Lai; Yong Xu; Jian Yang; Zhang, David

2017-02-01

Locality and label information of training samples play an important role in image classification. However, previous dictionary learning algorithms do not take the locality and label information of atoms into account together in the learning process, and thus their performance is limited. In this paper, a discriminative dictionary learning algorithm, called the locality-constrained and label embedding dictionary learning (LCLE-DL) algorithm, was proposed for image classification. First, the locality information was preserved using the graph Laplacian matrix of the learned dictionary instead of the conventional one derived from the training samples. Then, the label embedding term was constructed using the label information of atoms instead of the classification error term, which contained discriminating information of the learned dictionary. The optimal coding coefficients derived by the locality-based and label-based reconstruction were effective for image classification. Experimental results demonstrated that the LCLE-DL algorithm can achieve better performance than some state-of-the-art algorithms.
Fidelity-Based Ant Colony Algorithm with Q-learning of Quantum System

NASA Astrophysics Data System (ADS)

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.
Fidelity-Based Ant Colony Algorithm with Q-learning of Quantum System

NASA Astrophysics Data System (ADS)

Liao, Qin; Guo, Ying; Tu, Yifeng; Zhang, Hang

2017-12-01

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.
Human resource recommendation algorithm based on ensemble learning and Spark

NASA Astrophysics Data System (ADS)

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.
Visual Inference Programming

NASA Technical Reports Server (NTRS)

Wheeler, Kevin; Timucin, Dogan; Rabbette, Maura; Curry, Charles; Allan, Mark; Lvov, Nikolay; Clanton, Sam; Pilewskie, Peter

2002-01-01

The goal of visual inference programming is to develop a software framework data analysis and to provide machine learning algorithms for inter-active data exploration and visualization. The topics include: 1) Intelligent Data Understanding (IDU) framework; 2) Challenge problems; 3) What's new here; 4) Framework features; 5) Wiring diagram; 6) Generated script; 7) Results of script; 8) Initial algorithms; 9) Independent Component Analysis for instrument diagnosis; 10) Output sensory mapping virtual joystick; 11) Output sensory mapping typing; 12) Closed-loop feedback mu-rhythm control; 13) Closed-loop training; 14) Data sources; and 15) Algorithms. This paper is in viewgraph form.
A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials.

PubMed

Aziz, Omar; Musngi, Magnus; Park, Edward J; Mori, Greg; Robinovitch, Stephen N

2017-01-01

Falls are the leading cause of injury-related morbidity and mortality among older adults. Over 90 % of hip and wrist fractures and 60 % of traumatic brain injuries in older adults are due to falls. Another serious consequence of falls among older adults is the 'long lie' experienced by individuals who are unable to get up and remain on the ground for an extended period of time after a fall. Considerable research has been conducted over the past decade on the design of wearable sensor systems that can automatically detect falls and send an alert to care providers to reduce the frequency and severity of long lies. While most systems described to date incorporate threshold-based algorithms, machine learning algorithms may offer increased accuracy in detecting falls. In the current study, we compared the accuracy of these two approaches in detecting falls by conducting a comprehensive set of falling experiments with 10 young participants. Participants wore waist-mounted tri-axial accelerometers and simulated the most common causes of falls observed in older adults, along with near-falls and activities of daily living. The overall performance of five machine learning algorithms was greater than the performance of five threshold-based algorithms described in the literature, with support vector machines providing the highest combination of sensitivity and specificity.

On adaptive learning rate that guarantees convergence in feedforward networks.

PubMed

Behera, Laxmidhar; Kumar, Swagat; Patnaik, Awhan

2006-09-01

This paper investigates new learning algorithms (LF I and LF II) based on Lyapunov function for the training of feedforward neural networks. It is observed that such algorithms have interesting parallel with the popular backpropagation (BP) algorithm where the fixed learning rate is replaced by an adaptive learning rate computed using convergence theorem based on Lyapunov stability theory. LF II, a modified version of LF I, has been introduced with an aim to avoid local minima. This modification also helps in improving the convergence speed in some cases. Conditions for achieving global minimum for these kind of algorithms have been studied in detail. The performances of the proposed algorithms are compared with BP algorithm and extended Kalman filtering (EKF) on three bench-mark function approximation problems: XOR, 3-bit parity, and 8-3 encoder. The comparisons are made in terms of number of learning iterations and computational time required for convergence. It is found that the proposed algorithms (LF I and II) are much faster in convergence than other two algorithms to attain same accuracy. Finally, the comparison is made on a complex two-dimensional (2-D) Gabor function and effect of adaptive learning rate for faster convergence is verified. In a nutshell, the investigations made in this paper help us better understand the learning procedure of feedforward neural networks in terms of adaptive learning rate, convergence speed, and local minima.
Supervised Machine Learning Algorithms Can Classify Open-Text Feedback of Doctor Performance With Human-Level Accuracy

PubMed Central

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). Scores did not vary between doctors who were rated as popular or innovative and those who were not rated at all (P>.05). Conclusions Machine learning algorithms can classify open-text feedback of doctor performance into multiple themes derived by human raters with high performance. Colleague open-text comments that signal respect, professionalism, and being interpersonal may be key indicators of doctor’s performance. PMID:28298265
Supervised Machine Learning Algorithms Can Classify Open-Text Feedback of Doctor Performance With Human-Level Accuracy.

PubMed

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). Scores did not vary between doctors who were rated as popular or innovative and those who were not rated at all (P>.05). Machine learning algorithms can classify open-text feedback of doctor performance into multiple themes derived by human raters with high performance. Colleague open-text comments that signal respect, professionalism, and being interpersonal may be key indicators of doctor's performance. ©Chris Gibbons, Suzanne Richards, Jose Maria Valderas, John Campbell. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 15.03.2017.
Mirrored STDP Implements Autoencoder Learning in a Network of Spiking Neurons.

PubMed

Burbank, Kendra S

2015-12-01

The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be stacked to learn increasingly abstract representations. Several computational neuroscience models of sensory areas, including Olshausen & Field's Sparse Coding algorithm, can be seen as autoencoder variants, and autoencoders have seen extensive use in the machine learning community. Despite their power and versatility, autoencoders have been difficult to implement in a biologically realistic fashion. The challenges include their need to calculate differences between two neuronal activities and their requirement for learning rules which lead to identical changes at feedforward and feedback connections. Here, we study a biologically realistic network of integrate-and-fire neurons with anatomical connectivity and synaptic plasticity that closely matches that observed in cortical sensory areas. Our choice of synaptic plasticity rules is inspired by recent experimental and theoretical results suggesting that learning at feedback connections may have a different form from learning at feedforward connections, and our results depend critically on this novel choice of plasticity rules. Specifically, we propose that plasticity rules at feedforward versus feedback connections are temporally opposed versions of spike-timing dependent plasticity (STDP), leading to a symmetric combined rule we call Mirrored STDP (mSTDP). We show that with mSTDP, our network follows a learning rule that approximately minimizes an autoencoder loss function. When trained with whitened natural image patches, the learned synaptic weights resemble the receptive fields seen in V1. Our results use realistic synaptic plasticity rules to show that the powerful autoencoder learning algorithm could be within the reach of real biological networks.
Mirrored STDP Implements Autoencoder Learning in a Network of Spiking Neurons

PubMed Central

Burbank, Kendra S.

2015-01-01

The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be stacked to learn increasingly abstract representations. Several computational neuroscience models of sensory areas, including Olshausen & Field’s Sparse Coding algorithm, can be seen as autoencoder variants, and autoencoders have seen extensive use in the machine learning community. Despite their power and versatility, autoencoders have been difficult to implement in a biologically realistic fashion. The challenges include their need to calculate differences between two neuronal activities and their requirement for learning rules which lead to identical changes at feedforward and feedback connections. Here, we study a biologically realistic network of integrate-and-fire neurons with anatomical connectivity and synaptic plasticity that closely matches that observed in cortical sensory areas. Our choice of synaptic plasticity rules is inspired by recent experimental and theoretical results suggesting that learning at feedback connections may have a different form from learning at feedforward connections, and our results depend critically on this novel choice of plasticity rules. Specifically, we propose that plasticity rules at feedforward versus feedback connections are temporally opposed versions of spike-timing dependent plasticity (STDP), leading to a symmetric combined rule we call Mirrored STDP (mSTDP). We show that with mSTDP, our network follows a learning rule that approximately minimizes an autoencoder loss function. When trained with whitened natural image patches, the learned synaptic weights resemble the receptive fields seen in V1. Our results use realistic synaptic plasticity rules to show that the powerful autoencoder learning algorithm could be within the reach of real biological networks. PMID:26633645
Challenges in the Verification of Reinforcement Learning Algorithms

NASA Technical Reports Server (NTRS)

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.
Semi-supervised learning via regularized boosting working on multiple semi-supervised assumptions.

PubMed

Chen, Ke; Wang, Shihai

2011-01-01

Semi-supervised learning concerns the problem of learning in the presence of labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learning with various strategies. To our knowledge, however, none of them takes all three semi-supervised assumptions, i.e., smoothness, cluster, and manifold assumptions, together into account during boosting learning. In this paper, we propose a novel cost functional consisting of the margin cost on labeled data and the regularization penalty on unlabeled data based on three fundamental semi-supervised assumptions. Thus, minimizing our proposed cost functional with a greedy yet stagewise functional optimization procedure leads to a generic boosting framework for semi-supervised learning. Extensive experiments demonstrate that our algorithm yields favorite results for benchmark and real-world classification tasks in comparison to state-of-the-art semi-supervised learning algorithms, including newly developed boosting algorithms. Finally, we discuss relevant issues and relate our algorithm to the previous work.
Efficient Learning Algorithms with Limited Information

ERIC Educational Resources Information Center

De, Anindya

2013-01-01

The thesis explores efficient learning algorithms in settings which are more restrictive than the PAC model of learning (Valiant) in one of the following two senses: (i) The learning algorithm has a very weak access to the unknown function, as in, it does not get labeled samples for the unknown function (ii) The error guarantee required from the…
Compressive sensing of electrocardiogram signals by promoting sparsity on the second-order difference and by using dictionary learning.

PubMed

Pant, Jeevan K; Krishnan, Sridhar

2014-04-01

A new algorithm for the reconstruction of electrocardiogram (ECG) signals and a dictionary learning algorithm for the enhancement of its reconstruction performance for a class of signals are proposed. The signal reconstruction algorithm is based on minimizing the lp pseudo-norm of the second-order difference, called as the lp(2d) pseudo-norm, of the signal. The optimization involved is carried out using a sequential conjugate-gradient algorithm. The dictionary learning algorithm uses an iterative procedure wherein a signal reconstruction and a dictionary update steps are repeated until a convergence criterion is satisfied. The signal reconstruction step is implemented by using the proposed signal reconstruction algorithm and the dictionary update step is implemented by using the linear least-squares method. Extensive simulation results demonstrate that the proposed algorithm yields improved reconstruction performance for temporally correlated ECG signals relative to the state-of-the-art lp(1d)-regularized least-squares and Bayesian learning based algorithms. Also for a known class of signals, the reconstruction performance of the proposed algorithm can be improved by applying it in conjunction with a dictionary obtained using the proposed dictionary learning algorithm.
A theory of local learning, the learning channel, and the optimality of backpropagation.

PubMed

Baldi, Pierre; Sadowski, Peter

2016-11-01

In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic neurons, resulting in local learning rules. A systematic framework for studying the space of local learning rules is obtained by first specifying the nature of the local variables, and then the functional form that ties them together into each learning rule. Such a framework enables also the systematic discovery of new learning rules and exploration of relationships between learning rules and group symmetries. We study polynomial local learning rules stratified by their degree and analyze their behavior and capabilities in both linear and non-linear units and networks. Stacking local learning rules in deep feedforward networks leads to deep local learning. While deep local learning can learn interesting representations, it cannot learn complex input-output functions, even when targets are available for the top layer. Learning complex input-output functions requires local deep learning where target information is communicated to the deep layers through a backward learning channel. The nature of the communicated information about the targets and the structure of the learning channel partition the space of learning algorithms. For any learning algorithm, the capacity of the learning channel can be defined as the number of bits provided about the error gradient per weight, divided by the number of required operations per weight. We estimate the capacity associated with several learning algorithms and show that backpropagation outperforms them by simultaneously maximizing the information rate and minimizing the computational cost. This result is also shown to be true for recurrent networks, by unfolding them in time. The theory clarifies the concept of Hebbian learning, establishes the power and limitations of local learning rules, introduces the learning channel which enables a formal analysis of the optimality of backpropagation, and explains the sparsity of the space of learning rules discovered so far. Copyright © 2016 Elsevier Ltd. All rights reserved.
Unsupervised active learning based on hierarchical graph-theoretic clustering.

PubMed

Hu, Weiming; Hu, Wei; Xie, Nianhua; Maybank, Steve

2009-10-01

Most existing active learning approaches are supervised. Supervised active learning has the following problems: inefficiency in dealing with the semantic gap between the distribution of samples in the feature space and their labels, lack of ability in selecting new samples that belong to new categories that have not yet appeared in the training samples, and lack of adaptability to changes in the semantic interpretation of sample categories. To tackle these problems, we propose an unsupervised active learning framework based on hierarchical graph-theoretic clustering. In the framework, two promising graph-theoretic clustering algorithms, namely, dominant-set clustering and spectral clustering, are combined in a hierarchical fashion. Our framework has some advantages, such as ease of implementation, flexibility in architecture, and adaptability to changes in the labeling. Evaluations on data sets for network intrusion detection, image classification, and video classification have demonstrated that our active learning framework can effectively reduce the workload of manual classification while maintaining a high accuracy of automatic classification. It is shown that, overall, our framework outperforms the support-vector-machine-based supervised active learning, particularly in terms of dealing much more efficiently with new samples whose categories have not yet appeared in the training samples.
Recognition of strong earthquake-prone areas with a single learning class

NASA Astrophysics Data System (ADS)

Gvishiani, A. D.; Agayan, S. M.; Dzeboev, B. A.; Belov, I. O.

2017-05-01

This article presents a new Barrier recognition algorithm with learning, designed for recognition of earthquake-prone areas. In comparison to the Crust (Kora) algorithm, used by the classical EPA approach, the Barrier algorithm proceeds with learning just on one "pure" high-seismic class. The new algorithm operates in the space of absolute values of the geological-geophysical parameters of the objects. The algorithm is used for recognition of earthquake-prone areas with M ≥ 6.0 in the Caucasus region. Comparative analysis of the Crust and Barrier algorithms justifies their productive coherence.
Active machine learning-driven experimentation to determine compound effects on protein patterns

PubMed Central

Naik, Armaghan W; Kangas, Joshua D; Sullivan, Devin P; Murphy, Robert F

2016-01-01

High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance. DOI: http://dx.doi.org/10.7554/eLife.10047.001 PMID:26840049
Bare-Bones Teaching-Learning-Based Optimization

PubMed Central

Zou, Feng; Wang, Lei; Hei, Xinhong; Chen, Debao; Jiang, Qiaoyong; Li, Hongye

2014-01-01

Teaching-learning-based optimization (TLBO) algorithm which simulates the teaching-learning process of the class room is one of the recently proposed swarm intelligent (SI) algorithms. In this paper, a new TLBO variant called bare-bones teaching-learning-based optimization (BBTLBO) is presented to solve the global optimization problems. In this method, each learner of teacher phase employs an interactive learning strategy, which is the hybridization of the learning strategy of teacher phase in the standard TLBO and Gaussian sampling learning based on neighborhood search, and each learner of learner phase employs the learning strategy of learner phase in the standard TLBO or the new neighborhood search strategy. To verify the performance of our approaches, 20 benchmark functions and two real-world problems are utilized. Conducted experiments can been observed that the BBTLBO performs significantly better than, or at least comparable to, TLBO and some existing bare-bones algorithms. The results indicate that the proposed algorithm is competitive to some other optimization algorithms. PMID:25013844
Bare-bones teaching-learning-based optimization.

PubMed

Zou, Feng; Wang, Lei; Hei, Xinhong; Chen, Debao; Jiang, Qiaoyong; Li, Hongye

2014-01-01

Teaching-learning-based optimization (TLBO) algorithm which simulates the teaching-learning process of the class room is one of the recently proposed swarm intelligent (SI) algorithms. In this paper, a new TLBO variant called bare-bones teaching-learning-based optimization (BBTLBO) is presented to solve the global optimization problems. In this method, each learner of teacher phase employs an interactive learning strategy, which is the hybridization of the learning strategy of teacher phase in the standard TLBO and Gaussian sampling learning based on neighborhood search, and each learner of learner phase employs the learning strategy of learner phase in the standard TLBO or the new neighborhood search strategy. To verify the performance of our approaches, 20 benchmark functions and two real-world problems are utilized. Conducted experiments can been observed that the BBTLBO performs significantly better than, or at least comparable to, TLBO and some existing bare-bones algorithms. The results indicate that the proposed algorithm is competitive to some other optimization algorithms.
Spike sorting based upon machine learning algorithms (SOMA).

PubMed

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.
A strategy for quantum algorithm design assisted by machine learning

NASA Astrophysics Data System (ADS)

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.
Committee-Based Active Learning for Surrogate-Assisted Particle Swarm Optimization of Expensive Problems.

PubMed

Wang, Handing; Jin, Yaochu; Doherty, John

2017-09-01

Function evaluations (FEs) of many real-world optimization problems are time or resource consuming, posing a serious challenge to the application of evolutionary algorithms (EAs) to solve these problems. To address this challenge, the research on surrogate-assisted EAs has attracted increasing attention from both academia and industry over the past decades. However, most existing surrogate-assisted EAs (SAEAs) either still require thousands of expensive FEs to obtain acceptable solutions, or are only applied to very low-dimensional problems. In this paper, a novel surrogate-assisted particle swarm optimization (PSO) inspired from committee-based active learning (CAL) is proposed. In the proposed algorithm, a global model management strategy inspired from CAL is developed, which searches for the best and most uncertain solutions according to a surrogate ensemble using a PSO algorithm and evaluates these solutions using the expensive objective function. In addition, a local surrogate model is built around the best solution obtained so far. Then, a PSO algorithm searches on the local surrogate to find its optimum and evaluates it. The evolutionary search using the global model management strategy switches to the local search once no further improvement can be observed, and vice versa. This iterative search process continues until the computational budget is exhausted. Experimental results comparing the proposed algorithm with a few state-of-the-art SAEAs on both benchmark problems up to 30 decision variables as well as an airfoil design problem demonstrate that the proposed algorithm is able to achieve better or competitive solutions with a limited budget of hundreds of exact FEs.
A Methodology for the Hybridization Based in Active Components: The Case of cGA and Scatter Search

PubMed Central

Alba, Enrique; Leguizamón, Guillermo

2016-01-01

This work presents the results of a new methodology for hybridizing metaheuristics. By first locating the active components (parts) of one algorithm and then inserting them into second one, we can build efficient and accurate optimization, search, and learning algorithms. This gives a concrete way of constructing new techniques that contrasts the spread ad hoc way of hybridizing. In this paper, the enhanced algorithm is a Cellular Genetic Algorithm (cGA) which has been successfully used in the past to find solutions to such hard optimization problems. In order to extend and corroborate the use of active components as an emerging hybridization methodology, we propose here the use of active components taken from Scatter Search (SS) to improve cGA. The results obtained over a varied set of benchmarks are highly satisfactory in efficacy and efficiency when compared with a standard cGA. Moreover, the proposed hybrid approach (i.e., cGA+SS) has shown encouraging results with regard to earlier applications of our methodology. PMID:27403153
Online Feature Transformation Learning for Cross-Domain Object Category Recognition.

PubMed

Zhang, Xuesong; Zhuang, Yan; Wang, Wei; Pedrycz, Witold

2017-06-09

In this paper, we introduce a new research problem termed online feature transformation learning in the context of multiclass object category recognition. The learning of a feature transformation is viewed as learning a global similarity metric function in an online manner. We first consider the problem of online learning a feature transformation matrix expressed in the original feature space and propose an online passive aggressive feature transformation algorithm. Then these original features are mapped to kernel space and an online single kernel feature transformation (OSKFT) algorithm is developed to learn a nonlinear feature transformation. Based on the OSKFT and the existing Hedge algorithm, a novel online multiple kernel feature transformation algorithm is also proposed, which can further improve the performance of online feature transformation learning in large-scale application. The classifier is trained with k nearest neighbor algorithm together with the learned similarity metric function. Finally, we experimentally examined the effect of setting different parameter values in the proposed algorithms and evaluate the model performance on several multiclass object recognition data sets. The experimental results demonstrate the validity and good performance of our methods on cross-domain and multiclass object recognition application.

A linear recurrent kernel online learning algorithm with sparse updates.

PubMed

Fan, Haijin; Song, Qing

2014-02-01

In this paper, we propose a recurrent kernel algorithm with selectively sparse updates for online learning. The algorithm introduces a linear recurrent term in the estimation of the current output. This makes the past information reusable for updating of the algorithm in the form of a recurrent gradient term. To ensure that the reuse of this recurrent gradient indeed accelerates the convergence speed, a novel hybrid recurrent training is proposed to switch on or off learning the recurrent information according to the magnitude of the current training error. Furthermore, the algorithm includes a data-dependent adaptive learning rate which can provide guaranteed system weight convergence at each training iteration. The learning rate is set as zero when the training violates the derived convergence conditions, which makes the algorithm updating process sparse. Theoretical analyses of the weight convergence are presented and experimental results show the good performance of the proposed algorithm in terms of convergence speed and estimation accuracy. Copyright © 2013 Elsevier Ltd. All rights reserved.
Kernel Temporal Differences for Neural Decoding

PubMed Central

Bae, Jihye; Sanchez Giraldo, Luis G.; Pohlmeyer, Eric A.; Francis, Joseph T.; Sanchez, Justin C.; Príncipe, José C.

2015-01-01

We study the feasibility and capability of the kernel temporal difference (KTD)(λ) algorithm for neural decoding. KTD(λ) is an online, kernel-based learning algorithm, which has been introduced to estimate value functions in reinforcement learning. This algorithm combines kernel-based representations with the temporal difference approach to learning. One of our key observations is that by using strictly positive definite kernels, algorithm's convergence can be guaranteed for policy evaluation. The algorithm's nonlinear functional approximation capabilities are shown in both simulations of policy evaluation and neural decoding problems (policy improvement). KTD can handle high-dimensional neural states containing spatial-temporal information at a reasonable computational complexity allowing real-time applications. When the algorithm seeks a proper mapping between a monkey's neural states and desired positions of a computer cursor or a robot arm, in both open-loop and closed-loop experiments, it can effectively learn the neural state to action mapping. Finally, a visualization of the coadaptation process between the decoder and the subject shows the algorithm's capabilities in reinforcement learning brain machine interfaces. PMID:25866504
Changes in corticostriatal connectivity during reinforcement learning in humans.

PubMed

Horga, Guillermo; Maia, Tiago V; Marsh, Rachel; Hao, Xuejun; Xu, Dongrong; Duan, Yunsuo; Tau, Gregory Z; Graniello, Barbara; Wang, Zhishun; Kangarlu, Alayar; Martinez, Diana; Packard, Mark G; Peterson, Bradley S

2015-02-01

Many computational models assume that reinforcement learning relies on changes in synaptic efficacy between cortical regions representing stimuli and striatal regions involved in response selection, but this assumption has thus far lacked empirical support in humans. We recorded hemodynamic signals with fMRI while participants navigated a virtual maze to find hidden rewards. We fitted a reinforcement-learning algorithm to participants' choice behavior and evaluated the neural activity and the changes in functional connectivity related to trial-by-trial learning variables. Activity in the posterior putamen during choice periods increased progressively during learning. Furthermore, the functional connections between the sensorimotor cortex and the posterior putamen strengthened progressively as participants learned the task. These changes in corticostriatal connectivity differentiated participants who learned the task from those who did not. These findings provide a direct link between changes in corticostriatal connectivity and learning, thereby supporting a central assumption common to several computational models of reinforcement learning. © 2014 Wiley Periodicals, Inc.
Single-hidden-layer feed-forward quantum neural network based on Grover learning.

PubMed

Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min

2013-09-01

In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning. Copyright © 2013 Elsevier Ltd. All rights reserved.
Research on B Cell Algorithm for Learning to Rank Method Based on Parallel Strategy.

PubMed

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.
Research on B Cell Algorithm for Learning to Rank Method Based on Parallel Strategy

PubMed Central

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. PMID:27487242
Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods.

PubMed

Kerr, Jacqueline; Carlson, Jordan; Godbole, Suneeta; Cadmus-Bertram, Lisa; Bellettiere, John; Hartman, Sheri

2018-02-13

To improve estimates of sitting time from hip worn accelerometers used in large cohort studies by employing machine learning methods developed on free living activPAL data. Thirty breast cancer survivors concurrently wore a hip worn accelerometer and a thigh worn activPAL for 7 days. A random forest classifier, trained on the activPAL data, was employed to detect sitting, standing and sit-stand transitions in 5 second windows in the hip worn accelerometer. The classifier estimates were compared to the standard accelerometer cut point and significant differences across different bout lengths were investigated using mixed effect models. Overall, the algorithm predicted the postures with moderate accuracy (stepping 77%, standing 63%, sitting 67%, sit to stand 52% and stand to sit 51%). Daily level analyses indicated that errors in transition estimates were only occurring during sitting bouts of 2 minutes or less. The standard cut point was significantly different from the activPAL across all bout lengths, overestimating short bouts and underestimating long bouts. This is among the first algorithms for sitting and standing for hip worn accelerometer data to be trained from entirely free living activPAL data. The new algorithm detected prolonged sitting which has been shown to be most detrimental to health. Further validation and training in larger cohorts is warranted.This is an open access article distributed under the Creative Commons Attribution License 4.0 (CCBY), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Gradient descent learning algorithm overview: a general dynamical systems perspective.

PubMed

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.
Network congestion control algorithm based on Actor-Critic reinforcement learning model

NASA Astrophysics Data System (ADS)

Xu, Tao; Gong, Lina; Zhang, Wei; Li, Xuhong; Wang, Xia; Pan, Wenwen

2018-04-01

Aiming at the network congestion control problem, a congestion control algorithm based on Actor-Critic reinforcement learning model is designed. Through the genetic algorithm in the congestion control strategy, the network congestion problems can be better found and prevented. According to Actor-Critic reinforcement learning, the simulation experiment of network congestion control algorithm is designed. The simulation experiments verify that the AQM controller can predict the dynamic characteristics of the network system. Moreover, the learning strategy is adopted to optimize the network performance, and the dropping probability of packets is adaptively adjusted so as to improve the network performance and avoid congestion. Based on the above finding, it is concluded that the network congestion control algorithm based on Actor-Critic reinforcement learning model can effectively avoid the occurrence of TCP network congestion.
Deep learning for computational chemistry.

PubMed

Goh, Garrett B; Hodas, Nathan O; Vishnu, Abhinav

2017-06-15

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including quantitative structure activity relationship, virtual screening, protein structure prediction, quantum chemistry, materials design, and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non-neural networks state-of-the-art models across disparate research topics, and deep neural network-based models often exceeded the "glass ceiling" expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.
Using Ensemble Decisions and Active Selection to Improve Low-Cost Labeling for Multi-View Data

NASA Technical Reports Server (NTRS)

Rebbapragada, Umaa; Wagstaff, Kiri L.

2011-01-01

This paper seeks to improve low-cost labeling in terms of training set reliability (the fraction of correctly labeled training items) and test set performance for multi-view learning methods. Co-training is a popular multiview learning method that combines high-confidence example selection with low-cost (self) labeling. However, co-training with certain base learning algorithms significantly reduces training set reliability, causing an associated drop in prediction accuracy. We propose the use of ensemble labeling to improve reliability in such cases. We also discuss and show promising results on combining low-cost ensemble labeling with active (low-confidence) example selection. We unify these example selection and labeling strategies under collaborative learning, a family of techniques for multi-view learning that we are developing for distributed, sensor-network environments.
Algorithm Visualization System for Teaching Spatial Data Algorithms

ERIC Educational Resources Information Center

Nikander, Jussi; Helminen, Juha; Korhonen, Ari

2010-01-01

TRAKLA2 is a web-based learning environment for data structures and algorithms. The system delivers automatically assessed algorithm simulation exercises that are solved using a graphical user interface. In this work, we introduce a novel learning environment for spatial data algorithms, SDA-TRAKLA2, which has been implemented on top of the…
Measuring Constraint-Set Utility for Partitional Clustering Algorithms

NASA Technical Reports Server (NTRS)

Davidson, Ian; Wagstaff, Kiri L.; Basu, Sugato

2006-01-01

Clustering with constraints is an active area of machine learning and data mining research. Previous empirical work has convincingly shown that adding constraints to clustering improves the performance of a variety of algorithms. However, in most of these experiments, results are averaged over different randomly chosen constraint sets from a given set of labels, thereby masking interesting properties of individual sets. We demonstrate that constraint sets vary significantly in how useful they are for constrained clustering; some constraint sets can actually decrease algorithm performance. We create two quantitative measures, informativeness and coherence, that can be used to identify useful constraint sets. We show that these measures can also help explain differences in performance for four particular constrained clustering algorithms.
Active-learning strategies in computer-assisted drug discovery.

PubMed

Reker, Daniel; Schneider, Gisbert

2015-04-01

High-throughput compound screening is time and resource consuming, and considerable effort is invested into screening compound libraries, profiling, and selecting the most promising candidates for further testing. Active-learning methods assist the selection process by focusing on areas of chemical space that have the greatest chance of success while considering structural novelty. The core feature of these algorithms is their ability to adapt the structure-activity landscapes through feedback. Instead of full-deck screening, only focused subsets of compounds are tested, and the experimental readout is used to refine molecule selection for subsequent screening cycles. Once implemented, these techniques have the potential to reduce costs and save precious materials. Here, we provide a comprehensive overview of the various computational active-learning approaches and outline their potential for drug discovery. Copyright © 2014 Elsevier Ltd. All rights reserved.
Feature Selection in Classification of Eye Movements Using Electrooculography for Activity Recognition

PubMed Central

Mala, S.; Latha, K.

2014-01-01

Activity recognition is needed in different requisition, for example, reconnaissance system, patient monitoring, and human-computer interfaces. Feature selection plays an important role in activity recognition, data mining, and machine learning. In selecting subset of features, an efficient evolutionary algorithm Differential Evolution (DE), a very efficient optimizer, is used for finding informative features from eye movements using electrooculography (EOG). Many researchers use EOG signals in human-computer interactions with various computational intelligence methods to analyze eye movements. The proposed system involves analysis of EOG signals using clearness based features, minimum redundancy maximum relevance features, and Differential Evolution based features. This work concentrates more on the feature selection algorithm based on DE in order to improve the classification for faultless activity recognition. PMID:25574185
Feature selection in classification of eye movements using electrooculography for activity recognition.

PubMed

Mala, S; Latha, K

2014-01-01

Activity recognition is needed in different requisition, for example, reconnaissance system, patient monitoring, and human-computer interfaces. Feature selection plays an important role in activity recognition, data mining, and machine learning. In selecting subset of features, an efficient evolutionary algorithm Differential Evolution (DE), a very efficient optimizer, is used for finding informative features from eye movements using electrooculography (EOG). Many researchers use EOG signals in human-computer interactions with various computational intelligence methods to analyze eye movements. The proposed system involves analysis of EOG signals using clearness based features, minimum redundancy maximum relevance features, and Differential Evolution based features. This work concentrates more on the feature selection algorithm based on DE in order to improve the classification for faultless activity recognition.
Active learning strategies for the deduplication of electronic patient data using classification trees.

PubMed

Sariyar, M; Borg, A; Pommerening, K

2012-10-01

Supervised record linkage methods often require a clerical review to gain informative training data. Active learning means to actively prompt the user to label data with special characteristics in order to minimise the review costs. We conducted an empirical evaluation to investigate whether a simple active learning strategy using binary comparison patterns is sufficient or if string metrics together with a more sophisticated algorithm are necessary to achieve high accuracies with a small training set. Based on medical registry data with different numbers of attributes, we used active learning to acquire training sets for classification trees, which were then used to classify the remaining data. Active learning for binary patterns means that every distinct comparison pattern represents a stratum from which one item is sampled. Active learning for patterns consisting of the Levenshtein string metric values uses an iterative process where the most informative and representative examples are added to the training set. In this context, we extended the active learning strategy by Sarawagi and Bhamidipaty (2002). On the original data set, active learning based on binary comparison patterns leads to the best results. When dropping four or six attributes, using string metrics leads to better results. In both cases, not more than 200 manually reviewed training examples are necessary. In record linkage applications where only forename, name and birthday are available as attributes, we suggest the sophisticated active learning strategy based on string metrics in order to achieve highly accurate results. We recommend the simple strategy if more attributes are available, as in our study. In both cases, active learning significantly reduces the amount of manual involvement in training data selection compared to usual record linkage settings. Copyright © 2012 Elsevier Inc. All rights reserved.
Constrained Metric Learning by Permutation Inducing Isometries.

PubMed

Bosveld, Joel; Mahmood, Arif; Huynh, Du Q; Noakes, Lyle

2016-01-01

The choice of metric critically affects the performance of classification and clustering algorithms. Metric learning algorithms attempt to improve performance, by learning a more appropriate metric. Unfortunately, most of the current algorithms learn a distance function which is not invariant to rigid transformations of images. Therefore, the distances between two images and their rigidly transformed pair may differ, leading to inconsistent classification or clustering results. We propose to constrain the learned metric to be invariant to the geometry preserving transformations of images that induce permutations in the feature space. The constraint that these transformations are isometries of the metric ensures consistent results and improves accuracy. Our second contribution is a dimension reduction technique that is consistent with the isometry constraints. Our third contribution is the formulation of the isometry constrained logistic discriminant metric learning (IC-LDML) algorithm, by incorporating the isometry constraints within the objective function of the LDML algorithm. The proposed algorithm is compared with the existing techniques on the publicly available labeled faces in the wild, viewpoint-invariant pedestrian recognition, and Toy Cars data sets. The IC-LDML algorithm has outperformed existing techniques for the tasks of face recognition, person identification, and object classification by a significant margin.
A review of active learning approaches to experimental design for uncovering biological networks

PubMed Central

2017-01-01

Various types of biological knowledge describe networks of interactions among elementary entities. For example, transcriptional regulatory networks consist of interactions among proteins and genes. Current knowledge about the exact structure of such networks is highly incomplete, and laboratory experiments that manipulate the entities involved are conducted to test hypotheses about these networks. In recent years, various automated approaches to experiment selection have been proposed. Many of these approaches can be characterized as active machine learning algorithms. Active learning is an iterative process in which a model is learned from data, hypotheses are generated from the model to propose informative experiments, and the experiments yield new data that is used to update the model. This review describes the various models, experiment selection strategies, validation techniques, and successful applications described in the literature; highlights common themes and notable distinctions among methods; and identifies likely directions of future research and open problems in the area. PMID:28570593
Photometric Supernova Classification with Machine Learning

NASA Astrophysics Data System (ADS)

Lochner, Michelle; McEwen, Jason D.; Peiris, Hiranya V.; Lahav, Ofer; Winter, Max K.

2016-08-01

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

An incremental approach to genetic-algorithms-based classification.

PubMed

Guan, Sheng-Uei; Zhu, Fangming

2005-04-01

Incremental learning has been widely addressed in the machine learning literature to cope with learning tasks where the learning environment is ever changing or training samples become available over time. However, most research work explores incremental learning with statistical algorithms or neural networks, rather than evolutionary algorithms. The work in this paper employs genetic algorithms (GAs) as basic learning algorithms for incremental learning within one or more classifier agents in a multiagent environment. Four new approaches with different initialization schemes are proposed. They keep the old solutions and use an "integration" operation to integrate them with new elements to accommodate new attributes, while biased mutation and crossover operations are adopted to further evolve a reinforced solution. The simulation results on benchmark classification data sets show that the proposed approaches can deal with the arrival of new input attributes and integrate them with the original input space. It is also shown that the proposed approaches can be successfully used for incremental learning and improve classification rates as compared to the retraining GA. Possible applications for continuous incremental training and feature selection are also discussed.
Data-driven advice for applying machine learning to bioinformatics problems

PubMed Central

Olson, Randal S.; La Cava, William; Mustahsan, Zairah; Varik, Akshay; Moore, Jason H.

2017-01-01

As the bioinformatics field grows, it must keep pace not only with new data but with new algorithms. Here we contribute a thorough analysis of 13 state-of-the-art, commonly used machine learning algorithms on a set of 165 publicly available classification problems in order to provide data-driven algorithm recommendations to current researchers. We present a number of statistical and visual comparisons of algorithm performance and quantify the effect of model selection and algorithm tuning for each algorithm and dataset. The analysis culminates in the recommendation of five algorithms with hyperparameters that maximize classifier performance across the tested problems, as well as general guidelines for applying machine learning to supervised classification problems. PMID:29218881
A ranking method for the concurrent learning of compounds with various activity profiles.

PubMed

Dörr, Alexander; Rosenbaum, Lars; Zell, Andreas

2015-01-01

In this study, we present a SVM-based ranking algorithm for the concurrent learning of compounds with different activity profiles and their varying prioritization. To this end, a specific labeling of each compound was elaborated in order to infer virtual screening models against multiple targets. We compared the method with several state-of-the-art SVM classification techniques that are capable of inferring multi-target screening models on three chemical data sets (cytochrome P450s, dehydrogenases, and a trypsin-like protease data set) containing three different biological targets each. The experiments show that ranking-based algorithms show an increased performance for single- and multi-target virtual screening. Moreover, compounds that do not completely fulfill the desired activity profile are still ranked higher than decoys or compounds with an entirely undesired profile, compared to other multi-target SVM methods. SVM-based ranking methods constitute a valuable approach for virtual screening in multi-target drug design. The utilization of such methods is most helpful when dealing with compounds with various activity profiles and the finding of many ligands with an already perfectly matching activity profile is not to be expected.
Designing the Architecture of Hierachical Neural Networks Model Attention, Learning and Goal-Oriented Behavior

DTIC Science & Technology

1993-12-31

19,23,25,26,27,28,32,33,35,41]) - A new cost function is postulated and an algorithm that employs this cost function is proposed for the learning of...updates the controller parameters from time to time [53]. The learning control algorithm consist of updating the parameter estimates as used in the...proposed cost function with the other learning type algorithms , such as based upon learning of iterative tasks [Kawamura-85], variable structure
Active learning for solving the incomplete data problem in facial age classification by the furthest nearest-neighbor criterion.

PubMed

Wang, Jian-Gang; Sung, Eric; Yau, Wei-Yun

2011-07-01

Facial age classification is an approach to classify face images into one of several predefined age groups. One of the difficulties in applying learning techniques to the age classification problem is the large amount of labeled training data required. Acquiring such training data is very costly in terms of age progress, privacy, human time, and effort. Although unlabeled face images can be obtained easily, it would be expensive to manually label them on a large scale and getting the ground truth. The frugal selection of the unlabeled data for labeling to quickly reach high classification performance with minimal labeling efforts is a challenging problem. In this paper, we present an active learning approach based on an online incremental bilateral two-dimension linear discriminant analysis (IB2DLDA) which initially learns from a small pool of labeled data and then iteratively selects the most informative samples from the unlabeled set to increasingly improve the classifier. Specifically, we propose a novel data selection criterion called the furthest nearest-neighbor (FNN) that generalizes the margin-based uncertainty to the multiclass case and which is easy to compute, so that the proposed active learning algorithm can handle a large number of classes and large data sizes efficiently. Empirical experiments on FG-NET and Morph databases together with a large unlabeled data set for age categorization problems show that the proposed approach can achieve results comparable or even outperform a conventionally trained active classifier that requires much more labeling effort. Our IB2DLDA-FNN algorithm can achieve similar results much faster than random selection and with fewer samples for age categorization. It also can achieve comparable results with active SVM but is much faster than active SVM in terms of training because kernel methods are not needed. The results on the face recognition database and palmprint/palm vein database showed that our approach can handle problems with large number of classes. Our contributions in this paper are twofold. First, we proposed the IB2DLDA-FNN, the FNN being our novel idea, as a generic on-line or active learning paradigm. Second, we showed that it can be another viable tool for active learning of facial age range classification.
Behavioral Profiling of Scada Network Traffic Using Machine Learning Algorithms

DTIC Science & Technology

2014-03-27

BEHAVIORAL PROFILING OF SCADA NETWORK TRAFFIC USING MACHINE LEARNING ALGORITHMS THESIS Jessica R. Werling, Captain, USAF AFIT-ENG-14-M-81 DEPARTMENT...subject to copyright protection in the United States. AFIT-ENG-14-M-81 BEHAVIORAL PROFILING OF SCADA NETWORK TRAFFIC USING MACHINE LEARNING ...AFIT-ENG-14-M-81 BEHAVIORAL PROFILING OF SCADA NETWORK TRAFFIC USING MACHINE LEARNING ALGORITHMS Jessica R. Werling, B.S.C.S. Captain, USAF Approved
Super-resolution reconstruction of MR image with a novel residual learning network algorithm

NASA Astrophysics Data System (ADS)

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.
Hardware Acceleration of Adaptive Neural Algorithms.

DOE Office of Scientific and Technical Information (OSTI.GOV)

James, Conrad D.

As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - worldmore » conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.« less
Reliability and validity of bilateral ankle accelerometer algorithms for activity recognition and walking speed after stroke.

PubMed

Dobkin, Bruce H; Xu, Xiaoyu; Batalin, Maxim; Thomas, Seth; Kaiser, William

2011-08-01

Outcome measures of mobility for large stroke trials are limited to timed walks for short distances in a laboratory, step counters and ordinal scales of disability and quality of life. Continuous monitoring and outcome measurements of the type and quantity of activity in the community would provide direct data about daily performance, including compliance with exercise and skills practice during routine care and clinical trials. Twelve adults with impaired ambulation from hemiparetic stroke and 6 healthy controls wore triaxial accelerometers on their ankles. Walking speed for repeated outdoor walks was determined by machine-learning algorithms and compared to a stopwatch calculation of speed for distances not known to the algorithm. The reliability of recognizing walking, exercise, and cycling by the algorithms was compared to activity logs. A high correlation was found between stopwatch-measured outdoor walking speed and algorithm-calculated speed (Pearson coefficient, 0.98; P=0.001) and for repeated measures of algorithm-derived walking speed (P=0.01). Bouts of walking >5 steps, variations in walking speed, cycling, stair climbing, and leg exercises were correctly identified during a day in the community. Compared to healthy subjects, those with stroke were, as expected, more sedentary and slower, and their gait revealed high paretic-to-unaffected leg swing ratios. Test-retest reliability and concurrent and construct validity are high for activity pattern-recognition Bayesian algorithms developed from inertial sensors. This ratio scale data can provide real-world monitoring and outcome measurements of lower extremity activities and walking speed for stroke and rehabilitation studies.
Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning.

PubMed

Formisano, Elia; De Martino, Federico; Valente, Giancarlo

2008-09-01

Machine learning and pattern recognition techniques are being increasingly employed in functional magnetic resonance imaging (fMRI) data analysis. By taking into account the full spatial pattern of brain activity measured simultaneously at many locations, these methods allow detecting subtle, non-strictly localized effects that may remain invisible to the conventional analysis with univariate statistical methods. In typical fMRI applications, pattern recognition algorithms "learn" a functional relationship between brain response patterns and a perceptual, cognitive or behavioral state of a subject expressed in terms of a label, which may assume discrete (classification) or continuous (regression) values. This learned functional relationship is then used to predict the unseen labels from a new data set ("brain reading"). In this article, we describe the mathematical foundations of machine learning applications in fMRI. We focus on two methods, support vector machines and relevance vector machines, which are respectively suited for the classification and regression of fMRI patterns. Furthermore, by means of several examples and applications, we illustrate and discuss the methodological challenges of using machine learning algorithms in the context of fMRI data analysis.
Javascript Library for Developing Interactive Micro-Level Animations for Teaching and Learning Algorithms on One-Dimensional Arrays

ERIC Educational Resources Information Center

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…
Autonomous Motion Learning for Intra-Vehicular Activity Space Robot

NASA Astrophysics Data System (ADS)

Watanabe, Yutaka; Yairi, Takehisa; Machida, Kazuo

Space robots will be needed in the future space missions. So far, many types of space robots have been developed, but in particular, Intra-Vehicular Activity (IVA) space robots that support human activities should be developed to reduce human-risks in space. In this paper, we study the motion learning method of an IVA space robot with the multi-link mechanism. The advantage point is that this space robot moves using reaction force of the multi-link mechanism and contact forces from the wall as space walking of an astronaut, not to use a propulsion. The control approach is determined based on a reinforcement learning with the actor-critic algorithm. We demonstrate to clear effectiveness of this approach using a 5-link space robot model by simulation. First, we simulate that a space robot learn the motion control including contact phase in two dimensional case. Next, we simulate that a space robot learn the motion control changing base attitude in three dimensional case.
Interactive machine learning for health informatics: when do we need the human-in-the-loop?

PubMed

Holzinger, Andreas

2016-06-01

Machine learning (ML) is the fastest growing field in computer science, and health informatics is among the greatest challenges. The goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions. Most ML researchers concentrate on automatic machine learning (aML), where great advances have been made, for example, in speech recognition, recommender systems, or autonomous vehicles. Automatic approaches greatly benefit from big data with many training sets. However, in the health domain, sometimes we are confronted with a small number of data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive machine learning (iML) may be of help, having its roots in reinforcement learning, preference learning, and active learning. The term iML is not yet well used, so we define it as "algorithms that can interact with agents and can optimize their learning behavior through these interactions, where the agents can also be human." This "human-in-the-loop" can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human agent involved in the learning phase.
Inductive learning of thyroid functional states using the ID3 algorithm. The effect of poor examples on the learning result.

PubMed

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.
Privacy-preserving backpropagation neural network learning.

PubMed

Chen, Tingting; Zhong, Sheng

2009-10-01

With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets.
Learning Cue Phrase Patterns from Radiology Reports Using a Genetic Algorithm

DOE Office of Scientific and Technical Information (OSTI.GOV)

Patton, Robert M; Beckerman, Barbara G; Potok, Thomas E

2009-01-01

Various computer-assisted technologies have been developed to assist radiologists in detecting cancer; however, the algorithms still lack high degrees of sensitivity and specificity, and must undergo machine learning against a training set with known pathologies in order to further refine the algorithms with higher validity of truth. This work describes an approach to learning cue phrase patterns in radiology reports that utilizes a genetic algorithm (GA) as the learning method. The approach described here successfully learned cue phrase patterns for two distinct classes of radiology reports. These patterns can then be used as a basis for automatically categorizing, clustering, ormore » retrieving relevant data for the user.« less
A time series based sequence prediction algorithm to detect activities of daily living in smart home.

PubMed

Marufuzzaman, M; Reaz, M B I; Ali, M A M; Rahman, L F

2015-01-01

The goal of smart homes is to create an intelligent environment adapting the inhabitants need and assisting the person who needs special care and safety in their daily life. This can be reached by collecting the ADL (activities of daily living) data and further analysis within existing computing elements. In this research, a very recent algorithm named sequence prediction via enhanced episode discovery (SPEED) is modified and in order to improve accuracy time component is included. The modified SPEED or M-SPEED is a sequence prediction algorithm, which modified the previous SPEED algorithm by using time duration of appliance's ON-OFF states to decide the next state. M-SPEED discovered periodic episodes of inhabitant behavior, trained it with learned episodes, and made decisions based on the obtained knowledge. The results showed that M-SPEED achieves 96.8% prediction accuracy, which is better than other time prediction algorithms like PUBS, ALZ with temporal rules and the previous SPEED. Since human behavior shows natural temporal patterns, duration times can be used to predict future events more accurately. This inhabitant activity prediction system will certainly improve the smart homes by ensuring safety and better care for elderly and handicapped people.
Human Movement Recognition Based on the Stochastic Characterisation of Acceleration Data

PubMed Central

Munoz-Organero, Mario; Lotfi, Ahmad

2016-01-01

Human activity recognition algorithms based on information obtained from wearable sensors are successfully applied in detecting many basic activities. Identified activities with time-stationary features are characterised inside a predefined temporal window by using different machine learning algorithms on extracted features from the measured data. Better accuracy, precision and recall levels could be achieved by combining the information from different sensors. However, detecting short and sporadic human movements, gestures and actions is still a challenging task. In this paper, a novel algorithm to detect human basic movements from wearable measured data is proposed and evaluated. The proposed algorithm is designed to minimise computational requirements while achieving acceptable accuracy levels based on characterising some particular points in the temporal series obtained from a single sensor. The underlying idea is that this algorithm would be implemented in the sensor device in order to pre-process the sensed data stream before sending the information to a central point combining the information from different sensors to improve accuracy levels. Intra- and inter-person validation is used for two particular cases: single step detection and fall detection and classification using a single tri-axial accelerometer. Relevant results for the above cases and pertinent conclusions are also presented. PMID:27618063
Machine learning for neuroimaging with scikit-learn.

PubMed

Abraham, Alexandre; Pedregosa, Fabian; Eickenberg, Michael; Gervais, Philippe; Mueller, Andreas; Kossaifi, Jean; Gramfort, Alexandre; Thirion, Bertrand; Varoquaux, Gaël

2014-01-01

Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain.
Machine learning for neuroimaging with scikit-learn

PubMed Central

Abraham, Alexandre; Pedregosa, Fabian; Eickenberg, Michael; Gervais, Philippe; Mueller, Andreas; Kossaifi, Jean; Gramfort, Alexandre; Thirion, Bertrand; Varoquaux, Gaël

2014-01-01

Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain. PMID:24600388

A study of metaheuristic algorithms for high dimensional feature selection on microarray data

NASA Astrophysics Data System (ADS)

Dankolo, Muhammad Nasiru; Radzi, Nor Haizan Mohamed; Sallehuddin, Roselina; Mustaffa, Noorfa Haszlinna

2017-11-01

Microarray systems enable experts to examine gene profile at molecular level using machine learning algorithms. It increases the potentials of classification and diagnosis of many diseases at gene expression level. Though, numerous difficulties may affect the efficiency of machine learning algorithms which includes vast number of genes features comprised in the original data. Many of these features may be unrelated to the intended analysis. Therefore, feature selection is necessary to be performed in the data pre-processing. Many feature selection algorithms are developed and applied on microarray which including the metaheuristic optimization algorithms. This paper discusses the application of the metaheuristics algorithms for feature selection in microarray dataset. This study reveals that, the algorithms have yield an interesting result with limited resources thereby saving computational expenses of machine learning algorithms.
Comparison between extreme learning machine and wavelet neural networks in data classification

NASA Astrophysics Data System (ADS)

Yahia, Siwar; Said, Salwa; Jemai, Olfa; Zaied, Mourad; Ben Amar, Chokri

2017-03-01

Extreme learning Machine is a well known learning algorithm in the field of machine learning. It's about a feed forward neural network with a single-hidden layer. It is an extremely fast learning algorithm with good generalization performance. In this paper, we aim to compare the Extreme learning Machine with wavelet neural networks, which is a very used algorithm. We have used six benchmark data sets to evaluate each technique. These datasets Including Wisconsin Breast Cancer, Glass Identification, Ionosphere, Pima Indians Diabetes, Wine Recognition and Iris Plant. Experimental results have shown that both extreme learning machine and wavelet neural networks have reached good results.
Activity Learning as a Foundation for Security Monitoring in Smart Homes.

PubMed

Dahmen, Jessamyn; Thomas, Brian L; Cook, Diane J; Wang, Xiaobo

2017-03-31

Smart environment technology has matured to the point where it is regularly used in everyday homes as well as research labs. With this maturation of the technology, we can consider using smart homes as a practical mechanism for improving home security. In this paper, we introduce an activity-aware approach to security monitoring and threat detection in smart homes. We describe our approach using the CASAS smart home framework and activity learning algorithms. By monitoring for activity-based anomalies we can detect possible threats and take appropriate action. We evaluate our proposed method using data collected in CASAS smart homes and demonstrate the partnership between activity-aware smart homes and biometric devices in the context of the CASAS on-campus smart apartment testbed.
Optimizing the Learning Order of Chinese Characters Using a Novel Topological Sort Algorithm

PubMed Central

Wang, Jinzhao

2016-01-01

We present a novel algorithm for optimizing the order in which Chinese characters are learned, one that incorporates the benefits of learning them in order of usage frequency and in order of their hierarchal structural relationships. We show that our work outperforms previously published orders and algorithms. Our algorithm is applicable to any scheduling task where nodes have intrinsic differences in importance and must be visited in topological order. PMID:27706234
Creating Engaging Online Learning Material with the JSAV JavaScript Algorithm Visualization Library

ERIC Educational Resources Information Center

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…
Research on intelligent algorithm of electro - hydraulic servo control system

NASA Astrophysics Data System (ADS)

Wang, Yannian; Zhao, Yuhui; Liu, Chengtao

2017-09-01

In order to adapt the nonlinear characteristics of the electro-hydraulic servo control system and the influence of complex interference in the industrial field, using a fuzzy PID switching learning algorithm is proposed and a fuzzy PID switching learning controller is designed and applied in the electro-hydraulic servo controller. The designed controller not only combines the advantages of the fuzzy control and PID control, but also introduces the learning algorithm into the switching function, which makes the learning of the three parameters in the switching function can avoid the instability of the system during the switching between the fuzzy control and PID control algorithms. It also makes the switch between these two control algorithm more smoother than that of the conventional fuzzy PID.
Decision tree and ensemble learning algorithms with their applications in bioinformatics.

PubMed

Che, Dongsheng; Liu, Qi; Rasheed, Khaled; Tao, Xiuping

2011-01-01

Machine learning approaches have wide applications in bioinformatics, and decision tree is one of the successful approaches applied in this field. In this chapter, we briefly review decision tree and related ensemble algorithms and show the successful applications of such approaches on solving biological problems. We hope that by learning the algorithms of decision trees and ensemble classifiers, biologists can get the basic ideas of how machine learning algorithms work. On the other hand, by being exposed to the applications of decision trees and ensemble algorithms in bioinformatics, computer scientists can get better ideas of which bioinformatics topics they may work on in their future research directions. We aim to provide a platform to bridge the gap between biologists and computer scientists.
Learning Intelligent Genetic Algorithms Using Japanese Nonograms

ERIC Educational Resources Information Center

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…
Location-Aware Mobile Learning of Spatial Algorithms

ERIC Educational Resources Information Center

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…
A study of active learning methods for named entity recognition in clinical text.

PubMed

Chen, Yukun; Lasko, Thomas A; Mei, Qiaozhu; Denny, Joshua C; Xu, Hua

2015-12-01

Named entity recognition (NER), a sequential labeling task, is one of the fundamental tasks for building clinical natural language processing (NLP) systems. Machine learning (ML) based approaches can achieve good performance, but they often require large amounts of annotated samples, which are expensive to build due to the requirement of domain experts in annotation. Active learning (AL), a sample selection approach integrated with supervised ML, aims to minimize the annotation cost while maximizing the performance of ML-based models. In this study, our goal was to develop and evaluate both existing and new AL methods for a clinical NER task to identify concepts of medical problems, treatments, and lab tests from the clinical notes. Using the annotated NER corpus from the 2010 i2b2/VA NLP challenge that contained 349 clinical documents with 20,423 unique sentences, we simulated AL experiments using a number of existing and novel algorithms in three different categories including uncertainty-based, diversity-based, and baseline sampling strategies. They were compared with the passive learning that uses random sampling. Learning curves that plot performance of the NER model against the estimated annotation cost (based on number of sentences or words in the training set) were generated to evaluate different active learning and the passive learning methods and the area under the learning curve (ALC) score was computed. Based on the learning curves of F-measure vs. number of sentences, uncertainty sampling algorithms outperformed all other methods in ALC. Most diversity-based methods also performed better than random sampling in ALC. To achieve an F-measure of 0.80, the best method based on uncertainty sampling could save 66% annotations in sentences, as compared to random sampling. For the learning curves of F-measure vs. number of words, uncertainty sampling methods again outperformed all other methods in ALC. To achieve 0.80 in F-measure, in comparison to random sampling, the best uncertainty based method saved 42% annotations in words. But the best diversity based method reduced only 7% annotation effort. In the simulated setting, AL methods, particularly uncertainty-sampling based approaches, seemed to significantly save annotation cost for the clinical NER task. The actual benefit of active learning in clinical NER should be further evaluated in a real-time setting. Copyright © 2015 Elsevier Inc. All rights reserved.
Label consistent K-SVD: learning a discriminative dictionary for recognition.

PubMed

Jiang, Zhuolin; Lin, Zhe; Davis, Larry S

2013-11-01

A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse codes during the dictionary learning process. More specifically, we introduce a new label consistency constraint called "discriminative sparse-code error" and combine it with the reconstruction error and the classification error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. Our algorithm learns a single overcomplete dictionary and an optimal linear classifier jointly. The incremental dictionary learning algorithm is presented for the situation of limited memory resources. It yields dictionaries so that feature points with the same class labels have similar sparse codes. Experimental results demonstrate that our algorithm outperforms many recently proposed sparse-coding techniques for face, action, scene, and object category recognition under the same learning conditions.
Autonomous learning based on cost assumptions: theoretical studies and experiments in robot control.

PubMed

Ribeiro, C H; Hemerly, E M

2000-02-01

Autonomous learning techniques are based on experience acquisition. In most realistic applications, experience is time-consuming: it implies sensor reading, actuator control and algorithmic update, constrained by the learning system dynamics. The information crudeness upon which classical learning algorithms operate make such problems too difficult and unrealistic. Nonetheless, additional information for facilitating the learning process ideally should be embedded in such a way that the structural, well-studied characteristics of these fundamental algorithms are maintained. We investigate in this article a more general formulation of the Q-learning method that allows for a spreading of information derived from single updates towards a neighbourhood of the instantly visited state and converges to optimality. We show how this new formulation can be used as a mechanism to safely embed prior knowledge about the structure of the state space, and demonstrate it in a modified implementation of a reinforcement learning algorithm in a real robot navigation task.
Learning a trajectory using adjoint functions and teacher forcing

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad B.; Barhen, Jacob

1992-01-01

A new methodology for faster supervised temporal learning in nonlinear neural networks is presented which builds upon the concept of adjoint operators to allow fast computation of the gradients of an error functional with respect to all parameters of the neural architecture, and exploits the concept of teacher forcing to incorporate information on the desired output into the activation dynamics. The importance of the initial or final time conditions for the adjoint equations is discussed. A new algorithm is presented in which the adjoint equations are solved simultaneously (i.e., forward in time) with the activation dynamics of the neural network. We also indicate how teacher forcing can be modulated in time as learning proceeds. The results obtained show that the learning time is reduced by one to two orders of magnitude with respect to previously published results, while trajectory tracking is significantly improved. The proposed methodology makes hardware implementation of temporal learning attractive for real-time applications.
Predicting activities of daily living for cancer patients using an ontology-guided machine learning methodology.

PubMed

Min, Hua; Mobahi, Hedyeh; Irvin, Katherine; Avramovic, Sanja; Wojtusiak, Janusz

2017-09-16

Bio-ontologies are becoming increasingly important in knowledge representation and in the machine learning (ML) fields. This paper presents a ML approach that incorporates bio-ontologies and its application to the SEER-MHOS dataset to discover patterns of patient characteristics that impact the ability to perform activities of daily living (ADLs). Bio-ontologies are used to provide computable knowledge for ML methods to "understand" biomedical data. This retrospective study included 723 cancer patients from the SEER-MHOS dataset. Two ML methods were applied to create predictive models for ADL disabilities for the first year after a patient's cancer diagnosis. The first method is a standard rule learning algorithm; the second is that same algorithm additionally equipped with methods for reasoning with ontologies. The models showed that a patient's race, ethnicity, smoking preference, treatment plan and tumor characteristics including histology, staging, cancer site, and morphology were predictors for ADL performance levels one year after cancer diagnosis. The ontology-guided ML method was more accurate at predicting ADL performance levels (P < 0.1) than methods without ontologies. This study demonstrated that bio-ontologies can be harnessed to provide medical knowledge for ML algorithms. The presented method demonstrates that encoding specific types of hierarchical relationships to guide rule learning is possible, and can be extended to other types of semantic relationships present in biomedical ontologies. The ontology-guided ML method achieved better performance than the method without ontologies. The presented method can also be used to promote the effectiveness and efficiency of ML in healthcare, in which use of background knowledge and consistency with existing clinical expertise is critical.
Active machine learning for rapid landslide inventory mapping with VHR satellite images (Invited)

NASA Astrophysics Data System (ADS)

Stumpf, A.; Lachiche, N.; Malet, J.; Kerle, N.; Puissant, A.

2013-12-01

VHR satellite images have become a primary source for landslide inventory mapping after major triggering events such as earthquakes and heavy rainfalls. Visual image interpretation is still the prevailing standard method for operational purposes but is time-consuming and not well suited to fully exploit the increasingly better supply of remote sensing data. Recent studies have addressed the development of more automated image analysis workflows for landslide inventory mapping. In particular object-oriented approaches that account for spatial and textural image information have been demonstrated to be more adequate than pixel-based classification but manually elaborated rule-based classifiers are difficult to adapt under changing scene characteristics. Machine learning algorithm allow learning classification rules for complex image patterns from labelled examples and can be adapted straightforwardly with available training data. In order to reduce the amount of costly training data active learning (AL) has evolved as a key concept to guide the sampling for many applications. The underlying idea of AL is to initialize a machine learning model with a small training set, and to subsequently exploit the model state and data structure to iteratively select the most valuable samples that should be labelled by the user. With relatively few queries and labelled samples, an AL strategy yields higher accuracies than an equivalent classifier trained with many randomly selected samples. This study addressed the development of an AL method for landslide mapping from VHR remote sensing images with special consideration of the spatial distribution of the samples. Our approach [1] is based on the Random Forest algorithm and considers the classifier uncertainty as well as the variance of potential sampling regions to guide the user towards the most valuable sampling areas. The algorithm explicitly searches for compact regions and thereby avoids a spatially disperse sampling pattern inherent to most other AL methods. The accuracy, the sampling time and the computational runtime of the algorithm were evaluated on multiple satellite images capturing recent large scale landslide events. Sampling between 1-4% of the study areas the accuracies between 74% and 80% were achieved, whereas standard sampling schemes yielded only accuracies between 28% and 50% with equal sampling costs. Compared to commonly used point-wise AL algorithm the proposed approach significantly reduces the number of iterations and hence the computational runtime. Since the user can focus on relatively few compact areas (rather than on hundreds of distributed points) the overall labeling time is reduced by more than 50% compared to point-wise queries. An experimental evaluation of multiple expert mappings demonstrated strong relationships between the uncertainties of the experts and the machine learning model. It revealed that the achieved accuracies are within the range of the inter-expert disagreement and that it will be indispensable to consider ground truth uncertainties to truly achieve further enhancements in the future. The proposed method is generally applicable to a wide range of optical satellite images and landslide types. [1] A. Stumpf, N. Lachiche, J.-P. Malet, N. Kerle, and A. Puissant, Active learning in the spatial domain for remote sensing image classification, IEEE Transactions on Geosciece and Remote Sensing. 2013, DOI 10.1109/TGRS.2013.2262052.
Brain-Machine Interface control of a robot arm using actor-critic rainforcement learning.

PubMed

Pohlmeyer, Eric A; Mahmoudi, Babak; Geng, Shijia; Prins, Noeline; Sanchez, Justin C

2012-01-01

Here we demonstrate how a marmoset monkey can use a reinforcement learning (RL) Brain-Machine Interface (BMI) to effectively control the movements of a robot arm for a reaching task. In this work, an actor-critic RL algorithm used neural ensemble activity in the monkey's motor cortext to control the robot movements during a two-target decision task. This novel approach to decoding offers unique advantages for BMI control applications. Compared to supervised learning decoding methods, the actor-critic RL algorithm does not require an explicit set of training data to create a static control model, but rather it incrementally adapts the model parameters according to its current performance, in this case requiring only a very basic feedback signal. We show how this algorithm achieved high performance when mapping the monkey's neural states (94%) to robot actions, and only needed to experience a few trials before obtaining accurate real-time control of the robot arm. Since RL methods responsively adapt and adjust their parameters, they can provide a method to create BMIs that are robust against perturbations caused by changes in either the neural input space or the output actions they generate under different task requirements or goals.
QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms.

PubMed

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.
Autonomous reinforcement learning with experience replay.

PubMed

Wawrzyński, Paweł; Tanwani, Ajay Kumar

2013-05-01

This paper considers the issues of efficiency and autonomy that are required to make reinforcement learning suitable for real-life control tasks. A real-time reinforcement learning algorithm is presented that repeatedly adjusts the control policy with the use of previously collected samples, and autonomously estimates the appropriate step-sizes for the learning updates. The algorithm is based on the actor-critic with experience replay whose step-sizes are determined on-line by an enhanced fixed point algorithm for on-line neural network training. An experimental study with simulated octopus arm and half-cheetah demonstrates the feasibility of the proposed algorithm to solve difficult learning control problems in an autonomous way within reasonably short time. Copyright © 2012 Elsevier Ltd. All rights reserved.
Immune allied genetic algorithm for Bayesian network structure learning

NASA Astrophysics Data System (ADS)

Song, Qin; Lin, Feng; Sun, Wei; Chang, KC

2012-06-01

Bayesian network (BN) structure learning is a NP-hard problem. In this paper, we present an improved approach to enhance efficiency of BN structure learning. To avoid premature convergence in traditional single-group genetic algorithm (GA), we propose an immune allied genetic algorithm (IAGA) in which the multiple-population and allied strategy are introduced. Moreover, in the algorithm, we apply prior knowledge by injecting immune operator to individuals which can effectively prevent degeneration. To illustrate the effectiveness of the proposed technique, we present some experimental results.
Toward Intelligent Machine Learning Algorithms

DTIC Science & Technology

1988-05-01

Machine learning is recognized as a tool for improving the performance of many kinds of systems, yet most machine learning systems themselves are not...directed systems, and with the addition of a knowledge store for organizing and maintaining knowledge to assist learning, a learning machine learning (L...ML) algorithm is possible. The necessary components of L-ML systems are presented along with several case descriptions of existing machine learning systems

Data Mining Citizen Science Results

NASA Astrophysics Data System (ADS)

Borne, K. D.

2012-12-01

Scientific discovery from big data is enabled through multiple channels, including data mining (through the application of machine learning algorithms) and human computation (commonly implemented through citizen science tasks). We will describe the results of new data mining experiments on the results from citizen science activities. Discovering patterns, trends, and anomalies in data are among the powerful contributions of citizen science. Establishing scientific algorithms that can subsequently re-discover the same types of patterns, trends, and anomalies in automatic data processing pipelines will ultimately result from the transformation of those human algorithms into computer algorithms, which can then be applied to much larger data collections. Scientific discovery from big data is thus greatly amplified through the marriage of data mining with citizen science.
Active learning of neuron morphology for accurate automated tracing of neurites

PubMed Central

Gala, Rohan; Chapeton, Julio; Jitesh, Jayant; Bhavsar, Chintan; Stepanyants, Armen

2014-01-01

Automating the process of neurite tracing from light microscopy stacks of images is essential for large-scale or high-throughput quantitative studies of neural circuits. While the general layout of labeled neurites can be captured by many automated tracing algorithms, it is often not possible to differentiate reliably between the processes belonging to different cells. The reason is that some neurites in the stack may appear broken due to imperfect labeling, while others may appear fused due to the limited resolution of optical microscopy. Trained neuroanatomists routinely resolve such topological ambiguities during manual tracing tasks by combining information about distances between branches, branch orientations, intensities, calibers, tortuosities, colors, as well as the presence of spines or boutons. Likewise, to evaluate different topological scenarios automatically, we developed a machine learning approach that combines many of the above mentioned features. A specifically designed confidence measure was used to actively train the algorithm during user-assisted tracing procedure. Active learning significantly reduces the training time and makes it possible to obtain less than 1% generalization error rates by providing few training examples. To evaluate the overall performance of the algorithm a number of image stacks were reconstructed automatically, as well as manually by several trained users, making it possible to compare the automated traces to the baseline inter-user variability. Several geometrical and topological features of the traces were selected for the comparisons. These features include the total trace length, the total numbers of branch and terminal points, the affinity of corresponding traces, and the distances between corresponding branch and terminal points. Our results show that when the density of labeled neurites is sufficiently low, automated traces are not significantly different from manual reconstructions obtained by trained users. PMID:24904306
A Large-Scale Multi-Hop Localization Algorithm Based on Regularized Extreme Learning for Wireless Networks.

PubMed

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.
Spiking neuron network Helmholtz machine.

PubMed

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule.
Spiking neuron network Helmholtz machine

PubMed Central

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule. PMID:25954191
Distinct prediction errors in mesostriatal circuits of the human brain mediate learning about the values of both states and actions: evidence from high-resolution fMRI.

PubMed

Colas, Jaron T; Pauli, Wolfgang M; Larsen, Tobias; Tyszka, J Michael; O'Doherty, John P

2017-10-01

Prediction-error signals consistent with formal models of "reinforcement learning" (RL) have repeatedly been found within dopaminergic nuclei of the midbrain and dopaminoceptive areas of the striatum. However, the precise form of the RL algorithms implemented in the human brain is not yet well determined. Here, we created a novel paradigm optimized to dissociate the subtypes of reward-prediction errors that function as the key computational signatures of two distinct classes of RL models-namely, "actor/critic" models and action-value-learning models (e.g., the Q-learning model). The state-value-prediction error (SVPE), which is independent of actions, is a hallmark of the actor/critic architecture, whereas the action-value-prediction error (AVPE) is the distinguishing feature of action-value-learning algorithms. To test for the presence of these prediction-error signals in the brain, we scanned human participants with a high-resolution functional magnetic-resonance imaging (fMRI) protocol optimized to enable measurement of neural activity in the dopaminergic midbrain as well as the striatal areas to which it projects. In keeping with the actor/critic model, the SVPE signal was detected in the substantia nigra. The SVPE was also clearly present in both the ventral striatum and the dorsal striatum. However, alongside these purely state-value-based computations we also found evidence for AVPE signals throughout the striatum. These high-resolution fMRI findings suggest that model-free aspects of reward learning in humans can be explained algorithmically with RL in terms of an actor/critic mechanism operating in parallel with a system for more direct action-value learning.
Learning Activity Predictors from Sensor Data: Algorithms, Evaluation, and Applications.

PubMed

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.
Learning algorithms for human-machine interfaces.

PubMed

Danziger, Zachary; Fishbach, Alon; Mussa-Ivaldi, Ferdinando A

2009-05-01

The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The high-dimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore-Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction.
Learning Algorithms for Human–Machine Interfaces

PubMed Central

Fishbach, Alon; Mussa-Ivaldi, Ferdinando A.

2012-01-01

The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The high-dimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore–Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction. PMID:19203886
Implementing a self-structuring data learning algorithm

NASA Astrophysics Data System (ADS)

Graham, James; Carson, Daniel; Ternovskiy, Igor

2016-05-01

In this paper, we elaborate on what we did to implement our self-structuring data learning algorithm. To recap, we are working to develop a data learning algorithm that will eventually be capable of goal driven pattern learning and extrapolation of more complex patterns from less complex ones. At this point we have developed a conceptual framework for the algorithm, but have yet to discuss our actual implementation and the consideration and shortcuts we needed to take to create said implementation. We will elaborate on our initial setup of the algorithm and the scenarios we used to test our early stage algorithm. While we want this to be a general algorithm, it is necessary to start with a simple scenario or two to provide a viable development and testing environment. To that end, our discussion will be geared toward what we include in our initial implementation and why, as well as what concerns we may have. In the future, we expect to be able to apply our algorithm to a more general approach, but to do so within a reasonable time, we needed to pick a place to start.
Learning overcomplete representations from distributed data: a brief review

NASA Astrophysics Data System (ADS)

Raja, Haroon; Bajwa, Waheed U.

2016-05-01

Most of the research on dictionary learning has focused on developing algorithms under the assumption that data is available at a centralized location. But often the data is not available at a centralized location due to practical constraints like data aggregation costs, privacy concerns, etc. Using centralized dictionary learning algorithms may not be the optimal choice in such settings. This motivates the design of dictionary learning algorithms that consider distributed nature of data as one of the problem variables. Just like centralized settings, distributed dictionary learning problem can be posed in more than one way depending on the problem setup. Most notable distinguishing features are the online versus batch nature of data and the representative versus discriminative nature of the dictionaries. In this paper, several distributed dictionary learning algorithms that are designed to tackle different problem setups are reviewed. One of these algorithms is cloud K-SVD, which solves the dictionary learning problem for batch data in distributed settings. One distinguishing feature of cloud K-SVD is that it has been shown to converge to its centralized counterpart, namely, the K-SVD solution. On the other hand, no such guarantees are provided for other distributed dictionary learning algorithms. Convergence of cloud K-SVD to the centralized K-SVD solution means problems that are solvable by K-SVD in centralized settings can now be solved in distributed settings with similar performance. Finally, cloud K-SVD is used as an example to show the advantages that are attainable by deploying distributed dictionary algorithms for real world distributed datasets.
Sparsity-constrained PET image reconstruction with learned dictionaries

NASA Astrophysics Data System (ADS)

Tang, Jing; Yang, Bao; Wang, Yanhua; Ying, Leslie

2016-09-01

PET imaging plays an important role in scientific and clinical measurement of biochemical and physiological processes. Model-based PET image reconstruction such as the iterative expectation maximization algorithm seeking the maximum likelihood solution leads to increased noise. The maximum a posteriori (MAP) estimate removes divergence at higher iterations. However, a conventional smoothing prior or a total-variation (TV) prior in a MAP reconstruction algorithm causes over smoothing or blocky artifacts in the reconstructed images. We propose to use dictionary learning (DL) based sparse signal representation in the formation of the prior for MAP PET image reconstruction. The dictionary to sparsify the PET images in the reconstruction process is learned from various training images including the corresponding MR structural image and a self-created hollow sphere. Using simulated and patient brain PET data with corresponding MR images, we study the performance of the DL-MAP algorithm and compare it quantitatively with a conventional MAP algorithm, a TV-MAP algorithm, and a patch-based algorithm. The DL-MAP algorithm achieves improved bias and contrast (or regional mean values) at comparable noise to what the other MAP algorithms acquire. The dictionary learned from the hollow sphere leads to similar results as the dictionary learned from the corresponding MR image. Achieving robust performance in various noise-level simulation and patient studies, the DL-MAP algorithm with a general dictionary demonstrates its potential in quantitative PET imaging.
Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms.

PubMed

Ozcift, Akin; Gulten, Arif

2011-12-01

Improving accuracies of machine learning algorithms is vital in designing high performance computer-aided diagnosis (CADx) systems. Researches have shown that a base classifier performance might be enhanced by ensemble classification strategies. In this study, we construct rotation forest (RF) ensemble classifiers of 30 machine learning algorithms to evaluate their classification performances using Parkinson's, diabetes and heart diseases from literature. While making experiments, first the feature dimension of three datasets is reduced using correlation based feature selection (CFS) algorithm. Second, classification performances of 30 machine learning algorithms are calculated for three datasets. Third, 30 classifier ensembles are constructed based on RF algorithm to assess performances of respective classifiers with the same disease data. All the experiments are carried out with leave-one-out validation strategy and the performances of the 60 algorithms are evaluated using three metrics; classification accuracy (ACC), kappa error (KE) and area under the receiver operating characteristic (ROC) curve (AUC). Base classifiers succeeded 72.15%, 77.52% and 84.43% average accuracies for diabetes, heart and Parkinson's datasets, respectively. As for RF classifier ensembles, they produced average accuracies of 74.47%, 80.49% and 87.13% for respective diseases. RF, a newly proposed classifier ensemble algorithm, might be used to improve accuracy of miscellaneous machine learning algorithms to design advanced CADx systems. Copyright Â© 2011 Elsevier Ireland Ltd. All rights reserved.
Fast detection of peroxidase (POD) activity in tomato leaves which infected with Botrytis cinerea using hyperspectral imaging

NASA Astrophysics Data System (ADS)

Kong, Wenwen; Liu, Fei; Zhang, Chu; Bao, Yidan; Yu, Jiajia; He, Yong

2014-01-01

Tomatoes are cultivated around the world and gray mold is one of its most prominent and destructive diseases. An early disease detection method can decrease losses caused by plant diseases and prevent the spread of diseases. The activity of peroxidase (POD) is very important indicator of disease stress for plants. The objective of this study is to examine the possibility of fast detection of POD activity in tomato leaves which infected with Botrytis cinerea using hyperspectral imaging data. Five pre-treatment methods were investigated. Genetic algorithm-partial least squares (GA-PLS) was applied to select optimal wavelengths. A new fast learning neural algorithm named extreme learning machine (ELM) was employed as multivariate analytical tool in this study. 21 optimal wavelengths were selected by GA-PLS and used as inputs of three calibration models. The optimal prediction result was achieved by ELM model with selected wavelengths, and the r and RMSEP in validation were 0.8647 and 465.9880 respectively. The results indicated that hyperspectral imaging could be considered as a valuable tool for POD activity prediction. The selected wavelengths could be potential resources for instrument development.
Theoretical and Empirical Analysis of a Spatial EA Parallel Boosting Algorithm.

PubMed

Kamath, Uday; Domeniconi, Carlotta; De Jong, Kenneth

2018-01-01

Many real-world problems involve massive amounts of data. Under these circumstances learning algorithms often become prohibitively expensive, making scalability a pressing issue to be addressed. A common approach is to perform sampling to reduce the size of the dataset and enable efficient learning. Alternatively, one customizes learning algorithms to achieve scalability. In either case, the key challenge is to obtain algorithmic efficiency without compromising the quality of the results. In this article we discuss a meta-learning algorithm (PSBML) that combines concepts from spatially structured evolutionary algorithms (SSEAs) with concepts from ensemble and boosting methodologies to achieve the desired scalability property. We present both theoretical and empirical analyses which show that PSBML preserves a critical property of boosting, specifically, convergence to a distribution centered around the margin. We then present additional empirical analyses showing that this meta-level algorithm provides a general and effective framework that can be used in combination with a variety of learning classifiers. We perform extensive experiments to investigate the trade-off achieved between scalability and accuracy, and robustness to noise, on both synthetic and real-world data. These empirical results corroborate our theoretical analysis, and demonstrate the potential of PSBML in achieving scalability without sacrificing accuracy.
Basis Expansion Approaches for Regularized Sequential Dictionary Learning Algorithms With Enforced Sparsity for fMRI Data Analysis.

PubMed

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.
APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION

DOE Office of Scientific and Technical Information (OSTI.GOV)

Musson, John C.; Seaton, Chad; Spata, Mike F.

2012-11-01

Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an activation layer, is responsible for the removal of saturation effects. Implementationmore » of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.« less
Comparison of sampling strategies for object-based classification of urban vegetation from Very High Resolution satellite images

NASA Astrophysics Data System (ADS)

Rougier, Simon; Puissant, Anne; Stumpf, André; Lachiche, Nicolas

2016-09-01

Vegetation monitoring is becoming a major issue in the urban environment due to the services they procure and necessitates an accurate and up to date mapping. Very High Resolution satellite images enable a detailed mapping of the urban tree and herbaceous vegetation. Several supervised classifications with statistical learning techniques have provided good results for the detection of urban vegetation but necessitate a large amount of training data. In this context, this study proposes to investigate the performances of different sampling strategies in order to reduce the number of examples needed. Two windows based active learning algorithms from state-of-art are compared to a classical stratified random sampling and a third combining active learning and stratified strategies is proposed. The efficiency of these strategies is evaluated on two medium size French cities, Strasbourg and Rennes, associated to different datasets. Results demonstrate that classical stratified random sampling can in some cases be just as effective as active learning methods and that it should be used more frequently to evaluate new active learning methods. Moreover, the active learning strategies proposed in this work enables to reduce the computational runtime by selecting multiple windows at each iteration without increasing the number of windows needed.
Decoding the Formation of New Semantics: MVPA Investigation of Rapid Neocortical Plasticity during Associative Encoding through Fast Mapping.

PubMed

Atir-Sharon, Tali; Gilboa, Asaf; Hazan, Hananel; Koilis, Ester; Manevitz, Larry M

2015-01-01

Neocortical structures typically only support slow acquisition of declarative memory; however, learning through fast mapping may facilitate rapid learning-induced cortical plasticity and hippocampal-independent integration of novel associations into existing semantic networks. During fast mapping the meaning of new words and concepts is inferred, and durable novel associations are incidentally formed, a process thought to support early childhood's exuberant learning. The anterior temporal lobe, a cortical semantic memory hub, may critically support such learning. We investigated encoding of semantic associations through fast mapping using fMRI and multivoxel pattern analysis. Subsequent memory performance following fast mapping was more efficiently predicted using anterior temporal lobe than hippocampal voxels, while standard explicit encoding was best predicted by hippocampal activity. Searchlight algorithms revealed additional activity patterns that predicted successful fast mapping semantic learning located in lateral occipitotemporal and parietotemporal neocortex and ventrolateral prefrontal cortex. By contrast, successful explicit encoding could be classified by activity in medial and dorsolateral prefrontal and parahippocampal cortices. We propose that fast mapping promotes incidental rapid integration of new associations into existing neocortical semantic networks by activating related, nonoverlapping conceptual knowledge. In healthy adults, this is better captured by unique anterior and lateral temporal lobe activity patterns, while hippocampal involvement is less predictive of this kind of learning.
Microgrid energy dispatching for industrial zones with renewable generations and electric vehicles via stochastic optimization and learning

NASA Astrophysics Data System (ADS)

Zhang, Kai; Li, Jingzhi; He, Zhubin; Yan, Wanfeng

2018-07-01

In this paper, a stochastic optimization framework is proposed to address the microgrid energy dispatching problem with random renewable generation and vehicle activity pattern, which is closer to the practical applications. The patterns of energy generation, consumption and storage availability are all random and unknown at the beginning, and the microgrid controller design (MCD) is formulated as a Markov decision process (MDP). Hence, an online learning-based control algorithm is proposed for the microgrid, which could adapt the control policy with increasing knowledge of the system dynamics and converges to the optimal algorithm. We adopt the linear approximation idea to decompose the original value functions as the summation of each per-battery value function. As a consequence, the computational complexity is significantly reduced from exponential growth to linear growth with respect to the size of battery states. Monte Carlo simulation of different scenarios demonstrates the effectiveness and efficiency of our algorithm.

Implementation of K-Means Clustering Method for Electronic Learning Model

NASA Astrophysics Data System (ADS)

Latipa Sari, Herlina; Suranti Mrs., Dewi; Natalia Zulita, Leni

2017-12-01

Teaching and Learning process at SMK Negeri 2 Bengkulu Tengah has applied e-learning system for teachers and students. The e-learning was based on the classification of normative, productive, and adaptive subjects. SMK Negeri 2 Bengkulu Tengah consisted of 394 students and 60 teachers with 16 subjects. The record of e-learning database was used in this research to observe students’ activity pattern in attending class. K-Means algorithm in this research was used to classify students’ learning activities using e-learning, so that it was obtained cluster of students’ activity and improvement of student’s ability. Implementation of K-Means Clustering method for electronic learning model at SMK Negeri 2 Bengkulu Tengah was conducted by observing 10 students’ activities, namely participation of students in the classroom, submit assignment, view assignment, add discussion, view discussion, add comment, download course materials, view article, view test, and submit test. In the e-learning model, the testing was conducted toward 10 students that yielded 2 clusters of membership data (C1 and C2). Cluster 1: with membership percentage of 70% and it consisted of 6 members, namely 1112438 Anggi Julian, 1112439 Anis Maulita, 1112441 Ardi Febriansyah, 1112452 Berlian Sinurat, 1112460 Dewi Anugrah Anwar and 1112467 Eka Tri Oktavia Sari. Cluster 2:with membership percentage of 30% and it consisted of 4 members, namely 1112463 Dosita Afriyani, 1112471 Erda Novita, 1112474 Eskardi and 1112477 Fachrur Rozi.
Seismic waveform classification using deep learning

NASA Astrophysics Data System (ADS)

Kong, Q.; Allen, R. M.

2017-12-01

MyShake is a global smartphone seismic network that harnesses the power of crowdsourcing. It has an Artificial Neural Network (ANN) algorithm running on the phone to distinguish earthquake motion from human activities recorded by the accelerometer on board. Once the ANN detects earthquake-like motion, it sends a 5-min chunk of acceleration data back to the server for further analysis. The time-series data collected contains both earthquake data and human activity data that the ANN confused. In this presentation, we will show the Convolutional Neural Network (CNN) we built under the umbrella of supervised learning to find out the earthquake waveform. The waveforms of the recorded motion could treat easily as images, and by taking the advantage of the power of CNN processing the images, we achieved very high successful rate to select the earthquake waveforms out. Since there are many non-earthquake waveforms than the earthquake waveforms, we also built an anomaly detection algorithm using the CNN. Both these two methods can be easily extended to other waveform classification problems.
A Simple Deep Learning Method for Neuronal Spike Sorting

NASA Astrophysics Data System (ADS)

Yang, Kai; Wu, Haifeng; Zeng, Yu

2017-10-01

Spike sorting is one of key technique to understand brain activity. With the development of modern electrophysiology technology, some recent multi-electrode technologies have been able to record the activity of thousands of neuronal spikes simultaneously. The spike sorting in this case will increase the computational complexity of conventional sorting algorithms. In this paper, we will focus spike sorting on how to reduce the complexity, and introduce a deep learning algorithm, principal component analysis network (PCANet) to spike sorting. The introduced method starts from a conventional model and establish a Toeplitz matrix. Through the column vectors in the matrix, we trains a PCANet, where some eigenvalue vectors of spikes could be extracted. Finally, support vector machine (SVM) is used to sort spikes. In experiments, we choose two groups of simulated data from public databases availably and compare this introduced method with conventional methods. The results indicate that the introduced method indeed has lower complexity with the same sorting errors as the conventional methods.
PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lochner, Michelle; Peiris, Hiranya V.; Lahav, Ofer

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models tomore » curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k -nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.« less
Learning in Structured Connectionist Networks

DTIC Science & Technology

1988-04-01

the structure is too rigid and learning too difficult for cognitive modeling. Two algorithms for learning simple, feature-based concept descriptions...and learning too difficult for cognitive model- ing. Two algorithms for learning simple, feature-based concept descriptions were also implemented. The...Term Goals Recent progress in connectionist research has been encouraging; networks have success- fully modeled human performance for various cognitive
An Ensemble Approach in Converging Contents of LMS and KMS

ERIC Educational Resources Information Center

Sabitha, A. Sai; Mehrotra, Deepti; Bansal, Abhay

2017-01-01

Currently the challenges in e-Learning are converging the learning content from various sources and managing them within e-learning practices. Data mining learning algorithms can be used and the contents can be converged based on the Metadata of the objects. Ensemble methods use multiple learning algorithms and it can be used to converge the…
The Science of Home Automation

NASA Astrophysics Data System (ADS)

Thomas, Brian Louis

Smart home technologies and the concept of home automation have become more popular in recent years. This popularity has been accompanied by social acceptance of passive sensors installed throughout the home. The subsequent increase in smart homes facilitates the creation of home automation strategies. We believe that home automation strategies can be generated intelligently by utilizing smart home sensors and activity learning. In this dissertation, we hypothesize that home automation can benefit from activity awareness. To test this, we develop our activity-aware smart automation system, CARL (CASAS Activity-aware Resource Learning). CARL learns the associations between activities and device usage from historical data and utilizes the activity-aware capabilities to control the devices. To help validate CARL we deploy and test three different versions of the automation system in a real-world smart environment. To provide a foundation of activity learning, we integrate existing activity recognition and activity forecasting into CARL home automation. We also explore two alternatives to using human-labeled data to train the activity learning models. The first unsupervised method is Activity Detection, and the second is a modified DBSCAN algorithm that utilizes Dynamic Time Warping (DTW) as a distance metric. We compare the performance of activity learning with human-defined labels and with automatically-discovered activity categories. To provide evidence in support of our hypothesis, we evaluate CARL automation in a smart home testbed. Our results indicate that home automation can be boosted through activity awareness. We also find that the resulting automation has a high degree of usability and comfort for the smart home resident.
Semisupervised Support Vector Machines With Tangent Space Intrinsic Manifold Regularization.

PubMed

Sun, Shiliang; Xie, Xijiong

2016-09-01

Semisupervised learning has been an active research topic in machine learning and data mining. One main reason is that labeling examples is expensive and time-consuming, while there are large numbers of unlabeled examples available in many practical problems. So far, Laplacian regularization has been widely used in semisupervised learning. In this paper, we propose a new regularization method called tangent space intrinsic manifold regularization. It is intrinsic to data manifold and favors linear functions on the manifold. Fundamental elements involved in the formulation of the regularization are local tangent space representations, which are estimated by local principal component analysis, and the connections that relate adjacent tangent spaces. Simultaneously, we explore its application to semisupervised classification and propose two new learning algorithms called tangent space intrinsic manifold regularized support vector machines (TiSVMs) and tangent space intrinsic manifold regularized twin SVMs (TiTSVMs). They effectively integrate the tangent space intrinsic manifold regularization consideration. The optimization of TiSVMs can be solved by a standard quadratic programming, while the optimization of TiTSVMs can be solved by a pair of standard quadratic programmings. The experimental results of semisupervised classification problems show the effectiveness of the proposed semisupervised learning algorithms.
A game theoretic framework for incentive-based models of intrinsic motivation in artificial systems

PubMed Central

Merrick, Kathryn E.; Shafi, Kamran

2013-01-01

An emerging body of research is focusing on understanding and building artificial systems that can achieve open-ended development influenced by intrinsic motivations. In particular, research in robotics and machine learning is yielding systems and algorithms with increasing capacity for self-directed learning and autonomy. Traditional software architectures and algorithms are being augmented with intrinsic motivations to drive cumulative acquisition of knowledge and skills. Intrinsic motivations have recently been considered in reinforcement learning, active learning and supervised learning settings among others. This paper considers game theory as a novel setting for intrinsic motivation. A game theoretic framework for intrinsic motivation is formulated by introducing the concept of optimally motivating incentive as a lens through which players perceive a game. Transformations of four well-known mixed-motive games are presented to demonstrate the perceived games when players' optimally motivating incentive falls in three cases corresponding to strong power, affiliation and achievement motivation. We use agent-based simulations to demonstrate that players with different optimally motivating incentive act differently as a result of their altered perception of the game. We discuss the implications of these results both for modeling human behavior and for designing artificial agents or robots. PMID:24198797
A game theoretic framework for incentive-based models of intrinsic motivation in artificial systems.

PubMed

Merrick, Kathryn E; Shafi, Kamran

2013-01-01

An emerging body of research is focusing on understanding and building artificial systems that can achieve open-ended development influenced by intrinsic motivations. In particular, research in robotics and machine learning is yielding systems and algorithms with increasing capacity for self-directed learning and autonomy. Traditional software architectures and algorithms are being augmented with intrinsic motivations to drive cumulative acquisition of knowledge and skills. Intrinsic motivations have recently been considered in reinforcement learning, active learning and supervised learning settings among others. This paper considers game theory as a novel setting for intrinsic motivation. A game theoretic framework for intrinsic motivation is formulated by introducing the concept of optimally motivating incentive as a lens through which players perceive a game. Transformations of four well-known mixed-motive games are presented to demonstrate the perceived games when players' optimally motivating incentive falls in three cases corresponding to strong power, affiliation and achievement motivation. We use agent-based simulations to demonstrate that players with different optimally motivating incentive act differently as a result of their altered perception of the game. We discuss the implications of these results both for modeling human behavior and for designing artificial agents or robots.
Design of Learning Model of Logic and Algorithms Based on APOS Theory

ERIC Educational Resources Information Center

Hartati, Sulis Janu

2014-01-01

This research questions were "how do the characteristics of learning model of logic & algorithm according to APOS theory" and "whether or not these learning model can improve students learning outcomes". This research was conducted by exploration, and quantitative approach. Exploration used in constructing theory about the…
SUPAR: Smartphone as a ubiquitous physical activity recognizer for u-healthcare services.

PubMed

Fahim, Muhammad; Lee, Sungyoung; Yoon, Yongik

2014-01-01

Current generation smartphone can be seen as one of the most ubiquitous device for physical activity recognition. In this paper we proposed a physical activity recognizer to provide u-healthcare services in a cost effective manner by utilizing cloud computing infrastructure. Our model is comprised on embedded triaxial accelerometer of the smartphone to sense the body movements and a cloud server to store and process the sensory data for numerous kind of services. We compute the time and frequency domain features over the raw signals and evaluate different machine learning algorithms to identify an accurate activity recognition model for four kinds of physical activities (i.e., walking, running, cycling and hopping). During our experiments we found Support Vector Machine (SVM) algorithm outperforms for the aforementioned physical activities as compared to its counterparts. Furthermore, we also explain how smartphone application and cloud server communicate with each other.
Activity Learning as a Foundation for Security Monitoring in Smart Homes

PubMed Central

Dahmen, Jessamyn; Thomas, Brian L.; Cook, Diane J.; Wang, Xiaobo

2017-01-01

Smart environment technology has matured to the point where it is regularly used in everyday homes as well as research labs. With this maturation of the technology, we can consider using smart homes as a practical mechanism for improving home security. In this paper, we introduce an activity-aware approach to security monitoring and threat detection in smart homes. We describe our approach using the CASAS smart home framework and activity learning algorithms. By monitoring for activity-based anomalies we can detect possible threats and take appropriate action. We evaluate our proposed method using data collected in CASAS smart homes and demonstrate the partnership between activity-aware smart homes and biometric devices in the context of the CASAS on-campus smart apartment testbed. PMID:28362342
An improved clustering algorithm based on reverse learning in intelligent transportation

NASA Astrophysics Data System (ADS)

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.
Particle Swarm Optimization With Interswarm Interactive Learning Strategy.

PubMed

Qin, Quande; Cheng, Shi; Zhang, Qingyu; Li, Li; Shi, Yuhui

2016-10-01

The learning strategy in the canonical particle swarm optimization (PSO) algorithm is often blamed for being the primary reason for loss of diversity. Population diversity maintenance is crucial for preventing particles from being stuck into local optima. In this paper, we present an improved PSO algorithm with an interswarm interactive learning strategy (IILPSO) by overcoming the drawbacks of the canonical PSO algorithm's learning strategy. IILPSO is inspired by the phenomenon in human society that the interactive learning behavior takes place among different groups. Particles in IILPSO are divided into two swarms. The interswarm interactive learning (IIL) behavior is triggered when the best particle's fitness value of both the swarms does not improve for a certain number of iterations. According to the best particle's fitness value of each swarm, the softmax method and roulette method are used to determine the roles of the two swarms as the learning swarm and the learned swarm. In addition, the velocity mutation operator and global best vibration strategy are used to improve the algorithm's global search capability. The IIL strategy is applied to PSO with global star and local ring structures, which are termed as IILPSO-G and IILPSO-L algorithm, respectively. Numerical experiments are conducted to compare the proposed algorithms with eight popular PSO variants. From the experimental results, IILPSO demonstrates the good performance in terms of solution accuracy, convergence speed, and reliability. Finally, the variations of the population diversity in the entire search process provide an explanation why IILPSO performs effectively.
Learning neural connectivity from firing activity: efficient algorithms with provable guarantees on topology.

PubMed

Karbasi, Amin; Salavati, Amir Hesam; Vetterli, Martin

2018-04-01

The connectivity of a neuronal network has a major effect on its functionality and role. It is generally believed that the complex network structure of the brain provides a physiological basis for information processing. Therefore, identifying the network's topology has received a lot of attentions in neuroscience and has been the center of many research initiatives such as Human Connectome Project. Nevertheless, direct and invasive approaches that slice and observe the neural tissue have proven to be time consuming, complex and costly. As a result, the inverse methods that utilize firing activity of neurons in order to identify the (functional) connections have gained momentum recently, especially in light of rapid advances in recording technologies; It will soon be possible to simultaneously monitor the activities of tens of thousands of neurons in real time. While there are a number of excellent approaches that aim to identify the functional connections from firing activities, the scalability of the proposed techniques plays a major challenge in applying them on large-scale datasets of recorded firing activities. In exceptional cases where scalability has not been an issue, the theoretical performance guarantees are usually limited to a specific family of neurons or the type of firing activities. In this paper, we formulate the neural network reconstruction as an instance of a graph learning problem, where we observe the behavior of nodes/neurons (i.e., firing activities) and aim to find the links/connections. We develop a scalable learning mechanism and derive the conditions under which the estimated graph for a network of Leaky Integrate and Fire (LIf) neurons matches the true underlying synaptic connections. We then validate the performance of the algorithm using artificially generated data (for benchmarking) and real data recorded from multiple hippocampal areas in rats.
Regularised extreme learning machine with misclassification cost and rejection cost for gene expression data classification.

PubMed

Lu, Huijuan; Wei, Shasha; Zhou, Zili; Miao, Yanzi; Lu, Yi

2015-01-01

The main purpose of traditional classification algorithms on bioinformatics application is to acquire better classification accuracy. However, these algorithms cannot meet the requirement that minimises the average misclassification cost. In this paper, a new algorithm of cost-sensitive regularised extreme learning machine (CS-RELM) was proposed by using probability estimation and misclassification cost to reconstruct the classification results. By improving the classification accuracy of a group of small sample which higher misclassification cost, the new CS-RELM can minimise the classification cost. The 'rejection cost' was integrated into CS-RELM algorithm to further reduce the average misclassification cost. By using Colon Tumour dataset and SRBCT (Small Round Blue Cells Tumour) dataset, CS-RELM was compared with other cost-sensitive algorithms such as extreme learning machine (ELM), cost-sensitive extreme learning machine, regularised extreme learning machine, cost-sensitive support vector machine (SVM). The results of experiments show that CS-RELM with embedded rejection cost could reduce the average cost of misclassification and made more credible classification decision than others.
Decentralized indirect methods for learning automata games.

PubMed

Tilak, Omkar; Martin, Ryan; Mukhopadhyay, Snehasis

2011-10-01

We discuss the application of indirect learning methods in zero-sum and identical payoff learning automata games. We propose a novel decentralized version of the well-known pursuit learning algorithm. Such a decentralized algorithm has significant computational advantages over its centralized counterpart. The theoretical study of such a decentralized algorithm requires the analysis to be carried out in a nonstationary environment. We use a novel bootstrapping argument to prove the convergence of the algorithm. To our knowledge, this is the first time that such analysis has been carried out for zero-sum and identical payoff games. Extensive simulation studies are reported, which demonstrate the proposed algorithm's fast and accurate convergence in a variety of game scenarios. We also introduce the framework of partial communication in the context of identical payoff games of learning automata. In such games, the automata may not communicate with each other or may communicate selectively. This comprehensive framework has the capability to model both centralized and decentralized games discussed in this paper.
Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality.

PubMed

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.
Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality

PubMed Central

2016-01-01

Background 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. Objective Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Methods Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Results 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%). Conclusions 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. PMID:27185366

Machine Learning Control For Highly Reconfigurable High-Order Systems

DTIC Science & Technology

2015-01-02

develop and flight test a Reinforcement Learning based approach for autonomous tracking of ground targets using a fixed wing Unmanned...Reinforcement Learning - based algorithms are developed for learning agents’ time dependent dynamics while also learning to control them. Three algorithms...to a wide range of engineering- based problems . Implementation of these solutions, however, is often complicated by the hysteretic, non-linear,
A machine learning approach to computer-aided molecular design

NASA Astrophysics Data System (ADS)

Bolis, Giorgio; Di Pace, Luigi; Fabrocini, Filippo

1991-12-01

Preliminary results of a machine learning application concerning computer-aided molecular design applied to drug discovery are presented. The artificial intelligence techniques of machine learning use a sample of active and inactive compounds, which is viewed as a set of positive and negative examples, to allow the induction of a molecular model characterizing the interaction between the compounds and a target molecule. The algorithm is based on a twofold phase. In the first one — the specialization step — the program identifies a number of active/inactive pairs of compounds which appear to be the most useful in order to make the learning process as effective as possible and generates a dictionary of molecular fragments, deemed to be responsible for the activity of the compounds. In the second phase — the generalization step — the fragments thus generated are combined and generalized in order to select the most plausible hypothesis with respect to the sample of compounds. A knowledge base concerning physical and chemical properties is utilized during the inductive process.
ICPL: Intelligent Cooperative Planning and Learning for Multi-agent Systems

DTIC Science & Technology

2012-02-29

objective was to develop a new planning approach for teams!of multiple UAVs that tightly integrates learning and cooperative!control algorithms at... algorithms at multiple levels of the planning architecture. The research results enabled a team of mobile agents to learn to adapt and react to uncertainty in...expressive representation that incorporates feature conjunctions. Our algorithm is simple to implement, fast to execute, and can be combined with any
Training Strategies for the M1 Abrams Tank Driver Trainer

DTIC Science & Technology

1984-10-01

positive reinforcement. The automatic freeze after incorrect performance, for example, may even be aversive to the trainee. The TECEP learning algorithms ...Aagard, J.A. and Braby, R. Learning Guidelines and Algorithms for Types of Training Objectives. (TAEG Report No. 23). Orlando, FL: Training Analysis and...checklist ite. flake it identical to operational setting. () Cresponde to the g;uideli ne number Tor thiss oast. Figure B-I. Learning Algorithm for
Protein Sequence Classification with Improved Extreme Learning Machine Algorithms

PubMed Central

2014-01-01

Precisely classifying a protein sequence from a large biological protein sequences database plays an important role for developing competitive pharmacological products. Comparing the unseen sequence with all the identified protein sequences and returning the category index with the highest similarity scored protein, conventional methods are usually time-consuming. Therefore, it is urgent and necessary to build an efficient protein sequence classification system. In this paper, we study the performance of protein sequence classification using SLFNs. The recent efficient extreme learning machine (ELM) and its invariants are utilized as the training algorithms. The optimal pruned ELM is first employed for protein sequence classification in this paper. To further enhance the performance, the ensemble based SLFNs structure is constructed where multiple SLFNs with the same number of hidden nodes and the same activation function are used as ensembles. For each ensemble, the same training algorithm is adopted. The final category index is derived using the majority voting method. Two approaches, namely, the basic ELM and the OP-ELM, are adopted for the ensemble based SLFNs. The performance is analyzed and compared with several existing methods using datasets obtained from the Protein Information Resource center. The experimental results show the priority of the proposed algorithms. PMID:24795876
Energy design for protein-protein interactions

PubMed Central

Ravikant, D. V. S.; Elber, Ron

2011-01-01

Proteins bind to other proteins efficiently and specifically to carry on many cell functions such as signaling, activation, transport, enzymatic reactions, and more. To determine the geometry and strength of binding of a protein pair, an energy function is required. An algorithm to design an optimal energy function, based on empirical data of protein complexes, is proposed and applied. Emphasis is made on negative design in which incorrect geometries are presented to the algorithm that learns to avoid them. For the docking problem the search for plausible geometries can be performed exhaustively. The possible geometries of the complex are generated on a grid with the help of a fast Fourier transform algorithm. A novel formulation of negative design makes it possible to investigate iteratively hundreds of millions of negative examples while monotonically improving the quality of the potential. Experimental structures for 640 protein complexes are used to generate positive and negative examples for learning parameters. The algorithm designed in this work finds the correct binding structure as the lowest energy minimum in 318 cases of the 640 examples. Further benchmarks on independent sets confirm the significant capacity of the scoring function to recognize correct modes of interactions. PMID:21842951
Performance evaluation of the Champagne source reconstruction algorithm on simulated and real M/EEG data.

PubMed

Owen, Julia P; Wipf, David P; Attias, Hagai T; Sekihara, Kensuke; Nagarajan, Srikantan S

2012-03-01

In this paper, we present an extensive performance evaluation of a novel source localization algorithm, Champagne. It is derived in an empirical Bayesian framework that yields sparse solutions to the inverse problem. It is robust to correlated sources and learns the statistics of non-stimulus-evoked activity to suppress the effect of noise and interfering brain activity. We tested Champagne on both simulated and real M/EEG data. The source locations used for the simulated data were chosen to test the performance on challenging source configurations. In simulations, we found that Champagne outperforms the benchmark algorithms in terms of both the accuracy of the source localizations and the correct estimation of source time courses. We also demonstrate that Champagne is more robust to correlated brain activity present in real MEG data and is able to resolve many distinct and functionally relevant brain areas with real MEG and EEG data. Copyright © 2011 Elsevier Inc. All rights reserved.
Machine learning in cardiovascular medicine: are we there yet?

PubMed

Shameer, Khader; Johnson, Kipp W; Glicksberg, Benjamin S; Dudley, Joel T; Sengupta, Partho P

2018-01-19

Artificial intelligence (AI) broadly refers to analytical algorithms that iteratively learn from data, allowing computers to find hidden insights without being explicitly programmed where to look. These include a family of operations encompassing several terms like machine learning, cognitive learning, deep learning and reinforcement learning-based methods that can be used to integrate and interpret complex biomedical and healthcare data in scenarios where traditional statistical methods may not be able to perform. In this review article, we discuss the basics of machine learning algorithms and what potential data sources exist; evaluate the need for machine learning; and examine the potential limitations and challenges of implementing machine in the context of cardiovascular medicine. The most promising avenues for AI in medicine are the development of automated risk prediction algorithms which can be used to guide clinical care; use of unsupervised learning techniques to more precisely phenotype complex disease; and the implementation of reinforcement learning algorithms to intelligently augment healthcare providers. The utility of a machine learning-based predictive model will depend on factors including data heterogeneity, data depth, data breadth, nature of modelling task, choice of machine learning and feature selection algorithms, and orthogonal evidence. A critical understanding of the strength and limitations of various methods and tasks amenable to machine learning is vital. By leveraging the growing corpus of big data in medicine, we detail pathways by which machine learning may facilitate optimal development of patient-specific models for improving diagnoses, intervention and outcome in cardiovascular medicine. © Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2018. All rights reserved. No commercial use is permitted unless otherwise expressly granted.
A new learning paradigm: learning using privileged information.

PubMed

Vapnik, Vladimir; Vashist, Akshay

2009-01-01

In the Afterword to the second edition of the book "Estimation of Dependences Based on Empirical Data" by V. Vapnik, an advanced learning paradigm called Learning Using Hidden Information (LUHI) was introduced. This Afterword also suggested an extension of the SVM method (the so called SVM(gamma)+ method) to implement algorithms which address the LUHI paradigm (Vapnik, 1982-2006, Sections 2.4.2 and 2.5.3 of the Afterword). See also (Vapnik, Vashist, & Pavlovitch, 2008, 2009) for further development of the algorithms. In contrast to the existing machine learning paradigm where a teacher does not play an important role, the advanced learning paradigm considers some elements of human teaching. In the new paradigm along with examples, a teacher can provide students with hidden information that exists in explanations, comments, comparisons, and so on. This paper discusses details of the new paradigm and corresponding algorithms, introduces some new algorithms, considers several specific forms of privileged information, demonstrates superiority of the new learning paradigm over the classical learning paradigm when solving practical problems, and discusses general questions related to the new ideas.
Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma

PubMed Central

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 (p<0.001) and integrated discrimination improvement (p=0.04). The HALT-C model had a c-statistic of 0.60 (95%CI 0.50-0.70) in the validation cohort and was outperformed by the machine 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
A system for learning statistical motion patterns.

PubMed

Hu, Weiming; Xiao, Xuejuan; Fu, Zhouyu; Xie, Dan; Tan, Tieniu; Maybank, Steve

2006-09-01

Analysis of motion patterns is an effective approach for anomaly detection and behavior prediction. Current approaches for the analysis of motion patterns depend on known scenes, where objects move in predefined ways. It is highly desirable to automatically construct object motion patterns which reflect the knowledge of the scene. In this paper, we present a system for automatically learning motion patterns for anomaly detection and behavior prediction based on a proposed algorithm for robustly tracking multiple objects. In the tracking algorithm, foreground pixels are clustered using a fast accurate fuzzy K-means algorithm. Growing and prediction of the cluster centroids of foreground pixels ensure that each cluster centroid is associated with a moving object in the scene. In the algorithm for learning motion patterns, trajectories are clustered hierarchically using spatial and temporal information and then each motion pattern is represented with a chain of Gaussian distributions. Based on the learned statistical motion patterns, statistical methods are used to detect anomalies and predict behaviors. Our system is tested using image sequences acquired, respectively, from a crowded real traffic scene and a model traffic scene. Experimental results show the robustness of the tracking algorithm, the efficiency of the algorithm for learning motion patterns, and the encouraging performance of algorithms for anomaly detection and behavior prediction.
Mortality risk score prediction in an elderly population using machine learning.

PubMed

Rose, Sherri

2013-03-01

Standard practice for prediction often relies on parametric regression methods. Interesting new methods from the machine learning literature have been introduced in epidemiologic studies, such as random forest and neural networks. However, a priori, an investigator will not know which algorithm to select and may wish to try several. Here I apply the super learner, an ensembling machine learning approach that combines multiple algorithms into a single algorithm and returns a prediction function with the best cross-validated mean squared error. Super learning is a generalization of stacking methods. I used super learning in the Study of Physical Performance and Age-Related Changes in Sonomans (SPPARCS) to predict death among 2,066 residents of Sonoma, California, aged 54 years or more during the period 1993-1999. The super learner for predicting death (risk score) improved upon all single algorithms in the collection of algorithms, although its performance was similar to that of several algorithms. Super learner outperformed the worst algorithm (neural networks) by 44% with respect to estimated cross-validated mean squared error and had an R2 value of 0.201. The improvement of super learner over random forest with respect to R2 was approximately 2-fold. Alternatives for risk score prediction include the super learner, which can provide improved performance.
Algorithmic Case Pedagogy, Learning and Gender

ERIC Educational Resources Information Center

Bromley, Robert; Huang, Zhenyu

2015-01-01

Great investment has been made in developing algorithmically-based cases within online homework management systems. This has been done because publishers are convinced that textbook adoption decisions are influenced by the incorporation of these systems within their products. These algorithmic assignments are thought to promote learning while…
Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aziz, H. M. Abdul; Zhu, Feng; Ukkusuri, Satish V.

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 atmore » 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.« less
Distributed learning automata-based algorithm for community detection in complex networks

NASA Astrophysics Data System (ADS)

Khomami, Mohammad Mehdi Daliri; Rezvanian, Alireza; Meybodi, Mohammad Reza

2016-03-01

Community structure is an important and universal topological property of many complex networks such as social and information networks. The detection of communities of a network is a significant technique for understanding the structure and function of networks. In this paper, we propose an algorithm based on distributed learning automata for community detection (DLACD) in complex networks. In the proposed algorithm, each vertex of network is equipped with a learning automation. According to the cooperation among network of learning automata and updating action probabilities of each automaton, the algorithm interactively tries to identify high-density local communities. The performance of the proposed algorithm is investigated through a number of simulations on popular synthetic and real networks. Experimental results in comparison with popular community detection algorithms such as walk trap, Danon greedy optimization, Fuzzy community detection, Multi-resolution community detection and label propagation demonstrated the superiority of DLACD in terms of modularity, NMI, performance, min-max-cut and coverage.
Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns

PubMed Central

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning. PMID:29209191
Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns.

PubMed

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning.
Distributed Economic Dispatch in Microgrids Based on Cooperative Reinforcement Learning.

PubMed

Liu, Weirong; Zhuang, Peng; Liang, Hao; Peng, Jun; Huang, Zhiwu; Weirong Liu; Peng Zhuang; Hao Liang; Jun Peng; Zhiwu Huang; Liu, Weirong; Liang, Hao; Peng, Jun; Zhuang, Peng; Huang, Zhiwu

2018-06-01

Microgrids incorporated with distributed generation (DG) units and energy storage (ES) devices are expected to play more and more important roles in the future power systems. Yet, achieving efficient distributed economic dispatch in microgrids is a challenging issue due to the randomness and nonlinear characteristics of DG units and loads. This paper proposes a cooperative reinforcement learning algorithm for distributed economic dispatch in microgrids. Utilizing the learning algorithm can avoid the difficulty of stochastic modeling and high computational complexity. In the cooperative reinforcement learning algorithm, the function approximation is leveraged to deal with the large and continuous state spaces. And a diffusion strategy is incorporated to coordinate the actions of DG units and ES devices. Based on the proposed algorithm, each node in microgrids only needs to communicate with its local neighbors, without relying on any centralized controllers. Algorithm convergence is analyzed, and simulations based on real-world meteorological and load data are conducted to validate the performance of the proposed algorithm.
Support Vector Machine algorithm for regression and classification

DOE Office of Scientific and Technical Information (OSTI.GOV)

Yu, Chenggang; Zavaljevski, Nela

2001-08-01

The software is an implementation of the Support Vector Machine (SVM) algorithm that was invented and developed by Vladimir Vapnik and his co-workers at AT&T Bell Laboratories. The specific implementation reported here is an Active Set method for solving a quadratic optimization problem that forms the major part of any SVM program. The implementation is tuned to specific constraints generated in the SVM learning. Thus, it is more efficient than general-purpose quadratic optimization programs. A decomposition method has been implemented in the software that enables processing large data sets. The size of the learning data is virtually unlimited by themore » capacity of the computer physical memory. The software is flexible and extensible. Two upper bounds are implemented to regulate the SVM learning for classification, which allow users to adjust the false positive and false negative rates. The software can be used either as a standalone, general-purpose SVM regression or classification program, or be embedded into a larger software system.« less
Developing Novel Machine Learning Algorithms to Improve Sedentary Assessment for Youth Health Enhancement.

PubMed

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.

Interactive algorithms for teaching and learning acute medicine in the network of medical faculties MEFANET.

PubMed

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. Positive attitudes toward the interactive algorithms outnumbered negative trends. The peer-reviewed algorithms were used for conducting problem-based learning sessions in general medicine (first aid, anesthesiology and pain management, emergency medicine) and in nursing (emergency medicine for midwives, obstetric analgesia, and anesthesia for midwifes). The feedback from the survey suggests that the students found the interactive algorithms as effective learning tools, facilitating enhanced knowledge in the field of acute medicine. The interactive algorithms, as a software platform, are open to academic use worldwide. The existing algorithms, in the form of simulation-based learning objects, can be incorporated into any educational website (subject to the approval of the authors).
Interactive Algorithms for Teaching and Learning Acute Medicine in the Network of Medical Faculties MEFANET

PubMed Central

Štourač, Petr; Komenda, Martin; Harazim, Hana; Kosinová, Martina; Gregor, Jakub; Hůlek, Richard; Smékalová, Olga; Křikava, Ivo; Štoudek, Roman; Dušek, Ladislav

2013-01-01

Background 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. Objective 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. Methods 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. Results 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. Positive attitudes toward the interactive algorithms outnumbered negative trends. Conclusions The peer-reviewed algorithms were used for conducting problem-based learning sessions in general medicine (first aid, anesthesiology and pain management, emergency medicine) and in nursing (emergency medicine for midwives, obstetric analgesia, and anesthesia for midwifes). The feedback from the survey suggests that the students found the interactive algorithms as effective learning tools, facilitating enhanced knowledge in the field of acute medicine. The interactive algorithms, as a software platform, are open to academic use worldwide. The existing algorithms, in the form of simulation-based learning objects, can be incorporated into any educational website (subject to the approval of the authors). PMID:23835586
Last-position elimination-based learning automata.

PubMed

Zhang, Junqi; Wang, Cheng; Zhou, MengChu

2014-12-01

An update scheme of the state probability vector of actions is critical for learning automata (LA). The most popular is the pursuit scheme that pursues the estimated optimal action and penalizes others. This paper proposes a reverse philosophy that leads to last-position elimination-based learning automata (LELA). The action graded last in terms of the estimated performance is penalized by decreasing its state probability and is eliminated when its state probability becomes zero. All active actions, that is, actions with nonzero state probability, equally share the penalized state probability from the last-position action at each iteration. The proposed LELA is characterized by the relaxed convergence condition for the optimal action, the accelerated step size of the state probability update scheme for the estimated optimal action, and the enriched sampling for the estimated nonoptimal actions. The proof of the ϵ-optimal property for the proposed algorithm is presented. Last-position elimination is a widespread philosophy in the real world and has proved to be also helpful for the update scheme of the learning automaton via the simulations of well-known benchmark environments. In the simulations, two versions of the LELA, using different selection strategies of the last action, are compared with the classical pursuit algorithms Discretized Pursuit Reward-Inaction (DP(RI)) and Discretized Generalized Pursuit Algorithm (DGPA). Simulation results show that the proposed schemes achieve significantly faster convergence and higher accuracy than the classical ones. Specifically, the proposed schemes reduce the interval to find the best parameter for a specific environment in the classical pursuit algorithms. Thus, they can have their parameter tuning easier to perform and can save much more time when applied to a practical case. Furthermore, the convergence curves and the corresponding variance coefficient curves of the contenders are illustrated to characterize their essential differences and verify the analysis results of the proposed algorithms.
Distinct prediction errors in mesostriatal circuits of the human brain mediate learning about the values of both states and actions: evidence from high-resolution fMRI

PubMed Central

Pauli, Wolfgang M.; Larsen, Tobias; Tyszka, J. Michael; O’Doherty, John P.

2017-01-01

Prediction-error signals consistent with formal models of “reinforcement learning” (RL) have repeatedly been found within dopaminergic nuclei of the midbrain and dopaminoceptive areas of the striatum. However, the precise form of the RL algorithms implemented in the human brain is not yet well determined. Here, we created a novel paradigm optimized to dissociate the subtypes of reward-prediction errors that function as the key computational signatures of two distinct classes of RL models—namely, “actor/critic” models and action-value-learning models (e.g., the Q-learning model). The state-value-prediction error (SVPE), which is independent of actions, is a hallmark of the actor/critic architecture, whereas the action-value-prediction error (AVPE) is the distinguishing feature of action-value-learning algorithms. To test for the presence of these prediction-error signals in the brain, we scanned human participants with a high-resolution functional magnetic-resonance imaging (fMRI) protocol optimized to enable measurement of neural activity in the dopaminergic midbrain as well as the striatal areas to which it projects. In keeping with the actor/critic model, the SVPE signal was detected in the substantia nigra. The SVPE was also clearly present in both the ventral striatum and the dorsal striatum. However, alongside these purely state-value-based computations we also found evidence for AVPE signals throughout the striatum. These high-resolution fMRI findings suggest that model-free aspects of reward learning in humans can be explained algorithmically with RL in terms of an actor/critic mechanism operating in parallel with a system for more direct action-value learning. PMID:29049406
Airport Flight Departure Delay Model on Improved BN Structure Learning

NASA Astrophysics Data System (ADS)

Cao, Weidong; Fang, Xiangnong

An high score prior genetic simulated annealing Bayesian network structure learning algorithm (HSPGSA) by combining genetic algorithm(GA) with simulated annealing algorithm(SAA) is developed. The new algorithm provides not only with strong global search capability of GA, but also with strong local hill climb search capability of SAA. The structure with the highest score is prior selected. In the mean time, structures with lower score are also could be choice. It can avoid efficiently prematurity problem by higher score individual wrong direct growing population. Algorithm is applied to flight departure delays analysis in a large hub airport. Based on the flight data a BN model is created. Experiments show that parameters learning can reflect departure delay.
Fast detection of the fuzzy communities based on leader-driven algorithm

NASA Astrophysics Data System (ADS)

Fang, Changjian; Mu, Dejun; Deng, Zhenghong; Hu, Jun; Yi, Chen-He

2018-03-01

In this paper, we present the leader-driven algorithm (LDA) for learning community structure in networks. The algorithm allows one to find overlapping clusters in a network, an important aspect of real networks, especially social networks. The algorithm requires no input parameters and learns the number of clusters naturally from the network. It accomplishes this using leadership centrality in a clever manner. It identifies local minima of leadership centrality as followers which belong only to one cluster, and the remaining nodes are leaders which connect clusters. In this way, the number of clusters can be learned using only the network structure. The LDA is also an extremely fast algorithm, having runtime linear in the network size. Thus, this algorithm can be used to efficiently cluster extremely large networks.
Statistical Methods in Ai: Rare Event Learning Using Associative Rules and Higher-Order Statistics

NASA Astrophysics Data System (ADS)

Iyer, V.; Shetty, S.; Iyengar, S. S.

2015-07-01

Rare event learning has not been actively researched since lately due to the unavailability of algorithms which deal with big samples. The research addresses spatio-temporal streams from multi-resolution sensors to find actionable items from a perspective of real-time algorithms. This computing framework is independent of the number of input samples, application domain, labelled or label-less streams. A sampling overlap algorithm such as Brooks-Iyengar is used for dealing with noisy sensor streams. We extend the existing noise pre-processing algorithms using Data-Cleaning trees. Pre-processing using ensemble of trees using bagging and multi-target regression showed robustness to random noise and missing data. As spatio-temporal streams are highly statistically correlated, we prove that a temporal window based sampling from sensor data streams converges after n samples using Hoeffding bounds. Which can be used for fast prediction of new samples in real-time. The Data-cleaning tree model uses a nonparametric node splitting technique, which can be learned in an iterative way which scales linearly in memory consumption for any size input stream. The improved task based ensemble extraction is compared with non-linear computation models using various SVM kernels for speed and accuracy. We show using empirical datasets the explicit rule learning computation is linear in time and is only dependent on the number of leafs present in the tree ensemble. The use of unpruned trees (t) in our proposed ensemble always yields minimum number (m) of leafs keeping pre-processing computation to n × t log m compared to N2 for Gram Matrix. We also show that the task based feature induction yields higher Qualify of Data (QoD) in the feature space compared to kernel methods using Gram Matrix.
Maximization of Learning Speed Due to Neuronal Redundancy in Reinforcement Learning

NASA Astrophysics Data System (ADS)

Takiyama, Ken

2016-11-01

Adaptable neural activity contributes to the flexibility of human behavior, which is optimized in situations such as motor learning and decision making. Although learning signals in motor learning and decision making are low-dimensional, neural activity, which is very high dimensional, must be modified to achieve optimal performance based on the low-dimensional signal, resulting in a severe credit-assignment problem. Despite this problem, the human brain contains a vast number of neurons, leaving an open question: what is the functional significance of the huge number of neurons? Here, I address this question by analyzing a redundant neural network with a reinforcement-learning algorithm in which the numbers of neurons and output units are N and M, respectively. Because many combinations of neural activity can generate the same output under the condition of N ≫ M, I refer to the index N - M as neuronal redundancy. Although greater neuronal redundancy makes the credit-assignment problem more severe, I demonstrate that a greater degree of neuronal redundancy facilitates learning speed. Thus, in an apparent contradiction of the credit-assignment problem, I propose the hypothesis that a functional role of a huge number of neurons or a huge degree of neuronal redundancy is to facilitate learning speed.
Inference of genetic network of Xenopus frog egg: improved genetic algorithm.

PubMed

Wu, Shinq-Jen; Chou, Chia-Hsien; Wu, Cheng-Tao; Lee, Tsu-Tian

2006-01-01

An improved genetic algorithm (IGA) is proposed to achieve S-system gene network modeling of Xenopus frog egg. Via the time-courses training datasets from Michaelis-Menten model, the optimal parameters are learned. The S-system can clearly describe activative and inhibitory interaction between genes as generating and consuming process. We concern the mitotic control in cell-cycle of Xenopus frog egg to realize cyclin-Cdc2 and Cdc25 for MPF activity. The proposed IGA can achieve global search with migration and keep the best chromosome with elitism operation. The generated gene regulatory networks can provide biological researchers for further experiments in Xenopus frog egg cell cycle control.
Transfer Learning for Activity Recognition: A Survey

PubMed Central

Cook, Diane; Feuz, Kyle D.; Krishnan, Narayanan C.

2013-01-01

Many intelligent systems that focus on the needs of a human require information about the activities being performed by the human. At the core of this capability is activity recognition, which is a challenging and well-researched problem. Activity recognition algorithms require substantial amounts of labeled training data yet need to perform well under very diverse circumstances. As a result, researchers have been designing methods to identify and utilize subtle connections between activity recognition datasets, or to perform transfer-based activity recognition. In this paper we survey the literature to highlight recent advances in transfer learning for activity recognition. We characterize existing approaches to transfer-based activity recognition by sensor modality, by differences between source and target environments, by data availability, and by type of information that is transferred. Finally, we present some grand challenges for the community to consider as this field is further developed. PMID:24039326
A New Stochastic Technique for Painlevé Equation-I Using Neural Network Optimized with Swarm Intelligence

PubMed Central

Raja, Muhammad Asif Zahoor; Khan, Junaid Ali; Ahmad, Siraj-ul-Islam; Qureshi, Ijaz Mansoor

2012-01-01

A methodology for solution of Painlevé equation-I is presented using computational intelligence technique based on neural networks and particle swarm optimization hybridized with active set algorithm. The mathematical model of the equation is developed with the help of linear combination of feed-forward artificial neural networks that define the unsupervised error of the model. This error is minimized subject to the availability of appropriate weights of the networks. The learning of the weights is carried out using particle swarm optimization algorithm used as a tool for viable global search method, hybridized with active set algorithm for rapid local convergence. The accuracy, convergence rate, and computational complexity of the scheme are analyzed based on large number of independents runs and their comprehensive statistical analysis. The comparative studies of the results obtained are made with MATHEMATICA solutions, as well as, with variational iteration method and homotopy perturbation method. PMID:22919371
Utilizing Machine Learning to Downscale SMAP L3_SM_P Brightness Temperatures in Iowa for Agricultural Applications

NASA Astrophysics Data System (ADS)

Chakrabarti, S.; Judge, J.; Bindlish, R.; Bongiovanni, T.; Jackson, T. J.

2016-12-01

The NASA Soil Moisture Active Passive (SMAP) mission provides global observations of brightness temperatures (TB) at 36km. For these observations to be relevant to studies in agricultural regions, the TB values need to be downscaled to finer resolutions. In this study, a machine learning algorithm is introduced for downscaling of TB from 36km to 9km. The algorithm uses image segmentation to cluster the study region based on meteorological and land cover similarity, followed by a support vector machine based regression that computes the value of the disaggregated TB at all pixels. High resolution remote sensing products such as land surface temperature, normalized difference vegetation index, enhanced vegetation index, precipitation, soil texture, and land-cover were used for downscaling. The algorithm was implemented in Iowa, United States, during the growing season from April to July 2015 when the SMAP L3-SM_AP TB product at 9 km was available for comparison. In addition, the downscaled estimates from the algorithm are compared with 9km TB obtained by resampling SMAP L1B_TB product at 36km. It was found that the downscaled TB were very similar to the SMAP-L3_SM _AP TB product, even for vegetated areas with a mean difference ≤ 5K. However, the standard deviation of the downscaled was lower by 7K than that of the AP product. The probability density functions of the downscaled TB were similar to the SMAP- TB. The results indicate that these downscaling algorithms may be used for downscaling TB using complex non-linear correlations on a grid without using active microwave observations.
Reverse inference of memory retrieval processes underlying metacognitive monitoring of learning using multivariate pattern analysis.

PubMed

Stiers, Peter; Falbo, Luciana; Goulas, Alexandros; van Gog, Tamara; de Bruin, Anique

2016-05-15

Monitoring of learning is only accurate at some time after learning. It is thought that immediate monitoring is based on working memory, whereas later monitoring requires re-activation of stored items, yielding accurate judgements. Such interpretations are difficult to test because they require reverse inference, which presupposes specificity of brain activity for the hidden cognitive processes. We investigated whether multivariate pattern classification can provide this specificity. We used a word recall task to create single trial examples of immediate and long term retrieval and trained a learning algorithm to discriminate them. Next, participants performed a similar task involving monitoring instead of recall. The recall-trained classifier recognized the retrieval patterns underlying immediate and long term monitoring and classified delayed monitoring examples as long-term retrieval. This result demonstrates the feasibility of decoding cognitive processes, instead of their content. Copyright © 2016 Elsevier Inc. All rights reserved.
Robust Blind Learning Algorithm for Nonlinear Equalization Using Input Decision Information.

PubMed

Xu, Lu; Huang, Defeng David; Guo, Yingjie Jay

2015-12-01

In this paper, we propose a new blind learning algorithm, namely, the Benveniste-Goursat input-output decision (BG-IOD), to enhance the convergence performance of neural network-based equalizers for nonlinear channel equalization. In contrast to conventional blind learning algorithms, where only the output of the equalizer is employed for updating system parameters, the BG-IOD exploits a new type of extra information, the input decision information obtained from the input of the equalizer, to mitigate the influence of the nonlinear equalizer structure on parameters learning, thereby leading to improved convergence performance. We prove that, with the input decision information, a desirable convergence capability that the output symbol error rate (SER) is always less than the input SER if the input SER is below a threshold, can be achieved. Then, the BG soft-switching technique is employed to combine the merits of both input and output decision information, where the former is used to guarantee SER convergence and the latter is to improve SER performance. Simulation results show that the proposed algorithm outperforms conventional blind learning algorithms, such as stochastic quadratic distance and dual mode constant modulus algorithm, in terms of both convergence performance and SER performance, for nonlinear equalization.
A Novel Segment-Based Approach for Improving Classification Performance of Transport Mode Detection.

PubMed

Guvensan, M Amac; Dusun, Burak; Can, Baris; Turkmen, H Irem

2017-12-30

Transportation planning and solutions have an enormous impact on city life. To minimize the transport duration, urban planners should understand and elaborate the mobility of a city. Thus, researchers look toward monitoring people's daily activities including transportation types and duration by taking advantage of individual's smartphones. This paper introduces a novel segment-based transport mode detection architecture in order to improve the results of traditional classification algorithms in the literature. The proposed post-processing algorithm, namely the Healing algorithm, aims to correct the misclassification results of machine learning-based solutions. Our real-life test results show that the Healing algorithm could achieve up to 40% improvement of the classification results. As a result, the implemented mobile application could predict eight classes including stationary, walking, car, bus, tram, train, metro and ferry with a success rate of 95% thanks to the proposed multi-tier architecture and Healing algorithm.
Materials Selection. Resources in Technology.

ERIC Educational Resources Information Center

Technology Teacher, 1991

1991-01-01

This learning activity develops algorithms to ensure that the process of selecting materials is well defined and sound. These procedures require the use of many databases to provide the designer with information such as physical, mechanical, and chemical properties of the materials under consideration. A design brief, student quiz, and five…
A Calculus Activity with Foundations in Geometric Learning

ERIC Educational Resources Information Center

Wagner, Jennifer; Sharp, Janet

2017-01-01

Calculus, perhaps more than other areas of mathematics, has a reputation for being steeped with procedures. In fact, through the years, it has been noticed of many students getting caught in the trap of trying to memorize algorithms and rules without developing associated concept knowledge. Specifically, students often struggle with the…
Algebraic Procedures and Creative Thinking

ERIC Educational Resources Information Center

Tabach, Michal; Friedlander, Alex

2017-01-01

Simplifying symbolic expressions is usually perceived in middle school algebra as an algorithmic activity, achieved by performing sequences of short drill-and-practice tasks, which have little to do with conceptual learning or with creative mathematical thinking. The aim of this study is to explore possible ways by which ninth-grade students can…
An introduction to kernel-based learning algorithms.

PubMed

Müller, K R; Mika, S; Rätsch, G; Tsuda, K; Schölkopf, B

2001-01-01

This paper provides an introduction to support vector machines, kernel Fisher discriminant analysis, and kernel principal component analysis, as examples for successful kernel-based learning methods. We first give a short background about Vapnik-Chervonenkis theory and kernel feature spaces and then proceed to kernel based learning in supervised and unsupervised scenarios including practical and algorithmic considerations. We illustrate the usefulness of kernel algorithms by discussing applications such as optical character recognition and DNA analysis.
The 4A Metric Algorithm: A Unique E-Learning Engineering Solution Designed via Neuroscience to Counter Cheating and Reduce Its Recidivism by Measuring Student Growth through Systemic Sequential Online Learning

ERIC Educational Resources Information Center

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…

Genetic algorithm based fuzzy control of spacecraft autonomous rendezvous

NASA Technical Reports Server (NTRS)

Karr, C. L.; Freeman, L. M.; Meredith, D. L.

1990-01-01

The U.S. Bureau of Mines is currently investigating ways to combine the control capabilities of fuzzy logic with the learning capabilities of genetic algorithms. Fuzzy logic allows for the uncertainty inherent in most control problems to be incorporated into conventional expert systems. Although fuzzy logic based expert systems have been used successfully for controlling a number of physical systems, the selection of acceptable fuzzy membership functions has generally been a subjective decision. High performance fuzzy membership functions for a fuzzy logic controller that manipulates a mathematical model simulating the autonomous rendezvous of spacecraft are learned using a genetic algorithm, a search technique based on the mechanics of natural genetics. The membership functions learned by the genetic algorithm provide for a more efficient fuzzy logic controller than membership functions selected by the authors for the rendezvous problem. Thus, genetic algorithms are potentially an effective and structured approach for learning fuzzy membership functions.
Fuzzy Sarsa with Focussed Replacing Eligibility Traces for Robust and Accurate Control

NASA Astrophysics Data System (ADS)

Kamdem, Sylvain; Ohki, Hidehiro; Sueda, Naomichi

Several methods of reinforcement learning in continuous state and action spaces that utilize fuzzy logic have been proposed in recent years. This paper introduces Fuzzy Sarsa(λ), an on-policy algorithm for fuzzy learning that relies on a novel way of computing replacing eligibility traces to accelerate the policy evaluation. It is tested against several temporal difference learning algorithms: Sarsa(λ), Fuzzy Q(λ), an earlier fuzzy version of Sarsa and an actor-critic algorithm. We perform detailed evaluations on two benchmark problems : a maze domain and the cart pole. Results of various tests highlight the strengths and weaknesses of these algorithms and show that Fuzzy Sarsa(λ) outperforms all other algorithms tested for a larger granularity of design and under noisy conditions. It is a highly competitive method of learning in realistic noisy domains where a denser fuzzy design over the state space is needed for a more precise control.
Back-propagation learning of infinite-dimensional dynamical systems.

PubMed

Tokuda, Isao; Tokunaga, Ryuji; Aihara, Kazuyuki

2003-10-01

This paper presents numerical studies of applying back-propagation learning to a delayed recurrent neural network (DRNN). The DRNN is a continuous-time recurrent neural network having time delayed feedbacks and the back-propagation learning is to teach spatio-temporal dynamics to the DRNN. Since the time-delays make the dynamics of the DRNN infinite-dimensional, the learning algorithm and the learning capability of the DRNN are different from those of the ordinary recurrent neural network (ORNN) having no time-delays. First, two types of learning algorithms are developed for a class of DRNNs. Then, using chaotic signals generated from the Mackey-Glass equation and the Rössler equations, learning capability of the DRNN is examined. Comparing the learning algorithms, learning capability, and robustness against noise of the DRNN with those of the ORNN and time delay neural network, advantages as well as disadvantages of the DRNN are investigated.
PixelLearn

NASA Technical Reports Server (NTRS)

Mazzoni, Dominic; Wagstaff, Kiri; Bornstein, Benjamin; Tang, Nghia; Roden, Joseph

2006-01-01

PixelLearn is an integrated user-interface computer program for classifying pixels in scientific images. Heretofore, training a machine-learning algorithm to classify pixels in images has been tedious and difficult. PixelLearn provides a graphical user interface that makes it faster and more intuitive, leading to more interactive exploration of image data sets. PixelLearn also provides image-enhancement controls to make it easier to see subtle details in images. PixelLearn opens images or sets of images in a variety of common scientific file formats and enables the user to interact with several supervised or unsupervised machine-learning pixel-classifying algorithms while the user continues to browse through the images. The machinelearning algorithms in PixelLearn use advanced clustering and classification methods that enable accuracy much higher than is achievable by most other software previously available for this purpose. PixelLearn is written in portable C++ and runs natively on computers running Linux, Windows, or Mac OS X.
Multi-Source Multi-Target Dictionary Learning for Prediction of Cognitive Decline.

PubMed

Zhang, Jie; Li, Qingyang; Caselli, Richard J; Thompson, Paul M; Ye, Jieping; Wang, Yalin

2017-06-01

Alzheimer's Disease (AD) is the most common type of dementia. Identifying correct biomarkers may determine pre-symptomatic AD subjects and enable early intervention. Recently, Multi-task sparse feature learning has been successfully applied to many computer vision and biomedical informatics researches. It aims to improve the generalization performance by exploiting the shared features among different tasks. However, most of the existing algorithms are formulated as a supervised learning scheme. Its drawback is with either insufficient feature numbers or missing label information. To address these challenges, we formulate an unsupervised framework for multi-task sparse feature learning based on a novel dictionary learning algorithm. To solve the unsupervised learning problem, we propose a two-stage Multi-Source Multi-Target Dictionary Learning (MMDL) algorithm. In stage 1, we propose a multi-source dictionary learning method to utilize the common and individual sparse features in different time slots. In stage 2, supported by a rigorous theoretical analysis, we develop a multi-task learning method to solve the missing label problem. Empirical studies on an N = 3970 longitudinal brain image data set, which involves 2 sources and 5 targets, demonstrate the improved prediction accuracy and speed efficiency of MMDL in comparison with other state-of-the-art algorithms.
Segmentation of magnetic resonance images using fuzzy algorithms for learning vector quantization.

PubMed

Karayiannis, N B; Pai, P I

1999-02-01

This paper evaluates a segmentation technique for magnetic resonance (MR) images of the brain based on fuzzy algorithms for learning vector quantization (FALVQ). These algorithms perform vector quantization by updating all prototypes of a competitive network through an unsupervised learning process. Segmentation of MR images is formulated as an unsupervised vector quantization process, where the local values of different relaxation parameters form the feature vectors which are represented by a relatively small set of prototypes. The experiments evaluate a variety of FALVQ algorithms in terms of their ability to identify different tissues and discriminate between normal tissues and abnormalities.
Assessment of various supervised learning algorithms using different performance metrics

NASA Astrophysics Data System (ADS)

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.
Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments.

PubMed

Han, Wenjing; Coutinho, Eduardo; Ruan, Huabin; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

2016-01-01

Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances.
Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments

PubMed Central

Han, Wenjing; Coutinho, Eduardo; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

2016-01-01

Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances. PMID:27627768
Discriminative Cooperative Networks for Detecting Phase Transitions

NASA Astrophysics Data System (ADS)

Liu, Ye-Hua; van Nieuwenburg, Evert P. L.

2018-04-01

The classification of states of matter and their corresponding phase transitions is a special kind of machine-learning task, where physical data allow for the analysis of new algorithms, which have not been considered in the general computer-science setting so far. Here we introduce an unsupervised machine-learning scheme for detecting phase transitions with a pair of discriminative cooperative networks (DCNs). In this scheme, a guesser network and a learner network cooperate to detect phase transitions from fully unlabeled data. The new scheme is efficient enough for dealing with phase diagrams in two-dimensional parameter spaces, where we can utilize an active contour model—the snake—from computer vision to host the two networks. The snake, with a DCN "brain," moves and learns actively in the parameter space, and locates phase boundaries automatically.
Machine Learning for Big Data: A Study to Understand Limits at Scale

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sukumar, Sreenivas R.; Del-Castillo-Negrete, Carlos Emilio

This report aims to empirically understand the limits of machine learning when applied to Big Data. We observe that recent innovations in being able to collect, access, organize, integrate, and query massive amounts of data from a wide variety of data sources have brought statistical data mining and machine learning under more scrutiny, evaluation and application for gleaning insights from the data than ever before. Much is expected from algorithms without understanding their limitations at scale while dealing with massive datasets. In that context, we pose and address the following questions How does a machine learning algorithm perform on measuresmore » such as accuracy and execution time with increasing sample size and feature dimensionality? Does training with more samples guarantee better accuracy? How many features to compute for a given problem? Do more features guarantee better accuracy? Do efforts to derive and calculate more features and train on larger samples worth the effort? As problems become more complex and traditional binary classification algorithms are replaced with multi-task, multi-class categorization algorithms do parallel learners perform better? What happens to the accuracy of the learning algorithm when trained to categorize multiple classes within the same feature space? Towards finding answers to these questions, we describe the design of an empirical study and present the results. We conclude with the following observations (i) accuracy of the learning algorithm increases with increasing sample size but saturates at a point, beyond which more samples do not contribute to better accuracy/learning, (ii) the richness of the feature space dictates performance - both accuracy and training time, (iii) increased dimensionality often reflected in better performance (higher accuracy in spite of longer training times) but the improvements are not commensurate the efforts for feature computation and training and (iv) accuracy of the learning algorithms drop significantly with multi-class learners training on the same feature matrix and (v) learning algorithms perform well when categories in labeled data are independent (i.e., no relationship or hierarchy exists among categories).« less
An introduction to quantum machine learning

NASA Astrophysics Data System (ADS)

Schuld, Maria; Sinayskiy, Ilya; Petruccione, Francesco

2015-04-01

Machine learning algorithms learn a desired input-output relation from examples in order to interpret new inputs. This is important for tasks such as image and speech recognition or strategy optimisation, with growing applications in the IT industry. In the last couple of years, researchers investigated if quantum computing can help to improve classical machine learning algorithms. Ideas range from running computationally costly algorithms or their subroutines efficiently on a quantum computer to the translation of stochastic methods into the language of quantum theory. This contribution gives a systematic overview of the emerging field of quantum machine learning. It presents the approaches as well as technical details in an accessible way, and discusses the potential of a future theory of quantum learning.
Machine Learning to Improve Energy Expenditure Estimation in Children With Disabilities: A Pilot Study in Duchenne Muscular Dystrophy.

PubMed

Pande, Amit; Mohapatra, Prasant; Nicorici, Alina; Han, Jay J

2016-07-19

Children with physical impairments are at a greater risk for obesity and decreased physical activity. A better understanding of physical activity pattern and energy expenditure (EE) would lead to a more targeted approach to intervention. This study focuses on studying the use of machine-learning algorithms for EE estimation in children with disabilities. A pilot study was conducted on children with Duchenne muscular dystrophy (DMD) to identify important factors for determining EE and develop a novel algorithm to accurately estimate EE from wearable sensor-collected data. There were 7 boys with DMD, 6 healthy control boys, and 22 control adults recruited. Data were collected using smartphone accelerometer and chest-worn heart rate sensors. The gold standard EE values were obtained from the COSMED K4b2 portable cardiopulmonary metabolic unit worn by boys (aged 6-10 years) with DMD and controls. Data from this sensor setup were collected simultaneously during a series of concurrent activities. Linear regression and nonlinear machine-learning-based approaches were used to analyze the relationship between accelerometer and heart rate readings and COSMED values. Existing calorimetry equations using linear regression and nonlinear machine-learning-based models, developed for healthy adults and young children, give low correlation to actual EE values in children with disabilities (14%-40%). The proposed model for boys with DMD uses ensemble machine learning techniques and gives a 91% correlation with actual measured EE values (root mean square error of 0.017). Our results confirm that the methods developed to determine EE using accelerometer and heart rate sensor values in normal adults are not appropriate for children with disabilities and should not be used. A much more accurate model is obtained using machine-learning-based nonlinear regression specifically developed for this target population. ©Amit Pande, Prasant Mohapatra, Alina Nicorici, Jay J Han. Originally published in JMIR Rehabilitation and Assistive Technology (http://rehab.jmir.org), 19.07.2016.
MoleculeNet: a benchmark for molecular machine learning† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc02664a

PubMed Central

Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N.; Gomes, Joseph; Geniesse, Caleb; Pappu, Aneesh S.; Leswing, Karl

2017-01-01

Molecular machine learning has been maturing rapidly over the last few years. Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties. However, algorithmic progress has been limited due to the lack of a standard benchmark to compare the efficacy of proposed methods; most new algorithms are benchmarked on different datasets making it challenging to gauge the quality of proposed methods. This work introduces MoleculeNet, a large scale benchmark for molecular machine learning. MoleculeNet curates multiple public datasets, establishes metrics for evaluation, and offers high quality open-source implementations of multiple previously proposed molecular featurization and learning algorithms (released as part of the DeepChem open source library). MoleculeNet benchmarks demonstrate that learnable representations are powerful tools for molecular machine learning and broadly offer the best performance. However, this result comes with caveats. Learnable representations still struggle to deal with complex tasks under data scarcity and highly imbalanced classification. For quantum mechanical and biophysical datasets, the use of physics-aware featurizations can be more important than choice of particular learning algorithm. PMID:29629118
A novel data-driven learning method for radar target detection in nonstationary environments

DOE PAGES

Akcakaya, Murat; Nehorai, Arye; Sen, Satyabrata

2016-04-12

Most existing radar algorithms are developed under the assumption that the environment (clutter) is stationary. However, in practice, the characteristics of the clutter can vary enormously depending on the radar-operational scenarios. If unaccounted for, these nonstationary variabilities may drastically hinder the radar performance. Therefore, to overcome such shortcomings, we develop a data-driven method for target detection in nonstationary environments. In this method, the radar dynamically detects changes in the environment and adapts to these changes by learning the new statistical characteristics of the environment and by intelligibly updating its statistical detection algorithm. Specifically, we employ drift detection algorithms to detectmore » changes in the environment; incremental learning, particularly learning under concept drift algorithms, to learn the new statistical characteristics of the environment from the new radar data that become available in batches over a period of time. The newly learned environment characteristics are then integrated in the detection algorithm. Furthermore, we use Monte Carlo simulations to demonstrate that the developed method provides a significant improvement in the detection performance compared with detection techniques that are not aware of the environmental changes.« less
Semi-supervised and unsupervised extreme learning machines.

PubMed

Huang, Gao; Song, Shiji; Gupta, Jatinder N D; Wu, Cheng

2014-12-01

Extreme learning machines (ELMs) have proven to be efficient and effective learning mechanisms for pattern classification and regression. However, ELMs are primarily applied to supervised learning problems. Only a few existing research papers have used ELMs to explore unlabeled data. In this paper, we extend ELMs for both semi-supervised and unsupervised tasks based on the manifold regularization, thus greatly expanding the applicability of ELMs. The key advantages of the proposed algorithms are as follows: 1) both the semi-supervised ELM (SS-ELM) and the unsupervised ELM (US-ELM) exhibit learning capability and computational efficiency of ELMs; 2) both algorithms naturally handle multiclass classification or multicluster clustering; and 3) both algorithms are inductive and can handle unseen data at test time directly. Moreover, it is shown in this paper that all the supervised, semi-supervised, and unsupervised ELMs can actually be put into a unified framework. This provides new perspectives for understanding the mechanism of random feature mapping, which is the key concept in ELM theory. Empirical study on a wide range of data sets demonstrates that the proposed algorithms are competitive with the state-of-the-art semi-supervised or unsupervised learning algorithms in terms of accuracy and efficiency.
Finite time convergent learning law for continuous neural networks.

PubMed

Chairez, Isaac

2014-02-01

This paper addresses the design of a discontinuous finite time convergent learning law for neural networks with continuous dynamics. The neural network was used here to obtain a non-parametric model for uncertain systems described by a set of ordinary differential equations. The source of uncertainties was the presence of some external perturbations and poor knowledge of the nonlinear function describing the system dynamics. A new adaptive algorithm based on discontinuous algorithms was used to adjust the weights of the neural network. The adaptive algorithm was derived by means of a non-standard Lyapunov function that is lower semi-continuous and differentiable in almost the whole space. A compensator term was included in the identifier to reject some specific perturbations using a nonlinear robust algorithm. Two numerical examples demonstrated the improvements achieved by the learning algorithm introduced in this paper compared to classical schemes with continuous learning methods. The first one dealt with a benchmark problem used in the paper to explain how the discontinuous learning law works. The second one used the methane production model to show the benefits in engineering applications of the learning law proposed in this paper. Copyright © 2013 Elsevier Ltd. All rights reserved.
Hip and Wrist Accelerometer Algorithms for Free-Living Behavior Classification.

PubMed

Ellis, Katherine; Kerr, Jacqueline; Godbole, Suneeta; Staudenmayer, John; Lanckriet, Gert

2016-05-01

Accelerometers are a valuable tool for objective measurement of physical activity (PA). Wrist-worn devices may improve compliance over standard hip placement, but more research is needed to evaluate their validity for measuring PA in free-living settings. Traditional cut-point methods for accelerometers can be inaccurate and need testing in free living with wrist-worn devices. In this study, we developed and tested the performance of machine learning (ML) algorithms for classifying PA types from both hip and wrist accelerometer data. Forty overweight or obese women (mean age = 55.2 ± 15.3 yr; BMI = 32.0 ± 3.7) wore two ActiGraph GT3X+ accelerometers (right hip, nondominant wrist; ActiGraph, Pensacola, FL) for seven free-living days. Wearable cameras captured ground truth activity labels. A classifier consisting of a random forest and hidden Markov model classified the accelerometer data into four activities (sitting, standing, walking/running, and riding in a vehicle). Free-living wrist and hip ML classifiers were compared with each other, with traditional accelerometer cut points, and with an algorithm developed in a laboratory setting. The ML classifier obtained average values of 89.4% and 84.6% balanced accuracy over the four activities using the hip and wrist accelerometer, respectively. In our data set with average values of 28.4 min of walking or running per day, the ML classifier predicted average values of 28.5 and 24.5 min of walking or running using the hip and wrist accelerometer, respectively. Intensity-based cut points and the laboratory algorithm significantly underestimated walking minutes. Our results demonstrate the superior performance of our PA-type classification algorithm, particularly in comparison with traditional cut points. Although the hip algorithm performed better, additional compliance achieved with wrist devices might justify using a slightly lower performing algorithm.
Active learning for semi-supervised clustering based on locally linear propagation reconstruction.

PubMed

Chang, Chin-Chun; Lin, Po-Yi

2015-03-01

The success of semi-supervised clustering relies on the effectiveness of side information. To get effective side information, a new active learner learning pairwise constraints known as must-link and cannot-link constraints is proposed in this paper. Three novel techniques are developed for learning effective pairwise constraints. The first technique is used to identify samples less important to cluster structures. This technique makes use of a kernel version of locally linear embedding for manifold learning. Samples neither important to locally linear propagation reconstructions of other samples nor on flat patches in the learned manifold are regarded as unimportant samples. The second is a novel criterion for query selection. This criterion considers not only the importance of a sample to expanding the space coverage of the learned samples but also the expected number of queries needed to learn the sample. To facilitate semi-supervised clustering, the third technique yields inferred must-links for passing information about flat patches in the learned manifold to semi-supervised clustering algorithms. Experimental results have shown that the learned pairwise constraints can capture the underlying cluster structures and proven the feasibility of the proposed approach. Copyright © 2014 Elsevier Ltd. All rights reserved.
Incremental learning of concept drift in nonstationary environments.

PubMed

Elwell, Ryan; Polikar, Robi

2011-10-01

We introduce an ensemble of classifiers-based approach for incremental learning of concept drift, characterized by nonstationary environments (NSEs), where the underlying data distributions change over time. The proposed algorithm, named Learn(++). NSE, learns from consecutive batches of data without making any assumptions on the nature or rate of drift; it can learn from such environments that experience constant or variable rate of drift, addition or deletion of concept classes, as well as cyclical drift. The algorithm learns incrementally, as other members of the Learn(++) family of algorithms, that is, without requiring access to previously seen data. Learn(++). NSE trains one new classifier for each batch of data it receives, and combines these classifiers using a dynamically weighted majority voting. The novelty of the approach is in determining the voting weights, based on each classifier's time-adjusted accuracy on current and past environments. This approach allows the algorithm to recognize, and act accordingly, to the changes in underlying data distributions, as well as to a possible reoccurrence of an earlier distribution. We evaluate the algorithm on several synthetic datasets designed to simulate a variety of nonstationary environments, as well as a real-world weather prediction dataset. Comparisons with several other approaches are also included. Results indicate that Learn(++). NSE can track the changing environments very closely, regardless of the type of concept drift. To allow future use, comparison and benchmarking by interested researchers, we also release our data used in this paper. © 2011 IEEE

Time-oriented hierarchical method for computation of principal components using subspace learning algorithm.

PubMed

Jankovic, Marko; Ogawa, Hidemitsu

2004-10-01

Principal Component Analysis (PCA) and Principal Subspace Analysis (PSA) are classic techniques in statistical data analysis, feature extraction and data compression. Given a set of multivariate measurements, PCA and PSA provide a smaller set of "basis vectors" with less redundancy, and a subspace spanned by them, respectively. Artificial neurons and neural networks have been shown to perform PSA and PCA when gradient ascent (descent) learning rules are used, which is related to the constrained maximization (minimization) of statistical objective functions. Due to their low complexity, such algorithms and their implementation in neural networks are potentially useful in cases of tracking slow changes of correlations in the input data or in updating eigenvectors with new samples. In this paper we propose PCA learning algorithm that is fully homogeneous with respect to neurons. The algorithm is obtained by modification of one of the most famous PSA learning algorithms--Subspace Learning Algorithm (SLA). Modification of the algorithm is based on Time-Oriented Hierarchical Method (TOHM). The method uses two distinct time scales. On a faster time scale PSA algorithm is responsible for the "behavior" of all output neurons. On a slower scale, output neurons will compete for fulfillment of their "own interests". On this scale, basis vectors in the principal subspace are rotated toward the principal eigenvectors. At the end of the paper it will be briefly analyzed how (or why) time-oriented hierarchical method can be used for transformation of any of the existing neural network PSA method, into PCA method.
Characterizing volcanic activity: Application of freely-available webcams

NASA Astrophysics Data System (ADS)

Dehn, J.; Harrild, M.; Webley, P. W.

2017-12-01

In recent years, freely-available web-based cameras, or webcams, have become more readily available allowing an increased level of monitoring at active volcanoes across the globe. While these cameras have been extensively used as qualitative tools, they provide a unique dataset to perform quantitative analyzes of the changing behavior of the particular volcano within the cameras field of view. We focus on the multitude of these freely-available webcams and present a new algorithm to detect changes in volcanic activity using nighttime webcam data. Our approach uses a quick, efficient, and fully automated algorithm to identify changes in webcam data in near real-time, including techniques such as edge detection, Gaussian mixture models, and temporal/spatial statistical tests, which are applied to each target image. Often the image metadata (exposure, gain settings, aperture, focal length, etc.) are unknown, meaning we developed our algorithm to identify the quantity of volcanically incandescent pixels as well as the number of specific algorithm tests needed to detect thermal activity, instead of directly correlating brightness in the webcam to eruption temperatures. We compared our algorithm results to a manual analysis of webcam data for several volcanoes and determined a false detection rate of less than 3% for the automated approach. In our presentation, we describe the different tests integrated into our algorithm, lessons learned, and how we applied our method to several volcanoes across the North Pacific during its development and implementation. We will finish with a discussion on the global applicability of our approach and how to build a 24/7, 365 day a year tool that can be used as an additional data source for real-time analysis of volcanic activity.
A meta-learning system based on genetic algorithms

NASA Astrophysics Data System (ADS)

Pellerin, Eric; Pigeon, Luc; Delisle, Sylvain

2004-04-01

The design of an efficient machine learning process through self-adaptation is a great challenge. The goal of meta-learning is to build a self-adaptive learning system that is constantly adapting to its specific (and dynamic) environment. To that end, the meta-learning mechanism must improve its bias dynamically by updating the current learning strategy in accordance with its available experiences or meta-knowledge. We suggest using genetic algorithms as the basis of an adaptive system. In this work, we propose a meta-learning system based on a combination of the a priori and a posteriori concepts. A priori refers to input information and knowledge available at the beginning in order to built and evolve one or more sets of parameters by exploiting the context of the system"s information. The self-learning component is based on genetic algorithms and neural Darwinism. A posteriori refers to the implicit knowledge discovered by estimation of the future states of parameters and is also applied to the finding of optimal parameters values. The in-progress research presented here suggests a framework for the discovery of knowledge that can support human experts in their intelligence information assessment tasks. The conclusion presents avenues for further research in genetic algorithms and their capability to learn to learn.
Progressive sampling-based Bayesian optimization for efficient and automatic machine learning model selection.

PubMed

Zeng, Xueqiang; Luo, Gang

2017-12-01

Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge and many labor-intensive manual iterations. To lower the bar to machine learning, miscellaneous automatic selection methods for algorithms and/or hyper-parameter values have been proposed. Existing automatic selection methods are inefficient on large data sets. This poses a challenge for using machine learning in the clinical big data era. To address the challenge, this paper presents progressive sampling-based Bayesian optimization, an efficient and automatic selection method for both algorithms and hyper-parameter values. We report an implementation of the method. We show that compared to a state of the art automatic selection method, our method can significantly reduce search time, classification error rate, and standard deviation of error rate due to randomization. This is major progress towards enabling fast turnaround in identifying high-quality solutions required by many machine learning-based clinical data analysis tasks.
Reinforcement Learning in Distributed Domains: Beyond Team Games

NASA Technical Reports Server (NTRS)

Wolpert, David H.; Sill, Joseph; Turner, Kagan

2000-01-01

Distributed search algorithms are crucial in dealing with large optimization problems, particularly when a centralized approach is not only impractical but infeasible. Many machine learning concepts have been applied to search algorithms in order to improve their effectiveness. In this article we present an algorithm that blends Reinforcement Learning (RL) and hill climbing directly, by using the RL signal to guide the exploration step of a hill climbing algorithm. We apply this algorithm to the domain of a constellations of communication satellites where the goal is to minimize the loss of importance weighted data. We introduce the concept of 'ghost' traffic, where correctly setting this traffic induces the satellites to act to optimize the world utility. Our results indicated that the bi-utility search introduced in this paper outperforms both traditional hill climbing algorithms and distributed RL approaches such as team games.
A Novel Harmony Search Algorithm Based on Teaching-Learning Strategies for 0-1 Knapsack Problems

PubMed Central

Tuo, Shouheng; Yong, Longquan; Deng, Fang'an

2014-01-01

To enhance the performance of harmony search (HS) algorithm on solving the discrete optimization problems, this paper proposes a novel harmony search algorithm based on teaching-learning (HSTL) strategies to solve 0-1 knapsack problems. In the HSTL algorithm, firstly, a method is presented to adjust dimension dynamically for selected harmony vector in optimization procedure. In addition, four strategies (harmony memory consideration, teaching-learning strategy, local pitch adjusting, and random mutation) are employed to improve the performance of HS algorithm. Another improvement in HSTL method is that the dynamic strategies are adopted to change the parameters, which maintains the proper balance effectively between global exploration power and local exploitation power. Finally, simulation experiments with 13 knapsack problems show that the HSTL algorithm can be an efficient alternative for solving 0-1 knapsack problems. PMID:24574905
A novel harmony search algorithm based on teaching-learning strategies for 0-1 knapsack problems.

PubMed

Tuo, Shouheng; Yong, Longquan; Deng, Fang'an

2014-01-01

To enhance the performance of harmony search (HS) algorithm on solving the discrete optimization problems, this paper proposes a novel harmony search algorithm based on teaching-learning (HSTL) strategies to solve 0-1 knapsack problems. In the HSTL algorithm, firstly, a method is presented to adjust dimension dynamically for selected harmony vector in optimization procedure. In addition, four strategies (harmony memory consideration, teaching-learning strategy, local pitch adjusting, and random mutation) are employed to improve the performance of HS algorithm. Another improvement in HSTL method is that the dynamic strategies are adopted to change the parameters, which maintains the proper balance effectively between global exploration power and local exploitation power. Finally, simulation experiments with 13 knapsack problems show that the HSTL algorithm can be an efficient alternative for solving 0-1 knapsack problems.
Machine-Learning Algorithms to Code Public Health Spending Accounts

PubMed Central

Leider, Jonathon P.; Resnick, Beth A.; Alfonso, Y. Natalia; Bishai, David

2017-01-01

Objectives: 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. Methods: 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. Results: 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. Conclusions: 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. PMID:28363034
Machine-Learning Algorithms to Code Public Health Spending Accounts.

PubMed

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.
A new optimized GA-RBF neural network algorithm.

PubMed

Jia, Weikuan; Zhao, Dean; Shen, Tian; Su, Chunyang; Hu, Chanli; Zhao, Yuyan

2014-01-01

When confronting the complex problems, radial basis function (RBF) neural network has the advantages of adaptive and self-learning ability, but it is difficult to determine the number of hidden layer neurons, and the weights learning ability from hidden layer to the output layer is low; these deficiencies easily lead to decreasing learning ability and recognition precision. Aiming at this problem, we propose a new optimized RBF neural network algorithm based on genetic algorithm (GA-RBF algorithm), which uses genetic algorithm to optimize the weights and structure of RBF neural network; it chooses new ways of hybrid encoding and optimizing simultaneously. Using the binary encoding encodes the number of the hidden layer's neurons and using real encoding encodes the connection weights. Hidden layer neurons number and connection weights are optimized simultaneously in the new algorithm. However, the connection weights optimization is not complete; we need to use least mean square (LMS) algorithm for further leaning, and finally get a new algorithm model. Using two UCI standard data sets to test the new algorithm, the results show that the new algorithm improves the operating efficiency in dealing with complex problems and also improves the recognition precision, which proves that the new algorithm is valid.
Algorithmic detectability threshold of the stochastic block model

NASA Astrophysics Data System (ADS)

Kawamoto, Tatsuro

2018-03-01

The assumption that the values of model parameters are known or correctly learned, i.e., the Nishimori condition, is one of the requirements for the detectability analysis of the stochastic block model in statistical inference. In practice, however, there is no example demonstrating that we can know the model parameters beforehand, and there is no guarantee that the model parameters can be learned accurately. In this study, we consider the expectation-maximization (EM) algorithm with belief propagation (BP) and derive its algorithmic detectability threshold. Our analysis is not restricted to the community structure but includes general modular structures. Because the algorithm cannot always learn the planted model parameters correctly, the algorithmic detectability threshold is qualitatively different from the one with the Nishimori condition.
A learning approach to the bandwidth multicolouring problem

NASA Astrophysics Data System (ADS)

Akbari Torkestani, Javad

2016-05-01

In this article, a generalisation of the vertex colouring problem known as bandwidth multicolouring problem (BMCP), in which a set of colours is assigned to each vertex such that the difference between the colours, assigned to each vertex and its neighbours, is by no means less than a predefined threshold, is considered. It is shown that the proposed method can be applied to solve the bandwidth colouring problem (BCP) as well. BMCP is known to be NP-hard in graph theory, and so a large number of approximation solutions, as well as exact algorithms, have been proposed to solve it. In this article, two learning automata-based approximation algorithms are proposed for estimating a near-optimal solution to the BMCP. We show, for the first proposed algorithm, that by choosing a proper learning rate, the algorithm finds the optimal solution with a probability close enough to unity. Moreover, we compute the worst-case time complexity of the first algorithm for finding a 1/(1-ɛ) optimal solution to the given problem. The main advantage of this method is that a trade-off between the running time of algorithm and the colour set size (colouring optimality) can be made, by a proper choice of the learning rate also. Finally, it is shown that the running time of the proposed algorithm is independent of the graph size, and so it is a scalable algorithm for large graphs. The second proposed algorithm is compared with some well-known colouring algorithms and the results show the efficiency of the proposed algorithm in terms of the colour set size and running time of algorithm.
DOE Office of Scientific and Technical Information (OSTI.GOV)

Akcakaya, Murat; Nehorai, Arye; Sen, Satyabrata

Most existing radar algorithms are developed under the assumption that the environment (clutter) is stationary. However, in practice, the characteristics of the clutter can vary enormously depending on the radar-operational scenarios. If unaccounted for, these nonstationary variabilities may drastically hinder the radar performance. Therefore, to overcome such shortcomings, we develop a data-driven method for target detection in nonstationary environments. In this method, the radar dynamically detects changes in the environment and adapts to these changes by learning the new statistical characteristics of the environment and by intelligibly updating its statistical detection algorithm. Specifically, we employ drift detection algorithms to detectmore » changes in the environment; incremental learning, particularly learning under concept drift algorithms, to learn the new statistical characteristics of the environment from the new radar data that become available in batches over a period of time. The newly learned environment characteristics are then integrated in the detection algorithm. Furthermore, we use Monte Carlo simulations to demonstrate that the developed method provides a significant improvement in the detection performance compared with detection techniques that are not aware of the environmental changes.« less
Attention Recognition in EEG-Based Affective Learning Research Using CFS+KNN Algorithm.

PubMed

Hu, Bin; Li, Xiaowei; Sun, Shuting; Ratcliffe, Martyn

2018-01-01

The research detailed in this paper focuses on the processing of Electroencephalography (EEG) data to identify attention during the learning process. The identification of affect using our procedures is integrated into a simulated distance learning system that provides feedback to the user with respect to attention and concentration. The authors propose a classification procedure that combines correlation-based feature selection (CFS) and a k-nearest-neighbor (KNN) data mining algorithm. To evaluate the CFS+KNN algorithm, it was test against CFS+C4.5 algorithm and other classification algorithms. The classification performance was measured 10 times with different 3-fold cross validation data. The data was derived from 10 subjects while they were attempting to learn material in a simulated distance learning environment. A self-assessment model of self-report was used with a single valence to evaluate attention on 3 levels (high, neutral, low). It was found that CFS+KNN had a much better performance, giving the highest correct classification rate (CCR) of % for the valence dimension divided into three classes.
Leader-Follower Output Synchronization of Linear Heterogeneous Systems With Active Leader Using Reinforcement Learning.

PubMed

Yang, Yongliang; Modares, Hamidreza; Wunsch, Donald C; Yin, Yixin

2018-06-01

This paper develops optimal control protocols for the distributed output synchronization problem of leader-follower multiagent systems with an active leader. Agents are assumed to be heterogeneous with different dynamics and dimensions. The desired trajectory is assumed to be preplanned and is generated by the leader. Other follower agents autonomously synchronize to the leader by interacting with each other using a communication network. The leader is assumed to be active in the sense that it has a nonzero control input so that it can act independently and update its control to keep the followers away from possible danger. A distributed observer is first designed to estimate the leader's state and generate the reference signal for each follower. Then, the output synchronization of leader-follower systems with an active leader is formulated as a distributed optimal tracking problem, and inhomogeneous algebraic Riccati equations (AREs) are derived to solve it. The resulting distributed optimal control protocols not only minimize the steady-state error but also optimize the transient response of the agents. An off-policy reinforcement learning algorithm is developed to solve the inhomogeneous AREs online in real time and without requiring any knowledge of the agents' dynamics. Finally, two simulation examples are conducted to illustrate the effectiveness of the proposed algorithm.
HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition.

PubMed

Fan, Jianping; Zhao, Tianyi; Kuang, Zhenzhong; Zheng, Yu; Zhang, Ji; Yu, Jun; Peng, Jinye

2017-02-09

In this paper, a hierarchical deep multi-task learning (HD-MTL) algorithm is developed to support large-scale visual recognition (e.g., recognizing thousands or even tens of thousands of atomic object classes automatically). First, multiple sets of multi-level deep features are extracted from different layers of deep convolutional neural networks (deep CNNs), and they are used to achieve more effective accomplishment of the coarseto- fine tasks for hierarchical visual recognition. A visual tree is then learned by assigning the visually-similar atomic object classes with similar learning complexities into the same group, which can provide a good environment for determining the interrelated learning tasks automatically. By leveraging the inter-task relatedness (inter-class similarities) to learn more discriminative group-specific deep representations, our deep multi-task learning algorithm can train more discriminative node classifiers for distinguishing the visually-similar atomic object classes effectively. Our hierarchical deep multi-task learning (HD-MTL) algorithm can integrate two discriminative regularization terms to control the inter-level error propagation effectively, and it can provide an end-to-end approach for jointly learning more representative deep CNNs (for image representation) and more discriminative tree classifier (for large-scale visual recognition) and updating them simultaneously. Our incremental deep learning algorithms can effectively adapt both the deep CNNs and the tree classifier to the new training images and the new object classes. Our experimental results have demonstrated that our HD-MTL algorithm can achieve very competitive results on improving the accuracy rates for large-scale visual recognition.
Establishing a Dynamic Self-Adaptation Learning Algorithm of the BP Neural Network and Its Applications

NASA Astrophysics Data System (ADS)

Li, Xiaofeng; Xiang, Suying; Zhu, Pengfei; Wu, Min

2015-12-01

In order to avoid the inherent deficiencies of the traditional BP neural network, such as slow convergence speed, that easily leading to local minima, poor generalization ability and difficulty in determining the network structure, the dynamic self-adaptive learning algorithm of the BP neural network is put forward to improve the function of the BP neural network. The new algorithm combines the merit of principal component analysis, particle swarm optimization, correlation analysis and self-adaptive model, hence can effectively solve the problems of selecting structural parameters, initial connection weights and thresholds and learning rates of the BP neural network. This new algorithm not only reduces the human intervention, optimizes the topological structures of BP neural networks and improves the network generalization ability, but also accelerates the convergence speed of a network, avoids trapping into local minima, and enhances network adaptation ability and prediction ability. The dynamic self-adaptive learning algorithm of the BP neural network is used to forecast the total retail sale of consumer goods of Sichuan Province, China. Empirical results indicate that the new algorithm is superior to the traditional BP network algorithm in predicting accuracy and time consumption, which shows the feasibility and effectiveness of the new algorithm.
Comparison of machine learning and semi-quantification algorithms for (I123)FP-CIT classification: the beginning of the end for semi-quantification?

PubMed

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 performance was lower for the local database than the research database for both semi-quantitative and machine learning algorithms. However, for both databases, the machine learning methods generated equal or higher mean accuracies (with lower variance) than any of the semi-quantification approaches. The gain in performance from using machine learning algorithms as compared to semi-quantification was relatively small and may be insufficient, when considered in isolation, to offer significant advantages in the clinical context.
Learning Time-Varying Coverage Functions

PubMed Central

Du, Nan; Liang, Yingyu; Balcan, Maria-Florina; Song, Le

2015-01-01

Coverage functions are an important class of discrete functions that capture the law of diminishing returns arising naturally from applications in social network analysis, machine learning, and algorithmic game theory. In this paper, we propose a new problem of learning time-varying coverage functions, and develop a novel parametrization of these functions using random features. Based on the connection between time-varying coverage functions and counting processes, we also propose an efficient parameter learning algorithm based on likelihood maximization, and provide a sample complexity analysis. We applied our algorithm to the influence function estimation problem in information diffusion in social networks, and show that with few assumptions about the diffusion processes, our algorithm is able to estimate influence significantly more accurately than existing approaches on both synthetic and real world data. PMID:25960624
Learning Time-Varying Coverage Functions.

PubMed

Du, Nan; Liang, Yingyu; Balcan, Maria-Florina; Song, Le

2014-12-08

Coverage functions are an important class of discrete functions that capture the law of diminishing returns arising naturally from applications in social network analysis, machine learning, and algorithmic game theory. In this paper, we propose a new problem of learning time-varying coverage functions, and develop a novel parametrization of these functions using random features. Based on the connection between time-varying coverage functions and counting processes, we also propose an efficient parameter learning algorithm based on likelihood maximization, and provide a sample complexity analysis. We applied our algorithm to the influence function estimation problem in information diffusion in social networks, and show that with few assumptions about the diffusion processes, our algorithm is able to estimate influence significantly more accurately than existing approaches on both synthetic and real world data.

Classification of Parkinson's disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples.

PubMed

Zhang, He-Hua; Yang, Liuyang; Liu, Yuchuan; Wang, Pin; Yin, Jun; Li, Yongming; Qiu, Mingguo; Zhu, Xueru; Yan, Fang

2016-11-16

The use of speech based data in the classification of Parkinson disease (PD) has been shown to provide an effect, non-invasive mode of classification in recent years. Thus, there has been an increased interest in speech pattern analysis methods applicable to Parkinsonism for building predictive tele-diagnosis and tele-monitoring models. One of the obstacles in optimizing classifications is to reduce noise within the collected speech samples, thus ensuring better classification accuracy and stability. While the currently used methods are effect, the ability to invoke instance selection has been seldomly examined. In this study, a PD classification algorithm was proposed and examined that combines a multi-edit-nearest-neighbor (MENN) algorithm and an ensemble learning algorithm. First, the MENN algorithm is applied for selecting optimal training speech samples iteratively, thereby obtaining samples with high separability. Next, an ensemble learning algorithm, random forest (RF) or decorrelated neural network ensembles (DNNE), is used to generate trained samples from the collected training samples. Lastly, the trained ensemble learning algorithms are applied to the test samples for PD classification. This proposed method was examined using a more recently deposited public datasets and compared against other currently used algorithms for validation. Experimental results showed that the proposed algorithm obtained the highest degree of improved classification accuracy (29.44%) compared with the other algorithm that was examined. Furthermore, the MENN algorithm alone was found to improve classification accuracy by as much as 45.72%. Moreover, the proposed algorithm was found to exhibit a higher stability, particularly when combining the MENN and RF algorithms. This study showed that the proposed method could improve PD classification when using speech data and can be applied to future studies seeking to improve PD classification methods.
Evolving a Behavioral Repertoire for a Walking Robot.

PubMed

Cully, A; Mouret, J-B

2016-01-01

Numerous algorithms have been proposed to allow legged robots to learn to walk. However, most of these algorithms are devised to learn walking in a straight line, which is not sufficient to accomplish any real-world mission. Here we introduce the Transferability-based Behavioral Repertoire Evolution algorithm (TBR-Evolution), a novel evolutionary algorithm that simultaneously discovers several hundreds of simple walking controllers, one for each possible direction. By taking advantage of solutions that are usually discarded by evolutionary processes, TBR-Evolution is substantially faster than independently evolving each controller. Our technique relies on two methods: (1) novelty search with local competition, which searches for both high-performing and diverse solutions, and (2) the transferability approach, which combines simulations and real tests to evolve controllers for a physical robot. We evaluate this new technique on a hexapod robot. Results show that with only a few dozen short experiments performed on the robot, the algorithm learns a repertoire of controllers that allows the robot to reach every point in its reachable space. Overall, TBR-Evolution introduced a new kind of learning algorithm that simultaneously optimizes all the achievable behaviors of a robot.
Incremental social learning in particle swarms.

PubMed

de Oca, Marco A Montes; Stutzle, Thomas; Van den Enden, Ken; Dorigo, Marco

2011-04-01

Incremental social learning (ISL) was proposed as a way to improve the scalability of systems composed of multiple learning agents. In this paper, we show that ISL can be very useful to improve the performance of population-based optimization algorithms. Our study focuses on two particle swarm optimization (PSO) algorithms: a) the incremental particle swarm optimizer (IPSO), which is a PSO algorithm with a growing population size in which the initial position of new particles is biased toward the best-so-far solution, and b) the incremental particle swarm optimizer with local search (IPSOLS), in which solutions are further improved through a local search procedure. We first derive analytically the probability density function induced by the proposed initialization rule applied to new particles. Then, we compare the performance of IPSO and IPSOLS on a set of benchmark functions with that of other PSO algorithms (with and without local search) and a random restart local search algorithm. Finally, we measure the benefits of using incremental social learning on PSO algorithms by running IPSO and IPSOLS on problems with different fitness distance correlations.
A robust data scaling algorithm to improve classification accuracies in biomedical data.

PubMed

Cao, Xi Hang; Stojkovic, Ivan; Obradovic, Zoran

2016-09-09

Machine learning models have been adapted in biomedical research and practice for knowledge discovery and decision support. While mainstream biomedical informatics research focuses on developing more accurate models, the importance of data preprocessing draws less attention. We propose the Generalized Logistic (GL) algorithm that scales data uniformly to an appropriate interval by learning a generalized logistic function to fit the empirical cumulative distribution function of the data. The GL algorithm is simple yet effective; it is intrinsically robust to outliers, so it is particularly suitable for diagnostic/classification models in clinical/medical applications where the number of samples is usually small; it scales the data in a nonlinear fashion, which leads to potential improvement in accuracy. To evaluate the effectiveness of the proposed algorithm, we conducted experiments on 16 binary classification tasks with different variable types and cover a wide range of applications. The resultant performance in terms of area under the receiver operation characteristic curve (AUROC) and percentage of correct classification showed that models learned using data scaled by the GL algorithm outperform the ones using data scaled by the Min-max and the Z-score algorithm, which are the most commonly used data scaling algorithms. The proposed GL algorithm is simple and effective. It is robust to outliers, so no additional denoising or outlier detection step is needed in data preprocessing. Empirical results also show models learned from data scaled by the GL algorithm have higher accuracy compared to the commonly used data scaling algorithms.
Evolutionary algorithm optimization of biological learning parameters in a biomimetic neuroprosthesis

PubMed Central

Dura-Bernal, S.; Neymotin, S. A.; Kerr, C. C.; Sivagnanam, S.; Majumdar, A.; Francis, J. T.; Lytton, W. W.

2017-01-01

Biomimetic simulation permits neuroscientists to better understand the complex neuronal dynamics of the brain. Embedding a biomimetic simulation in a closed-loop neuroprosthesis, which can read and write signals from the brain, will permit applications for amelioration of motor, psychiatric, and memory-related brain disorders. Biomimetic neuroprostheses require real-time adaptation to changes in the external environment, thus constituting an example of a dynamic data-driven application system. As model fidelity increases, so does the number of parameters and the complexity of finding appropriate parameter configurations. Instead of adapting synaptic weights via machine learning, we employed major biological learning methods: spike-timing dependent plasticity and reinforcement learning. We optimized the learning metaparameters using evolutionary algorithms, which were implemented in parallel and which used an island model approach to obtain sufficient speed. We employed these methods to train a cortical spiking model to utilize macaque brain activity, indicating a selected target, to drive a virtual musculoskeletal arm with realistic anatomical and biomechanical properties to reach to that target. The optimized system was able to reproduce macaque data from a comparable experimental motor task. These techniques can be used to efficiently tune the parameters of multiscale systems, linking realistic neuronal dynamics to behavior, and thus providing a useful tool for neuroscience and neuroprosthetics. PMID:29200477
Adaptive Neuron Apoptosis for Accelerating Deep Learning on Large Scale Systems

DOE Office of Scientific and Technical Information (OSTI.GOV)

Siegel, Charles M.; Daily, Jeffrey A.; Vishnu, Abhinav

Machine Learning and Data Mining (MLDM) algorithms are becoming ubiquitous in {\\em model learning} from the large volume of data generated using simulations, experiments and handheld devices. Deep Learning algorithms -- a class of MLDM algorithms -- are applied for automatic feature extraction, and learning non-linear models for unsupervised and supervised algorithms. Naturally, several libraries which support large scale Deep Learning -- such as TensorFlow and Caffe -- have become popular. In this paper, we present novel techniques to accelerate the convergence of Deep Learning algorithms by conducting low overhead removal of redundant neurons -- {\\em apoptosis} of neurons --more » which do not contribute to model learning, during the training phase itself. We provide in-depth theoretical underpinnings of our heuristics (bounding accuracy loss and handling apoptosis of several neuron types), and present the methods to conduct adaptive neuron apoptosis. We implement our proposed heuristics with the recently introduced TensorFlow and using its recently proposed extension with MPI. Our performance evaluation on two difference clusters -- one connected with Intel Haswell multi-core systems, and other with nVIDIA GPUs -- using InfiniBand, indicates the efficacy of the proposed heuristics and implementations. Specifically, we are able to improve the training time for several datasets by 2-3x, while reducing the number of parameters by 30x (4-5x on average) on datasets such as ImageNet classification. For the Higgs Boson dataset, our implementation improves the accuracy (measured by Area Under Curve (AUC)) for classification from 0.88/1 to 0.94/1, while reducing the number of parameters by 3x in comparison to existing literature, while achieving a 2.44x speedup in comparison to the default (no apoptosis) algorithm.« less
LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices.

PubMed

He, Ziyang; Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-04-17

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.
LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

PubMed Central

Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-01-01

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices. PMID:29673171
Multi-Source Multi-Target Dictionary Learning for Prediction of Cognitive Decline

PubMed Central

Zhang, Jie; Li, Qingyang; Caselli, Richard J.; Thompson, Paul M.; Ye, Jieping; Wang, Yalin

2017-01-01

Alzheimer’s Disease (AD) is the most common type of dementia. Identifying correct biomarkers may determine pre-symptomatic AD subjects and enable early intervention. Recently, Multi-task sparse feature learning has been successfully applied to many computer vision and biomedical informatics researches. It aims to improve the generalization performance by exploiting the shared features among different tasks. However, most of the existing algorithms are formulated as a supervised learning scheme. Its drawback is with either insufficient feature numbers or missing label information. To address these challenges, we formulate an unsupervised framework for multi-task sparse feature learning based on a novel dictionary learning algorithm. To solve the unsupervised learning problem, we propose a two-stage Multi-Source Multi-Target Dictionary Learning (MMDL) algorithm. In stage 1, we propose a multi-source dictionary learning method to utilize the common and individual sparse features in different time slots. In stage 2, supported by a rigorous theoretical analysis, we develop a multi-task learning method to solve the missing label problem. Empirical studies on an N = 3970 longitudinal brain image data set, which involves 2 sources and 5 targets, demonstrate the improved prediction accuracy and speed efficiency of MMDL in comparison with other state-of-the-art algorithms. PMID:28943731
Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations: Translational controller results

NASA Technical Reports Server (NTRS)

Jani, Yashvant

1992-01-01

The reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Maximum Mission (SMM) satellite simulation. In utilizing these fuzzy learning techniques, we also use the Approximate Reasoning based Intelligent Control (ARIC) architecture, and so we use two terms interchangeable to imply the same. This activity is carried out in the Software Technology Laboratory utilizing the Orbital Operations Simulator (OOS). This report is the deliverable D3 in our project activity and provides the test results of the fuzzy learning translational controller. This report is organized in six sections. Based on our experience and analysis with the attitude controller, we have modified the basic configuration of the reinforcement learning algorithm in ARIC as described in section 2. The shuttle translational controller and its implementation in fuzzy learning architecture is described in section 3. Two test cases that we have performed are described in section 4. Our results and conclusions are discussed in section 5, and section 6 provides future plans and summary for the project.
Self-Grading: A Simple Strategy for Formative Assessment in Activity-Based Instruction.

ERIC Educational Resources Information Center

Ulmer, M. B.

This paper discusses the author's personal experiences in developing and implementing a problem-based college mathematics course for liberal arts majors. This project was initiated in response to the realization that most students are dependent on "patterning" learning algorithms and have no expectation that self-initiated thinking is a…
Calculus Challenges: An Active Learning Approach

ERIC Educational Resources Information Center

Crawford, Pam; Moseley, Daniel; Nancarrow, Mike; Ward, Erika

2018-01-01

One of the greatest challenges facing students new to calculus is the ability to persevere in the face of failure. Whether the student is choosing an integration technique or a series test, calculus is often the first course in mathematics where the path to the solution is not prescribed in an algorithmic way. At Jacksonville University we…
Adaptive control of nonlinear system using online error minimum neural networks.

PubMed

Jia, Chao; Li, Xiaoli; Wang, Kang; Ding, Dawei

2016-11-01

In this paper, a new learning algorithm named OEM-ELM (Online Error Minimized-ELM) is proposed based on ELM (Extreme Learning Machine) neural network algorithm and the spreading of its main structure. The core idea of this OEM-ELM algorithm is: online learning, evaluation of network performance, and increasing of the number of hidden nodes. It combines the advantages of OS-ELM and EM-ELM, which can improve the capability of identification and avoid the redundancy of networks. The adaptive control based on the proposed algorithm OEM-ELM is set up which has stronger adaptive capability to the change of environment. The adaptive control of chemical process Continuous Stirred Tank Reactor (CSTR) is also given for application. The simulation results show that the proposed algorithm with respect to the traditional ELM algorithm can avoid network redundancy and improve the control performance greatly. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.
Quantum machine learning for quantum anomaly detection

NASA Astrophysics Data System (ADS)

Liu, Nana; Rebentrost, Patrick

2018-04-01

Anomaly detection is used for identifying data that deviate from "normal" data patterns. Its usage on classical data finds diverse applications in many important areas such as finance, fraud detection, medical diagnoses, data cleaning, and surveillance. With the advent of quantum technologies, anomaly detection of quantum data, in the form of quantum states, may become an important component of quantum applications. Machine-learning algorithms are playing pivotal roles in anomaly detection using classical data. Two widely used algorithms are the kernel principal component analysis and the one-class support vector machine. We find corresponding quantum algorithms to detect anomalies in quantum states. We show that these two quantum algorithms can be performed using resources that are logarithmic in the dimensionality of quantum states. For pure quantum states, these resources can also be logarithmic in the number of quantum states used for training the machine-learning algorithm. This makes these algorithms potentially applicable to big quantum data applications.
Robust Online Hamiltonian Learning

NASA Astrophysics Data System (ADS)

Granade, Christopher; Ferrie, Christopher; Wiebe, Nathan; Cory, David

2013-05-01

In this talk, we introduce a machine-learning algorithm for the problem of inferring the dynamical parameters of a quantum system, and discuss this algorithm in the example of estimating the precession frequency of a single qubit in a static field. Our algorithm is designed with practicality in mind by including parameters that control trade-offs between the requirements on computational and experimental resources. The algorithm can be implemented online, during experimental data collection, or can be used as a tool for post-processing. Most importantly, our algorithm is capable of learning Hamiltonian parameters even when the parameters change from experiment-to-experiment, and also when additional noise processes are present and unknown. Finally, we discuss the performance of the our algorithm by appeal to the Cramer-Rao bound. This work was financially supported by the Canadian government through NSERC and CERC and by the United States government through DARPA. NW would like to acknowledge funding from USARO-DTO.
Online selective kernel-based temporal difference learning.

PubMed

Chen, Xingguo; Gao, Yang; Wang, Ruili

2013-12-01

In this paper, an online selective kernel-based temporal difference (OSKTD) learning algorithm is proposed to deal with large scale and/or continuous reinforcement learning problems. OSKTD includes two online procedures: online sparsification and parameter updating for the selective kernel-based value function. A new sparsification method (i.e., a kernel distance-based online sparsification method) is proposed based on selective ensemble learning, which is computationally less complex compared with other sparsification methods. With the proposed sparsification method, the sparsified dictionary of samples is constructed online by checking if a sample needs to be added to the sparsified dictionary. In addition, based on local validity, a selective kernel-based value function is proposed to select the best samples from the sample dictionary for the selective kernel-based value function approximator. The parameters of the selective kernel-based value function are iteratively updated by using the temporal difference (TD) learning algorithm combined with the gradient descent technique. The complexity of the online sparsification procedure in the OSKTD algorithm is O(n). In addition, two typical experiments (Maze and Mountain Car) are used to compare with both traditional and up-to-date O(n) algorithms (GTD, GTD2, and TDC using the kernel-based value function), and the results demonstrate the effectiveness of our proposed algorithm. In the Maze problem, OSKTD converges to an optimal policy and converges faster than both traditional and up-to-date algorithms. In the Mountain Car problem, OSKTD converges, requires less computation time compared with other sparsification methods, gets a better local optima than the traditional algorithms, and converges much faster than the up-to-date algorithms. In addition, OSKTD can reach a competitive ultimate optima compared with the up-to-date algorithms.
Melanoma segmentation based on deep learning.

PubMed

Zhang, Xiaoqing

2017-12-01

Malignant melanoma is one of the most deadly forms of skin cancer, which is one of the world's fastest-growing cancers. Early diagnosis and treatment is critical. In this study, a neural network structure is utilized to construct a broad and accurate basis for the diagnosis of skin cancer, thereby reducing screening errors. The technique is able to improve the efficacy for identification of normally indistinguishable lesions (such as pigment spots) versus clinically unknown lesions, and to ultimately improve the diagnostic accuracy. In the field of medical imaging, in general, using neural networks for image segmentation is relatively rare. The existing traditional machine-learning neural network algorithms still cannot completely solve the problem of information loss, nor detect the precise division of the boundary area. We use an improved neural network framework, described herein, to achieve efficacious feature learning, and satisfactory segmentation of melanoma images. The architecture of the network includes multiple convolution layers, dropout layers, softmax layers, multiple filters, and activation functions. The number of data sets can be increased via rotation of the training set. A non-linear activation function (such as ReLU and ELU) is employed to alleviate the problem of gradient disappearance, and RMSprop/Adam are incorporated to optimize the loss algorithm. A batch normalization layer is added between the convolution layer and the activation layer to solve the problem of gradient disappearance and explosion. Experiments, described herein, show that our improved neural network architecture achieves higher accuracy for segmentation of melanoma images as compared with existing processes.
Comparison of rule induction, decision trees and formal concept analysis approaches for classification

NASA Astrophysics Data System (ADS)

Kotelnikov, E. V.; Milov, V. R.

2018-05-01

Rule-based learning algorithms have higher transparency and easiness to interpret in comparison with neural networks and deep learning algorithms. These properties make it possible to effectively use such algorithms to solve descriptive tasks of data mining. The choice of an algorithm depends also on its ability to solve predictive tasks. The article compares the quality of the solution of the problems with binary and multiclass classification based on the experiments with six datasets from the UCI Machine Learning Repository. The authors investigate three algorithms: Ripper (rule induction), C4.5 (decision trees), In-Close (formal concept analysis). The results of the experiments show that In-Close demonstrates the best quality of classification in comparison with Ripper and C4.5, however the latter two generate more compact rule sets.
Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?

PubMed

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.
Utilising reinforcement learning to develop strategies for driving auditory neural implants.

PubMed

Lee, Geoffrey W; Zambetta, Fabio; Li, Xiaodong; Paolini, Antonio G

2016-08-01

In this paper we propose a novel application of reinforcement learning to the area of auditory neural stimulation. We aim to develop a simulation environment which is based off real neurological responses to auditory and electrical stimulation in the cochlear nucleus (CN) and inferior colliculus (IC) of an animal model. Using this simulator we implement closed loop reinforcement learning algorithms to determine which methods are most effective at learning effective acoustic neural stimulation strategies. By recording a comprehensive set of acoustic frequency presentations and neural responses from a set of animals we created a large database of neural responses to acoustic stimulation. Extensive electrical stimulation in the CN and the recording of neural responses in the IC provides a mapping of how the auditory system responds to electrical stimuli. The combined dataset is used as the foundation for the simulator, which is used to implement and test learning algorithms. Reinforcement learning, utilising a modified n-Armed Bandit solution, is implemented to demonstrate the model's function. We show the ability to effectively learn stimulation patterns which mimic the cochlea's ability to covert acoustic frequencies to neural activity. Time taken to learn effective replication using neural stimulation takes less than 20 min under continuous testing. These results show the utility of reinforcement learning in the field of neural stimulation. These results can be coupled with existing sound processing technologies to develop new auditory prosthetics that are adaptable to the recipients current auditory pathway. The same process can theoretically be abstracted to other sensory and motor systems to develop similar electrical replication of neural signals.

Learning relative values in the striatum induces violations of normative decision making

PubMed Central

Klein, Tilmann A.; Ullsperger, Markus; Jocham, Gerhard

2017-01-01

To decide optimally between available options, organisms need to learn the values associated with these options. Reinforcement learning models offer a powerful explanation of how these values are learnt from experience. However, human choices often violate normative principles. We suggest that seemingly counterintuitive decisions may arise as a natural consequence of the learning mechanisms deployed by humans. Here, using fMRI and a novel behavioural task, we show that, when suddenly switched to novel choice contexts, participants’ choices are incongruent with values learnt by standard learning algorithms. Instead, behaviour is compatible with the decisions of an agent learning how good an option is relative to an option with which it had previously been paired. Striatal activity exhibits the characteristics of a prediction error used to update such relative option values. Our data suggest that choices can be biased by a tendency to learn option values with reference to the available alternatives. PMID:28631734
Joint learning of labels and distance metric.

PubMed

Liu, Bo; Wang, Meng; Hong, Richang; Zha, Zhengjun; Hua, Xian-Sheng

2010-06-01

Machine learning algorithms frequently suffer from the insufficiency of training data and the usage of inappropriate distance metric. In this paper, we propose a joint learning of labels and distance metric (JLLDM) approach, which is able to simultaneously address the two difficulties. In comparison with the existing semi-supervised learning and distance metric learning methods that focus only on label prediction or distance metric construction, the JLLDM algorithm optimizes the labels of unlabeled samples and a Mahalanobis distance metric in a unified scheme. The advantage of JLLDM is multifold: 1) the problem of training data insufficiency can be tackled; 2) a good distance metric can be constructed with only very few training samples; and 3) no radius parameter is needed since the algorithm automatically determines the scale of the metric. Extensive experiments are conducted to compare the JLLDM approach with different semi-supervised learning and distance metric learning methods, and empirical results demonstrate its effectiveness.
Adiabatic Quantum Anomaly Detection and Machine Learning

NASA Astrophysics Data System (ADS)

Pudenz, Kristen; Lidar, Daniel

2012-02-01

We present methods of anomaly detection and machine learning using adiabatic quantum computing. The machine learning algorithm is a boosting approach which seeks to optimally combine somewhat accurate classification functions to create a unified classifier which is much more accurate than its components. This algorithm then becomes the first part of the larger anomaly detection algorithm. In the anomaly detection routine, we first use adiabatic quantum computing to train two classifiers which detect two sets, the overlap of which forms the anomaly class. We call this the learning phase. Then, in the testing phase, the two learned classification functions are combined to form the final Hamiltonian for an adiabatic quantum computation, the low energy states of which represent the anomalies in a binary vector space.
Generalization Analysis of Fredholm Kernel Regularized Classifiers.

PubMed

Gong, Tieliang; Xu, Zongben; Chen, Hong

2017-07-01

Recently, a new framework, Fredholm learning, was proposed for semisupervised learning problems based on solving a regularized Fredholm integral equation. It allows a natural way to incorporate unlabeled data into learning algorithms to improve their prediction performance. Despite rapid progress on implementable algorithms with theoretical guarantees, the generalization ability of Fredholm kernel learning has not been studied. In this letter, we focus on investigating the generalization performance of a family of classification algorithms, referred to as Fredholm kernel regularized classifiers. We prove that the corresponding learning rate can achieve [Formula: see text] ([Formula: see text] is the number of labeled samples) in a limiting case. In addition, a representer theorem is provided for the proposed regularized scheme, which underlies its applications.
Definition and Analysis of a System for the Automated Comparison of Curriculum Sequencing Algorithms in Adaptive Distance Learning

ERIC Educational Resources Information Center

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…
Mind the Gaps: Controversies about Algorithms, Learning and Trendy Knowledge

ERIC Educational Resources Information Center

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…
Estimation of Comfort/Disconfort Based on EEG in Massage by Use of Clustering according to Correration and Incremental Learning type NN

NASA Astrophysics Data System (ADS)

Teramae, Tatsuya; Kushida, Daisuke; Takemori, Fumiaki; Kitamura, Akira

Authors proposed the estimation method combining k-means algorithm and NN for evaluating massage. However, this estimation method has a problem that discrimination ratio is decreased to new user. There are two causes of this problem. One is that generalization of NN is bad. Another one is that clustering result by k-means algorithm has not high correlation coefficient in a class. Then, this research proposes k-means algorithm according to correlation coefficient and incremental learning for NN. The proposed k-means algorithm is method included evaluation function based on correlation coefficient. Incremental learning is method that NN is learned by new data and initialized weight based on the existing data. The effect of proposed methods are verified by estimation result using EEG data when testee is given massage.
A distributed algorithm for machine learning

NASA Astrophysics Data System (ADS)

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.
Comparing Learning Performance of Students Using Algorithm Visualizations Collaboratively on Different Engagement Levels

ERIC Educational Resources Information Center

Laakso, Mikko-Jussi; Myller, Niko; Korhonen, Ari

2009-01-01

In this paper, two emerging learning and teaching methods have been studied: collaboration in concert with algorithm visualization. When visualizations have been employed in collaborative learning, collaboration introduces new challenges for the visualization tools. In addition, new theories are needed to guide the development and research of the…
Interactive Learning Environment for Bio-Inspired Optimization Algorithms for UAV Path Planning

ERIC Educational Resources Information Center

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…
Efficient Actor-Critic Algorithm with Hierarchical Model Learning and Planning

PubMed Central

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
Efficient Actor-Critic Algorithm with Hierarchical Model Learning and Planning.

PubMed

Zhong, Shan; Liu, Quan; 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.
Do robots need to sleep?

PubMed

Fouks, J D; Besnard, S; Signac, L; Meurice, J C; Neau, J P; Paquereau, J

2004-04-01

The present paper exposes algorithmic results providing a vision about sleep functions which complements biological theory and experiments. Derived from the algorithmic theory of information, the theory of adaptation aims at quantifying how an inherited or acquired piece of knowledge helps individuals to survive. It gives a scale of complexity for survival problems and proves that some of them can only be solved by a dynamical management of memory associating continuous learning and forgetting methods. In this paper we explain how a virtual robot "Picota" has been designed to simulate the behavior of a living hen. In order to survive in its synthetical environment, our robot must recognize good seeds from bad ones, and should take rest during night periods. Within this frame, and facing the rapid evolution of to-be-recognized forms, the best way to equilibrate the energetic needs of the robot and ensure survival is to use the nightly rest to reorganize the pieces of data acquired during the daily learning, and to trash the less useful ones. Thanks to this time sharing, the same circuits can be used for both daily learning and nightly forgetting and thus costs are lower; however, this also forces the system to "paralyse" the virtual robot, and therefore the night algorithm is reminiscent of paradoxical (REM) sleep. The algorithm of the robot takes advantage of the alternation between wakefulness or activity and the rest period. This diagram quite accurately recalls the REM period. In the future, the convergence between the neurophysiology of sleep and the theory of complexity may give us a new line of research in order to elucidate sleep functions.
A neural network model for credit risk evaluation.

PubMed

Khashman, Adnan

2009-08-01

Credit scoring is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. This paper presents a credit risk evaluation system that uses a neural network model based on the back propagation learning algorithm. We train and implement the neural network to decide whether to approve or reject a credit application, using seven learning schemes and real world credit applications from the Australian credit approval datasets. A comparison of the system performance under the different learning schemes is provided, furthermore, we compare the performance of two neural networks; with one and two hidden layers following the ideal learning scheme. Experimental results suggest that neural networks can be effectively used in automatic processing of credit applications.
Any Two Learning Algorithms Are (Almost) Exactly Identical

NASA Technical Reports Server (NTRS)

Wolpert, David H.

2000-01-01

This paper shows that if one is provided with a loss function, it can be used in a natural way to specify a distance measure quantifying the similarity of any two supervised learning algorithms, even non-parametric algorithms. Intuitively, this measure gives the fraction of targets and training sets for which the expected performance of the two algorithms differs significantly. Bounds on the value of this distance are calculated for the case of binary outputs and 0-1 loss, indicating that any two learning algorithms are almost exactly identical for such scenarios. As an example, for any two algorithms A and B, even for small input spaces and training sets, for less than 2e(-50) of all targets will the difference between A's and B's generalization performance of exceed 1%. In particular, this is true if B is bagging applied to A, or boosting applied to A. These bounds can be viewed alternatively as telling us, for example, that the simple English phrase 'I expect that algorithm A will generalize from the training set with an accuracy of at least 75% on the rest of the target' conveys 20,000 bytes of information concerning the target. The paper ends by discussing some of the subtleties of extending the distance measure to give a full (non-parametric) differential geometry of the manifold of learning algorithms.
Using learning automata to determine proper subset size in high-dimensional spaces

NASA Astrophysics Data System (ADS)

Seyyedi, Seyyed Hossein; Minaei-Bidgoli, Behrouz

2017-03-01

In this paper, we offer a new method called FSLA (Finding the best candidate Subset using Learning Automata), which combines the filter and wrapper approaches for feature selection in high-dimensional spaces. Considering the difficulties of dimension reduction in high-dimensional spaces, FSLA's multi-objective functionality is to determine, in an efficient manner, a feature subset that leads to an appropriate tradeoff between the learning algorithm's accuracy and efficiency. First, using an existing weighting function, the feature list is sorted and selected subsets of the list of different sizes are considered. Then, a learning automaton verifies the performance of each subset when it is used as the input space of the learning algorithm and estimates its fitness upon the algorithm's accuracy and the subset size, which determines the algorithm's efficiency. Finally, FSLA introduces the fittest subset as the best choice. We tested FSLA in the framework of text classification. The results confirm its promising performance of attaining the identified goal.
Unsupervised spike sorting based on discriminative subspace learning.

PubMed

Keshtkaran, Mohammad Reza; Yang, Zhi

2014-01-01

Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. In this paper, we present two unsupervised spike sorting algorithms based on discriminative subspace learning. The first algorithm simultaneously learns the discriminative feature subspace and performs clustering. It uses histogram of features in the most discriminative projection to detect the number of neurons. The second algorithm performs hierarchical divisive clustering that learns a discriminative 1-dimensional subspace for clustering in each level of the hierarchy until achieving almost unimodal distribution in the subspace. The algorithms are tested on synthetic and in-vivo data, and are compared against two widely used spike sorting methods. The comparative results demonstrate that our spike sorting methods can achieve substantially higher accuracy in lower dimensional feature space, and they are highly robust to noise. Moreover, they provide significantly better cluster separability in the learned subspace than in the subspace obtained by principal component analysis or wavelet transform.
Deep Belief Networks for Electroencephalography: A Review of Recent Contributions and Future Outlooks.

PubMed

Movahedi, Faezeh; Coyle, James L; Sejdic, Ervin

2018-05-01

Deep learning, a relatively new branch of machine learning, has been investigated for use in a variety of biomedical applications. Deep learning algorithms have been used to analyze different physiological signals and gain a better understanding of human physiology for automated diagnosis of abnormal conditions. In this paper, we provide an overview of deep learning approaches with a focus on deep belief networks in electroencephalography applications. We investigate the state-of-the-art algorithms for deep belief networks and then cover the application of these algorithms and their performances in electroencephalographic applications. We covered various applications of electroencephalography in medicine, including emotion recognition, sleep stage classification, and seizure detection, in order to understand how deep learning algorithms could be modified to better suit the tasks desired. This review is intended to provide researchers with a broad overview of the currently existing deep belief network methodology for electroencephalography signals, as well as to highlight potential challenges for future research.
Annotating smart environment sensor data for activity learning.

PubMed

Szewcyzk, S; Dwan, K; Minor, B; Swedlove, B; Cook, D

2009-01-01

The pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to monitor the functional health of smart home residents, we need to design technologies that recognize and track the activities that people perform at home. Machine learning techniques can perform this task, but the software algorithms rely upon large amounts of sample data that is correctly labeled with the corresponding activity. Labeling, or annotating, sensor data with the corresponding activity can be time consuming, may require input from the smart home resident, and is often inaccurate. Therefore, in this paper we investigate four alternative mechanisms for annotating sensor data with a corresponding activity label. We evaluate the alternative methods along the dimensions of annotation time, resident burden, and accuracy using sensor data collected in a real smart apartment.
Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

PubMed

Shrestha, Akritee; Bergquist, Savannah; Montz, Ellen; Rose, Sherri

2017-12-15

To propose nonparametric ensemble machine learning for mental health and substance use disorders (MHSUD) spending risk adjustment formulas, including considering Clinical Classification Software (CCS) categories as diagnostic covariates over the commonly used Hierarchical Condition Category (HCC) system. 2012-2013 Truven MarketScan database. We implement 21 algorithms to predict MHSUD spending, as well as a weighted combination of these algorithms called super learning. The algorithm collection included seven unique algorithms that were supplied with three differing sets of MHSUD-related predictors alongside demographic covariates: HCC, CCS, and HCC + CCS diagnostic variables. Performance was evaluated based on cross-validated R 2 and predictive ratios. Results show that super learning had the best performance based on both metrics. The top single algorithm was random forests, which improved on ordinary least squares regression by 10 percent with respect to relative efficiency. CCS categories-based formulas were generally more predictive of MHSUD spending compared to HCC-based formulas. Literature supports the potential benefit of implementing a separate MHSUD spending risk adjustment formula. Our results suggest there is an incentive to explore machine learning for MHSUD-specific risk adjustment, as well as considering CCS categories over HCCs. © Health Research and Educational Trust.

Teaching-learning-based Optimization Algorithm for Parameter Identification in the Design of IIR Filters

NASA Astrophysics Data System (ADS)

Singh, R.; Verma, H. K.

2013-12-01

This paper presents a teaching-learning-based optimization (TLBO) algorithm to solve parameter identification problems in the designing of digital infinite impulse response (IIR) filter. TLBO based filter modelling is applied to calculate the parameters of unknown plant in simulations. Unlike other heuristic search algorithms, TLBO algorithm is an algorithm-specific parameter-less algorithm. In this paper big bang-big crunch (BB-BC) optimization and PSO algorithms are also applied to filter design for comparison. Unknown filter parameters are considered as a vector to be optimized by these algorithms. MATLAB programming is used for implementation of proposed algorithms. Experimental results show that the TLBO is more accurate to estimate the filter parameters than the BB-BC optimization algorithm and has faster convergence rate when compared to PSO algorithm. TLBO is used where accuracy is more essential than the convergence speed.
Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure

NASA Astrophysics Data System (ADS)

Asencio-Cortés, G.; Morales-Esteban, A.; Shang, X.; Martínez-Álvarez, F.

2018-06-01

Earthquake magnitude prediction is a challenging problem that has been widely studied during the last decades. Statistical, geophysical and machine learning approaches can be found in literature, with no particularly satisfactory results. In recent years, powerful computational techniques to analyze big data have emerged, making possible the analysis of massive datasets. These new methods make use of physical resources like cloud based architectures. California is known for being one of the regions with highest seismic activity in the world and many data are available. In this work, the use of several regression algorithms combined with ensemble learning is explored in the context of big data (1 GB catalog is used), in order to predict earthquakes magnitude within the next seven days. Apache Spark framework, H2 O library in R language and Amazon cloud infrastructure were been used, reporting very promising results.
On the Comparison of Wearable Sensor Data Fusion to a Single Sensor Machine Learning Technique in Fall Detection.

PubMed

Tsinganos, Panagiotis; Skodras, Athanassios

2018-02-14

In the context of the ageing global population, researchers and scientists have tried to find solutions to many challenges faced by older people. Falls, the leading cause of injury among elderly, are usually severe enough to require immediate medical attention; thus, their detection is of primary importance. To this effect, many fall detection systems that utilize wearable and ambient sensors have been proposed. In this study, we compare three newly proposed data fusion schemes that have been applied in human activity recognition and fall detection. Furthermore, these algorithms are compared to our recent work regarding fall detection in which only one type of sensor is used. The results show that fusion algorithms differ in their performance, whereas a machine learning strategy should be preferred. In conclusion, the methods presented and the comparison of their performance provide useful insights into the problem of fall detection.
Drought Management Activities of the National Drought Mitigation Center (NDMC): Contributions Toward a Global Drought Early Warning System (GDEWS)

NASA Astrophysics Data System (ADS)

Stumpf, A.; Lachiche, N.; Malet, J.; Kerle, N.; Puissant, A.

2011-12-01

VHR satellite images have become a primary source for landslide inventory mapping after major triggering events such as earthquakes and heavy rainfalls. Visual image interpretation is still the prevailing standard method for operational purposes but is time-consuming and not well suited to fully exploit the increasingly better supply of remote sensing data. Recent studies have addressed the development of more automated image analysis workflows for landslide inventory mapping. In particular object-oriented approaches that account for spatial and textural image information have been demonstrated to be more adequate than pixel-based classification but manually elaborated rule-based classifiers are difficult to adapt under changing scene characteristics. Machine learning algorithm allow learning classification rules for complex image patterns from labelled examples and can be adapted straightforwardly with available training data. In order to reduce the amount of costly training data active learning (AL) has evolved as a key concept to guide the sampling for many applications. The underlying idea of AL is to initialize a machine learning model with a small training set, and to subsequently exploit the model state and data structure to iteratively select the most valuable samples that should be labelled by the user. With relatively few queries and labelled samples, an AL strategy yields higher accuracies than an equivalent classifier trained with many randomly selected samples. This study addressed the development of an AL method for landslide mapping from VHR remote sensing images with special consideration of the spatial distribution of the samples. Our approach [1] is based on the Random Forest algorithm and considers the classifier uncertainty as well as the variance of potential sampling regions to guide the user towards the most valuable sampling areas. The algorithm explicitly searches for compact regions and thereby avoids a spatially disperse sampling pattern inherent to most other AL methods. The accuracy, the sampling time and the computational runtime of the algorithm were evaluated on multiple satellite images capturing recent large scale landslide events. Sampling between 1-4% of the study areas the accuracies between 74% and 80% were achieved, whereas standard sampling schemes yielded only accuracies between 28% and 50% with equal sampling costs. Compared to commonly used point-wise AL algorithm the proposed approach significantly reduces the number of iterations and hence the computational runtime. Since the user can focus on relatively few compact areas (rather than on hundreds of distributed points) the overall labeling time is reduced by more than 50% compared to point-wise queries. An experimental evaluation of multiple expert mappings demonstrated strong relationships between the uncertainties of the experts and the machine learning model. It revealed that the achieved accuracies are within the range of the inter-expert disagreement and that it will be indispensable to consider ground truth uncertainties to truly achieve further enhancements in the future. The proposed method is generally applicable to a wide range of optical satellite images and landslide types. [1] A. Stumpf, N. Lachiche, J.-P. Malet, N. Kerle, and A. Puissant, Active learning in the spatial domain for remote sensing image classification, IEEE Transactions on Geosciece and Remote Sensing. 2013, DOI 10.1109/TGRS.2013.2262052.
A sparse structure learning algorithm for Gaussian Bayesian Network identification from high-dimensional data.

PubMed

Huang, Shuai; Li, Jing; Ye, Jieping; Fleisher, Adam; Chen, Kewei; Wu, Teresa; Reiman, Eric

2013-06-01

Structure learning of Bayesian Networks (BNs) is an important topic in machine learning. Driven by modern applications in genetics and brain sciences, accurate and efficient learning of large-scale BN structures from high-dimensional data becomes a challenging problem. To tackle this challenge, we propose a Sparse Bayesian Network (SBN) structure learning algorithm that employs a novel formulation involving one L1-norm penalty term to impose sparsity and another penalty term to ensure that the learned BN is a Directed Acyclic Graph--a required property of BNs. Through both theoretical analysis and extensive experiments on 11 moderate and large benchmark networks with various sample sizes, we show that SBN leads to improved learning accuracy, scalability, and efficiency as compared with 10 existing popular BN learning algorithms. We apply SBN to a real-world application of brain connectivity modeling for Alzheimer's disease (AD) and reveal findings that could lead to advancements in AD research.
A Sparse Structure Learning Algorithm for Gaussian Bayesian Network Identification from High-Dimensional Data

PubMed Central

Huang, Shuai; Li, Jing; Ye, Jieping; Fleisher, Adam; Chen, Kewei; Wu, Teresa; Reiman, Eric

2014-01-01

Structure learning of Bayesian Networks (BNs) is an important topic in machine learning. Driven by modern applications in genetics and brain sciences, accurate and efficient learning of large-scale BN structures from high-dimensional data becomes a challenging problem. To tackle this challenge, we propose a Sparse Bayesian Network (SBN) structure learning algorithm that employs a novel formulation involving one L1-norm penalty term to impose sparsity and another penalty term to ensure that the learned BN is a Directed Acyclic Graph (DAG)—a required property of BNs. Through both theoretical analysis and extensive experiments on 11 moderate and large benchmark networks with various sample sizes, we show that SBN leads to improved learning accuracy, scalability, and efficiency as compared with 10 existing popular BN learning algorithms. We apply SBN to a real-world application of brain connectivity modeling for Alzheimer’s disease (AD) and reveal findings that could lead to advancements in AD research. PMID:22665720
Bidirectional extreme learning machine for regression problem and its learning effectiveness.

PubMed

Yang, Yimin; Wang, Yaonan; Yuan, Xiaofang

2012-09-01

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

NASA Technical Reports Server (NTRS)

Chu, Lon-Chan; Wah, Benjamin W.

1992-01-01

A minimization of learning-algorithm completion time is sought in the present optimal-mapping study of the learning process in multilayer feed-forward artificial neural networks (ANNs) for message-passing multicomputers. A novel approximation algorithm for mappings of this kind is derived from observations of the dominance of a parallel ANN algorithm over its communication time. Attention is given to both static and dynamic mapping schemes for systems with static and dynamic background workloads, as well as to experimental results obtained for simulated mappings on multicomputers with dynamic background workloads.
Epidermis area detection for immunofluorescence microscopy

NASA Astrophysics Data System (ADS)

Dovganich, Andrey; Krylov, Andrey; Nasonov, Andrey; Makhneva, Natalia

2018-04-01

We propose a novel image segmentation method for immunofluorescence microscopy images of skin tissue for the diagnosis of various skin diseases. The segmentation is based on machine learning algorithms. The feature vector is filled by three groups of features: statistical features, Laws' texture energy measures and local binary patterns. The images are preprocessed for better learning. Different machine learning algorithms have been used and the best results have been obtained with random forest algorithm. We use the proposed method to detect the epidermis region as a part of pemphigus diagnosis system.
Learning classification trees

NASA Technical Reports Server (NTRS)

Buntine, Wray

1991-01-01

Algorithms for learning classification trees have had successes in artificial intelligence and statistics over many years. How a tree learning algorithm can be derived from Bayesian decision theory is outlined. This introduces Bayesian techniques for splitting, smoothing, and tree averaging. The splitting rule turns out to be similar to Quinlan's information gain splitting rule, while smoothing and averaging replace pruning. Comparative experiments with reimplementations of a minimum encoding approach, Quinlan's C4 and Breiman et al. Cart show the full Bayesian algorithm is consistently as good, or more accurate than these other approaches though at a computational price.
Decentralized learning in Markov games.

PubMed

Vrancx, Peter; Verbeeck, Katja; Nowé, Ann

2008-08-01

Learning automata (LA) were recently shown to be valuable tools for designing multiagent reinforcement learning algorithms. One of the principal contributions of the LA theory is that a set of decentralized independent LA is able to control a finite Markov chain with unknown transition probabilities and rewards. In this paper, we propose to extend this algorithm to Markov games--a straightforward extension of single-agent Markov decision problems to distributed multiagent decision problems. We show that under the same ergodic assumptions of the original theorem, the extended algorithm will converge to a pure equilibrium point between agent policies.
Is it worth changing pattern recognition methods for structural health monitoring?

NASA Astrophysics Data System (ADS)

Bull, L. A.; Worden, K.; Cross, E. J.; Dervilis, N.

2017-05-01

The key element of this work is to demonstrate alternative strategies for using pattern recognition algorithms whilst investigating structural health monitoring. This paper looks to determine if it makes any difference in choosing from a range of established classification techniques: from decision trees and support vector machines, to Gaussian processes. Classification algorithms are tested on adjustable synthetic data to establish performance metrics, then all techniques are applied to real SHM data. To aid the selection of training data, an informative chain of artificial intelligence tools is used to explore an active learning interaction between meaningful clusters of data.
Discrete sequence prediction and its applications

NASA Technical Reports Server (NTRS)

Laird, Philip

1992-01-01

Learning from experience to predict sequences of discrete symbols is a fundamental problem in machine learning with many applications. We apply sequence prediction using a simple and practical sequence-prediction algorithm, called TDAG. The TDAG algorithm is first tested by comparing its performance with some common data compression algorithms. Then it is adapted to the detailed requirements of dynamic program optimization, with excellent results.
Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation

PubMed Central

Spratling, M. W.; De Meyer, K.; Kompass, R.

2009-01-01

This paper demonstrates that nonnegative matrix factorisation is mathematically related to a class of neural networks that employ negative feedback as a mechanism of competition. This observation inspires a novel learning algorithm which we call Divisive Input Modulation (DIM). The proposed algorithm provides a mathematically simple and computationally efficient method for the unsupervised learning of image components, even in conditions where these elementary features overlap considerably. To test the proposed algorithm, a novel artificial task is introduced which is similar to the frequently-used bars problem but employs squares rather than bars to increase the degree of overlap between components. Using this task, we investigate how the proposed method performs on the parsing of artificial images composed of overlapping features, given the correct representation of the individual components; and secondly, we investigate how well it can learn the elementary components from artificial training images. We compare the performance of the proposed algorithm with its predecessors including variations on these algorithms that have produced state-of-the-art performance on the bars problem. The proposed algorithm is more successful than its predecessors in dealing with overlap and occlusion in the artificial task that has been used to assess performance. PMID:19424442
Physical activity classification using the GENEA wrist-worn accelerometer.

PubMed

Zhang, Shaoyan; Rowlands, Alex V; Murray, Peter; Hurst, Tina L

2012-04-01

Most accelerometer-based activity monitors are worn on the waist or lower back for assessment of habitual physical activity. Output is in arbitrary counts that can be classified by activity intensity according to published thresholds. The purpose of this study was to develop methods to classify physical activities into walking, running, household, or sedentary activities based on raw acceleration data from the GENEA (Gravity Estimator of Normal Everyday Activity) and compare classification accuracy from a wrist-worn GENEA with a waist-worn GENEA. Sixty participants (age = 49.4 ± 6.5 yr, body mass index = 24.6 ± 3.4 kg·m⁻²) completed an ordered series of 10-12 semistructured activities in the laboratory and outdoor environment. Throughout, three GENEA accelerometers were worn: one at the waist, one on the left wrist, and one on the right wrist. Acceleration data were collected at 80 Hz. Features obtained from both fast Fourier transform and wavelet decomposition were extracted, and machine learning algorithms were used to classify four types of daily activities including sedentary, household, walking, and running activities. The computational results demonstrated that the algorithm we developed can accurately classify certain types of daily activities, with high overall classification accuracy for both waist-worn GENEA (0.99) and wrist-worn GENEA (right wrist = 0.97, left wrist = 0.96). We have successfully developed algorithms suitable for use with wrist-worn accelerometers for detecting certain types of physical activities; the performance is comparable to waist-worn accelerometers for assessment of physical activity.
Identifying seizure onset zone from electrocorticographic recordings: A machine learning approach based on phase locking value.

PubMed

Elahian, Bahareh; Yeasin, Mohammed; Mudigoudar, Basanagoud; Wheless, James W; Babajani-Feremi, Abbas

2017-10-01

Using a novel technique based on phase locking value (PLV), we investigated the potential for features extracted from electrocorticographic (ECoG) recordings to serve as biomarkers to identify the seizure onset zone (SOZ). We computed the PLV between the phase of the amplitude of high gamma activity (80-150Hz) and the phase of lower frequency rhythms (4-30Hz) from ECoG recordings obtained from 10 patients with epilepsy (21 seizures). We extracted five features from the PLV and used a machine learning approach based on logistic regression to build a model that classifies electrodes as SOZ or non-SOZ. More than 96% of electrodes identified as the SOZ by our algorithm were within the resected area in six seizure-free patients. In four non-seizure-free patients, more than 31% of the identified SOZ electrodes by our algorithm were outside the resected area. In addition, we observed that the seizure outcome in non-seizure-free patients correlated with the number of non-resected SOZ electrodes identified by our algorithm. This machine learning approach, based on features extracted from the PLV, effectively identified electrodes within the SOZ. The approach has the potential to assist clinicians in surgical decision-making when pre-surgical intracranial recordings are utilized. Copyright © 2017 British Epilepsy Association. Published by Elsevier Ltd. All rights reserved.
A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update

NASA Astrophysics Data System (ADS)

Lotte, F.; Bougrain, L.; Cichocki, A.; Clerc, M.; Congedo, M.; Rakotomamonjy, A.; Yger, F.

2018-06-01

Objective. Most current electroencephalography (EEG)-based brain–computer interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately ten years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. Approach. We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. Main results. We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. Significance. This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.
Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression

NASA Astrophysics Data System (ADS)

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

2017-11-01

We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is {>}1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions ({<}500 m). However, we show improved results of all the methods when data from a neighbouring meteorological tower are included, and also with a pre-processing scheme using a wavelet transform. Also presented are results of the algorithm performance in daytime and nighttime conditions, and for different prediction time horizons.
Beyond the "c" and the "x": Learning with Algorithms in Massive Open Online Courses (MOOCs)

ERIC Educational Resources Information Center

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…
A Computer Environment for Beginners' Learning of Sorting Algorithms: Design and Pilot Evaluation

ERIC Educational Resources Information Center

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…

Advanced methods in NDE using machine learning approaches

NASA Astrophysics Data System (ADS)

Wunderlich, Christian; Tschöpe, Constanze; Duckhorn, Frank

2018-04-01

Machine learning (ML) methods and algorithms have been applied recently with great success in quality control and predictive maintenance. Its goal to build new and/or leverage existing algorithms to learn from training data and give accurate predictions, or to find patterns, particularly with new and unseen similar data, fits perfectly to Non-Destructive Evaluation. The advantages of ML in NDE are obvious in such tasks as pattern recognition in acoustic signals or automated processing of images from X-ray, Ultrasonics or optical methods. Fraunhofer IKTS is using machine learning algorithms in acoustic signal analysis. The approach had been applied to such a variety of tasks in quality assessment. The principal approach is based on acoustic signal processing with a primary and secondary analysis step followed by a cognitive system to create model data. Already in the second analysis steps unsupervised learning algorithms as principal component analysis are used to simplify data structures. In the cognitive part of the software further unsupervised and supervised learning algorithms will be trained. Later the sensor signals from unknown samples can be recognized and classified automatically by the algorithms trained before. Recently the IKTS team was able to transfer the software for signal processing and pattern recognition to a small printed circuit board (PCB). Still, algorithms will be trained on an ordinary PC; however, trained algorithms run on the Digital Signal Processor and the FPGA chip. The identical approach will be used for pattern recognition in image analysis of OCT pictures. Some key requirements have to be fulfilled, however. A sufficiently large set of training data, a high signal-to-noise ratio, and an optimized and exact fixation of components are required. The automated testing can be done subsequently by the machine. By integrating the test data of many components along the value chain further optimization including lifetime and durability prediction based on big data becomes possible, even if components are used in different versions or configurations. This is the promise behind German Industry 4.0.
Image segmentation on adaptive edge-preserving smoothing

NASA Astrophysics Data System (ADS)

He, Kun; Wang, Dan; Zheng, Xiuqing

2016-09-01

Nowadays, typical active contour models are widely applied in image segmentation. However, they perform badly on real images with inhomogeneous subregions. In order to overcome the drawback, this paper proposes an edge-preserving smoothing image segmentation algorithm. At first, this paper analyzes the edge-preserving smoothing conditions for image segmentation and constructs an edge-preserving smoothing model inspired by total variation. The proposed model has the ability to smooth inhomogeneous subregions and preserve edges. Then, a kind of clustering algorithm, which reasonably trades off edge-preserving and subregion-smoothing according to the local information, is employed to learn the edge-preserving parameter adaptively. At last, according to the confidence level of segmentation subregions, this paper constructs a smoothing convergence condition to avoid oversmoothing. Experiments indicate that the proposed algorithm has superior performance in precision, recall, and F-measure compared with other segmentation algorithms, and it is insensitive to noise and inhomogeneous-regions.
Performances of Machine Learning Algorithms for Binary Classification of Network Anomaly Detection System

NASA Astrophysics Data System (ADS)

Nawir, Mukrimah; Amir, Amiza; Lynn, Ong Bi; Yaakob, Naimah; Badlishah Ahmad, R.

2018-05-01

The rapid growth of technologies might endanger them to various network attacks due to the nature of data which are frequently exchange their data through Internet and large-scale data that need to be handle. Moreover, network anomaly detection using machine learning faced difficulty when dealing the involvement of dataset where the number of labelled network dataset is very few in public and this caused many researchers keep used the most commonly network dataset (KDDCup99) which is not relevant to employ the machine learning (ML) algorithms for a classification. Several issues regarding these available labelled network datasets are discussed in this paper. The aim of this paper to build a network anomaly detection system using machine learning algorithms that are efficient, effective and fast processing. The finding showed that AODE algorithm is performed well in term of accuracy and processing time for binary classification towards UNSW-NB15 dataset.
Fully Decentralized Semi-supervised Learning via Privacy-preserving Matrix Completion.

PubMed

Fierimonte, Roberto; Scardapane, Simone; Uncini, Aurelio; Panella, Massimo

2016-08-26

Distributed learning refers to the problem of inferring a function when the training data are distributed among different nodes. While significant work has been done in the contexts of supervised and unsupervised learning, the intermediate case of Semi-supervised learning in the distributed setting has received less attention. In this paper, we propose an algorithm for this class of problems, by extending the framework of manifold regularization. The main component of the proposed algorithm consists of a fully distributed computation of the adjacency matrix of the training patterns. To this end, we propose a novel algorithm for low-rank distributed matrix completion, based on the framework of diffusion adaptation. Overall, the distributed Semi-supervised algorithm is efficient and scalable, and it can preserve privacy by the inclusion of flexible privacy-preserving mechanisms for similarity computation. The experimental results and comparison on a wide range of standard Semi-supervised benchmarks validate our proposal.
Systematic Poisoning Attacks on and Defenses for Machine Learning in Healthcare.

PubMed

Mozaffari-Kermani, Mehran; Sur-Kolay, Susmita; Raghunathan, Anand; Jha, Niraj K

2015-11-01

Machine learning is being used in a wide range of application domains to discover patterns in large datasets. Increasingly, the results of machine learning drive critical decisions in applications related to healthcare and biomedicine. Such health-related applications are often sensitive, and thus, any security breach would be catastrophic. Naturally, the integrity of the results computed by machine learning is of great importance. Recent research has shown that some machine-learning algorithms can be compromised by augmenting their training datasets with malicious data, leading to a new class of attacks called poisoning attacks. Hindrance of a diagnosis may have life-threatening consequences and could cause distrust. On the other hand, not only may a false diagnosis prompt users to distrust the machine-learning algorithm and even abandon the entire system but also such a false positive classification may cause patient distress. In this paper, we present a systematic, algorithm-independent approach for mounting poisoning attacks across a wide range of machine-learning algorithms and healthcare datasets. The proposed attack procedure generates input data, which, when added to the training set, can either cause the results of machine learning to have targeted errors (e.g., increase the likelihood of classification into a specific class), or simply introduce arbitrary errors (incorrect classification). These attacks may be applied to both fixed and evolving datasets. They can be applied even when only statistics of the training dataset are available or, in some cases, even without access to the training dataset, although at a lower efficacy. We establish the effectiveness of the proposed attacks using a suite of six machine-learning algorithms and five healthcare datasets. Finally, we present countermeasures against the proposed generic attacks that are based on tracking and detecting deviations in various accuracy metrics, and benchmark their effectiveness.
Algorithm Building and Learning Programming Languages Using a New Educational Paradigm

NASA Astrophysics Data System (ADS)

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.
CrossSim

DOE Office of Scientific and Technical Information (OSTI.GOV)

Plimpton, Steven J.; Agarwal, Sapan; Schiek, Richard

2016-09-02

CrossSim is a simulator for modeling neural-inspired machine learning algorithms on analog hardware, such as resistive memory crossbars. It includes noise models for reading and updating the resistances, which can be based on idealized equations or experimental data. It can also introduce noise and finite precision effects when converting values from digital to analog and vice versa. All of these effects can be turned on or off as an algorithm processes a data set and attempts to learn its salient attributes so that it can be categorized in the machine learning training/classification context. CrossSim thus allows the robustness, accuracy, andmore » energy usage of a machine learning algorithm to be tested on simulated hardware.« less
New Dandelion Algorithm Optimizes Extreme Learning Machine for Biomedical Classification Problems

PubMed Central

Li, Xiguang; Zhao, Liang; Gong, Changqing; Liu, Xiaojing

2017-01-01

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. PMID:29085425
One-Shot Learning of Human Activity With an MAP Adapted GMM and Simplex-HMM.

PubMed

Rodriguez, Mario; Orrite, Carlos; Medrano, Carlos; Makris, Dimitrios

2016-05-10

This paper presents a novel activity class representation using a single sequence for training. The contribution of this representation lays on the ability to train an one-shot learning recognition system, useful in new scenarios where capturing and labeling sequences is expensive or impractical. The method uses a universal background model of local descriptors obtained from source databases available on-line and adapts it to a new sequence in the target scenario through a maximum a posteriori adaptation. Each activity sample is encoded in a sequence of normalized bag of features and modeled by a new hidden Markov model formulation, where the expectation-maximization algorithm for training is modified to deal with observations consisting in vectors in a unit simplex. Extensive experiments in recognition have been performed using one-shot learning over the public datasets Weizmann, KTH, and IXMAS. These experiments demonstrate the discriminative properties of the representation and the validity of application in recognition systems, achieving state-of-the-art results.
Somato-dendritic Synaptic Plasticity and Error-backpropagation in Active Dendrites

PubMed Central

Schiess, Mathieu; Urbanczik, Robert; Senn, Walter

2016-01-01

In the last decade dendrites of cortical neurons have been shown to nonlinearly combine synaptic inputs by evoking local dendritic spikes. It has been suggested that these nonlinearities raise the computational power of a single neuron, making it comparable to a 2-layer network of point neurons. But how these nonlinearities can be incorporated into the synaptic plasticity to optimally support learning remains unclear. We present a theoretically derived synaptic plasticity rule for supervised and reinforcement learning that depends on the timing of the presynaptic, the dendritic and the postsynaptic spikes. For supervised learning, the rule can be seen as a biological version of the classical error-backpropagation algorithm applied to the dendritic case. When modulated by a delayed reward signal, the same plasticity is shown to maximize the expected reward in reinforcement learning for various coding scenarios. Our framework makes specific experimental predictions and highlights the unique advantage of active dendrites for implementing powerful synaptic plasticity rules that have access to downstream information via backpropagation of action potentials. PMID:26841235
Automatic machine-learning based identification of jogging periods from accelerometer measurements of adolescents under field conditions.

PubMed

Zdravevski, Eftim; Risteska Stojkoska, Biljana; Standl, Marie; Schulz, Holger

2017-01-01

Assessment of health benefits associated with physical activity depend on the activity duration, intensity and frequency, therefore their correct identification is very valuable and important in epidemiological and clinical studies. The aims of this study are: to develop an algorithm for automatic identification of intended jogging periods; and to assess whether the identification performance is improved when using two accelerometers at the hip and ankle, compared to when using only one at either position. The study used diarized jogging periods and the corresponding accelerometer data from thirty-nine, 15-year-old adolescents, collected under field conditions, as part of the GINIplus study. The data was obtained from two accelerometers placed at the hip and ankle. Automated feature engineering technique was performed to extract features from the raw accelerometer readings and to select a subset of the most significant features. Four machine learning algorithms were used for classification: Logistic regression, Support Vector Machines, Random Forest and Extremely Randomized Trees. Classification was performed using only data from the hip accelerometer, using only data from ankle accelerometer and using data from both accelerometers. The reported jogging periods were verified by visual inspection and used as golden standard. After the feature selection and tuning of the classification algorithms, all options provided a classification accuracy of at least 0.99, independent of the applied segmentation strategy with sliding windows of either 60s or 180s. The best matching ratio, i.e. the length of correctly identified jogging periods related to the total time including the missed ones, was up to 0.875. It could be additionally improved up to 0.967 by application of post-classification rules, which considered the duration of breaks and jogging periods. There was no obvious benefit of using two accelerometers, rather almost the same performance could be achieved from either accelerometer position. Machine learning techniques can be used for automatic activity recognition, as they provide very accurate activity recognition, significantly more accurate than when keeping a diary. Identification of jogging periods in adolescents can be performed using only one accelerometer. Performance-wise there is no significant benefit from using accelerometers on both locations.
Soft learning vector quantization and clustering algorithms based on ordered weighted aggregation operators.

PubMed

Karayiannis, N B

2000-01-01

This paper presents the development and investigates the properties of ordered weighted learning vector quantization (LVQ) and clustering algorithms. These algorithms are developed by using gradient descent to minimize reformulation functions based on aggregation operators. An axiomatic approach provides conditions for selecting aggregation operators that lead to admissible reformulation functions. Minimization of admissible reformulation functions based on ordered weighted aggregation operators produces a family of soft LVQ and clustering algorithms, which includes fuzzy LVQ and clustering algorithms as special cases. The proposed LVQ and clustering algorithms are used to perform segmentation of magnetic resonance (MR) images of the brain. The diagnostic value of the segmented MR images provides the basis for evaluating a variety of ordered weighted LVQ and clustering algorithms.
Learning classification with auxiliary probabilistic information

PubMed Central

Nguyen, Quang; Valizadegan, Hamed; Hauskrecht, Milos

2012-01-01

Finding ways of incorporating auxiliary information or auxiliary data into the learning process has been the topic of active data mining and machine learning research in recent years. In this work we study and develop a new framework for classification learning problem in which, in addition to class labels, the learner is provided with an auxiliary (probabilistic) information that reflects how strong the expert feels about the class label. This approach can be extremely useful for many practical classification tasks that rely on subjective label assessment and where the cost of acquiring additional auxiliary information is negligible when compared to the cost of the example analysis and labelling. We develop classification algorithms capable of using the auxiliary information to make the learning process more efficient in terms of the sample complexity. We demonstrate the benefit of the approach on a number of synthetic and real world data sets by comparing it to the learning with class labels only. PMID:25309141
Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: laboratory-based calibrations are not enough.

PubMed

Bastian, Thomas; Maire, Aurélia; Dugas, Julien; Ataya, Abbas; Villars, Clément; Gris, Florence; Perrin, Emilie; Caritu, Yanis; Doron, Maeva; Blanc, Stéphane; Jallon, Pierre; Simon, Chantal

2015-03-15

"Objective" methods to monitor physical activity and sedentary patterns in free-living conditions are necessary to further our understanding of their impacts on health. In recent years, many software solutions capable of automatically identifying activity types from portable accelerometry data have been developed, with promising results in controlled conditions, but virtually no reports on field tests. An automatic classification algorithm initially developed using laboratory-acquired data (59 subjects engaging in a set of 24 standardized activities) to discriminate between 8 activity classes (lying, slouching, sitting, standing, walking, running, and cycling) was applied to data collected in the field. Twenty volunteers equipped with a hip-worn triaxial accelerometer performed at their own pace an activity set that included, among others, activities such as walking the streets, running, cycling, and taking the bus. Performances of the laboratory-calibrated classification algorithm were compared with those of an alternative version of the same model including field-collected data in the learning set. Despite good results in laboratory conditions, the performances of the laboratory-calibrated algorithm (assessed by confusion matrices) decreased for several activities when applied to free-living data. Recalibrating the algorithm with data closer to real-life conditions and from an independent group of subjects proved useful, especially for the detection of sedentary behaviors while in transports, thereby improving the detection of overall sitting (sensitivity: laboratory model = 24.9%; recalibrated model = 95.7%). Automatic identification methods should be developed using data acquired in free-living conditions rather than data from standardized laboratory activity sets only, and their limits carefully tested before they are used in field studies. Copyright © 2015 the American Physiological Society.
Operational algorithm development and refinement approaches

NASA Astrophysics Data System (ADS)

Ardanuy, Philip E.

2003-11-01

Next-generation polar and geostationary systems, such as the National Polar-orbiting Operational Environmental Satellite System (NPOESS) and the Geostationary Operational Environmental Satellite (GOES)-R, will deploy new generations of electro-optical reflective and emissive capabilities. These will include low-radiometric-noise, improved spatial resolution multi-spectral and hyperspectral imagers and sounders. To achieve specified performances (e.g., measurement accuracy, precision, uncertainty, and stability), and best utilize the advanced space-borne sensing capabilities, a new generation of retrieval algorithms will be implemented. In most cases, these advanced algorithms benefit from ongoing testing and validation using heritage research mission algorithms and data [e.g., the Earth Observing System (EOS)] Moderate-resolution Imaging Spectroradiometer (MODIS) and Shuttle Ozone Limb Scattering Experiment (SOLSE)/Limb Ozone Retreival Experiment (LORE). In these instances, an algorithm's theoretical basis is not static, but rather improves with time. Once frozen, an operational algorithm can "lose ground" relative to research analogs. Cost/benefit analyses provide a basis for change management. The challenge is in reconciling and balancing the stability, and "comfort," that today"s generation of operational platforms provide (well-characterized, known, sensors and algorithms) with the greatly improved quality, opportunities, and risks, that the next generation of operational sensors and algorithms offer. By using the best practices and lessons learned from heritage/groundbreaking activities, it is possible to implement an agile process that enables change, while managing change. This approach combines a "known-risk" frozen baseline with preset completion schedules with insertion opportunities for algorithm advances as ongoing validation activities identify and repair areas of weak performance. This paper describes an objective, adaptive implementation roadmap that takes into account the specific maturities of each system"s (sensor and algorithm) technology to provide for a program that contains continuous improvement while retaining its manageability.
Machine Learning

NASA Astrophysics Data System (ADS)

Hoffmann, Achim; Mahidadia, Ashesh

The purpose of this chapter is to present fundamental ideas and techniques of machine learning suitable for the field of this book, i.e., for automated scientific discovery. The chapter focuses on those symbolic machine learning methods, which produce results that are suitable to be interpreted and understood by humans. This is particularly important in the context of automated scientific discovery as the scientific theories to be produced by machines are usually meant to be interpreted by humans. This chapter contains some of the most influential ideas and concepts in machine learning research to give the reader a basic insight into the field. After the introduction in Sect. 1, general ideas of how learning problems can be framed are given in Sect. 2. The section provides useful perspectives to better understand what learning algorithms actually do. Section 3 presents the Version space model which is an early learning algorithm as well as a conceptual framework, that provides important insight into the general mechanisms behind most learning algorithms. In section 4, a family of learning algorithms, the AQ family for learning classification rules is presented. The AQ family belongs to the early approaches in machine learning. The next, Sect. 5 presents the basic principles of decision tree learners. Decision tree learners belong to the most influential class of inductive learning algorithms today. Finally, a more recent group of learning systems are presented in Sect. 6, which learn relational concepts within the framework of logic programming. This is a particularly interesting group of learning systems since the framework allows also to incorporate background knowledge which may assist in generalisation. Section 7 discusses Association Rules - a technique that comes from the related field of Data mining. Section 8 presents the basic idea of the Naive Bayesian Classifier. While this is a very popular learning technique, the learning result is not well suited for human comprehension as it is essentially a large collection of probability values. In Sect. 9, we present a generic method for improving accuracy of a given learner by generatingmultiple classifiers using variations of the training data. While this works well in most cases, the resulting classifiers have significantly increased complexity and, hence, tend to destroy the human readability of the learning result that a single learner may produce. Section 10 contains a summary, mentions briefly other techniques not discussed in this chapter and presents outlook on the potential of machine learning in the future.
Clustering and Candidate Motif Detection in Exosomal miRNAs by Application of Machine Learning Algorithms.

PubMed

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.
An adaptive deep Q-learning strategy for handwritten digit recognition.

PubMed

Qiao, Junfei; Wang, Gongming; Li, Wenjing; Chen, Min

2018-02-22

Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time. Copyright © 2018 Elsevier Ltd. All rights reserved.
Classification of Multiple Seizure-Like States in Three Different Rodent Models of Epileptogenesis.

PubMed

Guirgis, Mirna; Serletis, Demitre; Zhang, Jane; Florez, Carlos; Dian, Joshua A; Carlen, Peter L; Bardakjian, Berj L

2014-01-01

Epilepsy is a dynamical disease and its effects are evident in over fifty million people worldwide. This study focused on objective classification of the multiple states involved in the brain's epileptiform activity. Four datasets from three different rodent hippocampal preparations were explored, wherein seizure-like-events (SLE) were induced by the perfusion of a low - Mg(2+) /high-K(+) solution or 4-Aminopyridine. Local field potentials were recorded from CA3 pyramidal neurons and interneurons and modeled as Markov processes. Specifically, hidden Markov models (HMM) were used to determine the nature of the states present. Properties of the Hilbert transform were used to construct the feature spaces for HMM training. By sequentially applying the HMM training algorithm, multiple states were identified both in episodes of SLE and nonSLE activity. Specifically, preSLE and postSLE states were differentiated and multiple inner SLE states were identified. This was accomplished using features extracted from the lower frequencies (1-4 Hz, 4-8 Hz) alongside those of both the low- (40-100 Hz) and high-gamma (100-200 Hz) of the recorded electrical activity. The learning paradigm of this HMM-based system eliminates the inherent bias associated with other learning algorithms that depend on predetermined state segmentation and renders it an appropriate candidate for SLE classification.
A fast elitism Gaussian estimation of distribution algorithm and application for PID optimization.

PubMed

Xu, Qingyang; Zhang, Chengjin; Zhang, Li

2014-01-01

Estimation of distribution algorithm (EDA) is an intelligent optimization algorithm based on the probability statistics theory. A fast elitism Gaussian estimation of distribution algorithm (FEGEDA) is proposed in this paper. The Gaussian probability model is used to model the solution distribution. The parameters of Gaussian come from the statistical information of the best individuals by fast learning rule. A fast learning rule is used to enhance the efficiency of the algorithm, and an elitism strategy is used to maintain the convergent performance. The performances of the algorithm are examined based upon several benchmarks. In the simulations, a one-dimensional benchmark is used to visualize the optimization process and probability model learning process during the evolution, and several two-dimensional and higher dimensional benchmarks are used to testify the performance of FEGEDA. The experimental results indicate the capability of FEGEDA, especially in the higher dimensional problems, and the FEGEDA exhibits a better performance than some other algorithms and EDAs. Finally, FEGEDA is used in PID controller optimization of PMSM and compared with the classical-PID and GA.

A Fast Elitism Gaussian Estimation of Distribution Algorithm and Application for PID Optimization

PubMed Central

Xu, Qingyang; Zhang, Chengjin; Zhang, Li

2014-01-01

Estimation of distribution algorithm (EDA) is an intelligent optimization algorithm based on the probability statistics theory. A fast elitism Gaussian estimation of distribution algorithm (FEGEDA) is proposed in this paper. The Gaussian probability model is used to model the solution distribution. The parameters of Gaussian come from the statistical information of the best individuals by fast learning rule. A fast learning rule is used to enhance the efficiency of the algorithm, and an elitism strategy is used to maintain the convergent performance. The performances of the algorithm are examined based upon several benchmarks. In the simulations, a one-dimensional benchmark is used to visualize the optimization process and probability model learning process during the evolution, and several two-dimensional and higher dimensional benchmarks are used to testify the performance of FEGEDA. The experimental results indicate the capability of FEGEDA, especially in the higher dimensional problems, and the FEGEDA exhibits a better performance than some other algorithms and EDAs. Finally, FEGEDA is used in PID controller optimization of PMSM and compared with the classical-PID and GA. PMID:24892059
Voice based gender classification using machine learning

NASA Astrophysics Data System (ADS)

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

2017-11-01

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

NASA Astrophysics Data System (ADS)

Moll, Mark; Bordeaux, Janice; Kavraki, Lydia E.

2013-12-01

Motion planning is a core problem in robotics concerned with finding feasible paths for a given robot. Motion planning algorithms perform a search in the high-dimensional continuous space of robot configurations and exemplify many of the core algorithmic concepts of search algorithms and associated data structures. Motion planning algorithms can be explained in a simplified two-dimensional setting, but this masks many of the subtleties and complexities of the underlying problem. We have developed software for project-based learning of motion planning that enables deep learning. The projects that we have developed allow advanced undergraduate students and graduate students to reflect on the performance of existing textbook algorithms and their own variations on such algorithms. Formative assessment has been conducted at three institutions. The core of the software used for this teaching module is also used within the Robot Operating System, a widely adopted platform by the robotics research community. This allows for transfer of knowledge and skills to robotics research projects involving a large variety robot hardware platforms.
Budgeted Interactive Learning

DTIC Science & Technology

2017-06-15

the methodology of reducing the online-algorithm-selecting problem as a contextual bandit problem, which is yet another interactive learning...KH2016a] Kuan-Hao Huang and Hsuan-Tien Lin. Linear upper confidence bound algorithm for contextual bandit problem with piled rewards. In Proceedings
A Parallel Multiclassification Algorithm for Big Data Using an Extreme Learning Machine.

PubMed

Duan, Mingxing; Li, Kenli; Liao, Xiangke; Li, Keqin

2018-06-01

As data sets become larger and more complicated, an extreme learning machine (ELM) that runs in a traditional serial environment cannot realize its ability to be fast and effective. Although a parallel ELM (PELM) based on MapReduce to process large-scale data shows more efficient learning speed than identical ELM algorithms in a serial environment, some operations, such as intermediate results stored on disks and multiple copies for each task, are indispensable, and these operations create a large amount of extra overhead and degrade the learning speed and efficiency of the PELMs. In this paper, an efficient ELM based on the Spark framework (SELM), which includes three parallel subalgorithms, is proposed for big data classification. By partitioning the corresponding data sets reasonably, the hidden layer output matrix calculation algorithm, matrix decomposition algorithm, and matrix decomposition algorithm perform most of the computations locally. At the same time, they retain the intermediate results in distributed memory and cache the diagonal matrix as broadcast variables instead of several copies for each task to reduce a large amount of the costs, and these actions strengthen the learning ability of the SELM. Finally, we implement our SELM algorithm to classify large data sets. Extensive experiments have been conducted to validate the effectiveness of the proposed algorithms. As shown, our SELM achieves an speedup on a cluster with ten nodes, and reaches a speedup with 15 nodes, an speedup with 20 nodes, a speedup with 25 nodes, a speedup with 30 nodes, and a speedup with 35 nodes.
Machine Learning for Biological Trajectory Classification Applications

NASA Technical Reports Server (NTRS)

Sbalzarini, Ivo F.; Theriot, Julie; Koumoutsakos, Petros

2002-01-01

Machine-learning techniques, including clustering algorithms, support vector machines and hidden Markov models, are applied to the task of classifying trajectories of moving keratocyte cells. The different algorithms axe compared to each other as well as to expert and non-expert test persons, using concepts from signal-detection theory. The algorithms performed very well as compared to humans, suggesting a robust tool for trajectory classification in biological applications.
Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain

PubMed Central

Tighe, Patrick J.; Harle, Christopher A.; Hurley, Robert W.; Aytug, Haldun; Boezaart, Andre P.; Fillingim, Roger B.

2015-01-01

Background Given their ability to process highly dimensional datasets with hundreds of variables, machine learning algorithms may offer one solution to the vexing challenge of predicting postoperative pain. Methods Here, we report on the application of machine learning algorithms to predict postoperative pain outcomes in a retrospective cohort of 8071 surgical patients using 796 clinical variables. Five algorithms were compared in terms of their ability to forecast moderate to severe postoperative pain: Least Absolute Shrinkage and Selection Operator (LASSO), gradient-boosted decision tree, support vector machine, neural network, and k-nearest neighbor, with logistic regression included for baseline comparison. Results In forecasting moderate to severe postoperative pain for postoperative day (POD) 1, the LASSO algorithm, using all 796 variables, had the highest accuracy with an area under the receiver-operating curve (ROC) of 0.704. Next, the gradient-boosted decision tree had an ROC of 0.665 and the k-nearest neighbor algorithm had an ROC of 0.643. For POD 3, the LASSO algorithm, using all variables, again had the highest accuracy, with an ROC of 0.727. Logistic regression had a lower ROC of 0.5 for predicting pain outcomes on POD 1 and 3. Conclusions Machine learning algorithms, when combined with complex and heterogeneous data from electronic medical record systems, can forecast acute postoperative pain outcomes with accuracies similar to methods that rely only on variables specifically collected for pain outcome prediction. PMID:26031220
Antimicrobial and Antibiofilm Activity and Machine Learning Classification Analysis of Essential Oils from Different Mediterranean Plants against Pseudomonas aeruginosa.

PubMed

Artini, Marco; Patsilinakos, Alexandros; Papa, Rosanna; Božović, Mijat; Sabatino, Manuela; Garzoli, Stefania; Vrenna, Gianluca; Tilotta, Marco; Pepi, Federico; Ragno, Rino; Selan, Laura

2018-02-23

Pseudomonas aeruginosa is a ubiquitous organism and opportunistic pathogen that can cause persistent infections due to its peculiar antibiotic resistance mechanisms and to its ability to adhere and form biofilm. The interest in the development of new approaches for the prevention and treatment of biofilm formation has recently increased. The aim of this study was to seek new non-biocidal agents able to inhibit biofilm formation, in order to counteract virulence rather than bacterial growth and avoid the selection of escape mutants. Herein, different essential oils extracted from Mediterranean plants were analyzed for their activity against P. aeruginosa . Results show that they were able to destabilize biofilm at very low concentration without impairing bacterial viability. Since the action is not related to a bacteriostatic/bactericidal activity on P. aeruginosa , the biofilm change of growth in presence of the essential oils was possibly due to a modulation of the phenotype. To this aim, application of machine learning algorithms led to the development of quantitative activity-composition relationships classification models that allowed to direct point out those essential oil chemical components more involved in the inhibition of biofilm production. The action of selected essential oils on sessile phenotype make them particularly interesting for possible applications such as prevention of bacterial contamination in the community and in healthcare environments in order to prevent human infections. We assayed 89 samples of different essential oils as P. aeruginosa anti-biofilm. Many samples inhibited P. aeruginosa biofilm at concentrations as low as 48.8 µg/mL. Classification of the models was developed through machine learning algorithms.
The kinetic activation-relaxation technique: an off-lattice, self-learning kinetic Monte Carlo algorithm with on-the-fly event search

NASA Astrophysics Data System (ADS)

Mousseau, Nomand

2012-02-01

While kinetic Monte Carlo algorithm has been proposed almost 40 years ago, its application in materials science has been mostly limited to lattice-based motion due to the difficulties associated with identifying new events and building usable catalogs when atoms moved into off-lattice position. Here, I present the kinetic activation-relaxation technique (kinetic ART) is an off-lattice, self-learning kinetic Monte Carlo algorithm with on-the-fly event search [1]. It combines ART nouveau [2], a very efficient unbiased open-ended activated method for finding transition states, with a topological classification [3] that allows a discrete cataloguing of local environments in complex systems, including disordered materials. In kinetic ART, local topologies are first identified for all atoms in a system. ART nouveau event searches are then launched for new topologies, building an extensive catalog of barriers and events. Next, all low energy events are fully reconstructed and relaxed, allowing to take complete account of elastic effects in the system's kinetics. Using standard kinetic Monte Carlo, the clock is brought forward and an event is then selected and applied before a new search for topologies is launched. In addition to presenting the various elements of the algorithm, I will discuss three recent applications to ion-bombarded silicon, defect diffusion in Fe and structural relaxation in amorphous silicon.[4pt] This work was done in collaboration with Laurent Karim B'eland, Peter Brommer, Fedwa El-Mellouhi, Jean-Francois Joly and Laurent Lewis.[4pt] [1] F. El-Mellouhi, N. Mousseau and L.J. Lewis, Phys. Rev. B. 78, 153202 (2008); L.K. B'eland et al., Phys. Rev. E 84, 046704 (2011).[2] G.T. Barkema and N. Mousseau, Phys. Rev. Lett. 77, 4358 (1996); E. Machado-Charry et al., J. Chem Phys. 135, 034102, (2011).[3] B.D. McKay, Congressus Numerantium 30, 45 (1981).
Cognitive Learning, Monitoring and Assistance of Industrial Workflows Using Egocentric Sensor Networks

PubMed Central

Bleser, Gabriele; Damen, Dima; Behera, Ardhendu; Hendeby, Gustaf; Mura, Katharina; Miezal, Markus; Gee, Andrew; Petersen, Nils; Maçães, Gustavo; Domingues, Hugo; Gorecky, Dominic; Almeida, Luis; Mayol-Cuevas, Walterio; Calway, Andrew; Cohn, Anthony G.; Hogg, David C.; Stricker, Didier

2015-01-01

Today, the workflows that are involved in industrial assembly and production activities are becoming increasingly complex. To efficiently and safely perform these workflows is demanding on the workers, in particular when it comes to infrequent or repetitive tasks. This burden on the workers can be eased by introducing smart assistance systems. This article presents a scalable concept and an integrated system demonstrator designed for this purpose. The basic idea is to learn workflows from observing multiple expert operators and then transfer the learnt workflow models to novice users. Being entirely learning-based, the proposed system can be applied to various tasks and domains. The above idea has been realized in a prototype, which combines components pushing the state of the art of hardware and software designed with interoperability in mind. The emphasis of this article is on the algorithms developed for the prototype: 1) fusion of inertial and visual sensor information from an on-body sensor network (BSN) to robustly track the user’s pose in magnetically polluted environments; 2) learning-based computer vision algorithms to map the workspace, localize the sensor with respect to the workspace and capture objects, even as they are carried; 3) domain-independent and robust workflow recovery and monitoring algorithms based on spatiotemporal pairwise relations deduced from object and user movement with respect to the scene; and 4) context-sensitive augmented reality (AR) user feedback using a head-mounted display (HMD). A distinguishing key feature of the developed algorithms is that they all operate solely on data from the on-body sensor network and that no external instrumentation is needed. The feasibility of the chosen approach for the complete action-perception-feedback loop is demonstrated on three increasingly complex datasets representing manual industrial tasks. These limited size datasets indicate and highlight the potential of the chosen technology as a combined entity as well as point out limitations of the system. PMID:26126116
Improving semi-automated segmentation by integrating learning with active sampling

NASA Astrophysics Data System (ADS)

Huo, Jing; Okada, Kazunori; Brown, Matthew

2012-02-01

Interactive segmentation algorithms such as GrowCut usually require quite a few user interactions to perform well, and have poor repeatability. In this study, we developed a novel technique to boost the performance of the interactive segmentation method GrowCut involving: 1) a novel "focused sampling" approach for supervised learning, as opposed to conventional random sampling; 2) boosting GrowCut using the machine learned results. We applied the proposed technique to the glioblastoma multiforme (GBM) brain tumor segmentation, and evaluated on a dataset of ten cases from a multiple center pharmaceutical drug trial. The results showed that the proposed system has the potential to reduce user interaction while maintaining similar segmentation accuracy.
Seizure Forecasting and the Preictal State in Canine Epilepsy.

PubMed

Varatharajah, Yogatheesan; Iyer, Ravishankar K; Berry, Brent M; Worrell, Gregory A; Brinkmann, Benjamin H

2017-02-01

The ability to predict seizures may enable patients with epilepsy to better manage their medications and activities, potentially reducing side effects and improving quality of life. Forecasting epileptic seizures remains a challenging problem, but machine learning methods using intracranial electroencephalographic (iEEG) measures have shown promise. A machine-learning-based pipeline was developed to process iEEG recordings and generate seizure warnings. Results support the ability to forecast seizures at rates greater than a Poisson random predictor for all feature sets and machine learning algorithms tested. In addition, subject-specific neurophysiological changes in multiple features are reported preceding lead seizures, providing evidence supporting the existence of a distinct and identifiable preictal state.
SEIZURE FORECASTING AND THE PREICTAL STATE IN CANINE EPILEPSY

PubMed Central

Varatharajah, Yogatheesan; Iyer, Ravishankar K.; Berry, Brent M.; Worrell, Gregory A.; Brinkmann, Benjamin H.

2017-01-01

The ability to predict seizures may enable patients with epilepsy to better manage their medications and activities, potentially reducing side effects and improving quality of life. Forecasting epileptic seizures remains a challenging problem, but machine learning methods using intracranial electroencephalographic (iEEG) measures have shown promise. A machine-learning-based pipeline was developed to process iEEG recordings and generate seizure warnings. Results support the ability to forecast seizures at rates greater than a Poisson random predictor for all feature sets and machine learning algorithms tested. In addition, subject-specific neurophysiological changes in multiple features are reported preceding lead seizures, providing evidence supporting the existence of a distinct and identifiable preictal state. PMID:27464854
Intelligent tutoring system for clinical reasoning skill acquisition in dental students.

PubMed

Suebnukarn, Siriwan

2009-10-01

Learning clinical reasoning is an important core activity of the modern dental curriculum. This article describes an intelligent tutoring system (ITS) for clinical reasoning skill acquisition. The system is designed to provide an experience that emulates that of live human-tutored problem-based learning (PBL) sessions as much as possible, while at the same time permitting the students to participate collaboratively from disparate locations. The system uses Bayesian networks to model individual student knowledge and activity, as well as that of the group. Tutoring algorithms use the models to generate tutoring hints. The system incorporates a multimodal interface that integrates text and graphics so as to provide a rich communication channel between the students and the system, as well as among students in the group. Comparison of learning outcomes shows that student clinical reasoning gains from the ITS are similar to those obtained from human-tutored sessions.
Cognitive tutoring induces widespread neuroplasticity and remediates brain function in children with mathematical learning disabilities.

PubMed

Iuculano, Teresa; Rosenberg-Lee, Miriam; Richardson, Jennifer; Tenison, Caitlin; Fuchs, Lynn; Supekar, Kaustubh; Menon, Vinod

2015-09-30

Competency with numbers is essential in today's society; yet, up to 20% of children exhibit moderate to severe mathematical learning disabilities (MLD). Behavioural intervention can be effective, but the neurobiological mechanisms underlying successful intervention are unknown. Here we demonstrate that eight weeks of 1:1 cognitive tutoring not only remediates poor performance in children with MLD, but also induces widespread changes in brain activity. Neuroplasticity manifests as normalization of aberrant functional responses in a distributed network of parietal, prefrontal and ventral temporal-occipital areas that support successful numerical problem solving, and is correlated with performance gains. Remarkably, machine learning algorithms show that brain activity patterns in children with MLD are significantly discriminable from neurotypical peers before, but not after, tutoring, suggesting that behavioural gains are not due to compensatory mechanisms. Our study identifies functional brain mechanisms underlying effective intervention in children with MLD and provides novel metrics for assessing response to intervention.
Data integration modeling applied to drill hole planning through semi-supervised learning: A case study from the Dalli Cu-Au porphyry deposit in the central Iran

NASA Astrophysics Data System (ADS)

Fatehi, Moslem; Asadi, Hooshang H.

2017-04-01

In this study, the application of a transductive support vector machine (TSVM), an innovative semi-supervised learning algorithm, has been proposed for mapping the potential drill targets at a detailed exploration stage. The semi-supervised learning method is a hybrid of supervised and unsupervised learning approach that simultaneously uses both training and non-training data to design a classifier. By using the TSVM algorithm, exploration layers at the Dalli porphyry Cu-Au deposit in the central Iran were integrated to locate the boundary of the Cu-Au mineralization for further drilling. By applying this algorithm on the non-training (unlabeled) and limited training (labeled) Dalli exploration data, the study area was classified in two domains of Cu-Au ore and waste. Then, the results were validated by the earlier block models created, using the available borehole and trench data. In addition to TSVM, the support vector machine (SVM) algorithm was also implemented on the study area for comparison. Thirty percent of the labeled exploration data was used to evaluate the performance of these two algorithms. The results revealed 87 percent correct recognition accuracy for the TSVM algorithm and 82 percent for the SVM algorithm. The deepest inclined borehole, recently drilled in the western part of the Dalli deposit, indicated that the boundary of Cu-Au mineralization, as identified by the TSVM algorithm, was only 15 m off from the actual boundary intersected by this borehole. According to the results of the TSVM algorithm, six new boreholes were suggested for further drilling at the Dalli deposit. This study showed that the TSVM algorithm could be a useful tool for enhancing the mineralization zones and consequently, ensuring a more accurate drill hole planning.
Advancing Research in Second Language Writing through Computational Tools and Machine Learning Techniques: A Research Agenda

ERIC Educational Resources Information Center

Crossley, Scott A.

2013-01-01

This paper provides an agenda for replication studies focusing on second language (L2) writing and the use of natural language processing (NLP) tools and machine learning algorithms. Specifically, it introduces a range of the available NLP tools and machine learning algorithms and demonstrates how these could be used to replicate seminal studies…
Diagnosing Learners' Problem-Solving Strategies Using Learning Environments with Algorithmic Problems in Secondary Education

ERIC Educational Resources Information Center

Kiesmuller, Ulrich

2009-01-01

At schools special learning and programming environments are often used in the field of algorithms. Particularly with regard to computer science lessons in secondary education, they are supposed to help novices to learn the basics of programming. In several parts of Germany (e.g., Bavaria) these fundamentals are taught as early as in the seventh…
Inverse Problems in Geodynamics Using Machine Learning Algorithms

NASA Astrophysics Data System (ADS)

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.
Feedback error learning control of magnetic satellites using type-2 fuzzy neural networks with elliptic membership functions.

PubMed

Khanesar, Mojtaba Ahmadieh; Kayacan, Erdal; Reyhanoglu, Mahmut; Kaynak, Okyay

2015-04-01

A novel type-2 fuzzy membership function (MF) in the form of an ellipse has recently been proposed in literature, the parameters of which that represent uncertainties are de-coupled from its parameters that determine the center and the support. This property has enabled the proposers to make an analytical comparison of the noise rejection capabilities of type-1 fuzzy logic systems with its type-2 counterparts. In this paper, a sliding mode control theory-based learning algorithm is proposed for an interval type-2 fuzzy logic system which benefits from elliptic type-2 fuzzy MFs. The learning is based on the feedback error learning method and not only the stability of the learning is proved but also the stability of the overall system is shown by adding an additional component to the control scheme to ensure robustness. In order to test the efficiency and efficacy of the proposed learning and the control algorithm, the trajectory tracking problem of a magnetic rigid spacecraft is studied. The simulations results show that the proposed control algorithm gives better performance results in terms of a smaller steady state error and a faster transient response as compared to conventional control algorithms.

On the fusion of tuning parameters of fuzzy rules and neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Learning fuzzy rule-based system with neural network can lead to a precise valuable empathy of several problems. Fuzzy logic offers a simple way to reach at a definite conclusion based upon its vague, ambiguous, imprecise, noisy or missing input information. Conventional learning algorithm for tuning parameters of fuzzy rules using training input-output data usually end in a weak firing state, this certainly powers the fuzzy rule and makes it insecure for a multiple-input fuzzy system. In this paper, we introduce a new learning algorithm for tuning the parameters of the fuzzy rules alongside with radial basis function neural network (RBFNN) in training input-output data based on the gradient descent method. By the new learning algorithm, the problem of weak firing using the conventional method was addressed. We illustrated the efficiency of our new learning algorithm by means of numerical examples. MATLAB R2014(a) software was used in simulating our result The result shows that the new learning method has the best advantage of training the fuzzy rules without tempering with the fuzzy rule table which allowed a membership function of the rule to be used more than one time in the fuzzy rule base.
Collaborative mining and transfer learning for relational data

NASA Astrophysics Data System (ADS)

Levchuk, Georgiy; Eslami, Mohammed

2015-06-01

Many of the real-world problems, - including human knowledge, communication, biological, and cyber network analysis, - deal with data entities for which the essential information is contained in the relations among those entities. Such data must be modeled and analyzed as graphs, with attributes on both objects and relations encode and differentiate their semantics. Traditional data mining algorithms were originally designed for analyzing discrete objects for which a set of features can be defined, and thus cannot be easily adapted to deal with graph data. This gave rise to the relational data mining field of research, of which graph pattern learning is a key sub-domain [11]. In this paper, we describe a model for learning graph patterns in collaborative distributed manner. Distributed pattern learning is challenging due to dependencies between the nodes and relations in the graph, and variability across graph instances. We present three algorithms that trade-off benefits of parallelization and data aggregation, compare their performance to centralized graph learning, and discuss individual benefits and weaknesses of each model. Presented algorithms are designed for linear speedup in distributed computing environments, and learn graph patterns that are both closer to ground truth and provide higher detection rates than centralized mining algorithm.
Quantum machine learning.

PubMed

Biamonte, Jacob; Wittek, Peter; Pancotti, Nicola; Rebentrost, Patrick; Wiebe, Nathan; Lloyd, Seth

2017-09-13

Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Quantum systems produce atypical patterns that classical systems are thought not to produce efficiently, so it is reasonable to postulate that quantum computers may outperform classical computers on machine learning tasks. The field of quantum machine learning explores how to devise and implement quantum software that could enable machine learning that is faster than that of classical computers. Recent work has produced quantum algorithms that could act as the building blocks of machine learning programs, but the hardware and software challenges are still considerable.
Quantum machine learning

NASA Astrophysics Data System (ADS)

Biamonte, Jacob; Wittek, Peter; Pancotti, Nicola; Rebentrost, Patrick; Wiebe, Nathan; Lloyd, Seth

2017-09-01

Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Quantum systems produce atypical patterns that classical systems are thought not to produce efficiently, so it is reasonable to postulate that quantum computers may outperform classical computers on machine learning tasks. The field of quantum machine learning explores how to devise and implement quantum software that could enable machine learning that is faster than that of classical computers. Recent work has produced quantum algorithms that could act as the building blocks of machine learning programs, but the hardware and software challenges are still considerable.
Using Reinforcement Learning to Provide Stable Brain-Machine Interface Control Despite Neural Input Reorganization

PubMed Central

Pohlmeyer, Eric A.; Mahmoudi, Babak; Geng, Shijia; Prins, Noeline W.; Sanchez, Justin C.

2014-01-01

Brain-machine interface (BMI) systems give users direct neural control of robotic, communication, or functional electrical stimulation systems. As BMI systems begin transitioning from laboratory settings into activities of daily living, an important goal is to develop neural decoding algorithms that can be calibrated with a minimal burden on the user, provide stable control for long periods of time, and can be responsive to fluctuations in the decoder’s neural input space (e.g. neurons appearing or being lost amongst electrode recordings). These are significant challenges for static neural decoding algorithms that assume stationary input/output relationships. Here we use an actor-critic reinforcement learning architecture to provide an adaptive BMI controller that can successfully adapt to dramatic neural reorganizations, can maintain its performance over long time periods, and which does not require the user to produce specific kinetic or kinematic activities to calibrate the BMI. Two marmoset monkeys used the Reinforcement Learning BMI (RLBMI) to successfully control a robotic arm during a two-target reaching task. The RLBMI was initialized using random initial conditions, and it quickly learned to control the robot from brain states using only a binary evaluative feedback regarding whether previously chosen robot actions were good or bad. The RLBMI was able to maintain control over the system throughout sessions spanning multiple weeks. Furthermore, the RLBMI was able to quickly adapt and maintain control of the robot despite dramatic perturbations to the neural inputs, including a series of tests in which the neuron input space was deliberately halved or doubled. PMID:24498055
Cuckoo Search Algorithm Based on Repeat-Cycle Asymptotic Self-Learning and Self-Evolving Disturbance for Function Optimization

PubMed Central

Wang, Jie-sheng; Li, Shu-xia; Song, Jiang-di

2015-01-01

In order to improve convergence velocity and optimization accuracy of the cuckoo search (CS) algorithm for solving the function optimization problems, a new improved cuckoo search algorithm based on the repeat-cycle asymptotic self-learning and self-evolving disturbance (RC-SSCS) is proposed. A disturbance operation is added into the algorithm by constructing a disturbance factor to make a more careful and thorough search near the bird's nests location. In order to select a reasonable repeat-cycled disturbance number, a further study on the choice of disturbance times is made. Finally, six typical test functions are adopted to carry out simulation experiments, meanwhile, compare algorithms of this paper with two typical swarm intelligence algorithms particle swarm optimization (PSO) algorithm and artificial bee colony (ABC) algorithm. The results show that the improved cuckoo search algorithm has better convergence velocity and optimization accuracy. PMID:26366164
A Distributed Learning Method for ℓ1-Regularized Kernel Machine over Wireless Sensor Networks

PubMed Central

Ji, Xinrong; Hou, Cuiqin; Hou, Yibin; Gao, Fang; Wang, Shulong

2016-01-01

In wireless sensor networks, centralized learning methods have very high communication costs and energy consumption. These are caused by the need to transmit scattered training examples from various sensor nodes to the central fusion center where a classifier or a regression machine is trained. To reduce the communication cost, a distributed learning method for a kernel machine that incorporates ℓ1 norm regularization (ℓ1-regularized) is investigated, and a novel distributed learning algorithm for the ℓ1-regularized kernel minimum mean squared error (KMSE) machine is proposed. The proposed algorithm relies on in-network processing and a collaboration that transmits the sparse model only between single-hop neighboring nodes. This paper evaluates the proposed algorithm with respect to the prediction accuracy, the sparse rate of model, the communication cost and the number of iterations on synthetic and real datasets. The simulation results show that the proposed algorithm can obtain approximately the same prediction accuracy as that obtained by the batch learning method. Moreover, it is significantly superior in terms of the sparse rate of model and communication cost, and it can converge with fewer iterations. Finally, an experiment conducted on a wireless sensor network (WSN) test platform further shows the advantages of the proposed algorithm with respect to communication cost. PMID:27376298
Managing and learning with multiple models: Objectives and optimization algorithms

USGS Publications Warehouse

Probert, William J. M.; Hauser, C.E.; McDonald-Madden, E.; Runge, M.C.; Baxter, P.W.J.; Possingham, H.P.

2011-01-01

The quality of environmental decisions should be gauged according to managers' objectives. Management objectives generally seek to maximize quantifiable measures of system benefit, for instance population growth rate. Reaching these goals often requires a certain degree of learning about the system. Learning can occur by using management action in combination with a monitoring system. Furthermore, actions can be chosen strategically to obtain specific kinds of information. Formal decision making tools can choose actions to favor such learning in two ways: implicitly via the optimization algorithm that is used when there is a management objective (for instance, when using adaptive management), or explicitly by quantifying knowledge and using it as the fundamental project objective, an approach new to conservation.This paper outlines three conservation project objectives - a pure management objective, a pure learning objective, and an objective that is a weighted mixture of these two. We use eight optimization algorithms to choose actions that meet project objectives and illustrate them in a simulated conservation project. The algorithms provide a taxonomy of decision making tools in conservation management when there is uncertainty surrounding competing models of system function. The algorithms build upon each other such that their differences are highlighted and practitioners may see where their decision making tools can be improved. ?? 2010 Elsevier Ltd.
Differentially Private Empirical Risk Minimization

PubMed Central

Chaudhuri, Kamalika; Monteleoni, Claire; Sarwate, Anand D.

2011-01-01

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the ε-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machine learning algorithm design. This method entails perturbing the objective function before optimizing over classifiers. If the loss and regularizer satisfy certain convexity and differentiability criteria, we prove theoretical results showing that our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. We further present a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees for the training process. We apply these results to produce privacy-preserving analogues of regularized logistic regression and support vector machines. We obtain encouraging results from evaluating their performance on real demographic and benchmark data sets. Our results show that both theoretically and empirically, objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance. PMID:21892342
Machine learning for medical images analysis.

PubMed

Criminisi, A

2016-10-01

This article discusses the application of machine learning for the analysis of medical images. Specifically: (i) We show how a special type of learning models can be thought of as automatically optimized, hierarchically-structured, rule-based algorithms, and (ii) We discuss how the issue of collecting large labelled datasets applies to both conventional algorithms as well as machine learning techniques. The size of the training database is a function of model complexity rather than a characteristic of machine learning methods. Crown Copyright © 2016. Published by Elsevier B.V. All rights reserved.
A regularized approach for geodesic-based semisupervised multimanifold learning.

PubMed

Fan, Mingyu; Zhang, Xiaoqin; Lin, Zhouchen; Zhang, Zhongfei; Bao, Hujun

2014-05-01

Geodesic distance, as an essential measurement for data dissimilarity, has been successfully used in manifold learning. However, most geodesic distance-based manifold learning algorithms have two limitations when applied to classification: 1) class information is rarely used in computing the geodesic distances between data points on manifolds and 2) little attention has been paid to building an explicit dimension reduction mapping for extracting the discriminative information hidden in the geodesic distances. In this paper, we regard geodesic distance as a kind of kernel, which maps data from linearly inseparable space to linear separable distance space. In doing this, a new semisupervised manifold learning algorithm, namely regularized geodesic feature learning algorithm, is proposed. The method consists of three techniques: a semisupervised graph construction method, replacement of original data points with feature vectors which are built by geodesic distances, and a new semisupervised dimension reduction method for feature vectors. Experiments on the MNIST, USPS handwritten digit data sets, MIT CBCL face versus nonface data set, and an intelligent traffic data set show the effectiveness of the proposed algorithm.
Prototype-Incorporated Emotional Neural Network.

PubMed

Oyedotun, Oyebade K; Khashman, Adnan

2017-08-15

Artificial neural networks (ANNs) aim to simulate the biological neural activities. Interestingly, many ''engineering'' prospects in ANN have relied on motivations from cognition and psychology studies. So far, two important learning theories that have been subject of active research are the prototype and adaptive learning theories. The learning rules employed for ANNs can be related to adaptive learning theory, where several examples of the different classes in a task are supplied to the network for adjusting internal parameters. Conversely, the prototype-learning theory uses prototypes (representative examples); usually, one prototype per class of the different classes contained in the task. These prototypes are supplied for systematic matching with new examples so that class association can be achieved. In this paper, we propose and implement a novel neural network algorithm based on modifying the emotional neural network (EmNN) model to unify the prototype- and adaptive-learning theories. We refer to our new model as ``prototype-incorporated EmNN''. Furthermore, we apply the proposed model to two real-life challenging tasks, namely, static hand-gesture recognition and face recognition, and compare the result to those obtained using the popular back-propagation neural network (BPNN), emotional BPNN (EmNN), deep networks, an exemplar classification model, and k-nearest neighbor.
Emotion Estimation Algorithm from Facial Image Analyses of e-Learning Users

NASA Astrophysics Data System (ADS)

Shigeta, Ayuko; Koike, Takeshi; Kurokawa, Tomoya; Nosu, Kiyoshi

This paper proposes an emotion estimation algorithm from e-Learning user's facial image. The algorithm characteristics are as follows: The criteria used to relate an e-Learning use's emotion to a representative emotion were obtained from the time sequential analysis of user's facial expressions. By examining the emotions of the e-Learning users and the positional change of the facial expressions from the experiment results, the following procedures are introduce to improve the estimation reliability; (1) some effective features points are chosen by the emotion estimation (2) dividing subjects into two groups by the change rates of the face feature points (3) selection of the eigenvector of the variance-co-variance matrices (cumulative contribution rate>=95%) (4) emotion calculation using Mahalanobis distance.
Automatic detection of Martian dark slope streaks by machine learning using HiRISE images

NASA Astrophysics Data System (ADS)

Wang, Yexin; Di, Kaichang; Xin, Xin; Wan, Wenhui

2017-07-01

Dark slope streaks (DSSs) on the Martian surface are one of the active geologic features that can be observed on Mars nowadays. The detection of DSS is a prerequisite for studying its appearance, morphology, and distribution to reveal its underlying geological mechanisms. In addition, increasingly massive amounts of Mars high resolution data are now available. Hence, an automatic detection method for locating DSSs is highly desirable. In this research, we present an automatic DSS detection method by combining interest region extraction and machine learning techniques. The interest region extraction combines gradient and regional grayscale information. Moreover, a novel recognition strategy is proposed that takes the normalized minimum bounding rectangles (MBRs) of the extracted regions to calculate the Local Binary Pattern (LBP) feature and train a DSS classifier using the Adaboost machine learning algorithm. Comparative experiments using five different feature descriptors and three different machine learning algorithms show the superiority of the proposed method. Experimental results utilizing 888 extracted region samples from 28 HiRISE images show that the overall detection accuracy of our proposed method is 92.4%, with a true positive rate of 79.1% and false positive rate of 3.7%, which in particular indicates great performance of the method at eliminating non-DSS regions.
Distribution-Preserving Stratified Sampling for Learning Problems.

PubMed

Cervellera, Cristiano; Maccio, Danilo

2017-06-09

The need for extracting a small sample from a large amount of real data, possibly streaming, arises routinely in learning problems, e.g., for storage, to cope with computational limitations, obtain good training/test/validation sets, and select minibatches for stochastic gradient neural network training. Unless we have reasons to select the samples in an active way dictated by the specific task and/or model at hand, it is important that the distribution of the selected points is as similar as possible to the original data. This is obvious for unsupervised learning problems, where the goal is to gain insights on the distribution of the data, but it is also relevant for supervised problems, where the theory explains how the training set distribution influences the generalization error. In this paper, we analyze the technique of stratified sampling from the point of view of distances between probabilities. This allows us to introduce an algorithm, based on recursive binary partition of the input space, aimed at obtaining samples that are distributed as much as possible as the original data. A theoretical analysis is proposed, proving the (greedy) optimality of the procedure together with explicit error bounds. An adaptive version of the algorithm is also introduced to cope with streaming data. Simulation tests on various data sets and different learning tasks are also provided.
Application of machine learning techniques to analyse the effects of physical exercise in ventricular fibrillation.

PubMed

Caravaca, Juan; Soria-Olivas, Emilio; Bataller, Manuel; Serrano, Antonio J; Such-Miquel, Luis; Vila-Francés, Joan; Guerrero, Juan F

2014-02-01

This work presents the application of machine learning techniques to analyse the influence of physical exercise in the physiological properties of the heart, during ventricular fibrillation. To this end, different kinds of classifiers (linear and neural models) are used to classify between trained and sedentary rabbit hearts. The use of those classifiers in combination with a wrapper feature selection algorithm allows to extract knowledge about the most relevant features in the problem. The obtained results show that neural models outperform linear classifiers (better performance indices and a better dimensionality reduction). The most relevant features to describe the benefits of physical exercise are those related to myocardial heterogeneity, mean activation rate and activation complexity. © 2013 Published by Elsevier Ltd.
Algorithm-Dependent Generalization Bounds for Multi-Task Learning.

PubMed

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.
Optimisation of a machine learning algorithm in human locomotion using principal component and discriminant function analyses.

PubMed

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.
Optimisation of a machine learning algorithm in human locomotion using principal component and discriminant function analyses

PubMed Central

Bisele, Maria; Bencsik, Martin; Lewis, Martin G. C.

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. PMID:28886059
A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon-Ocean Feedback in Typhoon Forecast Models

NASA Astrophysics Data System (ADS)

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.

Some links on this page may take you to non-federal websites. Their policies may differ from this site.