Search

Ensembles are a well established machine learning paradigm, leading to accurate and robust models, predominantly applied to predictive modeling tasks. Ensemble models comprise a finite set of diverse predictive models whose combined output is expected to yield an improved predictive performance as compared to an individual model. In this paper, we propose a new method for learning ensembles of process-based models of dynamic systems. The process-based modeling paradigm employs domain-specific knowledge to automatically learn models of dynamic systems from time-series observational data. Previous work has shown that ensembles based on sampling observational data (i.e., bagging and boosting), significantly improve predictive performance of process-based models. However, this improvement comes at the cost of a substantial increase of the computational time needed for learning. To address this problem, the paper proposes a method that aims at efficiently learning ensembles of process-based models, while maintaining their accurate long-term predictive performance. This is achieved by constructing ensembles with sampling domain-specific knowledge instead of sampling data. We apply the proposed method to and evaluate its performance on a set of problems of automated predictive modeling in three lake ecosystems using a library of process-based knowledge for modeling population dynamics. The experimental results identify the optimal design decisions regarding the learning algorithm. The results also show that the proposed ensembles yield significantly more accurate predictions of population dynamics as compared to individual process-based models. Finally, while their predictive performance is comparable to the one of ensembles obtained with the state-of-the-art methods of bagging and boosting, they are substantially more efficient. [ABSTRACT FROM AUTHOR]

With the convergence of various broadcasting systems, the amount of content available in mobile terminals including IPTV has significantly increased. In this paper, we propose a system that enables users to schedule programs considering both section video clips and full video clips based on the user detection method with similar preference. And, since the system constituting the contents can be classified according to the program, the proposed method can store a program desired by the user, and thus create and schedule a kind of individual channel. Experimental results show that the proposed method has a higher prediction accuracy; this is accomplished by comparing existing channel recommendation methods with the program recommendation methods proposed in this paper. [ABSTRACT FROM AUTHOR]

In palynology, the visual classification of pollen grains from different species is a hard task which is usually tackled by human operators using microscopes. Its complete automatization would save a high quantity of resources and provide valuable improvements especially for allergy-related information systems, but also for other application fields as paleoclimate reconstruction, quality control of honey based products, collection of evidences in criminal investigations or fabric dating and tracking. This paper presents three state-of-the-art deep learning classification methods applied to the recently published POLEN23E image dataset. The three methods make use of convolutional neural networks: the first one is strictly based on the idea of transfer learning, the second one is based on feature extraction and the third one represents a hybrid approach, combining transfer learning and feature extraction. The results from the three methods are indeed very good, reaching over 97% correct classification rates in images not previously seen by the models, where other authors reported around 70. [ABSTRACT FROM AUTHOR]

A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is when learning new information erases previously learned information. Catastrophic forgetting occurs in artificial neural networks (ANNs), which have fueled most recent advances in AI. A recent paper proposed that catastrophic forgetting in ANNs can be reduced by promoting modularity, which can limit forgetting by isolating task information to specific clusters of nodes and connections (functional modules). While the prior work did show that modular ANNs suffered less from catastrophic forgetting, it was not able to produce ANNs that possessed task-specific functional modules, thereby leaving the main theory regarding modularity and forgetting untested. We introduce diffusion-based neuromodulation, which simulates the release of diffusing, neuromodulatory chemicals within an ANN that can modulate (i.e. up or down regulate) learning in a spatial region. On the simple diagnostic problem from the prior work, diffusion-based neuromodulation 1) induces task-specific learning in groups of nodes and connections (task-specific localized learning), which 2) produces functional modules for each subtask, and 3) yields higher performance by eliminating catastrophic forgetting. Overall, our results suggest that diffusion-based neuromodulation promotes task-specific localized learning and functional modularity, which can help solve the challenging, but important problem of catastrophic forgetting. [ABSTRACT FROM AUTHOR]

In many computer vision and machine learning applications, the data sets distribute on certain low-dimensional subspaces. Subspace clustering is a powerful technology to find the underlying subspaces and cluster data points correctly. However, traditional subspace clustering methods can only be applied on data from one source, and how to extend these methods and enable the extensions to combine information from various data sources has become a hot area of research. Previous multi-view subspace methods aim to learn multiple subspace representation matrices simultaneously and these learning task for different views are treated equally. After obtaining representation matrices, they stack up the learned representation matrices as the common underlying subspace structure. However, for many problems, the importance of sources and the importance of features in one source both can be varied, which makes the previous approaches ineffective. In this paper, we propose a novel method called Robust Auto-weighted Multi-view Subspace Clustering (RAMSC). In our method, the weight for both the sources and features can be learned automatically via utilizing a novel trick and introducing a sparse norm. More importantly, the objective of our method is a common representation matrix which directly reflects the common underlying subspace structure. A new efficient algorithm is derived to solve the formulated objective with rigorous theoretical proof on its convergency. Extensive experimental results on five benchmark multi-view datasets well demonstrate that the proposed method consistently outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

In recent years, with the development of computer science, deep learning is held as competent enough to solve the problem of inference and learning in high dimensional space. Therefore, it has received unprecedented attention from both the academia and the business community. Compared with CPU/GPU, FPGA has attracted much attention for its high-energy efficiency, short development cycle and reconfigurability in the aspect of deep learning algorithm. However, because of the limited research on OpenCL optimization on FPGA of deep learning algorithms, OpenCL tools and models applied to CPU/GPU cannot be directly used on FPGA. This makes it difficult for software programmers to use FPGA when implementing deep learning algorithms for a rewarding performance. To solve this problem, this paper proposed an OpenCL computational model based on FPGA template architecture to optimize the time-consuming convolution layer in deep learning. The comparison between the program applying the computational model and the corresponding optimization program provided by Xilinx indicates that the former is 8-40 times higher than the latter in terms of performance. [ABSTRACT FROM AUTHOR]

Filter or screening methods are often used as a preprocessing step for reducing the number of variables used by a learning algorithm in obtaining a classification or regression model. While there are many such filter methods, there is a need for an objective evaluation of these methods. Such an evaluation is needed to compare them with each other and also to answer whether they are at all useful, or a learning algorithm could do a better job without them. For this purpose, many popular screening methods are partnered in this paper with three regression learners and five classification learners and evaluated on ten real datasets to obtain accuracy criteria such as R-square and area under the ROC curve (AUC). The obtained results are compared through curve plots and comparison tables in order to find out whether screening methods help improve the performance of learning algorithms and how they fare with each other. Our findings revealed that the screening methods were useful in improving the prediction of the best learner on two regression and two classification datasets out of the ten datasets evaluated. [ABSTRACT FROM AUTHOR]

Ex-ante online risk assessment for building emergency evacuation is essential to protect human life and property. Current risk assessment methods are limited by the tradeoff between accuracy and efficiency. In this paper, we propose an online method that overcomes this tradeoff based on multimedia data (e.g. videos data from surveillance cameras) and deep learning. The method consists of two parts. The first estimates the evacuee position as input for training the assessment model to then perform risk assessment in real scenarios. The second considers a social force model based on the evacuation simulation for the output of training model. We verify the proposed method in simulation and real scenarios. Model sensitivity analyses and large-scale tests demonstrate the usability and superiority of the proposed method. By the method, the computation time of risk assessment could be decreased from 10 minutes (by traditional simulation method) to 2.18 s. [ABSTRACT FROM AUTHOR]

The number of people diagnosed with dementia is expected to rise in the coming years. Given that there is currently no definite cure for dementia and the cost of care for this condition soars dramatically, slowing the decline and maintaining independent living are important goals for supporting people with dementia. This paper discusses a study that is called Technology Integrated Health Management (TIHM). TIHM is a technology assisted monitoring system that uses Internet of Things (IoT) enabled solutions for continuous monitoring of people with dementia in their own homes. We have developed machine learning algorithms to analyse the correlation between environmental data collected by IoT technologies in TIHM in order to monitor and facilitate the physical well-being of people with dementia. The algorithms are developed with different temporal granularity to process the data for long-term and short-term analysis. We extract higher-level activity patterns which are then used to detect any change in patients’ routines. We have also developed a hierarchical information fusion approach for detecting agitation, irritability and aggression. We have conducted evaluations using sensory data collected from homes of people with dementia. The proposed techniques are able to recognise agitation and unusual patterns with an accuracy of up to 80%. [ABSTRACT FROM AUTHOR]

Music genre classification is a challenging research concept, for which open questions remain regarding classification approach, music piece representation, distances between/within genres, and so on. In this paper an investigation on the classification of generated music pieces is performed, based on the idea that grouping close related known pieces in different sets –or clusters– and then generating in an automatic way a new song which is somehow “inspired” in each set, the new song would be more likely to be classified as belonging to the set which inspired it, based on the same distance used to separate the clusters. Different music pieces representations and distances among pieces are used; obtained results are promising, and indicate the appropriateness of the used approach even in a such a subjective area as music genre classification is. [ABSTRACT FROM AUTHOR]

In this paper, we propose a face recognition algorithm based on a combination of vector quantization (VQ) and Markov stationary features (MSF). The VQ algorithm has been shown to be an effective method for generating features; it extracts a codevector histogram as a facial feature representation for face recognition. Still, the VQ histogram features are unable to convey spatial structural information, which to some extent limits their usefulness in discrimination. To alleviate this limitation of VQ histograms, we utilize Markov stationary features (MSF) to extend the VQ histogram-based features so as to add spatial structural information. We demonstrate the effectiveness of our proposed algorithm by achieving recognition results superior to those of several state-of-the-art methods on publicly available face databases. [ABSTRACT FROM AUTHOR]

DNA-binding proteins play pivotal roles in alternative splicing, RNA editing, methylating and many other biological functions for both eukaryotic and prokaryotic proteomes. Predicting the functions of these proteins from primary amino acids sequences is becoming one of the major challenges in functional annotations of genomes. Traditional prediction methods often devote themselves to extracting physiochemical features from sequences but ignoring motif information and location information between motifs. Meanwhile, the small scale of data volumes and large noises in training data result in lower accuracy and reliability of predictions. In this paper, we propose a deep learning based method to identify DNA-binding proteins from primary sequences alone. It utilizes two stages of convolutional neutral network to detect the function domains of protein sequences, and the long short-term memory neural network to identify their long term dependencies, an binary cross entropy to evaluate the quality of the neural networks. When the proposed method is tested with a realistic DNA binding protein dataset, it achieves a prediction accuracy of 94.2% at the Matthew’s correlation coefficient of 0.961. Compared with the LibSVM on the arabidopsis and yeast datasets via independent tests, the accuracy raises by 9% and 4% respectively. Comparative experiments using different feature extraction methods show that our model performs similar accuracy with the best of others, but its values of sensitivity, specificity and AUC increase by 27.83%, 1.31% and 16.21% respectively. Those results suggest that our method is a promising tool for identifying DNA-binding proteins. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new automatic hyperparameter selection approach for determining the optimal network configuration (network structure and hyperparameters) for deep neural networks using particle swarm optimization (PSO) in combination with a steepest gradient descent algorithm. In the proposed approach, network configurations were coded as a set of real-number m-dimensional vectors as the individuals of the PSO algorithm in the search procedure. During the search procedure, the PSO algorithm is employed to search for optimal network configurations via the particles moving in a finite search space, and the steepest gradient descent algorithm is used to train the DNN classifier with a few training epochs (to find a local optimal solution) during the population evaluation of PSO. After the optimization scheme, the steepest gradient descent algorithm is performed with more epochs and the final solutions (pbest and gbest) of the PSO algorithm to train a final ensemble model and individual DNN classifiers, respectively. The local search ability of the steepest gradient descent algorithm and the global search capabilities of the PSO algorithm are exploited to determine an optimal solution that is close to the global optimum. We constructed several experiments on hand-written characters and biological activity prediction datasets to show that the DNN classifiers trained by the network configurations expressed by the final solutions of the PSO algorithm, employed to construct an ensemble model and individual classifier, outperform the random approach in terms of the generalization performance. Therefore, the proposed approach can be regarded an alternative tool for automatic network structure and parameter selection for deep neural networks. [ABSTRACT FROM AUTHOR]

Broken water pumps continue to impede efforts to deliver clean and economically-viable water to the global poor. The literature has demonstrated that customers’ health benefits and willingness to pay for clean water are best realized when clean water infrastructure performs extremely well (>99% uptime). In this paper, we used sensor data from 42 Afridev-brand handpumps observed for 14 months in western Kenya to demonstrate how sensors and supervised ensemble machine learning could be used to increase total fleet uptime from a best-practices baseline of about 70% to >99%. We accomplish this increase in uptime by forecasting pump failures and identifying existing failures very quickly. Comparing the costs of operating the pump per functional year over a lifetime of 10 years, we estimate that implementing this algorithm would save 7% on the levelized cost of water relative to a sensor-less scheduled maintenance program. Combined with a rigorous system for dispatching maintenance personnel, implementing this algorithm in a real-world program could significantly improve health outcomes and customers’ willingness to pay for water services. [ABSTRACT FROM AUTHOR]

With the continuing growth of multi-media learning resources, it is important to offer methods helping learners to explore and acquire relevant learning information effectively. As services that organize multi-media learning materials together to support programming learning, the digital case-based learning system is needed. In order to create a case-oriented e-learning system, this paper concentrates on the digital case study of multi-media resources and learning processes with an integrated framework. An integration of multi-media resources, testing and learning strategies recommendation as the learning unit is proposed in the digital case-based learning framework. The learning mechanism of learning guidance, multi-media materials learning and testing feedback is supported in our project. An improved personalized genetic algorithm which incorporates preference information and usage degree into the crossover and mutation process is proposed to assemble the personalized test sheet for each learner. A learning strategies recommendation solution is proposed to recommend learning strategies for learners to help them to learn. The experiments are conducted to prove that the proposed approaches are capable of constructing personalized sheets and the effectiveness of the framework. [ABSTRACT FROM AUTHOR]

In recent years, safer and more reliable biometric methods have been developed. Apart from the need for enhanced security, the media and entertainment sectors have also been applying biometrics in the emerging market of user-adaptable objects/systems to make these systems more user-friendly. However, the complexity of some state-of-the-art biometric systems (e.g., iris recognition) or their high false rejection rate (e.g., fingerprint recognition) is neither compatible with the simple hardware architecture required by reduced-size devices nor the new trend of implementing smart objects within the dynamic market of the Internet of Things (IoT). It was recently shown that an individual can be recognized by extracting features from their electrocardiogram (ECG). However, most current ECG-based biometric algorithms are computationally demanding and/or rely on relatively large (several seconds) ECG samples, which are incompatible with the aforementioned application fields. Here, we present a computationally low-cost method (patent pending), including simple mathematical operations, for identifying a person using only three ECG morphology-based characteristics from a single heartbeat. The algorithm was trained/tested using ECG signals of different duration from the Physionet database on more than 60 different training/test datasets. The proposed method achieved maximal averaged accuracy of 97.450% in distinguishing each subject from a ten-subject set and false acceptance and rejection rates (FAR and FRR) of 5.710±1.900% and 3.440±1.980%, respectively, placing Beat-ID in a very competitive position in terms of the FRR/FAR among state-of-the-art methods. Furthermore, the proposed method can identify a person using an average of 1.020 heartbeats. It therefore has FRR/FAR behavior similar to obtaining a fingerprint, yet it is simpler and requires less expensive hardware. This method targets low-computational/energy-cost scenarios, such as tiny wearable devices (e.g., a smart object that automatically adapts its configuration to the user). A hardware proof-of-concept implementation is presented as an annex to this paper. [ABSTRACT FROM AUTHOR]

In the sparse representation model, the design of overcomplete dictionaries plays a key role for the effectiveness and applicability in different domains. Recent research has produced several dictionary learning approaches, being proven that dictionaries learnt by data examples significantly outperform structured ones, e.g. wavelet transforms. In this context, learning consists in adapting the dictionary atoms to a set of training signals in order to promote a sparse representation that minimizes the reconstruction error. Finding the best fitting dictionary remains a very difficult task, leaving the question still open. A well-established heuristic method for tackling this problem is an iterative alternating scheme, adopted for instance in the well-known K-SVD algorithm. Essentially, it consists in repeating two stages; the former promotes sparse coding of the training set and the latter adapts the dictionary to reduce the error. In this paper we present R-SVD, a new method that, while maintaining the alternating scheme, adopts the Orthogonal Procrustes analysis to update the dictionary atoms suitably arranged into groups. Comparative experiments on synthetic data prove the effectiveness of R-SVD with respect to well known dictionary learning algorithms such as K-SVD, ILS-DLA and the online method OSDL. Moreover, experiments on natural data such as ECG compression, EEG sparse representation, and image modeling confirm R-SVD’s robustness and wide applicability. [ABSTRACT FROM AUTHOR]

Prediction of memory performance (remembered or forgotten) has various potential applications not only for knowledge learning but also for disease diagnosis. Recently, subsequent memory effects (SMEs)—the statistical differences in electroencephalography (EEG) signals before or during learning between subsequently remembered and forgotten events—have been found. This finding indicates that EEG signals convey the information relevant to memory performance. In this paper, based on SMEs we propose a computational approach to predict memory performance of an event from EEG signals. We devise a convolutional neural network for EEG, called ConvEEGNN, to predict subsequently remembered and forgotten events from EEG recorded during memory process. With the ConvEEGNN, prediction of memory performance can be achieved by integrating two main stages: feature extraction and classification. To verify the proposed approach, we employ an auditory memory task to collect EEG signals from scalp electrodes. For ConvEEGNN, the average prediction accuracy was 72.07% by using EEG data from pre-stimulus and during-stimulus periods, outperforming other approaches. It was observed that signals from pre-stimulus period and those from during-stimulus period had comparable contributions to memory performance. Furthermore, the connection weights of ConvEEGNN network can reveal prominent channels, which are consistent with the distribution of SME studied previously. [ABSTRACT FROM AUTHOR]

Melioration learning is an empirically well-grounded model of reinforcement learning. By means of computer simulations, this paper derives predictions for several repeatedly played two-person games from this model. The results indicate a likely convergence to a pure Nash equilibrium of the game. If no pure equilibrium exists, the relative frequencies of choice may approach the predictions of the mixed Nash equilibrium. Yet in some games, no stable state is reached. [ABSTRACT FROM AUTHOR]

The remaining useful life (RUL) prediction of Lithium-ion batteries is closely related to the capacity degeneration trajectories. Due to the self-charging and the capacity regeneration, the trajectories have the property of multimodality. Traditional prediction models such as the support vector machines (SVM) or the Gaussian Process regression (GPR) cannot accurately characterize this multimodality. This paper proposes a novel RUL prediction method based on the Gaussian Process Mixture (GPM). It can process multimodality by fitting different segments of trajectories with different GPR models separately, such that the tiny differences among these segments can be revealed. The method is demonstrated to be effective for prediction by the excellent predictive result of the experiments on the two commercial and chargeable Type 1850 Lithium-ion batteries, provided by NASA. The performance comparison among the models illustrates that the GPM is more accurate than the SVM and the GPR. In addition, GPM can yield the predictive confidence interval, which makes the prediction more reliable than that of traditional models. [ABSTRACT FROM AUTHOR]

Video based object recognition and classification has been widely studied in computer vision and image processing area. One main issue of this task is to develop an effective representation for video. This problem can generally be formulated as image set representation. In this paper, we present a new method called Multiple Covariance Discriminative Learning (MCDL) for image set representation and classification problem. The core idea of MCDL is to represent an image set using multiple covariance matrices with each covariance matrix representing one cluster of images. Firstly, we use the Nonnegative Matrix Factorization (NMF) method to do image clustering within each image set, and then adopt Covariance Discriminative Learning on each cluster (subset) of images. At last, we adopt KLDA and nearest neighborhood classification method for image set classification. Promising experimental results on several datasets show the effectiveness of our MCDL method. [ABSTRACT FROM AUTHOR]

The main purpose of this study is to propose, then analyze, and later test a spectral gradient algorithm for solving a convex minimization problem. The considered problem covers the matrix ℓ2,1-norm regularized least squares which is widely used in multi-task learning for capturing the joint feature among each task. To solve the problem, we firstly minimize a quadratic approximated model of the objective function to derive a search direction at current iteration. We show that this direction descends automatically and reduces to the original spectral gradient direction if the regularized term is removed. Secondly, we incorporate a nonmonotone line search along this direction to improve the algorithm’s numerical performance. Furthermore, we show that the proposed algorithm converges to a critical point under some mild conditions. The attractive feature of the proposed algorithm is that it is easily performable and only requires the gradient of the smooth function and the objective function’s values at each and every step. Finally, we operate some experiments on synthetic data, which verifies that the proposed algorithm works quite well and performs better than the compared ones. [ABSTRACT FROM AUTHOR]

Due to the rapid technological evolution and communications accessibility, data generated from different sources of information show an exponential growth behavior. That is, volume of data samples that need to be analyzed are getting larger, so the methods for its processing have to adapt to this condition, focusing mainly on ensuring the computation is efficient, especially when the analysis tools are based on computational intelligence techniques. As we know, if you do not have a good control of the handling of the volume of the data, some techniques that are based on learning iterative processes could represent an excessive load of computation and could take a prohibitive time in trying to find a solution that could not come close to desired. There are learning methods known as full batch, online and mini-batch, and they represent a good strategy to this problem since they are oriented to the processing of data according to the size or volume of available data samples that require analysis. In this first approach, synthetic datasets with a small and medium volume were used, since the main objective is to define its implementation and in experimentation phase through regression analysis obtain information that allows us to assess the performance and behavior of different learning methods under distinct conditions. To carry out this study, a Mamdani based neuro-fuzzy system with center-of-sets defuzzification with support of multiple inputs and outputs was designed and implemented that had the flexibility to use any of the three learning methods, which were implemented within the training process. Finally, results show that the learning method with best performances was Mini-Batch when compared to full batch and online learning methods. The results obtained by mini-batch learning method are as follows; mean correlation coefficient with 0.8268 and coefficient of determination with 0.7444, and is also the method with better control of the dispersion between the results obtained from the 30 experiments executed per each dataset processed. [ABSTRACT FROM AUTHOR]

As a promising research direction in recent decades, active learning allows an oracle to assign labels to typical examples for performance improvement in learning systems. Existing works mainly focus on designing criteria for screening examples of high value to be labeled in a handcrafted manner. Instead of manually developing strategies of querying the user to access labels for the desired examples, we utilized the reinforcement learning algorithm parameterized with the neural network to automatically explore query strategies in active learning when addressing stream-based one-shot classification problems. With the involvement of cross-entropy in the loss function of Q-learning, an efficient policy to decide when and where to predict or query an instance is learned through the developed framework. Compared with a former influential work, the advantages of our method are demonstrated experimentally with two image classification tasks, and it exhibited better performance, quick convergence, relatively good stability and fewer requests for labels. [ABSTRACT FROM AUTHOR]

Different performance measures are used to assess the behaviour, and to carry out the comparison, of classifiers in Machine Learning. Many measures have been defined on the literature, and among them, a measure inspired by Shannon’s entropy named the Confusion Entropy (CEN). In this work we introduce a new measure, MCEN, by modifying CEN to avoid its unwanted behaviour in the binary case, that disables it as a suitable performance measure in classification. We compare MCEN with CEN and other performance measures, presenting analytical results in some particularly interesting cases, as well as some heuristic computational experimentation. [ABSTRACT FROM AUTHOR]

Although a standard reinforcement learning model can capture many aspects of reward-seeking behaviors, it may not be practical for modeling human natural behaviors because of the richness of dynamic environments and limitations in cognitive resources. We propose a modular reinforcement learning model that addresses these factors. Based on this model, a modular inverse reinforcement learning algorithm is developed to estimate both the rewards and discount factors from human behavioral data, which allows predictions of human navigation behaviors in virtual reality with high accuracy across different subjects and with different tasks. Complex human navigation trajectories in novel environments can be reproduced by an artificial agent that is based on the modular model. This model provides a strategy for estimating the subjective value of actions and how they influence sensory-motor decisions in natural behavior. [ABSTRACT FROM AUTHOR]

We present insights and empirical results from an extensive numerical study of the evolutionary dynamics of the iterated prisoner’s dilemma. Fixation probabilities for Moran processes are obtained for all pairs of 164 different strategies including classics such as TitForTat, zero determinant strategies, and many more sophisticated strategies. Players with long memories and sophisticated behaviours outperform many strategies that perform well in a two player setting. Moreover we introduce several strategies trained with evolutionary algorithms to excel at the Moran process. These strategies are excellent invaders and resistors of invasion and in some cases naturally evolve handshaking mechanisms to resist invasion. The best invaders were those trained to maximize total payoff while the best resistors invoke handshake mechanisms. This suggests that while maximizing individual payoff can lead to the evolution of cooperation through invasion, the relatively weak invasion resistance of payoff maximizing strategies are not as evolutionarily stable as strategies employing handshake mechanisms. [ABSTRACT FROM AUTHOR]

Throughout recent times, cybersecurity problems have occurred in various business applications. Although previous researchers proposed to cope with the occurrence of cybersecurity issues, their methods repeatedly replicated the training processes for several times to classify datasets of these problems in streaming non-stationary environments. In dynamic environments, the conventional methods possibly deteriorate the adaptive solution to prevent these issues. This research proposes a one-pass-throw-away learning using the dynamical structure of the network to solve these problems in dynamic environments. Furthermore, to speed up the computational time and to maintain a minimum space complexity for streaming data, the new concepts of learning in forms of recursive functions were introduced. The information gain-based feature selection was also applied to reduce the learning time during the training process. The experimental results signified that the proposed algorithm outperformed the others in incremental-like and online ensemble learning algorithms in terms of classification accuracy, space complexity, and computational time. [ABSTRACT FROM AUTHOR]

Many modern applications of AI such as web search, mobile browsing, image processing, and natural language processing rely on finding similar items from a large database of complex objects. Due to the very large scale of data involved (e.g., users’ queries from commercial search engines), computing such near or nearest neighbors is a non-trivial task, as the computational cost grows significantly with the number of items. To address this challenge, we adopt Locality Sensitive Hashing (a.k.a, ) methods and evaluate four variants in a distributed computing environment (specifically, Hadoop). We identify several optimizations which improve performance, suitable for deployment in very large scale settings. The experimental results demonstrate our variants of achieve the robust performance with better recall compared with “vanilla” , even when using the same amount of space. [ABSTRACT FROM AUTHOR]

The ability to predict what courses a student may enroll in the coming semester plays a pivotal role in the allocation of learning resources, which is a hot topic in the domain of educational data mining. In this study, we propose an innovative approach to characterize students’ cross-college course enrollments by leveraging a novel contextual graph. Specifically, different kinds of variables, such as students, courses, colleges and diplomas, as well as various types of variable relations, are utilized to depict the context of each variable, and then a representation learning algorithm node2vec is applied to extracting sophisticated graph-based features for the enrollment analysis. In this manner, the relations between any pair of variables can be measured quantitatively, which enables the variable type to transform from nominal to ratio. These graph-based features are examined by the random forest algorithm, and experiments on 24,663 students, 1,674 courses and 417,590 enrollment records demonstrate that the contextual graph can successfully improve analyzing the cross-college course enrollments, where three of the graph-based features have significantly stronger impacts on prediction accuracy than the others. Besides, the empirical results also indicate that the student’s course preference is the most important factor in predicting future course enrollments, which is consistent to the previous studies that acknowledge the course interest is a key point for course recommendations. [ABSTRACT FROM AUTHOR]

Despite the growing interest in prediction-based word embedding learning methods, it remains unclear as to how the vector spaces learnt by the prediction-based methods differ from that of the counting-based methods, or whether one can be transformed into the other. To study the relationship between counting-based and prediction-based embeddings, we propose a method for learning a linear transformation between two given sets of word embeddings. Our proposal contributes to the word embedding learning research in three ways: (a) we propose an efficient method to learn a linear transformation between two sets of word embeddings, (b) using the transformation learnt in (a), we empirically show that it is possible to predict distributed word embeddings for novel unseen words, and (c) empirically it is possible to linearly transform counting-based embeddings to prediction-based embeddings, for frequent words, different POS categories, and varying degrees of ambiguities. [ABSTRACT FROM AUTHOR]

Building on developments in machine learning and prior work in the science of judicial prediction, we construct a model designed to predict the behavior of the Supreme Court of the United States in a generalized, out-of-sample context. To do so, we develop a time-evolving random forest classifier that leverages unique feature engineering to predict more than 240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015). Using only data available prior to decision, our model outperforms null (baseline) models at both the justice and case level under both parametric and non-parametric tests. Over nearly two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the justice vote level. More recently, over the past century, we outperform an in-sample optimized null model by nearly 5%. Our performance is consistent with, and improves on the general level of prediction demonstrated by prior work; however, our model is distinctive because it can be applied out-of-sample to the entire past and future of the Court, not a single term. Our results represent an important advance for the science of quantitative legal prediction and portend a range of other potential applications. [ABSTRACT FROM AUTHOR]

A clinical tool that can diagnose psychiatric illness using functional or structural magnetic resonance (MR) brain images has the potential to greatly assist physicians and improve treatment efficacy. Working toward the goal of automated diagnosis, we propose an approach for automated classification of ADHD and autism based on histogram of oriented gradients (HOG) features extracted from MR brain images, as well as personal characteristic data features. We describe a learning algorithm that can produce effective classifiers for ADHD and autism when run on two large public datasets. The algorithm is able to distinguish ADHD from control with hold-out accuracy of 69.6% (over baseline 55.0%) using personal characteristics and structural brain scan features when trained on the ADHD-200 dataset (769 participants in training set, 171 in test set). It is able to distinguish autism from control with hold-out accuracy of 65.0% (over baseline 51.6%) using functional images with personal characteristic data when trained on the Autism Brain Imaging Data Exchange (ABIDE) dataset (889 participants in training set, 222 in test set). These results outperform all previously presented methods on both datasets. To our knowledge, this is the first demonstration of a single automated learning process that can produce classifiers for distinguishing patients vs. controls from brain imaging data with above-chance accuracy on large datasets for two different psychiatric illnesses (ADHD and autism). Working toward clinical applications requires robustness against real-world conditions, including the substantial variability that often exists among data collected at different institutions. It is therefore important that our algorithm was successful with the large ADHD-200 and ABIDE datasets, which include data from hundreds of participants collected at multiple institutions. While the resulting classifiers are not yet clinically relevant, this work shows that there is a signal in the (f)MRI data that a learning algorithm is able to find. We anticipate this will lead to yet more accurate classifiers, over these and other psychiatric disorders, working toward the goal of a clinical tool for high accuracy differential diagnosis. [ABSTRACT FROM AUTHOR]

Missing data is a common problem in many research fields and is a challenge that always needs careful considerations. One approach is to impute the missing values, i.e., replace missing values with estimates. When imputation is applied, it is typically applied to all records with missing values indiscriminately. We note that the effects of imputation can be strongly dependent on what is missing. To help make decisions about which records should be imputed, we propose to use a machine learning approach to estimate the imputation error for each case with missing data. The method is thought to be a practical approach to help users using imputation after the informed choice to impute the missing data has been made. To do this all patterns of missing values are simulated in all complete cases, enabling calculation of the “true error” in each of these new cases. The error is then estimated for each case with missing values by weighing the “true errors” by similarity. The method can also be used to test the performance of different imputation methods. A universal numerical threshold of acceptable error cannot be set since this will differ according to the data, research question, and analysis method. The effect of threshold can be estimated using the complete cases. The user can set an a priori relevant threshold for what is acceptable or use cross validation with the final analysis to choose the threshold. The choice can be presented along with argumentation for the choice rather than holding to conventions that might not be warranted in the specific dataset. [ABSTRACT FROM AUTHOR]

We present a method to solve the binding problem by using a quantum algorithm for the retrieval of associations from associative memory during visual scene analysis. The problem is solved by mapping the information representing different objects into superposition by using entanglement and Grover’s amplification algorithm. [ABSTRACT FROM AUTHOR]

Background: Analytic measurement of serum tumour markers is one of commonly used methods for cancer risk management in certain areas of the world (e.g. Taiwan). Recently, cancer screening based on multiple serum tumour markers has been frequently discussed. However, the risk–benefit outcomes appear to be unfavourable for patients because of the low sensitivity and specificity. In this study, cancer screening models based on multiple serum tumour markers were designed using machine learning methods, namely support vector machine (SVM), k-nearest neighbour (KNN), and logistic regression, to improve the screening performance for multiple cancers in a large asymptomatic population. Methods: AFP, CEA, CA19-9, CYFRA21-1, and SCC were determined for 20 696 eligible individuals. PSA was measured in men and CA15-3 and CA125 in women. A variable selection process was applied to select robust variables from these serum tumour markers to design cancer detection models. The sensitivity, specificity, positive predictive value (PPV), negative predictive value, area under the curve, and Youden index of the models based on single tumour markers, combined test, and machine learning methods were compared. Moreover, relative risk reduction, absolute risk reduction (ARR), and absolute risk increase (ARI) were evaluated. Results: To design cancer detection models using machine learning methods, CYFRA21-1 and SCC were selected for women, and all tumour markers were selected for men. SVM and KNN models significantly outperformed the single tumour markers and the combined test for men. All 3 studied machine learning methods outperformed single tumour markers and the combined test for women. For either men or women, the ARRs were between 0.003–0.008; the ARIs were between 0.119–0.306. Conclusion: Machine learning methods outperformed the combined test in analysing multiple tumour markers for cancer detection. However, cancer screening based solely on the application of multiple tumour markers remains unfavourable because of the inadequate PPV, ARR, and ARI, even when machine learning methods were incorporated into the analysis. [ABSTRACT FROM AUTHOR]

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 (DA), 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. [ABSTRACT FROM AUTHOR]

The goal of this research is to recognize the nest digging activity of tortoises using a device mounted atop the tortoise carapace. The device classifies tortoise movements in order to discriminate between nest digging, and non-digging activity (specifically walking and eating). Accelerometer data was collected from devices attached to the carapace of a number of tortoises during their two-month nesting period. Our system uses an accelerometer and an activity recognition system (ARS) which is modularly structured using an artificial neural network and an output filter. For the purpose of experiment and comparison, and with the aim of minimizing the computational cost, the artificial neural network has been modelled according to three different architectures based on the input delay neural network (IDNN). We show that the ARS can achieve very high accuracy on segments of data sequences, with an extremely small neural network that can be embedded in programmable low power devices. Given that digging is typically a long activity (up to two hours), the application of ARS on data segments can be repeated over time to set up a reliable and efficient system, called Tortoise@, for digging activity recognition. [ABSTRACT FROM AUTHOR]

Botnet phenomenon in smartphones is evolving with the proliferation in mobile phone technologies after leaving imperative impact on personal computers. It refers to the network of computers, laptops, mobile devices or tablets which is remotely controlled by the cybercriminals to initiate various distributed coordinated attacks including spam emails, ad-click fraud, Bitcoin mining, Distributed Denial of Service (DDoS), disseminating other malwares and much more. Likewise traditional PC based botnet, Mobile botnets have the same operational impact except the target audience is particular to smartphone users. Therefore, it is import to uncover this security issue prior to its widespread adaptation. We propose SMARTbot, a novel dynamic analysis framework augmented with machine learning techniques to automatically detect botnet binaries from malicious corpus. SMARTbot is a component based off-device behavioral analysis framework which can generate mobile botnet learning model by inducing Artificial Neural Networks’ back-propagation method. Moreover, this framework can detect mobile botnet binaries with remarkable accuracy even in case of obfuscated program code. The results conclude that, a classifier model based on simple logistic regression outperform other machine learning classifier for botnet apps’ detection, i.e 99.49% accuracy is achieved. Further, from manual inspection of botnet dataset we have extracted interesting trends in those applications. As an outcome of this research, a mobile botnet dataset is devised which will become the benchmark for future studies. [ABSTRACT FROM AUTHOR]

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble’s output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) − k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer’s disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases. [ABSTRACT FROM AUTHOR]