Search

There is a growing trend of using artificial intelligence, particularly deep learning algorithms, in medical diagnostics, revolutionizing healthcare by improving efficiency, accuracy, and patient outcomes. However, the use of artificial intelligence in medical diagnostics comes with the critical need to explain the reasoning behind artificial intelligence‐based predictions and ensure transparency in decision‐making. Explainable artificial intelligence has emerged as a crucial research area to address the need for transparency and interpretability in medical diagnostics. Explainable artificial intelligence techniques aim to provide insights into the decision‐making process of artificial intelligence systems, enabling clinicians to understand the factors the algorithms consider in reaching their predictions. This paper presents a detailed review of saliency‐based (visual) methods, such as class activation methods, which have gained popularity in medical imaging as they provide visual explanations by highlighting the regions of an image most influential in the artificial intelligence's decision. We also present the literature on non‐visual methods, but the focus will be on visual methods. We also use the existing literature to experiment with infrared breast images for detecting breast cancer. Towards the end of this paper, we also propose an "attention guided Grad‐CAM" that enhances the visualizations for explainable artificial intelligence. The existing literature shows that explainable artificial intelligence techniques are not explored in the context of infrared medical images and opens up a wide range of opportunities for further research to make clinical thermography into assistive technology for the medical community. [ABSTRACT FROM AUTHOR]

Deep learning models have overcome traditional machine learning techniques for text classification domains in the field of natural language processing (NLP). Since, NLP is a branch of machine learning, used for interpreting language, classifying text of interest, and the same can be applied to analyse the medical clinical electronic health records. Medical text consists of lot of rich data which can altogether provide a good insight, by determining patterns from the clinical text data. In this paper, bidirectional‐long short‐term memory (Bi‐LSTM), bi‐LSTM attention and bidirectional encoder representations from transformers (BERT) base models are used to classify the text which are of privacy concern to a person and which should be extracted and can be tagged as sensitive. This text data which we might think not of privacy concern would majorly reveal a lot about the patient's integrity and personal life. Clinical data not only have patient demographic data but lot of hidden data which might go unseen and thus could arise privacy issues. Bi‐LSTM with attention layer is also added on top to realize the importance of critical words which will be of great importance in terms of classification, we are able to achieve accuracy of about 92%. About 206,926 sentences are used out of which 80% are used for training and rest for testing we get accuracy of 90% approx. with Bi‐LSTM alone. The same set of datasets is used for BERT model with accuracy of 93% approx. [ABSTRACT FROM AUTHOR]

The traditional target recognition and classification is mostly done manually, with low efficiency and high cost. Improving the level of target recognition automatically has become an important research topic. This paper proposes a target recognition method based on transfer learning to effectively complete the classification and recognition of targets using a brain–computer interface (BCI) model. Based on the construction of the faster‐RCNN deep learning model, the pre‐training of the model is achieved by VGG‐16 and Inception‐v2, and the transfer learning algorithm is used to optimize the faster‐RCNN deep learning model based on the kinematics model. Experiments are carried out with the aim to detect tableware by the persons whose brain signals recognition rate has been substantially improved using faster‐RCNN. Compared with the traditional recognition methods, the results at the lab‐scale level illustrated that the proposed algorithm can effectively improve the speed and accuracy of target recognition by using the BCI model to classify tableware of different colors and shapes in a complex background. [ABSTRACT FROM AUTHOR]

Epilepsy is a common mental disorder that affects about 70 million people worldwide. Epileptic electroencephalogram (EEG) signal, an important means to judge epileptic seizure, needs neurologists' prior knowledge to mark manually. This marking method is time‐consuming and laborious. Currently, the existing automated diagnosis methods have achieved good results on one benchmark EEG dataset, most of which can achieve accuracy of more than 0.95. However, the method has limitations on the dataset, and the accuracy of the diagnosis results on another new dataset drops sharply to nearly 0.5. Aiming at the existing EEG signal diagnosis lacks stability and generalization ability, this paper proposed a multilayer‐weighted integrated self‐learning algorithm for different classifiers. For this algorithm, weighted voting was first conducted on the the diagnostic results by different classifiers to obtain a result, which was weighted again to produce the final diagnostic results. This algorithm improves the problem that the traditional self‐learning algorithm is greatly affected by data noise, which shows a strong stability in different data sets and in clinical epileptic EEG signal data detection, so as to reduce the workload of neurologists and provide support and assistance for the diagnosis and treatment of epilepsy. The experiment result shows that the algorithm can improve the stability and reliability of EEG automatic diagnosis of epilepsy. The accuracy and AUC area of its classification in two different public data sets and clinical data can reach 0.80 to 0.95. [ABSTRACT FROM AUTHOR]

Cost‐sensitive ensemble learning as a combination of two approaches, ensemble learning and cost‐sensitive learning, enables generation of cost‐sensitive tree‐based ensemble models using the cost‐sensitive decision tree (CSDT) learning algorithm. In general, tree‐based models characterize nice graphical representation that can explain a model's decision‐making process. However, the depth of the tree and the number of base models in the ensemble can be a limiting factor in comprehending the model's decision for each sample. The CSDT models are widely used in finance (e.g., credit scoring and fraud detection) but lack effective explanation methods. We previously addressed this gap with cost‐sensitive tree Shapley Additive Explanation Method (CSTreeSHAP), a cost‐sensitive tree explanation method for the single‐tree CSDT model. Here, we extend the introduced methodology to cost‐sensitive ensemble models, particularly cost‐sensitive random forest models. The paper details the theoretical foundation and implementation details of CSTreeSHAP for both single CSDT and ensemble models. The usefulness of the proposed method is demonstrated by providing explanations for single and ensemble CSDT models trained on well‐known benchmark credit scoring datasets. Finally, we apply our methodology and analyze the stability of explanations for those models compared to the cost‐insensitive tree‐based models. Our analysis reveals statistically significant differences between SHAP values despite seemingly similar global feature importance plots of the models. This highlights the value of our methodology as a comprehensive tool for explaining CSDT models. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the leading causes of death among women worldwide. In most cases, the misinterpretation of medical diagnosis plays a vital role in increased fatality rates due to breast cancer. Breast cancer can be diagnosed by classifying tumors. There are two different types of tumors, such as malignant and benign tumors. Identifying the type of tumor is a tedious task, even for experts. Hence, an automated diagnosis is necessary. The role of machine learning in medical diagnosis is eminent as it provides more accurate results in classifying and predicting diseases. In this paper, we propose a deep ensemble network (DEN) method for classifying and predicting breast cancer. This method uses a stacked convolutional neural network, artificial neural network and recurrent neural network as the base classifiers in the ensemble. The random forest algorithm is used as the meta‐learner for providing the final prediction. Experimental results show that the proposed DEN technique outperforms all the existing approaches in terms of accuracy, sensitivity, specificity, F‐score and area under the curve (AUC) measures. The analysis of variance test proves that the proposed DEN model is statistically more significant than the other existing classification models; thus, the proposed approach may aid in the early detection and diagnosis of breast cancer in women, hence aiding in the development of early treatment techniques to increase survival rate. [ABSTRACT FROM AUTHOR]

Recently, graph neural networks (GNNs) have attracted much attention in the field of machine learning due to their remarkable success in learning from graph‐structured data. However, implementing GNNs in practice faces a critical bottleneck from the high complexity of communication and computation, which arises from the frequent exchange of graphic data during model training, especially in limited communication scenarios. To address this issue, we propose a novel framework of federated graph neural networks, where multiple mobile users collaboratively train the global model of graph neural networks in a federated way. The utilization of federated learning into the training of graph neural networks can help reduce the communication overhead of the system and protect the data privacy of local users. In addition, the federated training can help reduce the system computational complexity significantly. We further introduce a greedy‐based user selection for the federated graph neural networks, where the wireless bandwidth is dynamically allocated among users to encourage more users to attend the federated training of neural networks. We perform the convergence analysis on the federated training of neural networks, in order to obtain some more insights on the impact of critical parameters on the system design. Finally, we perform the simulations on the coriolis ocean for reAnalysis (CORA) dataset and show the advantages of the proposed method in this paper. [ABSTRACT FROM AUTHOR]

Stock prices forecasting has always been a challenging task. Although many research projects adopt machine learning and deep learning algorithms to address the problem, few of them pay attention to the varying degrees of dependencies between stock prices. In this paper we introduce a hybrid model that improves stock price prediction by emphasizing the dependencies between adjacent stock prices. The proposed model, ResNLS, is mainly composed of two neural architectures, ResNet and LSTM. ResNet serves as a feature extractor to identify dependencies between stock prices across time windows, while LSTM analyses the initial time‐series data with the combination of dependencies which considered as residuals. In predicting the SSE Composite Index, our experiment reveals that when the closing price data for the previous five consecutive trading days is used as the input, the performance of the model (ResNLS‐5) is optimal compared to those with other inputs. Furthermore, ResNLS‐5 outperforms vanilla CNN, RNN, LSTM, and BiLSTM models in terms of prediction accuracy. It also demonstrates at least a 20% improvement over the current state‐of‐the‐art baselines. To verify whether ResNLS‐5 can help clients effectively avoid risks and earn profits in the stock market, we construct a quantitative trading framework for back testing. The experimental results show that the trading strategy based on predictions from ResNLS‐5 can successfully mitigate losses during declining stock prices and generate profits in the periods of rising stock prices. [ABSTRACT FROM AUTHOR]

This paper proposes an unsupervised algorithm for learning a finite mixture of scaled Dirichlet distributions. Parameters estimation is based on the maximum likelihood approach, and the minimum message length (MML) criterion is proposed for selecting the optimal number of components. This research work is motivated by the flexibility issues of the Dirichlet distribution, the widely used model for multivariate proportional data, which has prompted a number of scholars to search for generalizations of the Dirichlet. By introducing the extra parameters of the scaled Dirichlet, several useful statistical models could be obtained. Experimental results are presented using both synthetic and real datasets. Moreover, challenging real‐world applications are empirically investigated to evaluate the efficiency of our proposed statistical framework. [ABSTRACT FROM AUTHOR]

With the surge of searching and reading online health‐based articles, maintaining the quality and credibility of online health‐based articles has become crucial. The circulation of deceptive health information on numerous social media sites can mislead people and can potentially cause adverse effects on people's health. To address these problems, this work uses deep learning approaches to automate the assessment and scoring of online health‐related articles' credibility. The paper proposed an Attention‐based Recurrent Multichannel Convolutional Neural Network (ARMCNN) model. The proposed model incorporates a BiLSTM layer, a multichannel CNN layer, and an attention layer and predicts the credibility of online health information. To perform a reliable evaluation of the presented model, we utilize the health articles reviewed by the experts, compiled in a labeled dataset termed "Pubhealth," which consists of thousands of health articles. The results are evaluated using five performance measures, accuracy, precision, recall, f1‐score, and area under the ROC curve (AUC). Furthermore, we extensively compared the proposed model with different deep learning and machine learning models such as Long short‐term memory (LSTM), Bidirectional LSTM, CNN (Convolutional neural network), and RNN‐CNN. The experimental results showed that the proposed model produced state‐of‐the‐art performance on the used dataset by achieving an accuracy of 0.88, precision of 0.92, recall of 0.87, f1‐score of 0.90, and AUC of 0.94. Further, the proposed model yielded better performance than other benchmarked techniques for the credibility assessment of online health articles. [ABSTRACT FROM AUTHOR]

Alzheimer's disorder (AD) causes permanent impairment in the brain's memory of the cellular system, leading to the initiation of dementia. Earlier detection of Alzheimer's disease in the initial stages is challenging for researchers. Deep learning and machine learning‐based techniques can help resolve many issues associated with brain imaging exploration. Brain MR Images (Brain‐MRI) are used to detect Alzheimer's in computable research work. To correctly categorize the stages of Alzheimer's disease, discriminative features need to be extracted from the MR images. Recently, many studies have used deep learning methods for the early detection of this disorder. However, overfitting degrades the deep learning method's performance because the dataset's selection images are smaller and imbalanced. Some studies could not reach more discriminative and effectual attention‐aware features for Alzheimer's stage classification to increase the model performance. In this paper, we develop a novel hierarchical residual attention learning‐inspired multistage conjoined twin network (HRAL‐CTNN) to classify the stages of Alzheimer's. We used augmentation approaches to scale insufficient and imbalanced data. The HRAL‐CTNN is efficiently overcoming the issues of not obtaining efficient attention‐aware and generative features for Alzheimer's stage classification. The proposed model solved the problem of redundant features by extracting attentive discriminant features, and scaling imbalance data by data augmentation, after that training and validation using HRAL‐CTNN. The execution of this proposed work has been performed on the ADNI MRI dataset. This work achieved outstanding accuracy of 99.97 ±$$ \pm $$ 0.01% and F1 score of 99.30 ±$$ \pm $$ 0.02% for Alzheimer's stage classification. This model proposed by our group outperformed the existing related studies in terms of the model's performance score. [ABSTRACT FROM AUTHOR]

In the field of automated planning, the central research focus is on domain‐independent planning engines that accept planning tasks (domain models and problem descriptions) in a description language, such as Planning Domain Definition Language, and return solution plans. The performance of planning engines can be improved by gathering additional knowledge about specific planning domain models/tasks (such as control rules) that can narrow the search for a solution plan. Such knowledge is often learned from training plans and solutions of simple tasks. Using techniques to reformulate the given planning task to incorporate additional knowledge, while keeping to the same input language, allows to exploit off‐the‐shelf planning engines. In this paper, we present inner entanglements that are relations between pairs of operators and predicates that represent the exclusivity of predicate achievement or requirement between the given operators. Inner entanglements can be encoded into a planner's input language by transforming the original planning task; hence, planning engines can exploit them. The contribution of this paper is to provide an in‐depth analysis and evaluation of inner entanglements, covering theoretical aspects such as complexity results, and an extensive empirical study using International Planning Competition benchmarks and state‐of‐the‐art planning engines. [ABSTRACT FROM AUTHOR]

The dramatic growth in machine learning has brought in significant features and quantified non‐linear associations in the data derived from sensitive medical datasets. The data should be preserved without influencing the associated classifications by applying a robust, effective and reliable data perturbation technique before enforcing ensemble classification. In this paper, an Integrated Condensation Scheme imposed Privacy Preserving Rotation‐based Data Perturbation and Ensemble Classification (ICS‐PPR‐DPEC) is proposed for ensuring privacy of such sensitive data. Condensation Algorithm‐based Data Perturbation is used for constructing homogenous groups determined from the distance between tuples. It also generates a rotation matrix for conducting perturbation that ensures higher data sensitivity protection before it is sent for classification. Advanced Extreme Learning Machine‐based Ensemble Classification Scheme includes kernel, norm‐optimized and regularized Extreme Learning Machine (ELM)‐based classifiers for attaining predominant classification accuracy in identifying human DNA sequences. This approach facilitates classification by constructing ensembles which are trained through randomly resampled ELM classifiers. It includes an objective function that systematically improves the accuracy and diversity among resulting ensembles. The experimental results of the proposed ICS‐PPR‐DPEC are found to be excellent in terms of classification Accuracy, Precision, Recall, and Kappa statistic when compared to the benchmarked techniques. [ABSTRACT FROM AUTHOR]

Approximately 15% of all cancer deaths among women worldwide is due to breast cancer. Mammography is one of the most useful methods for the early detection of this disease. Over the last decade, several papers were published reporting the usage of different computer‐aided diagnosis systems using pattern recognition techniques as a second opinion to obtain a more accurate diagnosis. However, the theory of formal languages has not been explored in this field. In this context, the main contribution of this study is to present the usage of a new syntactic approach that is able to classify breast masses found in mammograms as benign or malignant. The experimental tests were performed using a dataset that contains 111 images from different sources. The grammar‐based classifiers achieved accuracy values ranging from 89% to 100% depending on the features and the model employed. Furthermore, to achieve a feature dimension reduction, a feature selection technique based on the Gini importance of each feature was employed. Additionally, we compared the obtained results with the grammar‐based classifiers to the more traditional classifiers used in this research area, such as artificial neural networks, support vector machines, k‐nearest neighbors, and random forest. The best result achieved by the grammar‐based classifiers was approximately 10% higher, in terms of accuracy, than the best results produced by the traditional classifiers, showing the strength of this grammatical approach. [ABSTRACT FROM AUTHOR]

Abstract: We propose an approach to image segmentation that views it as one of pixel classification using simple features defined over the local neighborhood. We use a support vector machine for pixel classification, making the approach automatically adaptable to a large number of image segmentation applications. Since our approach utilizes only local information for classification, both training and application of the image segmentor can be done on a distributed computing platform. This makes our approach scalable to larger images than the ones tested. This article describes the methodology in detail and tests it efficacy against 5 other comparable segmentation methods on 2 well‐known image segmentation databases. Hence, we present the results together with the analysis that support the following conclusions: (i) the approach is as effective, and often better than its studied competitors; (ii) the approach suffers from very little overfitting and hence generalizes well to unseen images; (iii) the trained image segmentation program can be run on a distributed computing environment, resulting in linear scalability characteristics. The overall message of this paper is that using a strong classifier with simple pixel‐centered features gives as good or better segmentation results than some sophisticated competitors and does so in a computationally scalable fashion. [ABSTRACT FROM AUTHOR]

Credit score classification is a prominent research problem in the banking or financial industry, and its predictive performance is responsible for the profitability of financial industry. This paper addresses how Spiking Extreme Learning Machine (SELM) can be effectively used for credit score classification. A novel spike‐generating function is proposed in Leaky Nonlinear Integrate and Fire Model (LNIF). Its interspike period is computed and utilized in the extreme learning machine (ELM) for credit score classification. The proposed model is named as SELM and is validated on five real‐world credit scoring datasets namely: Australian, German‐categorical, German‐numerical, Japanese, and Bankruptcy. Further, results obtained by SELM are compared with back propagation, probabilistic neural network, ELM, voting‐based Q‐generalized extreme learning machine, Radial basis neural network and ELM with some existing spiking neuron models in terms of classification accuracy, Area under curve (AUC), H‐measure and computational time. From the experimental results, it has been noticed that improvement in accuracy and execution time for the proposed SELM is highly statistically important for all aforementioned credit scoring datasets. Thus, integrating a biological spiking function with ELM makes it more efficient for categorization. [ABSTRACT FROM AUTHOR]

We study the problem of entity salience by proposing the design and implementation of Swat, a system that identifies the salient Wikipedia entities occurring in an input document. Swat consists of several modules that are able to detect and classify on‐the‐fly Wikipedia entities as salient or not, based on a large number of syntactic, semantic, and latent features properly extracted via a supervised process, which has been trained over millions of examples drawn from the New York Times corpus. The validation process is performed through a large experimental assessment, eventually showing that Swat improves known solutions over all publicly available datasets. We release Swat via an API that we describe and comment in the paper to ease its use in other software. [ABSTRACT FROM AUTHOR]

This paper describes a machine learning approach to building an efficient and accurate name spotting system. Finding names in free text is an important task in many text-based applications. Most previous approaches were based on hand-crafted modules encoding language and genre-specific knowledge. These approaches had at least two shortcomings: They required large amounts of time and expertise to develop and were not easily portable to new languages and genres. This paper describes an extensible system that automatically combines weak evidence from different, easily available sources: parts-of-speech tags, dictionaries, and surface-level syntactic information such as capitalization and punctuation. Individually, each piece of evidence is insufficient for robust name detection. However, the combination of evidence, through standard machine learning techniques, yields a system that achieves performance equivalent to the best existing hand-crafted approaches. [ABSTRACT FROM AUTHOR]

Many industries, inclusive of the automobile industry, have shifted their attention toward predictive maintenance. The automobile industry finds predictive maintenance a key player in improving the servicing and vehicles they deliver. It is also vital for the vehicle owners to diagnose the vehicles to prevent risks the vehicle may face by timely servicing. Even though, with so many benefits of predictive maintenance, it is challenging to detect a breakdown in advance in the automobile sector. This is due to the restricted accessibility to sensors and the unavailability of some design applications. However, with the continuous advances in technology, machine learning (ML) methods have come forward as a viable solution to analyze data and develop solutions even when the data is scarce. This article intends to provide the literature review of ML techniques used for predictive maintenance of automobiles and diagnosis of the vehicle's health using ML. This review focuses on machine learning techniques in practice, extraction of data from the onboard diagnosis system and difficulties that models face. The article also explores the possibility and scope of positive work efforts in this area. [ABSTRACT FROM AUTHOR]

Ensemble learning is a popular classification method where many individual simple learners contribute to a final prediction. Constructing an ensemble of learners has been shown to often improve prediction accuracy over a single learner. Bagging and boosting are the most common ensemble methods, each with distinct advantages. While boosting methods are typically very tunable with numerous parameters, to date, the type of flexibility this allows has been missing for general bagging ensembles. In this paper, we propose a new tunable weighted bagged ensemble methodology, resulting in a very flexible method for classification. We explore the impact tunable weighting has on the votes of each learner in an ensemble and compare the results with pure bagging and the best known bagged ensemble method, namely, the random forest. [ABSTRACT FROM AUTHOR]

Detecting subjectivity expressed toward concerned targets is an interesting problem and has received intensive study. Previous work often treated each target independently, ignoring the potential (sometimes very strong) dependency that could exist among targets (eg, the subjectivity expressed toward two products or two political candidates in an election). In this paper, we relieve such an independence assumption in order to jointly model the subjectivity expressed toward multiple targets. We propose and show that an attention‐based encoder‐decoder framework is very effective for this problem, outperforming several alternatives that jointly learn dependent subjectivity through cascading classification or multitask learning, as well as models that independently predict subjectivity toward individual targets. [ABSTRACT FROM AUTHOR]

Unsupervised feature selection is an important problem, especially for high‐dimensional data. However, until now, it has been scarcely studied and the existing algorithms cannot provide satisfying performance. Thus, in this paper, we propose a new unsupervised feature selection algorithm using similarity‐based feature clustering, Feature Selection‐based Feature Clustering (FSFC). FSFC removes redundant features according to the results of feature clustering based on feature similarity. First, it clusters the features according to their similarity. A new feature clustering algorithm is proposed, which overcomes the shortcomings of K‐means. Second, it selects a representative feature from each cluster, which contains most interesting information of features in the cluster. The efficiency and effectiveness of FSFC are tested upon real‐world data sets and compared with two representative unsupervised feature selection algorithms, Feature Selection Using Similarity (FSUS) and Multi‐Cluster‐based Feature Selection (MCFS) in terms of runtime, feature compression ratio, and the clustering results of K‐means. The results show that FSFC can not only reduce the feature space in less time, but also significantly improve the clustering performance of K‐means. [ABSTRACT FROM AUTHOR]

Summary: To classify high‐dimensional data, feature selection plays a key role to eliminate irrelevant attributes and enhance the classification accuracy and efficiency. Since feature selection is an NP‐Hard problem, many heuristics and metaheuristics have been used to tackle in practice this problem. In this article, we propose a novel approach that consists in a probabilistic selection hyper‐heuristic called the synergy Thompson sampling hyper‐heuristic. The Thompson sampling selection strategy is a probabilistic reinforcement learning mechanism to assess the behavior of the low‐level heuristics, and to predict which one will be more efficient at each point during the search process. The proposed hyper‐heuristic is combined with a 1 nearest neighbor classifier from the Weka framework. It aims to find the best subset of features that maximizes the classification accuracy rate. Experimental results show a good performance in favor of the proposed method when comparing with other existing approaches. [ABSTRACT FROM AUTHOR]

Subjective pattern recognition is a class of pattern recognition problems, where we not only merely know a few, if any, the strategies our brains employ in making decisions in daily life but also have only limited ideas on the standards our brains use in determining the equality/inequality among the objects. Face recognition is a typical example of such problems. For solving a subjective pattern recognition problem by machinery, application accuracy is the standard performance metric for evaluating algorithms. However, we indeed do not know the connection between algorithm design and application accuracy in subjective pattern recognition. Consequently, the research in this area follows a 'trial and error' process in a general sense: try different parameters of an algorithm, try different algorithms, and try different algorithms with different parameters. This phenomenon can be observed clearly in the nearly 30 years research of the face recognition: although huge advances have been made, no algorithm has ever been shown a potential to be consistently better than most of the algorithms developed earlier; it was even shown that a naïve algorithm can work, in the sense of accuracy, at least no worse than many newly developed ones in a few benchmarks. We argue that, the primary objective of subjective pattern recognition research should be moved to theoretical robustness from application accuracy so that we can evaluate and compare algorithms without or with only few 'trial and error' steps. We in this paper introduce an analytical model for studying the theoretical stabilities of multicandidate Electoral College and Direct Popular Vote schemes (aka regional voting scheme and national voting scheme, respectively), which can be expressed as the a posteriori probability that a winning candidate will continue to be chosen after the system is subjected to noise. This model shows that, in the context of multicandidate elections, generally, Electoral College is more stable than Direct Popular Vote, that the stability of Electoral College increases from that of Direct Popular Vote as the size of the subdivided regions decreases from the original nation size, up to a certain level, and then the stability starts to decrease approaching the stability of Direct Popular Vote as the region size approaches the original unit cell size; and that the stability of Electoral College approaches that of Direct Popular Vote in the two extremities as the region size increases to the original national size or decreases to the unit cell size. It also shows a special situation of white noise dominance with negligibly small concentrated noise, where Direct Popular Vote is surprisingly more stable than Electoral College, although the existence of such a special situation is questionable. We observe that 'high stability' in theory indeed always reveals itself in 'high accuracy' in applications. Extensive experiments on two human face benchmark databases applying an Electoral College framework embedded with standard baseline and newly developed holistic algorithms have been conducted. The impressive improvement by Electoral College over regular holistic algorithms verifies the stability theory on the voting systems. It also shows an evidential support for adopting theoretical stability instead of application accuracy as the primary objective for subjective pattern recognition research. [ABSTRACT FROM AUTHOR]

Abstract: In classical feedforward neural networks such as multilayer perceptron, radial basis function network, or counter‐propagation network, the neurons in the input layer correspond to features of the training patterns. The number of these features may be large, and their meaningfulness can be various. Therefore, the selection of appropriate input neurons should be regarded. The aim of this paper is to present a complete step‐by‐step algorithm for determining the significance of particular input neurons of the probabilistic neural network (PNN). It is based on the sensitivity analysis procedure applied to a trained PNN. The proposed algorithm is utilized in the task of reduction of the input layer of the considered network, which is achieved by removing appropriately indicated features from the data set. For comparison purposes, the PNN's input neuron significance is established by using the ReliefF and variable importance procedures that provide the relevance of the input features in the data set. The performance of the reduced PNN is verified against a full structure network in classification problems using real benchmark data sets from an available machine learning repository. The achieved results are also referred to the ones attained by entropy‐based algorithms. The prediction ability expressed in terms of misclassifications is obtained by means of a 10‐fold cross‐validation procedure. Received outcomes point out interesting properties of the proposed algorithm. It is shown that the efficiency determined by all tested reduction methods is comparable. [ABSTRACT FROM AUTHOR]

Abstract: Classifier combination methods have proved to be an effective tool to increase the performance of classification techniques that can be used in any pattern recognition applications. Despite a significant number of publications describing successful classifier combination implementations, the theoretical basis is still not matured enough and achieved improvements are inconsistent. In this paper, we propose a novel statistical validation technique known as correlation‐based classifier combination technique for combining classifier in any pattern recognition problem. This validation has significant influence on the performance of combinations, and their utilization is necessary for complete theoretical understanding of combination algorithms. The analysis presented is statistical in nature but promises to lead to a class of algorithms for rank‐based decision combination. The potentials of the theoretical and practical issues in implementation are illustrated by applying it on 2 standard datasets in pattern recognition domain, namely, handwritten digit recognition and letter image recognition datasets taken from UCI Machine Learning Database Repository ( http://www.ics.uci.edu/_mlearn). An empirical evaluation using 8 well‐known distinct classifiers confirms the validity of our approach compared to some other combinations of multiple classifiers algorithms. Finally, we also suggest a methodology for determining the best mix of individual classifiers. [ABSTRACT FROM AUTHOR]

Abstract: One of the problems with traditional genetic algorithms (GAs) is premature convergence, which makes them incapable of finding good solutions to the problem. The memetic algorithm (MA) is an extension of the GA. It uses a local search method to either accelerate the discovery of good solutions, for which evolution alone would take too long to discover, or reach solutions that would otherwise be unreachable by evolution or a local search method alone. In this paper, we introduce a new algorithm based on learning automata (LAs) and an MA, and we refer to it as LA‐MA. This algorithm is composed of 2 parts: a genetic section and a memetic section. Evolution is performed in the genetic section, and local search is performed in the memetic section. The basic idea of LA‐MA is to use LAs during the process of searching for solutions in order to create a balance between exploration performed by evolution and exploitation performed by local search. For this purpose, we present a criterion for the estimation of success of the local search at each generation. This criterion is used to calculate the probability of applying the local search to each chromosome. We show that in practice, the proposed probabilistic measure can be estimated reliably. On the basis of the relationship between the genetic section and the memetic section, 3 versions of LA‐MA are introduced. LLA‐MA behaves according to the Lamarckian learning model, BLA‐MA behaves according to the Baldwinian learning model, and HLA‐MA behaves according to both the Baldwinian and Lamarckian learning models. To evaluate the efficiency of these algorithms, they have been used to solve the graph isomorphism problem. The results of computer experimentations have shown that all the proposed algorithms outperform the existing algorithms in terms of quality of solution and rate of convergence. [ABSTRACT FROM AUTHOR]

Abstract: The entity linking task consists in automatically identifying and linking the entities mentioned in a text to their uniform resource identifiers in a given knowledge base. This task is very challenging due to its natural language ambiguity. However, not all the entities mentioned in the document have the same utility in understanding the topics being discussed. Thus, the related problem of identifying the most relevant entities present in the document, also known as salient entities (SE), is attracting increasing interest. In this paper, we propose salient entity linking, a novel supervised 2‐step algorithm comprehensively addressing both entity linking and saliency detection. The first step is aimed at identifying a set of candidate entities that are likely to be mentioned in the document. The second step, besides detecting linked entities, also scores them according to their saliency. Experiments conducted on 2 different data sets show that the proposed algorithm outperforms state‐of‐the‐art competitors and is able to detect SE with high accuracy. Furthermore, we used salient entity linking for extractive text summarization. We found that entity saliency can be incorporated into text summarizers to extract salient sentences from text. The resulting summarizers outperform well‐known summarization systems, proving the importance of using the SE information. [ABSTRACT FROM AUTHOR]

We have developed a machine learning framework to accurately extract complex genetic interactions from text. Employing type-specific classifiers, this framework processes research articles to extract various biological events. Subsequently, the algorithm identifies regulation events that take other events as arguments, allowing a nested structure of predictions. All predictions are merged into an integrated network, useful for visualization and for deduction of new biological knowledge. In this paper, we discuss several design choices for an event-based extraction framework. These detailed studies help improving on existing systems, which is illustrated by the relative performance gain of 10% of our system compared to the official results in the recent BioNLP'09 Shared Task. Our framework now achieves state-of-the-art performance with 37.43 recall, 54.81 precision and 44.48 F-score. We further present the first study of feature selection for bio-molecular event extraction from text. While producing more cost-effective models, feature selection can also lead to a better insight into the complexity of the challenge. Finally, this paper tries to bridge the gap between theoretical relation extraction from text and experimental work on bio-molecular interactions by discussing interesting opportunities to employ event-based text mining tools for real-life tasks such as hypothesis generation, database curation and knowledge discovery. [ABSTRACT FROM AUTHOR]

This paper reports our investigation of machine learning methods applied to anaphora resolution for biology texts, particularly paper abstracts. Our primary concern is the investigation of features and their combinations for effective anaphora resolution. In this paper, we focus on the resolution of demonstrative phrases and definite determiner phrases, the two most prevalent forms of anaphoric expressions that we find in biology research articles. Different resolution models are developed for demonstrative and definite determiner phrases. Our work shows that models may be optimized differently for each of the phrase types. Also, because a significant number of definite determiner phrases are not anaphoric, we induce a model to detect anaphoricity, i.e., a model that classifies phrases as either anaphoric or nonanaphoric. We propose several novel features that we call highlighting features, and consider their utility particularly for processing paper abstracts. The system using the highlighting features achieved accuracies of 78% and 71% for demonstrative phrases and definite determiner phrases, respectively. The use of the highlighting features reduced the error rate by about 10%. [ABSTRACT FROM AUTHOR]

Machine learning algorithms for sound classification can be supported by multiple temporal, spectral, and perceptual features extracted from the sound signal. The number of features affects the classification accuracy but also the computational resources requested, so the number of features has to be carefully selected. In this work, we propose a methodology for feature selection based on the principal component analysis. The case study has been the classification of classroom sounds during face‐to‐face module delivery and six sound types have been defined. The proposed method is applied upon a set of 143 sound features to produce feature ranking. The ranking results are compared with those provided by the Relief‐F. Then the selected features are used by five classification algorithms, Linear Discriminant Analysis (LDA), Quadratic Support Vector Machine (QSVM), k Nearest Neighbors, Boosted Trees, and Random Forest. The algorithms are executed with increasing number of features, from 1 to 143, considering both feature rankings, creating 1430 models. The performance of the classification algorithms increases rapidly with the number of features with LDA, QSVM, and Boosted Trees outperforming other methods and surpassing the accuracy ratio of 90% with 25 features. [ABSTRACT FROM AUTHOR]

Recently, blockchain intersected the Internet of Things (IoT) has come up with an integrated opportunity for different applications such as industries, medical diagnosis, and the education sector. Several conflicts have risen during the intersection, where the purpose of addressing the enormous resource utilization of blockchain, efficiency, and security issues of massive IoT has not been tackled in the present scenario. Presently, Ruff‐chain, blockchain consortium basis, mobile cloud blockchain (MCBC), probed IoT, and proof of work deployed to overcome the drawback of blockchain intersected IoT demands high resource utilization and power consumption. To address this issue, a light chain consensus reinforcement machine learning (LCC‐RML) method has been developed to optimize the blockchain effectively intersected IoT system and it assists in providing a learning methodology from the aspects of resource utilization, data security decentralization, scalability, and latency. In LCC‐RML, without affecting the decentralization system, security, and latency, scalability has been improved with the underlying blockchain approach. Here, a lighter model is designed especially for the blockchain intersected IoT platform, which contains optimized learning procedures, reduced block size, lightweight consensus data structure, and related effective block interval to streamline the data processing. The experimental analysis has been evaluated in the learning framework to improve the performance of the blockchain intersected IoT system with a computational speed of 84.89% and resource utilization reduction of 85.88%. Further in the power consumption has been reduced up to 57.55% with the computation cost of 29.55% with the scalability ratio of 86.88%. [ABSTRACT FROM AUTHOR]

Although complex machine learning models (eg, random forest, neural networks) are commonly outperforming the traditional and simple interpretable models (eg, linear regression, decision tree), in the healthcare domain, clinicians find it hard to understand and trust these complex models due to the lack of intuition and explanation of their predictions. With the new general data protection regulation (GDPR), the importance for plausibility and verifiability of the predictions made by machine learning models has become essential. Hence, interpretability techniques for machine learning models are an area focus of research. In general, the main aim of these interpretability techniques is to shed light and provide insights into the prediction process of the machine learning models and to be able to explain how the results from the prediction was generated. A major problem in this context is that both the quality of the interpretability techniques and trust of the machine learning model predictions are challenging to measure. In this article, we propose four fundamental quantitative measures for assessing the quality of interpretability techniques—similarity, bias detection, execution time, and trust. We present a comprehensive experimental evaluation of six recent and popular local model agnostic interpretability techniques, namely, LIME, SHAP, Anchors, LORE, ILIME" and MAPLE on different types of real‐world healthcare data. Building on previous work, our experimental evaluation covers different aspects for its comparison including identity, stability, separability, similarity, execution time, bias detection, and trust. The results of our experiments show that MAPLE achieves the highest performance for the identity across all data sets included in this study, while LIME achieves the lowest performance for the identity metric. LIME achieves the highest performance for the separability metric across all data sets. On average, SHAP has the smallest average time to output explanation across all data sets included in this study. For detecting the bias, SHAP and MAPLE enable the participants to better detect the bias. For the trust metric, Anchors achieves the highest performance on all data sets included in this work. [ABSTRACT FROM AUTHOR]

Sobel edge detector is an algorithm commonly used in image processing and computer vision to extract edges from input images using derivative of image pixels in x and y directions against surrounding pixels. Most artificial intelligence and machine learning applications require image processing algorithms running in real time on hardware systems like field‐programmable gate array (FPGAs). They typically require high throughput to match real‐time speeds and since they run alongside other processing algorithms, they are required to be area efficient as well. This article proposes a high‐speed and low‐area implementation of the Sobel edge detection algorithm. We created the design using a novel high‐level synthesis (HLS) design method based on application specific bit widths for intermediate data nodes. Register transfer level code was generated using MATLAB hardware description language (HDL) coder for HLS. The generated HDL code was implemented on Xilinx Kintex 7 field programmable gate array (FPGA) using Xilinx Vivado software. Our implementation results are superior to those obtained for similar implementations using the vendor library block sets as well as those obtained by other researchers using similar implementations in the recent past in terms of area and speed. We tested our algorithm on Kintex 7 using real‐time input video with a frame resolution of 1920 × 1080. We also verified the functional simulation results with a golden MATLAB implementation using FPGA in the loop feature of HDL Verifier. In addition, we propose a generic area, speed, and power improvement methodology for different HLS tools and application designs. [ABSTRACT FROM AUTHOR]

Fall is a major threat to the health and life of the elders. A Fall Detection System (FDS) assist the elders by identifying the fall and save their life. Machine Learning‐ (ML) based FDS has turned into a major research area due to its capability to assist the elders automatically. The efficiency of a FDS depends on its strength to identify the fall from nonfall accurately. The initial fall detection scheme depends on the threshold‐based classification to classify the fall from the Activity of Daily Living (ADL) but this classification method has failed to reduce the false alarm rate, which raises a question on the efficiency of the technique. This review work identifies the problems in threshold‐based classification from existing works and finds the need for an efficient ML‐based classification technique to accurately identify the fall. Then, presents a comprehensive literature review on various ML‐based classification in fall detection. Moreover, the scrutiny investigates the shortcomings associated with the ML‐based techniques for future research. This study finds that present ML‐based FDS has not addressed problems like data preprocessing and data dimensionality reduction techniques even though ML‐based techniques are far superior to threshold‐based techniques. The study concludes that Self‐Adaptive‐based FDS, as well as the complexity reduction of ML‐based models, should be concentrated in future research. [ABSTRACT FROM AUTHOR]

Social network analysis can be used to address the challenges of link prediction in a social network through the measuring and processing of the inherent structural properties of the network. By developing relationships between the anonymous types on networks such as Facebook and Twitter, social network analysis can determine the prediction of future and missing links among the nodes, as well as assist in developing a predictive system. Various techniques have been discussed with proposals for network link prediction methodologies. The scaling of social networks, differences in local and global features, and efficient and precise prediction of links are issues for further study. We propose a collaborative model for link prediction that offers the benefit of structural‐based and machine learning techniques. The model produces meaningful results for the prediction of strong and weak links. In this study, we consider node‐based feature parameters for the clustering of the social network. [ABSTRACT FROM AUTHOR]

Sentiment analysis focuses on identifying and classifying the sentiments expressed in text messages and reviews. Social networks like Twitter, Facebook, and Instagram generate heaps of data filled with sentiments, and the analysis of such data is very fruitful when trying to improve the quality of both products and services alike. Classic machine learning techniques have a limited capability to efficiently analyze such large amounts of data and produce precise results; they are thus supported by deep learning models to achieve higher accuracy. This study proposes a combination of convolutional neural network and long short‐term memory (CNN‐LSTM) deep network for performing sentiment analysis on Twitter datasets. The performance of the proposed model is analyzed with machine learning classifiers, including the support vector classifier, random forest (RF), stochastic gradient descent (SGD), logistic regression, a voting classifier (VC) of RF and SGD, and state‐of‐the‐art classifier models. Furthermore, two feature extraction methods (term frequency‐inverse document frequency and word2vec) are also investigated to determine their impact on prediction accuracy. Three datasets (US airline sentiments, women's e‐commerce clothing reviews, and hate speech) are utilized to evaluate the performance of the proposed model. Experiment results demonstrate that the CNN‐LSTM achieves higher accuracy than those of other classifiers. [ABSTRACT FROM AUTHOR]

Malicious online advertisement detection has attracted increasing attention in recent years in both academia and industry. The existing advertising blocking systems are vulnerable to the evolution of new attacks and can cause time latency issues by analyzing web content or querying remote servers. This article proposes a lightweight detection system for advertisement Uniform resource locators (URLs) detection, depending only on lexical‐based features. Deep learning algorithms are used for online advertising classification. After optimizing the deep neural network architecture, our proposed approach can achieve satisfactory results with false negative rate as low as 1.31%. We also design a novel unsupervised method for data clustering. With the implementation of AutoEncoder for feature preprocessing and t‐distributed stochastic neighbor embedding for clustering and visualization, our model outperforms other dimensionality reduction algorithms by generating clear clusterings for different URL families. [ABSTRACT FROM AUTHOR]

Modern surveillance systems for practical applications with diverse and mobile sensors are large, complex, and expensive. It is known that unexpected behaviors can emerge from such systems, and when these behaviors correspond to weaknesses in a surveillance system, we call them emergent vulnerabilities. Given their cost and importance to security, it is essential to test these systems for such vulnerabilities prior to deployment. To that end, we automate the testing process with multiagent systems and machine learning. However, the conventional-and most intuitive-approach is to focus the machine learning on the subject system, which leads to a high-dimensional problem that is intractable. Instead, we demonstrate in this paper that learning attacks on the system is tractable and provides a viable testing method. We demonstrate this with a series of studies in simulation and with a small-scale model system featuring elements typically found in real physical surveillance systems. Our machine learning method finds successful attacks in simulation, which we can duplicate with the physical system. The method is scalable, with the implication that it could be used to test larger, real surveillance installations. [ABSTRACT FROM AUTHOR]

Aspect category detection (ACD) is an important subtask of aspect‐based sentiment analysis (ABSA). It is a challenging problem due to subjectivity involved in categorization, as well as the existence of overlapping classes. Among various approaches that have been applied to ACD include rule‐based approaches along with other machine learning approaches, and most of them are statistical in nature. In this article, we have used an association rule‐based approach. To deal with the statistical limitation of association rules, we proposed a hybridized rule‐based approach that combines association rules with the semantic association. For semantic associations, we have used the notion of word‐embeddings. Experiments were performed on SemEval dataset, a standard benchmark dataset for aspect categorization in the restaurant domain. We observed that semantic associations can complement statistical association and improve the accuracy of classification. The proposed method performs better than several state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Selecting a subset of salient features for performing clustering using a clustering learning algorithm has been explored extensively in many real-world applications. To select salient features during training, the filter model evaluates the intrinsic characteristics of each individual feature but is not permitted to use a clustering learning algorithm that provides clustered information to train the features. In particular, the filter model aims to predict unobservable clusters and measure how the features help provide satisfactory within-cluster and between-cluster scatters to achieve a good clustering quality. However, it is generally difficult to achieve both scatters in the filter model. For example, a random variable with a large variance may raise only the between-cluster scatter, whereas another variable following a uniform distribution may raise only the within-cluster scatter. In this paper, we present a new filter-based method to quantify features that consider feature compactness and separability to ensure that both scatters are raised. Moreover, our method adopts a new search strategy to locate the best feature salience vector instead of visiting the space of all the possible feature subsets. After the benchmark data sets are tested, the experimental results indicate that our method performs better than many benchmark filter-based methods at selecting a feature subset to perform clustering. [ABSTRACT FROM AUTHOR]

Boosting has been shown to improve the predictive performance of unstable learners such as decision trees, but not of stable learners like Support Vector Machines (SVM), k-nearest neighbors and Naive Bayes classifiers. In addition to the model stability problem, the high time complexity of some stable learners such as SVM prohibits them from generating multiple models to form an ensemble for large data sets. This paper introduces a simple method that not only enables Boosting to improve the predictive performance of stable learners, but also significantly reduces the computational time to generate an ensemble of stable learners such as SVM for large data sets that would otherwise be infeasible. The method proposes to build local models, instead of global models; and it is the first method, to the best of our knowledge, to solve the two problems in Boosting stable learners at the same time. We implement the method by using a decision tree to define local regions and build a local model for each local region. We show that this implementation of the proposed method enables successful Boosting of three types of stable learners: SVM, k-nearest neighbors and Naive Bayes classifiers. [ABSTRACT FROM AUTHOR]

Algorithms for planning under uncertainty require accurate action models that explicitly capture the uncertainty of the environment. Unfortunately, obtaining these models is usually complex. In environments with uncertainty, actions may produce countless outcomes and hence, specifying them and their probability is a hard task. As a consequence, when implementing agents with planning capabilities, practitioners frequently opt for architectures that interleave classical planning and execution monitoring following a replanning when failure paradigm. Though this approach is more practical, it may produce fragile plans that need continuous replanning episodes or even worse, that result in execution dead-ends. In this paper, we propose a new architecture to relieve these shortcomings. The architecture is based on the integration of a relational learning component and the traditional planning and execution monitoring components. The new component allows the architecture to learn probabilistic rules of the success of actions from the execution of plans and to automatically upgrade the planning model with these rules. The upgraded models can be used by any classical planner that handles metric functions or, alternatively, by any probabilistic planner. This architecture proposal is designed to integrate off-the-shelf interchangeable planning and learning components so it can profit from the last advances in both fields without modifying the architecture. [ABSTRACT FROM AUTHOR]

Reinforcement Programming (RP) is a new approach to automatically generating algorithms that uses reinforcement learning techniques. This paper introduces the RP approach and demonstrates its use to generate a generalized, in-place, iterative sort algorithm. The RP approach improves on earlier results that use genetic programming (GP). The resulting algorithm is a novel algorithm that is more efficient than comparable sorting routines. RP learns the sort in fewer iterations than GP and with fewer resources. Experiments establish interesting empirical bounds on learning the sort algorithm: A list of size 4 is sufficient to learn the generalized sort algorithm. The training set only requires one element and learning took less than 200,000 iterations. Additionally RP was used to generate three binary addition algorithms: a full adder, a binary incrementer, and a binary adder. [ABSTRACT FROM AUTHOR]

Context-specific independence representations, such as tree-structured conditional probability distributions, capture local independence relationships among the random variables in a Bayesian network (BN). Local independence relationships among the random variables can also be captured by using attribute-value hierarchies to find an appropriate abstraction level for the values used to describe the conditional probability distributions. Capturing this local structure is important because it reduces the number of parameters required to represent the distribution. This can lead to more robust parameter estimation and structure selection, more efficient inference algorithms, and more interpretable models. In this paper, we introduce Tree-Abstraction-Based Search (TABS), an approach for learning a data distribution by inducing the graph structure and parameters of a BN from training data. TABS combines tree structure and attribute-value hierarchies to compactly represent conditional probability tables. To construct the attribute-value hierarchies, we investigate two data-driven techniques: a global clustering method, which uses all of the training data to build the attribute-value hierarchies, and can be performed as a preprocessing step; and a local clustering method, which uses only the local network structure to learn attribute-value hierarchies. We present empirical results for three real-world domains, finding that (1) combining tree structure and attribute-value hierarchies improves the accuracy of generalization, while providing a significant reduction in the number of parameters in the learned networks, and (2) data-derived hierarchies perform as well or better than expert-provided hierarchies. [ABSTRACT FROM AUTHOR]

This paper describes the Adaptive Constraint Engine (ACE), an ambitious ongoing research project to support constraint programmers, both human and machine. The program begins with substantial knowledge about constraint satisfaction. The program harnesses a cognitively-oriented architecture (FORR) to manage search heuristics and to learn new ones. ACE can transfer what it learns on simple problems to solve more difficult ones, and can readily export its knowledge to ordinary constraint solvers. It currently serves both as a learner and as a test bed for the constraint community. [ABSTRACT FROM AUTHOR]

This paper addresses the question of allocating computational resources among a set of algorithms to achieve the best performance on scheduling problems. Our primary motivation in addressing this problem is to reduce the expertise needed to apply optimization technology. Therefore, we investigate algorithm control techniques that make decisions based only on observations of the improvement in solution quality achieved by each algorithm. We call our approach “low knowledge” since it does not rely on complex prediction models, either of the problem domain or of algorithm behavior. We show that a low-knowledge approach results in a system that achieves significantly better performance than all of the pure algorithms without requiring additional human expertise. Furthermore the low-knowledge approach achieves performance equivalent to a perfect high-knowledge classification approach. [ABSTRACT FROM AUTHOR]

A great challenge in developing planning systems for practical applications is the difficulty of acquiring the domain information needed to guide such systems. This paper describes a way to learn some of that knowledge. More specifically, the following points are discussed. (1) We introduce a theoretical basis for formally defining algorithms that learn preconditions for Hierarchical Task Network (HTN) methods. (2) We describe Candidate Elimination Method Learner ( CaMeL), a supervised, eager, and incremental learning process for preconditions of HTN methods. We state and prove theorems about CaMeL's soundness, completeness, and convergence properties. (3) We present empirical results about CaMeL's convergence under various conditions. Among other things, CaMeL converges the fastest on the preconditions of the HTN methods that are needed the most often. Thus CaMeL's output can be useful even before it has fully converged. [ABSTRACT FROM AUTHOR]

Over the years we have developed the Disciple theory, methodology, and family of tools for building knowledge-based agents. This approach consists of developing an agent shell that can be taught directly by a subject matter expert in a way that resembles how the expert would teach a human apprentice when solving problems in cooperation. This paper presents the most recent version of the Disciple approach and its implementation in the Disciple–RKF (rapid knowledge formation) system. Disciple–RKF is based on mixed-initiative problem solving, where the expert solves the more creative parts of the problem and the agent solves the more routine ones, integrated teaching and learning, where the agent helps the expert to teach it, by asking relevant questions, and the expert helps the agent to learn, by providing examples, hints, and explanations, and multistrategy learning, where the agent integrates multiple learning strategies, such as learning from examples, learning from explanations, and learning by analogy, to learn from the expert how to solve problems. Disciple–RKF has been applied to build learning and reasoning agents for military center of gravity analysis, which are used in several courses at the US Army War College. [ABSTRACT FROM AUTHOR]

This paper examines the potential and the impact of introducing learning capabilities into autonomous agents that make decisions at run-time about which mechanism to exploit to coordinate their activities. Specifically, our motivating hypothesis is that to deal with dynamic and unpredictable environments it is important to have agents that learn the right situations in which to attempt coordination, and the right coordination method to use in those situations. In particular, the efficacy of learning is evaluated when agents have varying types and amounts of information when those coordinating decisions are taken. This hypothesis is evaluated empirically, in a grid-world scenario in which (a) an agent's predictions about the other agents in the environment are approximately correct and (b) an agent cannot correctly predict the others' behavior. The results presented show when, where and why learning is effective when it comes to making a decision about selecting a coordination mechanism. [ABSTRACT FROM AUTHOR]