Search

A cohort refers to a group of candidates interacting and competing with one another. The basic idea of cohort is inspired from the social tendency of following/learning from one another and adapting the qualities of certain candidate. Based upon this approach, seven variations of cohort intelligence (CI) are presented in this paper. The seven variations of CI are: follow best, follow better, follow worst, follow itself, follow median, follow roulette wheel selection and alienate-and-random selection. The proposed variations are tested on seven multimodal and three uni-modal unconstrained test functions, and the numerical results are analyzed to decide which variation works best for a particular type of problem. The performance of these variations is compared with some well-known algorithms namely PSO, CMAES, ABC, JDE, CLPSO, SADE and BSA. The analysis of variations gives very important insight about the strategy that should be followed while working in a cohort. The variations proposed may provide insight into variegated applicability domain of the CI methodology. The choice of the right variation may also further open doors for CI to solve different real-world problems. [ABSTRACT FROM AUTHOR]

Analyzing source code to solve software engineering problems such as fault prediction, cost, and effort estimation always receives attention of researchers as well as companies. The traditional approaches are based on machine learning, and software metrics obtained by computing standard measures of software projects. However, these methods have faced many challenges due to limitations of using software metrics which were not enough to capture the complexity of programs. To overcome the limitations, this paper aims to solve software engineering problems by exploring information of programs' abstract syntax trees (ASTs) instead of software metrics. We propose two combination models between a tree-based convolutional neural network (TBCNN) and k-Nearest Neighbors (kNN), support vector machines (SVMs) to exploit both structural and semantic ASTs' information. In addition, to deal with high-dimensional data of ASTs, we present several pruning tree techniques which not only reduce the complexity of data but also enhance the performance of classifiers in terms of computational time and accuracy. We survey many machine learning algorithms on different types of program representations including software metrics, sequences, and tree structures. The approaches are evaluated based on classifying 52000 programs written in C language into 104 target labels. The experiments show that the tree-based classifiers dramatically achieve high performance in comparison with those of metrics-based or sequences-based; and two proposed models TBCNN + SVM and TBCNN + kNN rank as the top and the second classifiers. Pruning redundant AST branches leads to not only a substantial reduction in execution time but also an increase in accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we present an approach to the problem of Robot Learning from Demonstration (RLfD) in a dynamic environment, i.e. an environment whose state changes throughout the course of performing a task. RLfD mostly has been successfully exploited only in non-varying environments to reduce the programming time and cost, e.g. fixed manufacturing workspaces. Non-conventional production lines necessitate Human–Robot Collaboration (HRC) implying robots and humans must work in shared workspaces. In such conditions, the robot needs to avoid colliding with the objects that are moved by humans in the workspace. Therefore, not only is the robot: (i) required to learn a task model from demonstrations; but also, (ii) must learn a control policy to avoid a stationary obstacle. Furthermore, (iii) it needs to build a control policy from demonstration to avoid moving obstacles. Here, we present an incremental approach to RLfD addressing all these three problems. We demonstrate the effectiveness of the proposed RLfD approach, by a series of pick-and-place experiments by an ABB YuMi robot. The experimental results show that a person can work in a workspace shared with a robot where the robot successfully avoids colliding with him. [ABSTRACT FROM AUTHOR]

Advances in mathematical models and optimization introduce powerful tools for solving the visual object tracking problem, but this fundamental problem remains unsolved due to various challenges such as illumination variation, deformation and occlusion. Recent progress in correlation filter based models has provided an effective and efficient tracking solution. This type of trackers exploits the property of convolution theorem to significantly speed up their computational processes. However, their scheme of training correlation filters restricts them to use only a few negative examples to train their model, consequently lowers their performance. Therefore, in this paper, we propose to combine the fast calculation advantage of correlation filter with an online discriminative learning model, which can fully exploit the negative examples in the context around the target. The proposed tracker proceeds in a coarse-to-fine scheme: the proposed tracker will first employ a correlation filter to generate a coarse estimation of the location of the target, and then employ a translating model to refine its estimation and calculate the scale variation of the target via a scaling model. Both the translating model and the scaling model are formulated in the framework of our online discriminative model. Besides, we also propose an effective offline representation learning method to generate robust image feature for our correlation filter. Extensive experiments on the online Object Tracking Benchmark against the state-of-the-art methods validate the effectiveness of the proposed tracker. [ABSTRACT FROM AUTHOR]

Person re-identification aims to match images of the same person across disjoint camera views, which is a challenging problem in video surveillance. The major challenge of this task lies in how to preserve the similarity of the same person against large variations caused by complex backgrounds, mutual occlusions and different illuminations, while discriminating the different individuals. In this paper, we present a novel deep ranking model with feature learning and fusion by learning a large adaptive margin between the intra-class distance and inter-class distance to solve the person re-identification problem. Specifically, we organize the training images into a batch of pairwise samples. Treating these pairwise samples as inputs, we build a novel part-based deep convolutional neural network (CNN) to learn the layered feature representations by preserving a large adaptive margin. As a result, the final learned model can effectively find out the matched target to the anchor image among a number of candidates in the gallery image set by learning discriminative and stable feature representations. Overcoming the weaknesses of conventional fixed-margin loss functions, our adaptive margin loss function is more appropriate for the dynamic feature space. On four benchmark datasets, PRID2011, Market1501, CUHK01 and 3DPeS, we extensively conduct comparative evaluations to demonstrate the advantages of the proposed method over the state-of-the-art approaches in person re-identification. [ABSTRACT FROM AUTHOR]

Many real-world optimization problems involve several conflicting objectives that must be optimized simultaneously. Furthermore, most optimization problems have a dynamic structure and change over time. In addition to trying to establish trade-offs among conflicting objectives and explore a diverse set of solutions on a Pareto-optimal front, a dynamic multi-objective optimization (DMOO) algorithm tries to detect changes and track them, using the knowledge of prior environments to converge to the new Pareto-optimal front more quickly. In this paper, a cellular automata-based approach is first proposed for managing and evaluating solutions during the optimization process. Then, using the above approach and the teaching-learning-based optimization algorithm, two new algorithms are introduced for DMOO problems. The first algorithm works to optimize the objectives all at once in a multi-objective manner, while the second algorithm uses the vector evaluated technique to evolve solutions in collaborative single-objective optimization units, and then analyzes them from a multi-objective perspective. These algorithms have been evaluated and compared with some other DMOO algorithms for some standard benchmark problems. The results indicate their superiority in many of the experiments. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) has become one of the new research hotspots in the field of pattern recognition and machine learning. However, the existing extreme learning machine algorithms cannot better use identification information of data. Aiming at solving this problem, we propose a regularized extreme learning machine (algorithm) based on discriminative information (called IELM). In order to evaluate and verify the effectiveness of the proposed method, experiments use widely used image data sets. The comparative experimental results show that the proposed algorithm in the paper can significantly improve the classification performance and generalization ability of ELM. [ABSTRACT FROM AUTHOR]

Multi-objective particle swarm optimization (MOPSO) algorithms are shown to have enormous potential in solving multi-objective optimization problems (MOPs). However, most MOPSO is difficult to balance the exploration and exploitation, which may cause some problems to find true Pareto fronts when tackling some complex MOPs. A multi-objective decomposition particle swarm optimization based on completion-checking (C-DMOPSO) is improved in this paper. The updating mode of velocity is changed dynamically according to the algorithm's evolutionary process, which balances the exploration and exploitation effectively. In addition, simulated binary crossover and opposition-based learning are adopted to improve the diversity, and the archive set strategy is added to store the optimal solutions. Furthermore, polynomial mutation is performed in archive. The effectiveness of the proposed algorithm is tested by nineteen standard functions, including ZDT, DTLZ and UF, and the experimental results show that C-DMOPSO performs better on most of test problems. [ABSTRACT FROM AUTHOR]

This paper describes how to achieve highly accurate unsupervised spatial lexical acquisition from speech-recognition results including phoneme recognition errors. In most research into lexical acquisition, the robot has no pre-existing lexical knowledge. The robot acquires sequences of some phonemes as words from continuous speech signals. In a previous study, we proposed a nonparametric Bayesian spatial concept acquisition method (SpCoA) that integrates the robot’s position and words obtained by unsupervised word segmentation from uncertain syllable recognition results. However, SpCoA has a very critical problem to be solved in lexical acquisition; the boundaries of word segmentation are incorrect in many cases because of many phoneme recognition errors. Therefore, we propose an unsupervised machine learning method (SpCoA++) for the robust lexical acquisition of novel words relating to places visited by the robot. The proposed SpCoA++ method performs an iterative estimation of learning spatial concepts and updating a language model using place information. SpCoA++ can select a candidate including many words that better represent places from multiple word-segmentation results by maximizing the mutual information between segmented words and spatial concepts. The experimental results demonstrate a significant improvement of the phoneme accuracy rate of learned words relating to place in the proposed method by word-segmentation results based on place information, in comparison to the conventional methods. We indicate that the proposed method enables the robot to acquire words from speech signals more accurately, and improves the estimation accuracy of the spatial concepts. [ABSTRACT FROM AUTHOR]

Learning from imbalanced datasets is a frequent but challenging task for standard classification algorithms. Although there are different strategies to address this problem, methods that generate artificial data for the minority class constitute a more general approach compared to algorithmic modifications. Standard oversampling methods are variations of the SMOTE algorithm, which generates synthetic samples along the line segment that joins minority class samples. Therefore, these approaches are based on local information, rather on the overall minority class distribution. Contrary to these algorithms, in this paper the conditional version of Generative Adversarial Networks (cGAN) is used to approximate the true data distribution and generate data for the minority class of various imbalanced datasets. The performance of cGAN is compared against multiple standard oversampling algorithms. We present empirical results that show a significant improvement in the quality of the generated data when cGAN is used as an oversampling algorithm. [ABSTRACT FROM AUTHOR]

Radio frequency identification (RFID) has been widely used for the automatic identification, tracking and tracing of goods throughout the supply chain from the manufacturer to the customer. However, one technological problem that impedes the productive and reliable use of RFID is the constraint of false positive readings, which refers to tags that are detected accidentally by the reader but not the ones of interest. This paper focuses on the use of machine learning algorithms to identify such RFID readings. A total of 11 statistical features are extracted from received signal strength (RSS) and phase rotations derived from the raw RFID data. Each of the features is highly statistically different to distinguish the false positive readings, but satisfactory classification cannot be achieved when these features are considered individually. Classifiers based on logistic regression (LR), support vector machine (SVM) and decision tree (DT) are constructed, which combine all of the extracted features to classify the RFID readings more effectively. The performance of the classifiers is evaluated in a real-world factory. Results show that SVM provides the highest accuracy of up to 95.3%. DT shows slightly better accuracy (92.85%) than LR (92.75%), while LR has the larger area under the curve (0.976) than DT (0.949). Overall, machine learning algorithms could achieve accuracy of 93% on average. The proposed methodology provides a much more reliable RFID application as false-positive readings are detected immediately without human intervention, which enables a significant potential of fully automatic identification and tracking of goods throughout the supply chain. [ABSTRACT FROM AUTHOR]

The detection and location of objects concealed under clothing is a very challenging task that has crucial applications in security. In this domain, passive millimeter-wave images (PMMWIs) can be used. However, the quality of the acquired images, and the unknown position, shape, and size of hidden objects render this task difficult. In this paper, we propose a machine learning-based solution to this detection/localization problem. Our method outperforms currently used approaches. The effect of non-stationary noise on different classification algorithms is analyzed and discussed, and a detailed experimental comparative study of classification techniques is presented using a new and comprehensive PMMWI database. The low computational testing cost of this solution allows for its use in real-time applications. [ABSTRACT FROM AUTHOR]

A Siamese Deep Forest (SDF) is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. It can be also regarded as an alternative to the well-known Siamese neural networks. The SDF uses a modified training set consisting of concatenated pairs of vectors. Moreover, it defines the class distributions in the deep forest as the weighted sum of the tree class probabilities such that the weights are determined in order to reduce distances between similar pairs and to increase them between dissimilar points. We show that the weights can be obtained by solving a quadratic optimization problem. The SDF aims to prevent overfitting which takes place in neural networks when only limited training data are available. The numerical experiments illustrate the proposed distance metric method. [ABSTRACT FROM AUTHOR]

Cellular learning automata (CLAs) are learning models that bring together the computational power of cellular automata and also the learning capability of learning automata in unknown environments. CLAs can be open or closed. In a closed CLA , the action of each learning automaton depends on the neighboring cells, whereas in an open CLA , the action of each learning automaton depends on the neighboring cells, and a global environment. These models can be synchronous or asynchronous . In a synchronous CLA , all cells are activated at the same time, but in an asynchronous CLA , at a given time only some cells are activated. These models can be also static or dynamic . In a dynamic CLA, one of its aspects such as structure, local rule or neighborhood may vary with time . All existing dynamic models of the CLAs are closed. In this paper, an open asynchronous dynamic CLA has been introduced. In order to show the potential of this model, an algorithm based on this model for solving allocation hub location problem with imprecise distances among nodes has been designed. To evaluate the proposed algorithm computer simulations have been conducted. The results of simulations show that the proposed algorithm is more robust to imprecise distances as compared to existing algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we invest the domain transfer learning problem with multi-instance data. We assume we already have a well-trained multi-instance dictionary and its corresponding classifier from the source domain, which can be used to represent and classify the bags. But it cannot be directly used to the target domain. Thus we propose to adapt them to the target domain by adding an adaptive term to the source domain classifier. The adaptive function is a linear function based on a domain transfer multi-instance dictionary. Given a target domain bag, we first map it to a bag-level feature space using the domain transfer dictionary and then apply a linear adaptive function to its bag-level feature vector. To learn the domain transfer dictionary and the adaptive function parameter, we simultaneously minimize the average classification error of the target domain classifier over the target domain training set, and the complexities of both the adaptive function parameter and the domain transfer dictionary. The minimization problem is solved by an iterative algorithm which updates the dictionary and the function parameter alternately. Experiments over several benchmark data sets show the advantage of the proposed method over existing state-of-the-art domain transfer multi-instance learning methods. [ABSTRACT FROM AUTHOR]

Universum, a set of examples that do not belong to any class of interest for a classification problem, has been playing an important role in improving the performance of many machine learning methods. Since Universum examples are not required to have the same distribution as the training data, they can contain prior information for the possible classifiers. In this paper, we propose a novel distance metric learning method for nearest-neighbor (NN) classification, namely U -LMNN, that exploits prior information contained in the available Universum examples. Based on the large-margin nearest neighbor (LMNN) method, U -LMNN maximizes, for each training example, the margin between its nearest neighbor of the same class and the neighbors of different classes, while controlling the generalization capacity through the number of contradictions on Universum examples. Experimental results on synthetic as well as real-world data sets demonstrate a good performance of U -LMNN compared to the conventional LMNN method. [ABSTRACT FROM AUTHOR]

Data imbalance occurs on most real-world classification problems and decreases the performance of classifiers. An oversampling method addresses the imbalance problem by generating synthetic samples to balance the data distribution. However, many of the existing oversampling methods have potential problems in generating wrong and unnecessary synthetic samples, which makes the learning tasks difficult. This paper proposes a new segmented oversampling method for imbalanced data classification. The input space is first partitioned into several linearly separable local partitions along the potential separation boundary by introducing a bottom-up, minimal-spanning-tree-based clustering method; an oversampling method is then applied within each local linear partition to prevent the generation of wrong and unnecessary synthetic samples; a quasi-linear support vector machine is finally used to realize the classification by taking advantages of the local linear partitions. Simulation results on different real-world datasets show that the proposed segmented oversampling method is effective for imbalanced data classifications. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

We propose a cost-effective system for the determination of metal ion concentration in water, addressing a central issue in water resources management. The system combines novel luminometric label array technology with a machine learning algorithm that selects a minimal number of array reagents (modulators) and liquid sample dilutions, such that enable accurate quantification. The algorithm is able to identify the optimal modulators and sample dilutions leading to cost reductions since less manual labour and resources are needed. Inferring the ion detector involves a unique type of a structured feature selection problem, which we formalize in this paper. We propose a novel Cartesian greedy forward feature selection algorithm for solving the problem. The novel algorithm was evaluated in the concentration assessment of five metal ions and the performance was compared to two known feature selection approaches. The results demonstrate that the proposed system can assist in lowering the costs with minimal loss in accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel Evolutionary Mamdani Fuzzy Rule-based System named DECO 3 RUM ( D ifferential E volution based Co operative and Co mpeting learning of Co mpact Ru le-based M odels). The main advantage of DECO 3 RUM is that it offers simple and descriptive Mamdani models, without sacrificing the accuracy. It has further been designed to work with Big Data problems, where the number of patterns or features is significant. This is achieved through the successive use of three stages: (a) an instance selection stage, (b) an evolutionary rule base learning stage following the Genetic Cooperative Competitive Learning approach (where the novel Fuzzy Token Competition method based on AdaBoost tackles the cooperation-competition problem), which utilizes Differential Evolution as its learning algorithm, and (c) a post-processing stage to simplify the derived model and enhance its accuracy. DECO 3 RUM was validated using 24 datasets, and was additionally applied to one real-world high dimensional dataset from the domain of soil science. Through the comparisons with other state of the art evolutionary fuzzy systems it was demonstrated that DECO 3 RUM achieves a fair balance between accuracy and interpretability, performing better than its Mamdani counterparts. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) has proved to be well suited to different kinds of classification and regression problems. However, failing to seek deep representation of raw data completely brought by shallow architecture has made a plenty of research work stagnant, when ELM was chosen as the basic model. Recent years, deep ELM models like Hierarchical ELM (H-ELM), deep representations learning via ELM (Dr-ELM) have been proposed to be applied in multiple applications in machine learning. In this paper, a novel double deep ELMs ensemble system (DD-ELMs-ES) is proposed to focus on the problem of time series forecasting. In the proposed system, besides H-ELM and Dr-ELM are utilized as the basic models, a novel Constrained H-ELM (CH-ELM) is presented and serves as another basic model as well. CH-ELM intends to constrain the hidden neurons’ input connection weights, so that they could be consistent with the directions of sample vectors. Whats more, a self-adaptive ReTSP-Trend pruning technique is proposed to implement ensemble pruning in DD-ELMs-ES. Benefited from the merits of combining deep learning scheme with ensemble pruning paradigm, in the empirical results, DD-ELMs-ES demonstrates better generalization performance than the basic deep ELM models and some other state-of-the-art algorithms in tackling with time series forecasting tasks. [ABSTRACT FROM AUTHOR]

In this paper we deal with the problem of designing a classifier able to learn the classification of existing units in inventory and then use it to classify new units according to their attributes in a multi-criteria ABC inventory classification environment. To solve this problem we design a multi-start constructive algorithm to train a discrete artificial neural network using a randomized greedy strategy to add neurons to the network hidden layer. The process of weights’ searching for the neurons to be added is based on solving linear programming formulations. The computational experiments show that the proposed algorithm is much more efficient when the dual formulations are used to find the weights of the network neurons and that the obtained classifier has good levels of generalization accuracy. In addition, the proposed algorithm can be straight applied to other multi-class classification problems with more than three classes. [ABSTRACT FROM AUTHOR]

This paper presents a new general methodological approach to imbalanced learning as one of the challenging problems in pattern classification. The presented method is founded on maximization of the sample entropy. The method involves detection of distributive properties of ideally balanced regular lattice sample and acceptable transfer of these properties to an arbitrary imbalanced sample increasing its representativeness. The proposed procedure assumes undersampling applied on areas of high probability density in the sample space combined with oversampling in the areas of low density. The main achievement of this method is the increased sample class entropy which reduces the inductive learner’s tendency to favor prominent class, or cluster. In addition to class balancing, this method can be useful for function approximation, clustering, and sample dimension reduction. The high degree of generality of the method implies its applicability on data of various complexity and imbalance. The presented theoretical foundation of the method was verified on a set of proper synthetic samples. The method’s practical usability is confirmed by a comparative classification of a large set of databases including speech signal samples. [ABSTRACT FROM AUTHOR]

Multimodal recognition of affective states is a difficult problem, unless the recording conditions are carefully controlled. For recognition “in the wild”, large variances in face pose and illumination, cluttered backgrounds, occlusions, audio and video noise, as well as issues with subtle cues of expression are some of the issues to target. In this paper, we describe a multimodal approach for video-based emotion recognition in the wild. We propose using summarizing functionals of complementary visual descriptors for video modeling. These features include deep convolutional neural network (CNN) based features obtained via transfer learning, for which we illustrate the importance of flexible registration and fine-tuning. Our approach combines audio and visual features with least squares regression based classifiers and weighted score level fusion. We report state-of-the-art results on the EmotiW Challenge for “in the wild” facial expression recognition. Our approach scales to other problems, and ranked top in the ChaLearn-LAP First Impressions Challenge 2016 from video clips collected in the wild. [ABSTRACT FROM AUTHOR]

With in-depth research of action recognition, the conceptions and algorithms of multi-view had been proposed and demonstrated its superiority by researchers, but these algorithms usually neglected the relatedness of multi-views. For the sake of overcome the shortage, this paper proposes a 3D human action recognition model based on image set and regularized multi-task learning. Specifically, we first extract dense trajectory feature for each camera, and then propose to construct the shared codebook by k-means for all cameras, after that, Bag-of-Word ( BOW ) weight scheme is employed to code dense trajectory feature by the shared codebook for each camera, respectively. Furthermore, we formulate the 3D human action recognition into regularized multi-task learning problem penalized by image set and relevant and irrelevant decomposition to discover the underlying relationship among different tasks and different views, and consequently boost the performances. Large scale experimental results on three public multi-view action3D datasets – IXMAX, UCLA and CVS-MV-RGBD-SINGLE , show that multi-task learning approach is very helpful for discovering the latent relationships among different tasks, which can significantly improve performance over the single-task learning method. Moreover, the image set regularized term, which is utilized to combine different views, can further improve the performance. In a word, the performance of our proposed method is comparable to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recently, learning-based hashing methods which are designed to preserve the semantic information, have shown promising results for approximate nearest neighbor (ANN) search problems. However, most of these methods require a large number of labeled data which are difficult to access in many real applications. With very limited labeled data available, in this paper we propose a semi-supervised hashing method by integrating manifold embedding, feature representation and classifier learning into a joint framework. Specifically, a semi-supervised manifold embedding is explored to simultaneously optimize feature representation and classifier learning to make the learned binary codes optimal for classification. A two-stage hashing strategy is proposed to effectively address the corresponding optimization problem. At the first stage, an iterative algorithm is designed to obtain a relaxed solution. At the second stage, the hashing function is refined by introducing an orthogonal transformation to reduce the quantization error. Extensive experiments on three benchmark databases demonstrate the effectiveness of the proposed method in comparison with several state-of-the-art hashing methods. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is a popular machine learning method which can flexibly simulate the relationships of real-world classification applications. When facing problems ( i.e. , data sets) with a smaller number of samples ( i.e. , instances), ELM may often result in the overfitting trouble. In this paper, we propose a new Instance Cloned Extreme Learning Machine (IC-ELM for short) which can handle numerous different classification problems. IC-ELM uses an instance cloning method to balance the input data’s distribution and extend the training data set, which alleviates the overfitting issue and enhances the testing classification accuracy. Experiments and comparisons on 20 UCI data sets, and validations on image and text classification applications, demonstrate that IC-ELM is able to achieve superior results compared to the original ELM algorithm and its variants, as well as several other classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

• A new intelligent method is formed by combining the novel idea with BP-PSO neural network. • This method can solve the previously unsolvable shape-finding problem of tree-like structures. • This method displays the universality, efficiency and intelligence in shape-finding process. With the rapid development of machine learning (ML), it is regarded as an effective approach for the shape-finding method of tree-like structures, for optimizing their structural forms. Considering that the existing shape-finding methods are do not easily solve the shape-finding problem of tree-like structures under a non-uniform load or supporting an irregular surface roof, the combination of a shape-finding concept and ML opens a new direction for shape-finding design. This paper presents a novel ML approach by combining a new shape-finding concept with a backpropagation and particle swarm optimization neural network. The core concept is to locate the load-bearing centre of each shape-finding unit by executing a positioning program, which finds the coordinates of the optimized nodes to achieve shape-finding design. Taking a tree-like structure with bottom two-bifurcate and upper four-bifurcate types as a shape-finding example, this paper elaborates the ML shape-finding method and specific steps in detail. Moreover, different shape-finding cases are analysed and compared with the inverse-hang recursive method. Results show that the ML shape-finding method can not only solve the unsolvable problem of shape-finding design of tree-like structures under a non-uniform load or supporting an irregular surface roof but also has higher efficiency than the compared method. [ABSTRACT FROM AUTHOR]

• Applying MSE to the field of lithology discrimination. • Designing a lithology recognition model based on SA optimized SVM algorithm. • Forming a set of lithology recognition methods based on machine learning. • Establishing a lithology intelligent recognition model. Lithology identification is an important part of petroleum drilling engineering. Accurate identification of lithology is the foundation to ensure the smooth operation of drilling engineering. Conventional lithology recognition mainly relies on human experience. The recognition accuracy depends on the level of technical personnel and the recognition response time is lagging. It is difficult to meet the demand. How to achieve rapid and intelligent recognition of lithology is one of the core technical problems faced by oil drilling. In order to solve this problem, this paper uses the mechanical specific energy and other ground parameters to establish a rapid and intelligent recognition method of lithology based on the simulated annealing optimization support vector machine model. In order to improve the accuracy of the model recognition, a large number of methods have been developed from two classes and multiple classes, simulation analysis results show that the lithology recognition model based on the principle of mechanical specific energy and the simulated annealing optimization support vector machine algorithm can predict a priori unknown data with a prediction accuracy of over 90%. Compared with the support vector machine model and the K-means model, simulated annealing optimization support vector machine is used for comparative analysis, the algorithm to establish a lithology recognition model has better performance and higher accuracy. The intelligent identification model of lithology based on the principle of mechanical specific energy and simulated annealing optimization support vector machine algorithm established in this paper can quickly and accurately identify lithology, and provide new technical support for oil drilling formation analysis. [ABSTRACT FROM AUTHOR]

In this paper, an online autonomous learning and prediction (ALP) scheme is proposed for machine learning assisted structural optimization (MLaSO) to reduce total computational time with controlled accuracy of objective function prediction. In MLaSO, information in selected routine iterations is used via online learning to train a Neural Network, which is then used to perform online prediction of information in subsequent other iterations. Although using MLaSO with pre-defined learning and prediction scheme can save total computational time, it is difficult to determine the most suitable learning and prediction scheme prior to solving an optimization problem. The present ALP method enables autonomous activation of online learnings and predictions via maximizing specific computational efficiency while constraining the accuracy of the objective function prediction. Four numerical 2D and 3D examples are presented to demonstrate the computational benefits of integrating ALP with gradient based MLaSO method. The present numerical results demonstrate that: (a) using ALP in MLaSO can save more computational time than using the pre-defined scheme with similar prediction accuracy, and (b) more computational time can be saved by allowing larger tolerance in the accuracy of objective function prediction. • A framework to accelerate gradient-based structural optimization assisted by machine learning. • An online autonomous learning and prediction scheme for maximum efficiency with accuracy control. • Pareto solutions for computational timesaving and accuracy for selected 2D and 3D examples. [ABSTRACT FROM AUTHOR]

Abstract: In a recent paper [M. Anthony, J. Ratsaby, Maximal width learning of binary functions, Theoretical Computer Science 411 (2010) 138–147] the notion of sample width for binary classifiers mapping from the real line was introduced, and it was shown that the performance of such classifiers could be quantified in terms of this quantity. This paper considers how to generalize the notion of sample width so that we can apply it where the classifiers map from some finite metric space. By relating the learning problem to one involving the domination numbers of certain graphs, we obtain generalization error bounds that depend on the sample width and on certain measures of ‘density’ of the underlying metric space. We also discuss how to employ a greedy set-covering heuristic to bound generalization error. [Copyright &y& Elsevier]

Abstract: In this paper, we propose a new learning algorithm, named as the Cooperative and Geometric Learning Algorithm (CGLA), to solve problems of maneuverability, collision avoidance and information sharing in path planning for Unmanned Aerial Vehicles (UAVs). The contributions of CGLA are three folds: (1) CGLA is designed for path planning based on cooperation of multiple UAVs. Technically, CGLA exploits a new defined individual cost matrix, which leads to an efficient path planning algorithm for multiple UAVs. (2) The convergence of the proposed algorithm for calculating the cost matrix is proven theoretically, and the optimal path in terms of path length and risk measure from a starting point to a target point can be calculated in polynomial time. (3) In CGLA, the proposed individual weight matrix can be efficiently calculated and adaptively updated based on the geometric distance and risk information shared among UAVs. Finally, risk evaluation is introduced first time in this paper for UAV navigation and extensive computer simulation results validate the effectiveness and feasibility of CGLA for safe navigation of multiple UAVs. [Copyright &y& Elsevier]

Despite a very strong synergy between Robotics and AI at their early beginning, the two fields progressed widely apart in the following decades. However, we are witnessing a revival of interest in the fertile domain of embodied machine intelligence. This is due in particular to the dissemination of more mature techniques from both areas, to more accessible robot platforms with advanced sensory motor capabilities, and to a better understanding of the scientific challenges of the AI-Robotics intersection.The ambition of this paper is to contribute to this revival. It proposes an overview of problems and approaches to autonomous deliberate action in robotics. The paper advocates for a broad understanding of deliberation functions. It presents a synthetic perspective on planning, acting, perceiving, monitoring, goal reasoning and their integrative architectures, which is illustrated through several contributions that addressed deliberation from the AI-Robotics point of view. [ABSTRACT FROM AUTHOR]

Abstract: One of the first steps when approaching any machine learning task is to select, among all the available procedures, which one is the most adequate to solve a particular problem; in automated problem solving this is known as the algorithm selection problem. Of course, this problem is also present in the field of time series forecasting, there, one needs to select the forecaster that makes the most accurate predictions. Generally, this selection task is manually performed by analyzing the characteristics of the time series, thus relying on the expertise that one has on the available forecasters. In this paper, we propose an automatic procedure to choose a forecaster given a set of candidates, i.e., to solve the algorithm selection problem on this domain. To do so, we follow two paths. Firstly, we propose to model the performance of the forecasters using a linear combination of features that were previously used to assess the problem difficulty of evolutionary algorithms, together with a set of features we propose in this paper. Then, this model is used to predict the performance of the forecasters and based on these predictions the forecaster is selected. Our second approach is to treat this algorithm selection process as a classification task where the descriptors of each time series are the proposed features. To show the capabilities of our approach, we test the forecasters on the time series of the M1 and M3 time series competitions and used three different forecasters. In all the cases tested, our proposals outperform the performance of the three forecasters indicating the viability of our approach. [Copyright &y& Elsevier]

In this paper, we propose a Hierarchical Sampling-based Multi-Instance ensemble LEarning (HSMILE) method. Due to the unique multi-instance learning nature, a positive bag contains at least one positive instance whereas samples (instance and sample are interchangeable terms in this paper) in a negative bag are all negative, simply applying bootstrap sampling to individual bags may severely damage a positive bag because a sampled positive bag may not contain any positive sample at all. To solve the problem, we propose to calculate probable positive sample distributions in each positive bag and use the distributions to preserve at least one positive instance in a sampled bag. The hierarchical sampling involves inter- and intrabag sampling to adequately perturb bootstrap sample sets for multi-instance ensemble learning. Theoretical analysis and experiments confirm that HSMILE outperforms existing multi-instance ensemble learning methods. [ABSTRACT FROM PUBLISHER]

This paper deals with a single-machine scheduling problem with setup time and learning effects. The setup times are proportional to the length of the already processed jobs, i.e., the setup times are job-independent and past-sequence-dependent, and the learning effects are job-independent and position-dependent. The objective is to minimize the sum of earliness penalties subject to no tardy jobs. Wang, Wang, Gao, and Huang [Int J Adv Manuf Technol 48: 739-746, ] showed that an optimal sequence for this problem could be obtained by arranging jobs in non-increasing order of processing times. In this paper, we first demonstrate that this result is incorrect, and then introduce new exact solution strategies that polynomially solve problems whose earliness penalties are strictly increasing functions of job earliness. Polynomial time solutions are also presented for some special cases. [ABSTRACT FROM AUTHOR]

The wheel tread wear of heavy haul freight car in operation leads to shortened wheel turning period, reduced operation life, and poor train operation performance. In addition, wheel rail wear is a complex non-linear problem that integrates multiple disciplines. Thus, using a single physical or mathematical model to accurately describe and predict it is difficult. How to establish a model that could accurately predict wheel tread wear is an urgent problem and challenge that needs to be solved. In this paper, a tread wear prediction and optimization method based on chaotic quantum particle swarm optimization (CQPSO)-optimized derived extreme learning machine (DELM), namely CQPSO-DELM, is proposed to overcome this problem. First, an extreme learning machine model with derivative characteristics is proposed (DELM). Next, the chaos algorithm is introduced into the quantum particle swarm optimization algorithm to optimize the parameters of DELM. Then, through the CQPSO-DELM prediction model, the vehicle dynamics model simulates the maximum wheel tread wear under different test parameters to train and predict. Results show that the error performance index of the CQPSO-DELM prediction model is smaller than that of other algorithms. Thus, it could better reflect the influence of different parameters on the value of wheel tread wear. CQPSO is used to optimize the tread coordinates to obtain a wheel profile with low wear. The optimized wheel profile is fitted and reconstructed by the cubic non-uniform rational B-spline (NURBS) theory, and the optimized wear value of the tread is compared with the original wear value. The optimized wear value is less than the original wear value, thus verifying the effectiveness of the optimization model. The CQPSO-DELM model proposed in this paper could predict the wear value of different working conditions and tree shapes and solve the problem that different operating conditions and complex environment could have a considerable effect on the prediction of tread wear value. The optimization of wheel tread and the wear prediction of different tread shapes are realized from the angle of artificial intelligence for the first time. • Increasing the mapping ability of extreme learning machine to complex data. • Prediction of wheel tread wear based on Neural Network. • In this paper, a constrained multi-objective quantum particle swarm optimization algorithm for tread optimization is proposed. • Accurate fitting of tread shape is realized. [ABSTRACT FROM AUTHOR]

It is necessary to solve the problem of food corruption and oxidation to improve food quality. Peptides are a good candidate to solve the above problems. In this paper, a machine learning method was used to construct an antioxidant peptide classification model based on the pseudo-amino acid composition and motifs of peptides as input features. The AUC of PseAAC-dipeptide-motif hybrid model is 0.939 and the average precision score is 0.947, which is the best among all models in this paper. Besides, the classification threshold has been increased to make the model precision above 0.95. Then, the model was used as predictor to discover potential antioxidant peptides from a random peptide dataset. According to the predicted results, 5 potential antioxidant peptides (PSGK, LKPQ, GRP, QCQ, QGM) were synthesized to determine their DPPH radical-scavenging activity and the total antioxidant capacity (T-AOC). The experimental results show that QCQ has strong antioxidant properties, its T-AOC value is 9.59U/mg prot, and the DPPH scavenging activity is 95.52% at concentration of 125 μg/mL. Meantime, the predictor can be used to mine multifunctional peptides with antioxidant function. In general, the predictor is an effective tool for discovering peptides with antioxidant function. • A machine learning-based predictor was developed for virtual screening antioxidant. • Peptides of unknown function can be quickly identified whether they have antioxidant properties. • Multifunctional peptides with antioxidant function were quickly discovered based on a new strategy. • A low-cost and not time-consuming method for discovering antioxidant peptides. [ABSTRACT FROM AUTHOR]

Name entity recognition (NER) is one of the most basic tasks for extracting information from Internet text. Chinese NER remains a major challenge due to the language complexity. Although researchers have recently used domain knowledge to embed word-level information into the deep learning models to deal with the Chinese NER, they have not considered the global interdependence between word-level information, i.e., the entities in the same document should be semantically related to each other. In addition, domain knowledge often cannot be used efficiently due to the presence of irregular expressions in the Internet text, such as abbreviations and aliases. In this paper, we propose a referent graph embedding model for the NER, specifically concentrating on the Chinese car review. First, domain knowledge is used to generate character-level candidate entities and model the global interdependence between these entities based on the referent graph model. Second, the latest BERT-based character vectors and the character-level candidate entities are jointly embedded into the deep learning model to perform the NER. Last, Chinese car reviews are collected and labeled for use as the experimental dataset. The experimental results demonstrate the efficiency and effectiveness of the proposed model for the Chinese car NER task compared with the other start-of-the-art models. • This paper proposes an RGE-NER model to solve the NER problem for Chinese car reviews. The model innovatively combines referent graph and deep learning models. • Word-based and pronunciation-based methods are designed to expand the index range of entities in lexicon, which reduces the impact of irregular text expressions. • The latest BERT-based character vectors and the character-level candidate entities are jointly embedded into the deep learning model to perform the NER. • The embedding weights of candidate entities are measured by exploiting the global interdependence between candidate entities instead of algorithm learning, which significantly reduces the time complexity while improving the model performance. [ABSTRACT FROM AUTHOR]

As a result of environmental pollution and the ever-growing demand for energy, there has been a shift from conventional vehicles towards electric vehicles (EVs). Public acceptance of EVs and their large-scale deployment raises requires a fully operational charging infrastructure. Charging infrastructure planning is an intricate process involving various activities, such as charging station placement, charging demand prediction, and charging scheduling. This planning process involves interactions between power distribution and the road network. The advent of machine learning has made data-driven approaches a viable means for solving charging infrastructure planning problems. Consequently, researchers have started using machine learning techniques to solve the aforementioned problems associated with charging infrastructure planning. This work aims to provide a comprehensive review of the machine learning applications used to solve charging infrastructure planning problems. Furthermore, three case studies on charging station placement and charging demand prediction are presented. This paper is an extension of: Deb, S. (2021, June). Machine Learning for Solving Charging Infrastructure Planning: A Comprehensive Review. In the 2021 5th International Conference on Smart Grid and Smart Cities (ICSGSC) (pp. 16–22). IEEE. I would like to confirm that the paper has been extended by more than 50%. [ABSTRACT FROM AUTHOR]

In this paper, we provide external image features and use the internal attention mechanism to solve the VQA problem given a dataset of textual questions and related images. Most previous models for VQA use a pair of images and questions as input. In addition, the model adopts a question-oriented attention mechanism to extract the features of the entire image and then perform feature fusion. However, the shortcoming of these models is that they cannot effectively eliminate the irrelevant features of the image. In addition, the problem-oriented attention mechanism lacks in the mining of image features, which will bring in redundant image features. In this paper, we propose a VQA model based on adversarial learning and bidirectional attention. We exploit external image features that are not related to the question to form an adversarial mechanism to boost the accuracy of the model. Target detection is performed on the image—that is, the image-oriented attention mechanism. The bidirectional attention mechanism is conducive to promoting model attention and eliminating interference. Experimental results are evaluated on benchmark datasets, and our model performs better than other models based on attention methods. In addition, the qualitative results show the attention maps on the images and leads to predicting correct answers. [ABSTRACT FROM AUTHOR]

In this paper, we study the problem of learning from weakly labeled data, where labels of the training examples are incomplete. This includes, for example, (i) semi-supervised learning where labels are partially known; (ii) multi-instance learning where labels are implicitly known; and (iii) clustering where labels are completely unknown. Unlike supervised learning, learning with weak labels involves a difficult Mixed-Integer Programming (MIP) problem. Therefore, it can suffer from poor scalability and may also get stuck in local minimum. In this paper, we focus on SVMs and propose the WELLSVM via a novel label generation strategy. This leads to a convex relaxation of the original MIP, which is at least as tight as existing convex Semi-Definite Programming (SDP) relaxations. Moreover, the WELLSVM can be solved via a sequence of SVM subproblems that are much more scalable than previous convex SDP relaxations. Experiments on three weakly labeled learning tasks, namely, (i) semi-supervised learning; (ii)multi-instance learning for locating regions of interest in content-based information retrieval; and (iii) clustering, clearly demonstrate improved performance, and WELLSVM is also readily applicable on large data sets. [ABSTRACT FROM AUTHOR]

Intrusion detection systems (IDS) are systems aimed at analyzing and detecting security problems. The IDS may be structured into misuse and anomaly detection. The former are often signature/rule IDS that detect malicious software by inspecting the content of packets or files looking for a 'signature' labeling malware. They are often very efficient, but their drawback stands in the weakness of the information to check (eg, the signature), which may be quickly dated, and in the computation time because each packet or file needs to be inspected. The IDS based on anomaly detection and, in particular, on statistical analysis have been originated to bypass the mentioned problems. Instead of inspecting packets, each traffic flow is observed so getting a statistical characterization, which represents the fingerprint of the flow. This paper introduces a statistical analysis based intrusion detection system, which, after extracting the statistical fingerprint, uses machine learning classifiers to decide whether a flow is affected by malware or not. A large set of tests is presented. The obtained results allow selecting the best classifiers and show the performance of a decision maker that exploits the decisions of a bank of classifiers acting in parallel. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of script identification in scene text images. Facing this problem with state of the art CNN classifiers is not straightforward, as they fail to address a key characteristic of scene text instances: their extremely variable aspect ratio. Instead of resizing input images to a fixed aspect ratio as in the typical use of holistic CNN classifiers, we propose here a patch-based classification framework in order to preserve discriminative parts of the image that are characteristic of its class. We describe a novel method based on the use of ensembles of conjoined networks to jointly learn discriminative stroke-parts representations and their relative importance in a patch-based classification scheme. Our experiments with this learning procedure demonstrate state-of-the-art results in two public script identification datasets. In addition, we propose a new public benchmark dataset for the evaluation of multi-lingual scene text end-to-end reading systems. Experiments done in this dataset demonstrate the key role of script identification in a complete end-to-end system that combines our script identification method with a previously published text detector and an off-the-shelf OCR engine. [ABSTRACT FROM AUTHOR]

Statistical models of 3D human shape and pose learned from scan databases have developed into valuable tools to solve a variety of vision and graphics problems. Unfortunately, most publicly available models are of limited expressiveness as they were learned on very small databases that hardly reflect the true variety in human body shapes. In this paper, we contribute by rebuilding a widely used statistical body representation from the largest commercially available scan database, and making the resulting model available to the community (visit http://humanshape.mpi-inf.mpg.de ). As preprocessing several thousand scans for learning the model is a challenge in itself, we contribute by developing robust best practice solutions for scan alignment that quantitatively lead to the best learned models. We make implementations of these preprocessing steps also publicly available. We extensively evaluate the improved accuracy and generality of our new model, and show its improved performance for human body reconstruction from sparse input data. [ABSTRACT FROM AUTHOR]

Cutting plane algorithm (CPA) is a generalization of iterative first-order gradient method, in which the objective function is approximated successively by supporting hyperplanes. CPA has been tailored to solve regularized loss minimization in machine learning by exploiting the regularization structure. In particular, for linear Support Vector Machine (SVM) embedding a line search procedure effectively remedies the fluctuations of function value and speeds up the convergence in practical issue. However, the existing line search strategy based on sorting algorithm takes O ( m log  m ) time. In this paper, we propose a more effective line search solver which spends only linear time. It can be extended to multiclass SVM in which an optimized explicit piecewise linear function finding algorithm is prearranged. The total SVM training time is proved to reduce theoretically and experiments consistently confirm the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Big data analytics and machine learning applications are often used to detect and classify anomalous behaviour in telecom network measurement data. The accuracy of findings during the analysis phase greatly depends on the quality of the training dataset. If the training dataset contains data from network elements (NEs) with high number of failures and high failure rates, such behaviour will be assumed as normal. As a result, the analysis phase will fail to detect NEs with such behaviour. Effective post-processing techniques are needed to analyse the anomalies, to determine the different kinds of anomalies, as well as their relevance in real-world scenarios. Manual post-processing of anomalies detected in an Anomaly Detection experiment is a cumbersome task, and ways to automate this process are not much researched upon. There exists no universally accepted method for effective classification of anomalous behaviour. High failure ratios have traditionally been considered as signs of faults in NEs. Operators use well-known key performance indicators (KPIs) such as drop call ratio and handover failure ratio to identify misbehaving NEs. The main problem with these KPIs based on failure ratios is their unstable nature. This paper proposes a method of measuring the significance of failures. The usage of this method is proposed in two stages of anomaly detection: training set filtering (pre-processing stage) and classification of anomalies (post-processing stage) using an automated process. [ABSTRACT FROM AUTHOR]