Abstract This work presents a new neuro-evolutionary model, called NEVE (Neuroevolutionary Ensemble), based on an ensemble of Multi-Layer Perceptron (MLP) neural networks for learning in nonstationary environments. NEVE makes use of quantum-inspired evolutionary models to automatically configure the ensemble members and combine their output. The quantum-inspired evolutionary models identify the most

Abstract The alignment and fusion of knowledge graphs have been at entity alignment and fusion which match and align knowledge graphs (KGs) by measuring similarity of the entities in KGs. Nevertheless, false fusion of completely different KGs can be easily caused if only considering entity similarity but ignoring entity relationship similarity. This paper focuses on entity relationship similarity model

Abstract Multimodal Biometric Systems are extensively employed over unimodal counterparts for user authentication in the digital world. However, the application of multimodal systems to security-critical applications is limited mainly due to non-adaptiveness of these systems to the dynamic environment and inability to distinguish between spoofing attack and the noisy input image. In order to address

Abstract Feature representation is generally applied to reducing the dimensions of high-dimensional data to accelerate the process of data handling and enhance the performance of pattern recognition. However, the dimensionality of data nowadays appears to be a rapidly increasing trend. Existing unsupervised feature representation methods are susceptible to the rapidly increasing dimensionality of data

Abstract Existing smoky vehicle detection methods are vulnerable to false alarms because of the continuous interferences from common passed vehicles and the complex characteristics of smoke. This paper presents a video smoky vehicle detection method based on dynamic features. Three groups of features, including Multi-Sequence Integral Projection (MS-IP), Center-Symmetric Local Binary Patterns on Three

Abstract Distracted driver action is the main cause of road traffic crashes, which threatens the security of human life and public property. Based on the observation that cues (like the hand holding the cigarette) reveal what the driver is doing, a driver action recognition model is proposed, which is called deformable and dilated Faster R-CNN (DD-RCNN). Our approach utilizes the detection of motion-specific

Abstract Semantic segmentation can be considered as a per-pixel localization and classification problem, which gives a meaningful label to each pixel in an input image. Deep convolutional neural networks have made extremely successful in semantic segmentation in recent years. However, some challenges still exist. The first challenge task is that most current networks are complex and it is hard to deploy

Abstract Noise leads to the ambiguity in regions of interest detection by corrupting the pixel information and is a vital problem in image processing domain. A novel hybrid technique based on fuzzy filtering and fuzzy thresholding is proposed here to extract the object regions accurately in presence of Gaussian noises. The proposed method is automated, does not need any parameter tuning as well does

Abstract The Sine Cosine Algorithm (SCA) is a recently developed efficient metaheuristic algorithm to find the solution of global optimization problems. However, in some circumstances, this algorithm suffers the problem of low exploitation, skipping of true solutions and insufficient balance between exploration and exploitation. Therefore, the present paper aims to alleviate these issues from SCA by

Abstract In the current paper, a novel approach is proposed for bi-clustering of gene expression data using the fusion of differential evolution framework and self-organizing map (SOM), named as BiClustSMEA. Variable number of gene and condition cluster centers are encoded in different solutions of the population to determine the number of bi-clusters from a dataset in an automated way. The concept

Abstract High quality crowd density maps preserve a large amount of spatial information of crowd distribution, which provides significant priori information for the field of crowd behavior analysis and anomaly detection. Recent work on crowd density estimation pays more attention to the accuracy of crowd counting, ignoring the quality of crowd density map estimation. Hence, in this paper, we propose

Abstract Intuitionistic Fuzzy Sets is one of the most influential extension and development of Zadeh’s fuzzy set theory. It has strong performance in dealing with uncertain information, while taking into account information on membership degree, non-membership degree and hesitation degree. In this paper, a new loose Pareto dominant relationship named intuitionistic fuzzy dominance is adopted to research

Abstract The aim of the subspace clustering is to segment the high-dimensional data into the corresponding subspace. The structured sparse subspace clustering and the block diagonal representation clustering are quite advanced spectral-type subspace clustering algorithms when handling to the linear subspaces. In this paper, the respective advantages of these two algorithms are fully exploited, and

Abstract Supplier selection can be regarded as a classic multiple criteria decision making (MCDM) problem. To a great extent, experts’ evaluations play a decisive role in the decision-making process. There will inevitable exist a variety of indefinite factors, which result from imprecision, uncertainty, and fuzziness due to the subjective judgment of human beings. As an effective tool to express uncertain

Abstract Community detection is the process of detecting communities in complex networks. Communities are important structures that can help us further study the properties of complex networks. In recent years, swarm intelligence algorithms have been applied to community detection and have achieved remarkable results. However, these existing algorithms have limited search ability and easily fall into

Abstract Class imbalance problem poses a difficulty to learning algorithms in pattern classification. Oversampling techniques is one of the most widely used techniques to solve these problems, but the majority of them use the sample size ratio as an imbalanced standard. This paper proposes a fuzzy representativeness difference-based oversampling technique, using affinity propagation and the chromosome

Abstract Data in real-world application often exhibit skewed class distribution which poses an intense challenge for machine learning. Conventional classification algorithms are not effective in case of imbalanced data distribution, and may fail when the data distribution is highly imbalanced. To address this issue, we propose a general imbalanced classification model based on deep reinforcement learning

Abstract As an emerging online interaction service in Twitter-like social media systems, mention serves to significantly improve both user interaction experience and information propagation. In recent years, the problem of mentionee recommendation, i.e., recommending mentionees (mentioned users) when mentioners (mentioning users) mention others, has received considerable attention. However, the extreme

Abstract The present paper aims to propose an information-theoretic method for interpreting the inference mechanism of neural networks. The new method aims to interpret the inference mechanism minimally by disentangling complex information into simpler and easily interpretable information. This disentanglement of complex information can be realized by maximizing mutual information between input patterns

Abstract When the elevation of targets is smaller than beamwidth, the coherent multi-path signals will significantly degrade the direction of arrival (DOA) estimation accuracy of existing methods for a very-high-frequency (VHF) radar system. Through detailed theoretical analysis, we demonstrate that the phase distortion is the key factor of degrading the accuracy of DOA estimation. Hence, a novel phase

Abstract Recently, reinforcement learning models have achieved great success, mastering complex tasks such as Go and other games with higher scores than human players. Many of these models store considerable data on the tasks and achieve high performance by extracting visual and time-series features using convolutional neural networks (CNNs) and recurrent neural networks respectively. However, these

Abstract Topic modeling has demonstrated its value in short text topic discovery. For this task, a common way adopted by many topic models is to perform a full analysis to find all the possible topics. However, these topic models overlook the importance of deeper topics, leading to confusing topics discovered. In practice, people always tend to find more focused topics on some special aspects (or events)

Abstract Multi-objective virtual machine (VM) placement is a powerful tool, which can achieve different goals in data centers. It is an NP-hard problem, and various works have been proposed to solve it. However, almost all of them ignore the selection of weights. The selection of weights is difficult, but it is essential for multi-objective optimization. The inappropriate weights will cause the obtained

Abstract The increment of new words and text categories requires more accurate and robust classification methods. In this paper, we propose a novel multi-label text classification method that combines dynamic semantic representation model and deep neural network (DSRM-DNN). DSRM-DNN first utilizes word embedding model and clustering algorithm to select semantic words. Then the selected words are designated

Abstract The accurate identification of KRAS mutation status on medical images is critical for doctors to specify treatment options for patients with rectal cancer. Deep learning methods have recently been successfully introduced to medical diagnosis and treatment problems, although substantial challenges remain in the computer-aided diagnosis (CAD) due to the lack of large training datasets. In this

Abstract Aiming at the complexity, nonlinearity and difficulty in modeling of nonlinear system. In this paper, an improved back-propagation(BP) neural network based on restricted boltzmann machine(RBM-IBPNN) is proposed for nonlinear systems modeling. First, the structure of BP neural network(BPNN) is optimized by using sensitivity analysis(SA) and mutual information(MI) of the hidden neurons. Namely

Abstract The hierarchical classification with an imbalance class problem is a challenge for in machine learning, and is caused by data with an uneven distribution. Learning from an imbalanced dataset can lead to performance degradation of the classifier. Cost-sensitive learning is a useful solution for handling the gap probability of majority and minority classes. This paper proposes a cost-sensitive

Abstract In this paper, a twin support vector machine (TWSVM) based on improved artificial fish swarm algorithm (IAFSA) for fire flame recognition is proposed in view of the large computation burden and slow classification speed of the traditional support vector machine (SVM). Twin support vector machine is a machine learning algorithm developing from standard support vector machine. However, twin

Abstract Multiple birth support vector machine (MBSVM) is a new classification algorithm, which includes the advantages of low complexity and high computing efficiency. However, the traditional MBSVM does not take into account the correlation sequence information among all dimensions of the samples when using the method to classify datasets, which limits the further improvement of the classification

Abstract This paper addresses the challenging problem of developing the automatic algorithm for solving direct current circuit problem. Leveraging on the innovated methods it proposes a high-performance relation based algorithm, called RaDCC. The challenges of the problem lie in relation acquisition and relation inference presentation after adopting the newly-established relation principle of solving

Abstract With the rapid development of wireless communication technology, digital filters are now key components in many modern digital systems. Dual-passband digital filter is an important module of digital filter and has attracted wide attention. This paper proposes a novel evolutionary method to design diversified structure digital filters. Our proposed method using an adaptive multiple-elites-

Abstract Selecting the most suitable design scheme in sponge city construction can be seen as a multiple attribute decision-making (MADM) problem. To express the uncertain and fuzzy decision-making information, interval type-2 fuzzy sets (IT2FSs) are useful tools. The paper focuses on decision making with trapezoidal interval type-2 fuzzy numbers (TIT2FNs) and discusses the evaluation of municipal

Abstract Learning Automata (LA) is a popular decision making mechanism to “determine the optimal action out of a set of allowable actions” (Agache and Oommen, IEEE Trans Syst Man Cybern-Part B Cybern 2002(6): 738–749, 2002). The distinguishing characteristic of automata-based learning is that the search for the optimising parameter vector is conducted in the space of probability distributions defined

Abstract This paper presents a bi-objective mathematical formulation for the multi-skill resource-constrained project scheduling problem (MSRCPSP) with the deterioration effect and financial constraints. The objectives are to optimize the makespan and cost of project, simultaneously. Due to the high NP-hardness of the proposed model, a Pareto-based Grey Wolf Optimizer (P-GWO) algorithm has been developed

Abstract Based on the powerful feature extraction capability of deep convolutional neural networks, image-level retrieval methods have achieved superior performance compared to the hand-crafted features and indexing algorithms. However, people tend to focus on foreground objects of interest in images. Locating objects accurately and using object-level features for retrieval become the essential tasks

Abstract Currently, image denoising is a challenge in many applications of computer vision. The existing denoising methods depend on the information of noise types or levels, which are generally classified by experts. These methods have not applied computational methods to pre-classify the image noise types. Furthermore, some methods assume that the noise type of the image is a certain one like Gaussian

Abstract In many practical situations, images are not only down sampled but also compressed for efficient transmission and storage. JPEG and MPEG-2 compressions often introduce blocking artifacts because they process the data as 8 × 8 blocks. Many of the existing super resolution (SR) methods assume low resolution images as a down sampled version of high resolution (HR) image, and neglect the degradation

Abstract The ability to sequentially learn from few examples and re-utilize previous knowledge is an important milestone on the path to artificial general intelligence. In this paper, we propose Teach Machine to Learn (TML), a few-shot learning model for hand-drawn multi-symbol sketch recognition. The model decomposes multi-symbol sketch into stroke primitives and then explains the observed sequences

Abstract Class imbalance is one of the critical areas in classification. The challenges become more severe when the data set has a large number of features. Traditional classifiers generally favour the majority class because of skewed class distributions. In recent years, feature selection is being used to select the appropriate features for better classification of minority class. However, these studies

Abstract Particle filtering is one of the most important algorithms for solving state estimation of nonlinear systems and has been widely studied in many fields. However, due to the unknown complex noise in the actual system, its estimation performance is degraded. Moreover, when the number of particles increase, the real-time performance of the algorithm is poor. For these two problems above, this

Abstract A belief rule-based (BRB) model with attribute reliability (BRB-r) has been developed recently, where the systematic uncertainty is regarded as attribute reliability by extending the traditional BRB model. The BRB-r model provides a framework to deal with the systematic uncertainty, but the drawbacks in modeling and inference reduces the accuracy of it. This paper proposed a new modeling and

Abstract Quantitative analysis of neural networks is a critical issue to improve their performance. In this paper, we investigate a long-term time series prediction based on the echo state network operating at the edge of chaos. We also assess the eigenfunction of echo state networks and its criticality by the Hermite polynomials. A Hermite polynomial-based activation function design with fast convergence

Abstract To improve the searching effectiveness of the harmony search (HS) algorithm, an enhanced harmony search algorithm with circular region perturbation (EHS_CRP) is proposed in this paper. In the EHS_CRP algorithm, a global and local dimension selection strategy is designed to accelerate the search speed of the algorithm. A selection learning operator based on the global and local mean level is

Abstract Due to cluster instability, not in the cluster monitoring system. This paper focuses on the missing data imputation processing for the cluster monitoring application and proposes a new hybrid multiple imputation framework. This new imputation approach is different from the conventional multiple imputation technologies in the fact that it attempts to impute the missing data for an arbitrary

Abstract Kriging or Gaussian Process Regression is applied in many fields as a non-linear regression model as well as a surrogate model in the field of evolutionary computation. However, the computational and space complexity of Kriging, that is cubic and quadratic in the number of data points respectively, becomes a major bottleneck with more and more data available nowadays. In this paper, we propose

Abstract 3D-R2N2 and other advanced 3D reconstruction neural networks have achieved impressive results, however most of them still suffer from training difficulties and detail losing, due to their weak feature extraction capability and improper loss function. This paper aims to overcome these shortcomings and defects by building a brand new model based on 3D-R2N2. The new model adopts densely connected

Abstract Multi-label linear discriminant analysis (MLDA) has been explored for multi-label dimension reduction. However, MLDA involves dense matrices eigen-decomposition which is known to be computationally expensive for large-scale problems. In this paper, we show that the formulation of MLDA can be equivalently casted as a least squares problem so as to significantly reduce the computation burden

Abstract The expressivity of machine learning algorithms is considered to be critical in intelligent data analysis tasks for practical application. As an alternative set of classification rule learning algorithms to conventional decision tree, Prism family of algorithms induce modular rules concisely, thus exhibiting good expressiveness for human users. However, existing Prism rule induction techniques

Abstract The task of Application Layer Multicast (ALM) routing is to establish a proper routing tree on application layer network, which transmits data packages from a source to multiple destinations. ALM routing tree is instable due to the end-hosts’ departure or failure. In view of this, we formulated the ALM routing as a multi-objective optimization problem, where the aim is to optimize the ALM

Abstract Given travel history, travel location recommendation can automatically suggest users where to visit. Huge efforts have been devoted to introducing different additional information (e.g., sequential, textual, geographical, and visual information) for enhancing recommendation performance. However, existing methods only consider limited additional information and treat different information equally

Abstract Kernel functions are powerful techniques that have been used successfully in many machine learning algorithms. Explicit kernel maps have emerged as an alternative to standard kernel functions in order to overcome the latter’s scalability issues. An explicit kernel map such as Random Fourier Features (RFF) is a popular method for approximating shift invariant kernels. However, it requires large

Abstract The rapid development of e-commerce gives researchers confidence that customers will be willing to share more and more online data, which in turn, would allow for improved mining algorithms. Many companies also foresee vast profits in mining data from online interaction, behavior, and activity. Opinion mining, also known as sentiment analysis, means automatically detecting and understanding

Abstract This paper puts forward a novel methodology for Heterogeneous Face Recognition (HFR), where we present a new-fangled image representation technique called the Local Radius of Gyration Face (LRGF), which has been theoretically proved to be invariant to changes in illumination, rotation and noise. Finally, a novel Local Triangular Coil Binary Pattern (LTCBP) is presented so as to apprehend the

Abstract Huge amount of time series data over several domains such as engineering, biomedical and finance, demands the development of efficient methods for the problem of time series classification. The classification of univariate and multivariate time series together using a single architecture is a very difficult task. In this work, a bio-inspired convolutional spiking neural network (CSNN) is proposed

Abstract Rapid thermal processing (RTP) is an important process in the fabrication of semiconductor devices. It is difficult to achieve temperature uniformity control of the wafer in RTP since the system is a highly nonlinear process with strong spatial distribution. In this study, a transfer learning-based three-dimensional (3D) fuzzy multivariable control scheme is proposed for the temperature uniformity

Abstract Object recognition occurs accurately with human visual neural mechanism despite in different complex background interference. For computer system, it is still a challenging work of object recognition and classification. Recently, many methods for object recognition based on human visual perception mechanism are presented. However, most methods cannot achieve a better recognition accuracy when

Abstract Recently, some algorithms have been reported for mining multi-graph Frequent Approximate Subgraphs (FASs). This kind of algorithm has a large applicability in social network analysis, image classification tasks and clustering, among others. However, all of them mine a large number of patterns. For this reason, some algorithms for mining a subset of FASs have been proposed. In this paper, we

Abstract Multiple birth support vector machine (MBSVM) is an extension of twin support vector machine on multi-class classification problem. In MBSVM, the size of each QP problem is restricted by the number of patterns in one of the K classes, so the computational complexity of MBSVM is much lower and the training speed of it is faster than the existing multi-class SVM. However, MBSVM neglects the

Abstract Many fundamental problems in machine learning require some form of dimensionality reduction. To this end, two different strategies were used: Manifold Learning and Feature Selection. Manifold learning (or data embedding) attempts to compute a subspace from original data by feature recombination/transformation. Feature selection aims to select the most relevant features in the original space

Abstract Quantum machine learning bridges the gap between abstract developments in quantum computing and the applied research on machine learning. It generally exposes the synthesis of important machine learning algorithms in a quantum framework. Dimensionality reduction of a dataset with a suitable feature selection strategy is one of the most important tasks in knowledge discovery and data mining