Search

Dictionary learning has played an important role in the success of sparse representation. Although several dictionary learning approaches have been developed for image classification, discriminative dictionary pair learning, i.e., jointly learning a synthesis dictionary and an analysis dictionary, is still in its infant stage. In this paper, we proposed a novel model of Fisher discrimination dictionary pair learning (FDDPL), in which Fisher discrimination information is embedded into analysis representation, analysis dictionary, and synthesis dictionary representation. With the proposed Fisher-like discrimination term, discrimination of both synthesis dictionary representation and analysis dictionary representation is introduced into the dictionary pair learning model. An iterative algorithm to efficiently solve the proposed FDDPL and a FDDPL based classifier are also presented in this paper. The experiments on face recognition, scene categorization, gender classification, and action recognition clearly show the advantage of the proposed FDDPL.

Particle swarm optimisation (PSO) is a bio-inspired swarm based approach to solving optimisation problems. The algorithm functions as a result of particles traversing and evaluating the problem space, eventually converging on the optimum solution. This paper applies a number of PSO variants to the dynamic economic emission dispatch (DEED) problem. The DEED problem is a multi-objective optimisation problem in which the goal is to optimise two conflicting objectives: cost and emissions. The PSO variants tested include: the standard PSO (SPSO), the PSO with avoidance of worst locations (PSO AWL), and also a selection of different topologies including the PSO with a gradually increasing directed neighbourhood (PSO GIDN). The aim of the paper is to test the performance of different variants of the PSO AWL against variants of the SPSO on the DEED problem. The results show that the PSO AWL outperforms the SPSO for every topology implemented. The results are also compared to state of the art genetic algorithm (NSGA-II) and multi-agent eeinforcement learning (MARL). This paper then examines the performance of each PSO algorithm when the power demand is modified to form a triangle wave. The purpose of this experiment was to analyse the performance of different PSO variants on an increasingly constrained problem.

In this paper, stabilization is presented for a networked control system with actuator saturation and network-induced delays. A method is exploited at updating steps of control signal rather than sampling steps in the networked control system under actuator saturation. A network-based controller is designed under the limitation of actuator saturation. With a cone complementary linearization approach, a presented scheme is also used to estimate the domain of attraction for the networked control system. A numerical simulation is provided to show the effectiveness and correctness of the method in this paper.

Disruptions are prevalent phenomenons that prevent airline from operating as original scheduled. This paper adopts the iterative fixed-point method for integer programming proposed by Dang and Ye [1] to generate feasible flight routes that are used to construct an aircraft reassignment in response to the grounding of one aircraft. Two division methods are proposed with which the solution space can be divided into several independent segments and implemented a distributed computation. The second division method is emphasized in this paper for the good performance of partial feasible flight routes which are generated by this division approach. Comparison with CPLEX CP Optimizer [2] shows that less partial feasible flight routes which are generated by Dang’s algorithm [1] are required to find an aircraft reassignment when disruptions happen, and this division method is more promising when dealing with long haul airline disruption problem.

This paper studies how to maximize the lifetime of a centralized sensor system and meanwhile maintain a certain level of the estimation performance. The model is as follows. A group of sensors measure the states of a dynamic process and transmit the measurements to a remote estimator, which computes the estimates of the states. Constrained by its energy budget, each sensor has limited transmission times and may not transmit data at each time slot. Meanwhile, the time duration to maintain a certain level of the estimation performance of the estimator depends on the scheduling of sensor transmission. The notion of lifetime is defined as the largest time duration within which the system maintains a required estimation performance under a given schedule. This paper aims at studying the optimal scheduling which maximizes the lifetime of the system when a level of estimation performance is required. Both the scenarios of deterministic and stochastic scheduling are considered. In deterministic scheduling, three algorithms are proposed, where the schedules are given by solving convex problems and then discretizing the scheduling variables. In stochastic scheduling, two relaxed problems are considered, where the bounds of the original objective are used. The maximum of lifetime is also studied. Examples are given in the end.

Copy–Move (CM) is a common type of digital image forgery where a part of the original image is copied and pasted at another position in the same image. Sometimes, to increase the invisibility of the copying process, some processing procedures on the copied region are performed before or after pasting. Although block matching (BM) is the common well-used procedure for CM tempering detection, blind CM detection with geometric or intensity transformations is still a challenge. In this paper, we propose an efficient methodology for enhancing BM based Copy–Move forgery detection. The main contribution of this work is the utilization of polar representation to get the representative features for each block. The main feature used in this paper is the frequency of each block based on Fourier transform. The experimental results show the efficiency of the proposed method for detecting CM regions, even when the copied region has undergone severe image manipulations such as rotation, scaling, Gaussian blurring, brightness modification, JPEG compression and noise addition.

Redundancy resolution of parallel manipulators is widely studied and have brought many challenges in the control of robotic manipulators. The dual neural network, which is categorized under the recurrent neural network inherits parallel processing capabilities, are widely investigated for the control of serial manipulators in past decades and has been extended to the control of parallel Stewart platforms in our previous work. However, conventional dual neural network solutions for redundancy resolution requires prior knowledge of the robot, which may not accessible accurately in real applications. In this paper, we establish a model-free dual neural network to control the end-effector of a Stewart platform for the tracking of a desired spacial trajectory, at the same time as learning the unknown time-varying parameters. The proposed model is purely data driven. It does not rely on the system parameters as a priori and provides a new solution for stabilization of the self motion of Stewart platforms. Theoretical analysis and results show that global convergence can be achieved for the neural network employed in this paper with dual dynamics. It is also shown to be optimal per the model free criterion. In this paper, we carried out numerical simulations which highlight and illustrate relatable performance capability in terms of model-free optimization. Simulation results provided, verify the tracking control of the end effector efficiently while controlling the dynamic motion of the Stewart platform.

In this paper, the hardware circuit of the memristor with voltage threshold control system (abbreviated as MVTCS) adapted to the real-time control system (abbreviated as RTCS) is designed based on the weight modification process of the memristor nerve morphology circuit. A novel forced erase mode, called no read, high voltage write (abbreviated as NR-HVW), is proposed to eliminate the need for a read process and to conduct the write process into the memristor. The authors combine the low voltage read and high voltage write (abbreviated as LVR-HVW) and the high voltage read and high voltage write (abbreviated as HVR-HVW) modes, and then compare and analyze the advantages and disadvantages of the three read and write modes from the perspective of energy consumption. The numerical simulation technology is used to verify the design proposed by the author, and the simulation results demonstrate that the LVR-HVW mode has the lowest energy consumption, the HVR-HVW mode comes the second, and the NR-HVW mode is the highest. However, the NR-HVW mode can meet high-precision requirements for the RTCS without testing equipment. The research of this paper is believed to provide some technical support for the application of the memristor with voltage threshold (abbreviated as MVT) in the RTCS.

An instance is often represented from different aspects (views or modalities), which leads to high-dimensional features and even multiple labels. In this paper, we focus on the feature selection problem in multi-label classification, for which a trivial solution is handling the labels dividedly. Obviously, such a scheme may not work well by leaving the label relationship out of consideration. Recently, several research works conduct feature selection directly under a multi-label framework by implicitly or explicitly modeling label relationship. However, these works assume that all labels share the same feature subset or subspace, which is not reasonable enough for some scenarios since different labels tend to convey different semantics. To address this problem, we develop a novel approach in this paper to select label-dependent features for multi-label classification. Specifically, we (1) formulate a convex model based on a more general and practical assumption that different labels convey different semantics with specific features; (2) design an alternating optimization algorithm based on Nesterov's method and L1-ball projection for efficiently finding the optimal solution, which can realize multi-label classification, feature selection, and label relationship estimation simultaneously. Finally, experiments on publicly available datasets show that the proposed algorithm achieves better performance than several related methods.

Personal recommendation technology is becoming a useful and popular solution to solve the problem of information overload with the popularity of big data cloud services. But most recommendation algorithms pay too much attention to the similarity to focus on the social trust between users. So this paper focus on the research of hybrid Recommendation algorithm for big data based on the optimization combining with the similarity and trust in sociology. In this paper, we introduced some user trust models including trust path model and loop trust model, and then we took these models into the calculation of mixed weighting. The experiment results show that the recommendation algorithm considering the trust models has the higher accuracy than the traditional recommendation algorithm, and we have a 2% increase in both MEA (Mean Absolute Error) and RMSE (Root Mean Square Error).

The Internet of Things (IoT) refers to an infrastructure that integrates things over standard wired/wireless networks and allows them to exchange information with each other. The IoT is a very complex heterogeneous network, enabling seamless integration of these things is a huge challenge. A publish/subscribe method of integration can be formulated to solve the problems of interconnecting billions of heterogeneous things. In our work, an IoT framework that uses an abstraction layer that decouples an application from the service calls and network interfaces is required to send and receive messages on a particular thing. This paper provides definitions and classifications for heterogeneous data/events/services according to the properties of the things in order to integrate them into a framework for description. Based on these definitions and classifications, heterogeneous data/events/services in the IoT were integrated via topic description through the Data Distribution Service (DDS) middleware standard for real-time publish/subscribe. This paper also concludes with general remarks and a discussion of future work.

This paper presents a method for determining how close a neural network (and its design) is to the systems it is intended to represent and model. The output of this method is a normalized numerical value (an index) which can be compared to other indices. It can also be used to compare one artificial neural network with another. The objective is to develop a numerical index of quality that would make it possible to compare a variety of methods and computational techniques. A brief revisit to the concept from which this paper originated is presented in section 2 (where authors summarize the Statistical Index of Quality), and the outline of the Neural Network Index of Quality is shown in subsection 3.2. Subsection 3.3 illustrates sample calculations and comparisons with other similar methods for neural network evaluation. Finally, section 4 addresses certain implications and outlines future research in pursuit of automated quality analysis of computational techniques. As proposed, the method is effective to compare different computational techniques adequately, with results close to ‘1’ for well-designed networks and results close to ‘0’ for neural networks with possible design flaws. The proposed method is designed for fixed-size, supervised artifical neural networks.

BrainComputer Interface (BCI) systems analyze brain signals to generate control commands for computer applications or external devices. Utilized as alternative communication channel, BCIs have the potential to assist people with severe motor disabilities to interact with their environment and to participate in daily life activities. Handicapped people from all age groups could benefit from such BCI technologies. Although some papers have previously reported slightly worse BCI performance by older subjects, in many studies BCI systems were tested with young subjects only.In the presented paper age-associated differences in BCI performance were investigated. We compared accuracy and speed of a steady-state visual evoked potential (SSVEP)-based BCI spelling application controlled by participants of two different equally sized age groups. Twenty subjects (eleven female and nine male) participated in this study; each age group consisted of ten subjects, ranging from 19 to 27 years and from 64 to 76 years. Our results confirm that elderly people may have a deteriorated information transfer rate (ITR). The mean (SD) ITR of the young age group was 27.36 (6.50) bit/min while the elderly people achieved a significantly lower ITR of 16.10 (5.90) bit/min. The average time window length associated with the signal classification was usually larger for the participants of advanced age. These findings show that the subject age must be taken into account during the development of SSVEP-based applications.

In this paper, a self-organizing map (SOM) neural network is used to visualize corrective actions of failure modes and effects analysis (FMEA). SOM is a popular unsupervised neural network model that aims to produce a low-dimensional map (typically a two-dimensional map) for visualizing high-dimensional data. With regards to FMEA, it is a popular methodology to identify potential failure modes for a product or a process, to assess the risk associated with those failure modes, also, to identify and carry out corrective actions to address the most serious concerns. Despite the popularity of FMEA in a wide range of industries, two well-known shortcomings are the complexity of the FMEA worksheet and its intricacy of use. To the best of our knowledge, the use of computation techniques for solving the aforementioned shortcomings is limited. The use of SOM in FMEA is new. In this paper, corrective actions in FMEA are described in their severity, occurrence and detect scores. SOM is then used as a visualization aid for FMEA users to see the relationship among corrective actions via a map. Color information from the SOM map is then included to the FMEA worksheet for better visualization. In addition, a Risk Priority Number Interval is used to allow corrective actions to be evaluated and ordered in groups. Such approach provides a quick and easily understandable framework to elucidate important information from a complex FMEA worksheet; therefore facilitating the decision-making tasks by FMEA users. The significance of this study is two-fold, viz., the use of SOM as an effective neural network learning paradigm to facilitate FMEA implementations, and the use of a computational visualization approach to tackle the two well-known shortcomings of FMEA.

The paper investigates application of several methods of feature selection to identification of the most important genes in autism disorder. The study is based on the expression microarray of genes. The applied methods analyze the importance of genes on the basis of different principles of selection. The most important step is to fuse the results of these selections into common set of genes, which are the best associated with autism. These genes may be treated as the biomarkers of this disorder and used in early prediction of autism. The paper proposes and compares three different methods of such fusion: purity of the clusterization space, application of genetic algorithm and random forest in the role of integrator. The numerical experiments are concerned with the identification of the most important biomarkers and their application in autism recognition. They show the applied fusion strategy of many independent selection methods leads to the significant improvement of the autism recognition rate.

The main contributions in this paper are as follows:Neural-network-based observers are established for NMASs to recover the unknown system dynamics.Based on the observed states, an online optimal consensus controller is designed for each agent using ADP method.Only critic network architecture is adopted for each agent to reduce the computation load. This paper investigates optimal coordination tracking control for nonlinear multi-agent systems (NMASs) with unknown internal states by using an adaptive dynamic programing (ADP) method. Actually, the optimal coordination control for MASs depends on the solutions to the coupled HamiltonJacobiBellman (HJB) equations which are almost impossible to be solved analytically. And whats worse is that the accurate system models are either infeasible or difficult to obtain in practical applications. To surmount these deficiencies, a neural network (NN) based observer is designed for each agent to reconstruct its internal states by utilizing the measurable inputoutput data rather than accurate system models. Based on the observed states and Bellman optimality principle, we derive optimal coordination control policies from the coupled HJB equations. In order to implement the proposed ADP method, a critic network framework is proposed for each agent to approximate its value function and help calculate the optimal coordination control policy. Then we prove the local coordination tracking errors and weight estimation errors are uniformly ultimately bounded (UUB) while the approximated control policies converge to their target values. Finally, two simulation examples are given to show the effectiveness of the proposed ADP method.

The paper deals with the problem of a neural network-based robust state and actuator fault estimator design for non-linear discrete-time systems. It starts from a review of recent developments in the area of robust estimators and observers for non-linear discrete-time systems and proposes less restrictive procedure for designing a neural network-based H observer. The proposed approach guaranties a predefined disturbance attenuation level and convergence of the observer, as well as unknown input decoupling and state and actuator fault estimation. The main advantage of the design procedure is its simplicity. The paper presents an observer design procedure that is reduced to solving a set of linear matrix inequalities. The final part of the paper presents an illustrative example concerning an application of the proposed approach to the multi-tank system benchmark.

An efficient adaptive neural controller is firstly developed for a class of high order MJNSs with unmodeled dynamics and dead zone inputs.To the best of the authors knowledge, it is also the first control solution for the pure-Markovian jumping nonlinear systems. In this paper, all of the parameters and functions, no matter known or unknown, are allowed to vary with the switching modes.The computation load can be reduced because the number of the adaptive parameters is not related to the number of the switching modes or the order of the concerned system. This paper focuses on the adaptive control design for a class of high order Markovian jump nonlinear systems with unmodeled dynamics and unknown dead-zone inputs. The unknown parameter vector, the dynamic uncertainties, the unknown nonlinear functions and the actuator dead-zone nonlinearities are all allowed to be randomly varying with the Markovian modes. By introducing the bound estimation approach, the effect of randomly jumping unknown parameters and the varying dead-zone nonlinearities are tackled. Moreover, aiming at the unmodeled dynamics and completely unknown nonlinear functions which have Markovian jumping features, several two-layer neural networks (NNs) are introduced for each mode and the adaptive backstepping control law is finally established. The stochastic stability analysis for the closed-loop system are also performed. At last, a numerical example is provided to illustrate the efficiency and advantages of the proposed method.

In this paper we aim at tackling the problem of searching for novel and high-performing product designs. Generally speaking, the conventional schemes usually optimize a (multi) objective function on a dynamic model/simulation, then perform a number of representative real-world experiments to validate and test the accuracy of the some product performance metric. However, in a number of scenarios involving complex product configuration, e.g. optimum vehicle design and large-scale spacecraft layout design, the conventional schemes using simulations and experiments are restrictive, inaccurate and expensive.In this paper, in order to guide/complement the conventional schemes, we propose a new approach to search for novel and high-performing product designs by optimizing not only a proposed novelty metric, but also a performance function which is learned from historical data. Rigorous computational experiments using more than twenty thousand vehicle models over the last thirty years and a relevant set of well-known gradient-free optimization algorithms shows the feasibility and usefulness to obtain novel and high performing vehicle layouts under tight and relaxed search scenarios.The promising results of the proposed method opens new possibilities to build unique and high-performing systems in a wider set of design engineering problems.

This paper investigates the adaptive neural network optimal output feedback control design problem for nonlinear continuous-time systems with actuator saturation. The system dynamics and states of the controlled system are unknown. A neural network state observer is constructed to estimate the system states. This paper uses two neural networks, one is used to construct the neural network state observer, the other (critic neural network) is used to approximate the cost functions, which comprise an observer-critic architecture. In this architecture, the critic neural network weights are tuned based on both the current data and the previous data, thus the conditions of the persistent excitation in the previous literatures are relaxed. By utilizing adaptive dynamic programming approach, a new observer-based optimal control scheme is developed. It is proved that the proposed adaptive neural network output feedback optimal control scheme can ensure that the whole closed-loop system is stable. Moreover, the estimate errors of the critic neural network weights are asymptotically stable. A simulation example is given to validate the effectiveness of the proposed method.

The performance of many machine learning algorithms depends crucially on the hyperparameter settings, especially in Deep Learning. Manually tuning the hyperparameters is laborious and time consuming. To address this issue, Bayesian optimization (BO) methods and their extensions have been proposed to optimize the hyperparameters automatically. However, they still suffer from highly computational expense when applying to deep generative models (DGMs) due to their strategy of the black-box function optimization. This paper provides a new hyperparameter optimization procedure at the pre-training phase of the DGMs, where we avoid combining all layers as one black-box function by taking advantage of the layer-by-layer learning strategy. Following this procedure, we are able to optimize multiple hyperparameters in an adaptive way by using Gaussian process. In contrast to the traditional BO methods, which mainly focus on the supervised models, the pre-training procedure is unsupervised where there is no validation error can be used. To alleviate this problem, this paper proposes a new holdout loss, the free energy gap, which takes into account both factors of the model fitting and over-fitting. The empirical evaluations demonstrate that our method not only speeds up the process of hyperparameter optimization, but also improves the performances of DGMs significantly in both the supervised and unsupervised learning tasks.

In this paper, we study the cooperative output regulation problem for discrete-time linear time-delay multi-agent systems subject to jointly connected switching networks. Our distributed control law is composed of a purely decentralized control law and a distributed switched observer. In contrast to the same problem with static networks, the closed-loop system of this paper is a switched system, the stability analysis of the closed-loop system cannot be conducted by the existing frequency domain technique. Therefore, we need to establish two lemmas to lay the foundation for solving the problem and then present the solution to the problem by a distributed dynamic output feedback control law. An example is used to illustrate our approach.

To compact the architecture of extreme learning machine (ELM), two incremental learning algorithms are proposed in this paper. The previous incremental learning algorithms for ELM recruit hidden nodes randomly, which is equivalent to implementing a random selection from a candidate set of infinite size. Hence, it is impossible to recruit good hidden nodes, and thus it usually requires more hidden nodes than traditional neural networks to achieve matched performance. To improve the quality of the hidden nodes recruited, an incremental learning algorithm for ELM is presented based on Gram--Schmidt process (GSI-ELM), which recruits the best hidden node from a random subset of fixed size via defining an evaluating criterion at each learning step. However, the “nesting effect” exists in the GSI-ELM, that is to say, the hidden nodes once recruited by GSI-ELM can not be later discarded. To treat this “nesting problem”, the improved GSI-ELM (IGSI-ELM) is generated with an elimination mechanism. At each learning step IGSI-ELM eliminates the worst hidden node from the already-recruited group if it is not the newly-recruited one. Finally, to verify the efficacy and feasibility of the proposed algorithms, i.e. GSI-ELM and IGSI-ELM, in this paper, experiments on regression and classification benchmark data sets are investigated.

Multi-task learning employs a shared representation of knowledge for learning several instances of the same problem. Multi-step time series problem is one of the most challenging problems for machine learning methods. The performance of a prediction model face challenges for higher prediction horizons due to the accumulation of errors. Cooperative coevolution employs in a divide and conquer approach for training neural networks and has been very promising for single step ahead time series prediction. Recently, co-evolutionary multi-task learning has been proposed for dynamic time series prediction. In this paper, we adapt co-evolutionary multi-task learning for multi-step prediction where predictive recurrence is developed to feature knowledge from previous states for future prediction horizon. The goal of the paper is to present a network architecture with predictive recurrence which is capable of multi-step prediction through a form of multi-task learning. We employ cooperative neuro-evolution and an evolutionary algorithm as baselines for comparison. The results show that the proposed method provides the best generalization performance in most cases. Comparison of results with the literature has shown to be promising which motivates further application of the approach for related real-world problems.

The voice conversion system modifies the speaker specific characteristics of the source speaker to that of the target speaker, so it perceives like target speaker. The speaker specific characteristics of the speech signal are reflected at different levels such as the shape of the vocal tract, shape of the glottal excitation and long term prosody. The shape of the vocal tract is represented by Line Spectral Frequency (LSF) and the shape of glottal excitation by Linear Predictive (LP) residuals. In this paper, the fourth level wavelet packet transform is applied to LP-residual to generate the sixteen sub-bands. This approach not only reduces the computational complexity but also presents a genuine transformation model over state of the art statistical prediction methods. In voice conversion, the alignment is an essential process which aligns the features of the source and target speakers. In this paper, the Mel Frequency Cepstrum Coefficients (MFCC) based warping path is proposed to align the LSF and LP-residual sub-bands using proposed constant source and constant target alignment. The conventional alignment technique is compared with two proposed approaches namely, constant source and constant target. Analysis shows that, constant source alignment using MFCC warping path performs slightly better than the constant target alignment and the state-of-the-art alignment approach. Generalized mapping models are developed for each sub-band using Radial Basis Function neural network (RBF) and are compared with Gaussian Mixture mapping model (GMM) and residual selection approach. Various subjective and objective evaluation measures indicate significant performance of RBF based residual mapping approach over the state-of-the-art approaches. HighlightsThe LSF fails to represent formant valleys but good for formant peaks. Hence, calculated warping path is not satisfactory to yield a better alignment.This LSF based warping overcome through a new alignment using MFCC based warping path, which improves the conversion performance of proposed system.Further, the existing techniques for mapping the LP-residual suffer from issues of artifacts generated in consecutive frames. The residual signal is also quite complex to map.In order to solve the high dimensionality issue of residual signal is reduced and the complexity of the model is decreased, the WPT and RBF pairs are employed.The experimental results prove that the proposed MFCC based warping path and the WPT-RBF based transformation for residual signal outperforms the state of the art methods of residual selection and GMM model.

Population coding has been established as the key mechanism for decoding sensory information received from periphery organs such as retinas and cochlear. In this paper a novel architecture is presented to embed population coding in neuromorphic hardware. A resonance based mechanism between two layers of neuron is utilized in the presented work. The mechanism discussed in this paper facilitates selective triggering of higher layer neurons which serves as target ensemble for evaluation of a particular input of interest. It has been shown that presented model can be used to detect any physical quantity (light intensity, temperature, etc.) feed to the sensor on the basis of population coding.

This paper investigates the time-optimal state-feedback stabilization of switched Boolean control networks (SBCNs). Based on the properties of the semi-tensor product (STP) of matrices, a technique is proposed to merge the switching signal and all inputs of subnetworks into a single input variable. This technique allows us to transfer a SBCN to an equivalent non-switching logical control network (LCN) and eases the analysis and design process significantly. So long as a state-feedback stabilizer is obtained for the resulting non-switching LCN, it can then be decomposed uniquely into the respective state feedbacks of the sub-networks and the state-dependent switching law. Based on this technique, the controllability and stabilisability of such SBCNs are solved and an algorithm for finding all time-optimal switching state feedbacks is proposed. An example is described to illustrate the main results and the design process proposed in this paper.

The paper presents a subspace neuro-fuzzy system with ordering of data items.The system assigns fuzzy weights to attributes in each fuzzy rule.The ordering technique makes the system robust to outliers.The presented system can outperform a subspace neuro-fuzzy system for noisy data. Neuro-fuzzy systems are known for their ability to both approximate and generalize presented data. In real life data sets not always all attributes (dimensions) of data are relevant or have the same importance. Some of them may be noninformative or unnecessary. This is why subspace technique is applied. Unfortunately this technique is vulnerable to noise and outliers that are often present in real life data. The paper describes a subspace neuro-fuzzy system with data ordering technique. Data items are ordered and assigned with typicalities. Data items with low typicalities have lower influence on the elaborated fuzzy model. This technique makes fuzzy models more robust to noise and outliers. The paper is accompanied by numerical experiments on real life data sets.

Recently, sparse representation has been applied in object tracking successfully. However, the existing sparse representation captures either the holistic features of the target or the local features of the target. In this paper, we propose a dual-scale structural local sparse appearance (DSLSA) model based on overlapped patches, which can capture the quasi-holistic features and the local features of the target simultaneously. This paper first proposes two-scales structural local sparse appearance models based on overlapped patches. The larger-scale model is used to capture the structural quasi-holistic feature of the target, and the smaller-scale model is used to capture the structural local features of the target. Then, we propose a new mechanism to associate these two scale models as a new dual-scale appearance model. Both qualitative and quantitative analyses on challenging benchmark image sequences indicate that the tracker with our DSLSA model performs favorably against several state-of-the-art trackers.

This paper concerns with the global Lagrange stability of inertial neural networks with discrete and distributed time-varying delays. By choosing a proper variable substitution, the inertial neural networks can be rewritten as a first-order differential system. Based on the Lyapunov functional method, inequality techniques and analytical method, several sufficient conditions are derived to guarantee the global exponential stability of the inertial neural networks in Lagrange sense. Meanwhile, the global exponential attractive set is also given. Simulation results demonstrate the effectiveness of the theoretical results. HighlightsNeural networks with the inertial terms are discussed.Lagrange stability is investigated.Inertial neural networks with discrete and distributed time delay are studied.The neuron activation function discussed in the paper is neither bounded nor monotonically non-decreasing.

In this paper, a decentralized fault tolerant control (DFTC) scheme is proposed for a class of large-scale nonlinear systems based on self-tuned local feedback gain against partial loss of actuator effectiveness (PLOAE). Consider a large-scale nonlinear system as a set of interconnected subsystems, a decentralized control method is proposed by employing two radial basis function neural networks (RBFNNs) for the fault-free system. Then, the unknown system is identified using RBFNNs. By establishing a decentralized observer, the derived self-tuned local feedback gain is placed before the proposed decentralized controller to guarantee control performance for the subsystem suffering from PLOAE fault. Finally, simulation examples are provided to demonstrate the effectiveness of the present DFTC scheme. The main contributions of this paper are: i) The unknown large-scale nonlinear system can be identified using locally measured states, so the actuator fault can be handled in its local subsystem. It implies that the performance degradation of the faulty subsystem cannot affect the fault-free subsystems. ii) The estimated effectiveness factor is placed before the proposed decentralized scheme. The fault tolerant control structure is simple since it does not need to be redesigned in the case of PLOAE.

How to extract proper features is very important for synthetic aperture radar (SAR) target configuration recognition. However, most of feature extraction methods are hand-designed and usually can not achieve a satisfactory performance. In this paper, we propose a novel method based on the biologically inspired model to extract features automatically from limited data. Specifically, we learn episodic features (containing the key components and their spatial relations) and semantic features (i.e., semantic descriptions of the key components) which are two important types of features for the human cognition process. Episode features are learned through a deep neural network (DNN) and then semantic geometric features of the key components are defined. Moreover, SAR images are very sensitive to aspect angles. Therefore, we use episode features to estimate aspect angles of testing samples for the final recognition. This paper is a preliminary study and the preliminary experimental results on the moving and stationary target automatic recognition (MSTAR) database demonstrate the effectiveness of the proposed method.

This paper investigates the generalized matrix projective outer synchronization (GMPOS) between two non-dissipatively coupled time-varying complex dynamical networks via open-plus- closed-loop dynamical compensation controllers. To be more consistent with the real-world networks, besides non-dissipatively couplings, the drive and response networks in our paper can possess different nodes, different time-varying outer coupling configuration matrices and different nonlinear inner coupling functions. Thus, our network models are more general and extensive than almost all of those in the existing literatures about outer synchronization of networks. In order to make our drive and response networks realize the GMPOS, the open-plus-closed-loop dynamical compensation controllers are designed based on the Lyapunov stability theory and Barbalat's lemma. Moreover, the speed of achieving the GMPOS between two networks can be improved by adjusting the parameters in our dynamical compensation systems. A simulation example with different hyperchaotic nodes is given to verify the effectiveness and feasibility of our theoretical results.

In this paper, an adaptive prescribed performance control problem is studied for a class of switched uncertain nonlinear systems under arbitrary switching signals. Radial basis function neural networks (RBFNNs) are employed to approximate the unknown terms. By introducing the transformation errors, the original system with prescribed performance constraints are transformed into a class of new systems without constraints. Then, we design controllers to stabilize the transformed system. In this way, the original system is stabilizable and the prescribed performance is guaranteed. Update laws are designed such that the parameter estimation is fixed until its corresponding subsystem is active. Compared with the existing results, the main contributions of this paper are characterized as follows: (1) a PPC approach is proposed for a class of switched uncertain nonlinear systems in a general form and (2) RBFNNs are used to approximate the unknown terms of each subsystem. In the end, a simulation example is developed to illustrate the effectiveness of the present approach.

The attention of this paper is mainly concentrated on the H ∞ state estimator's design problem for a kind of discrete-time memristive neural networks (MNNs) with multiple fading measurements. The phenomenon of multiple fading measurements is represented by a set of individual stochastic variables obeying a predetermined distribution on interval 0,1. Firstly, the augmented system comprised of MNNs and the dynamics of estimation errors are put forward to implement the performance analysis. Then, under the framework of the difference inclusion theory combined with the Lyapunov function method, several sufficient conditions are established to guarantee the exponential mean-square stability as well as H ∞ performance index. Furthermore, the desired estimator parameter is obtained in view of the solution of a convex optimization problem. In the end, an illustrative numerical example is exploited to check the reliability and usefulness of the design scheme in this paper.

[EN] This paper presents an approach of a social emotional model, which allows to extract the social emotion of a group of intelligent entities. The emotional model PAD allows to represent the emotion of an intelligent entity in 3-D space, allowing the representation of different emotional states. The social emotional model presented in this paper uses individual emotions of each one of the entities, which are represented in the emotional space PAD. Using a social emotional model within intelligent entities allows the creation of more real simulations, in which emotional states can influence decision-making. The result of this social emotional mode is represented by a series of examples, which are intended to represent a number of situations in which the emotions of each individual modify the emotion of the group. Moreover, the paper introduces an example which employs the proposed model in order to learn and predict future actions trying to influence in the social emotion of a group of people., This work is partially supported by the MINECO/FEDER TIN2015-65515-C4-1-R and the FPI grant AP2013-01276 awarded to Jaime-Andres Rincon.

This paper is concerned with the passivity problem for neural networks with leakage delay and time-varying transmission delay. Using some novel Lyapunov-Krasovskii (L-K) functionals, and combining with the Wirtinger integral inequality, some less conservative delay-dependent passivity conditions are proposed in terms of linear matrix inequalities (LMIs). Different from the existing approaches, the model transformation is abandoned in this paper, and the proposed L-K functionals incorporate the interconnected terms related to both the leakage delay and the time-varying delay. Numerical examples show that the obtained conditions are less conservative.

In this paper, a new design problem of the H ∞ state estimator is developed for a kind of artificial neural networks (ANNs), where both infinite distributed delays and redundant channels are happening. These adopted redundant channels can effectively improve the reliability of networked systems from the viewpoint of engineering. Two series of stochastic variables satisfying Bernoulli distribution, are introduced to govern the infinite distributed delays and schedule the redundant channels. By utilizing both stochastic analysis and Lyapunov functional approach, we obtain a lot of sufficient conditions to ensure the desired H ∞ performance, while the mean-square stability is also satisfied for this investigated state estimation issues of ANNs. The needed estimator gains are designed making use of the matrix inequalities' solution. In final, a simulation is showed to demonstrate the effectiveness and usefulness of the developed state estimator in this paper.

This paper addresses the trajectory-tracking control problem of mobile robot systems with nonholonomic constraints, in the presence of time-varying parametric uncertainties and external disturbances. This necessitates an accurate controller to meet as much control objectives, as possible. Therefore, this paper deals with an artificial intelligence control technique to design a robust controller to meet the control objectives. The design of the intelligent controller is based on the optimal control theory, the adaptive neural network system, and the robust control technique. The trajectory-tracking problem is solved using the optimal control methodology. Since the nonholonomic wheeled mobile robot is strongly nonlinear, the neural network system is applied to approximate the nonlinear function in the optimal control law. The robust controller, for his part, is then applied to adaptively estimate an unknown upper bound of the time-varying parametric uncertainties, external disturbances and approximation error of the neural network system. The stability of the closed-loop robot system is proven using the optimal control theory and Lyapunov stability analysis. The results of the simulation studies on three typical nonholonomic mobile robots are provided to demonstrate the effectiveness of the proposed controller. In addition, a comparative study with a recent robust adaptive controller shows that our proposed intelligent controller gives better results, in the sense that the output trajectory converges to the steady state faster with smaller tracking error.

With the advance of multimedia and pattern recognition based medical technologies, smart medical applications in smart hospital and smart medical for individual, such as disease diagnosis and health monitoring, play an important role in our life. However, the communication infrastructure of supporting these applications is a challenge. This paper studies the energy-efficient multicast routing problem in multi-hop wireless networks for these medical applications. Energy consumption has become the main problem of sustainable development of communication networks, particularly for these applications. How to carry out high energy-efficient communication is an important research topic for wired and wireless networks to implement green communications. This paper proposes an energy-efficient multicast routing approach to multi-hop wireless networks for smart medical applications. Different from previous methods, we aim at maximizing energy efficiency of networks. To this end, we make use of topology control and sleeping mechanism to obtain the optimal routing strategy with maximum network energy efficiency to construct the network multicast route. Simulation results show that the proposed approach is effective and feasible.

This paper concentrates on the input-to-state stability problem for a class of memristor-based complex-valued neural networks with time delays. Different from the input-to-state stability criteria of real-valued neural networks, several new stability criteria of complex-valued neural networks are proposed by utilizing the Lyapunov function method, the differential inclusions theory and set-valued maps. The obtained results generalize some existing literature about real-valued neural networks as special conditions. A numerical example is presented to demonstrate the effectiveness of our theoretical results. HighlightsThe paper concentrates on the input-to-state stability of memristor-based complex-valued neural networks with time delays.Several new stability criteria are proposed by utilizing the Lyapunov function, differential inclusions theory and set-valued maps.The obtained results generalize some existing literature about real-valued neural networks as special conditions.

This paper addresses the problem of pose estimation in video sequences in which human pose changes drastically over time. Popular strategies for video pose estimation first yield multiple pose candidates for each frame and then achieve consistent pose estimation by enforcing temporal constraints across frames. To enrich pose candidates, previous methods typically employ local motion cues to propagate pose detections to adjacent frames. Reasonable pose proposals can be achieved only when the local motion estimation is accurate and good detections exist among adjacent frames, both of which are hard to be satisfied under drastic human pose changes. In this paper, we propose to propagate pose detections to entire video sequence through global motion cues which provide a long term holistic non-rigid motion transformation for the given video. We exploit the temporal continuity of both single parts and part pairs in the inference over a spatio-temporal model to stitch the reasonable trajectory fragments for each part and obtain the final pose estimation. Experimental results demonstrate remarkable performance improvement in comparison with the state-of-the-art methods.

Dictionary learning has played an important role in the success of sparse representation. Although discriminative synthesis dictionary learning for sparse representation with a high-computational-complexity l0 or l1 norm constraint has been well studied for image classification, jointly and discriminatively learning an analysis dictionary and a synthesis dictionary is still in its infant stage. As a dual of synthesis dictionary, the recently developed analysis dictionary can provide a complementary view of data representation, which can have a much lower time complexity than sparse synthesis representation. Although several class-specific analysis-synthesis dictionary, which may have a big correlation between different classes' dictionaries, have been developed, how to learn a more compact and discriminative universal analysis-synthesis dictionary is still open. In this paper, to provide a more complete view of discriminative data representation, we propose a novel model of discriminative analysis-synthesis dictionary learning (DASDL), in which a linear classifier based on the coding coefficient is jointly learned with the dictionary pair, thus the performance of the classifier and the representational power of the dictionary pair being considered at the same time by the same optimization procedure. The size of the learned dictionaries can be very small since the analysis-synthesis dictionary is shared by all class data. An iterative algorithm to efficiently solve the proposed DASDL is presented in this paper. The experiments on face recognition, gender classification, action recognition and image classification clearly show the superiority of the proposed DASDL.

With the advent of multimedia and pattern recognition based medical technology, intelligence medical applications in smart hospital, smart clinic, and smart medical for Individual, such as disease diagnosis, rehabilitation, health monitoring, and so on, have received extensive attentions. However, the communication infrastructure of supporting these applications is facing a larger challenge. This paper studies the channel allocation problem in cognitive wireless networks for these medical applications. Channel allocations are of importance for cognitive wireless networks. How to assign the appropriate channels to each cognitive user is fairly challenging. In this paper we study this problem by combining collaborations of network nodes. We take the maximum network connectivity as an optimal objective to build our collaborative channel allocation model. Our approach takes in account the channel idle status and the transmission radiuses of cognitive users. We allocate firstly the idle channel to bottleneck node and assign the suited channels to all other cognitive users as possible. In such a way, we present three channel allocation strategies with the maximum network connectivity via the omni-directional and direction antennas. We also propose the corresponding algorithm to perform the channel allocation for all cognitive users in cognitive wireless networks. Simulation results show that our approach is promising.

Abnormal event detection in video surveillance is extremely important, especially for crowded scenes. In recent years, many algorithms have been proposed based on hand-crafted features. However, it still remains challenging to decide which kind of feature is suitable for a specific situation. In addition, it is hard and time-consuming to design an effective descriptor. In this paper, video events are automatically represented and modeled in unsupervised fashions. Specifically, appearance and motion features are simultaneously extracted using a PCANet from 3D gradients. In order to model event patterns, a deep Gaussian mixture model (GMM) is constructed with observed normal events. The deep GMM is a scalable deep generative model which stacks multiple GMM-layers on top of each other. As a result, the proposed method acquires competitive performance with relatively few parameters. In the testing phase, the likelihood is calculated to judge whether a video event is abnormal or not. In this paper, the proposed method is verified on two publicly available datasets and compared with state-of-the-art algorithms. Experimental results show that the deep model is effective for abnormal event detection in video surveillance.

Remote medical resources configuration and management involves complex combinatorial Multi-Objective Optimization problem, whose computational complexity is a typical NP problem. Based on the MOEA/D framework, this paper applies the two-way local search strategy and the new selection strategy based on domination amount and proposes the IMOEA/D framework, following which each individual produces two individuals in mutation. In this paper, by using a new selection strategy, the parent individual is compared with two mutated offspring individuals, and the more excellent one is selected for the next generation of evolution. The proposed algorithm IMOEA/D is compared with eMOEA, MOEA/D and NSGA-II, and experimental results show that for most test functions, IMOEA/D proposed is superior to the other three algorithms in terms of convergence rate and distribution.

With the increasing public consciousness in environmental protection, the green partner selection problem (G-PSP) is an important issue in virtual enterprises. In this paper, the green criterion is introduced to partner selection problem (PSP), and a green partner selection model based on six criteria is proposed. As PSP has been proven to be an NP problem, and G-PSP cannot be solved in reasonable time by traditional methods. In this paper, an improved algorithm I-GSA/PSO that combines gravitational search algorithm and particle swarm optimization is developed to solve G-PSP in virtual enterprises. Experimental results show that I-GSA/PSO is effective and outperforms other evolutionary algorithms in solving G-PSP.

Rolling bearings are necessary parts in rotary machines. However, the problem of early fault diagnosis for rolling bearings is difficult to solve due to its low signal-to-noise ratio and non-linear and non-stationary signal. Based on a detailed investigation of rolling bearing vibration signals, this paper proposes a method for determining whether a fault occurs by comparing the high-frequency band power. If a fault occurs, we first de-noise the vibration signals using wavelet de-noising and then extract the fault characteristics in both the time domain and the time-frequency domain to avoid the limitations of using only one domain. Finally, the fault location is identified using the grey correlation method. According to the method application results, the recognition accuracy using the method proposed in this paper is satisfactory, proving that the method has superior performance.

In this paper, energy consumption of an office building is predicted based on echo state networks (ESNs). Energy consumption of the office building is divided into consumptions from sockets, lights and air-conditioners, which are measured in each room of the office building by three ammeters installed inside, respectively. On the other hand, an office building generally consists of several types of rooms, i.e., office rooms, computer rooms, storage rooms, meeting rooms, etc., the energy consumption of which varies in accordance with different working routines in each type of rooms. In this paper, several novel reservoir topologies of ESNs are developed, the performance of ESNs with different reservoir topologies in predicting the energy consumption of rooms in the office building is compared, and the energy consumption of all the rooms in the office building is predicted with the developed topologies. Moreover, parameter sensitivity of ESNs with different reservoir topologies is analyzed. A case study shows that the developed simplified reservoir topologies are sufficient to achieve outstanding performance of ESNs in the prediction of building energy consumption.

The person re-identification is an active research branch of the computer vision and attracts many researchers study on it. However, because of the variance in viewpoints, illumination, pedestrians' pose and some of other factors, building a robust person re-identification algorithm in open-world is rather challenging. In this paper, we propose two algorithms, indiscriminative patches trim strategy and multi-instance multi-label learning method, to fix the person re-identification in closed short-term surveillance network. There are two main contributions of this paper: first, we define the discriminative region in a person's image. Correspondingly, an adapted canopy-kmeans algorithm is proposed to evaluate the discriminability of image patches which form the discriminative regions. Besides, two strategies, in local image and in global gallery dataset, are proposed to filter out distractions. Finally, the true discriminative patches are employed to compute the similarity between two images, and then used to re-identify pedestrians. Second, we first introduce the multi-instance multi-label learning methods into re-identification, and hence we propose a framework of solving person re-identification by applying MIMLL. We employ two MIMLL methods, the MIMLBOOST and the MIMLSVM, to detect attributes in each image, and those detected attributes contribute to recognize different pedestrians. Experiments on two benchmark datasets show the competitive performance of the two proposed algorithms.