Search

In this paper, a novel control scheme is developed to solve an optimal containment control problem of unknown continuous-time multi-agent systems. Different from traditional adaptive dynamic programming (ADP) algorithms, this paper proposes an internal reinforcement ADP algorithm (IR-ADP), in which the internal reinforcement signals are added in order to facilitate the learning process. Then a distributed containment control law is designed for each agent with the internal reinforcement signal. The convergence of this IR-ADP algorithm and the stability of the closed-loop multi-agent system are analyzed theoretically. For the implementation of the optimal controllers, three neural networks (NNs), namely internal reinforcement NNs, critic NNs and actor NNs, are utilized to approximate the internal reinforcement signals, the performance indices and optimal control laws, respectively. Finally, some simulation results are provided to demonstrate the effectiveness of the proposed algorithm.

In this paper, distributed consensus control protocols are given for linear multi-agent systems with input delay under direct communication graphs. Compared with the multi-agent systems under continuous communication, there are more challenges in the consensus problems of multi-agent systems under discontinuous communication. Furthermore, the consensus of multi-agent systems with control input delay and discontinuous communication are much more similar to the practical engineering situation, which further increases the difficulties of consensus control. Based on these discussions, two consensus problems, including leader following case and leaderless case, are studied in this paper. A prediction of the system’s state information over the delay time is approximated by the zero input solution of the agent system model. We also propose a new discontinuous communication mode, which combines event triggered mechanism and a uniform quantization method. Unlike the existing discontinuous communication method, our proposed control protocols ensure that each agent decides when to transport its state information to its neighbors such that continuous communication between any two agents is no longer needed. In addition, through the non-smooth analysis of the closed-loop systems, the uniformly bounded consensus results are guaranteed, and the bound of the consensus error can be adjusted by choosing appropriate parameters.

Implementing associative memory experiments with nanoscale memristors is an interesting subject, which can allow robots to mimic human thinking. This paper is concerned with a new emotion model of memristor-based neural network and its circuit implementation. The model has three inputs and two outputs, which can feel happy when it receives good news or feel sad when it receives bad news. Unknown news can be recognized through associative memory, which simulates human emotions. Associative learning and three kinds of forgetting process together make up the full-function emotion model. In addition, the Ag/AgInSbTe/Ta-based model closely related to the actual physical properties of memristors is used to design synaptic structures. The circuits of memristor-based neural networks are also simplified. Furthermore, the new emotion model is able to adjust the changing rate of emotion. The process reflects the fact that humans learn the same thing faster at the second time, compared with the first time. Finally, PSPICE is used to simulate all the circuits of the emotion model. The presented emotion model in this paper offers more possibilities for designing intelligent machines.

Deep learning technologies have been rapidly developing recently. They have shown excellent performances in many fields. However, deep learning networks have weak adaptability to small sample sizes. Usually, deep learning networks require tens of thousands of samples to avoid overfitting. In contrast, the kernel method can deal with small sample sizes. In this paper, we use only dozens of samples to train a successful classifier. Deep multiple kernel learning (DMKL) has emerged in recent years. It combines the ideas of deep learning and multiple kernel learning. Unfortunately, the DMKL network with a fixed structure cannot adapt to data of different dimensions and sizes. Therefore, in this paper, we propose a novel depth-width-scaling multiple kernel learning (DWS-MKL) algorithm. It has the ability to adjust the architecture according to the input data. We optimize the estimation of leave-one-out error by using the span bound instead of the dual objective function. Finally, we choose a large number of data sets from the UCI benchmark data sets for classification tasks. We also evaluate DWS-MKL on the MNIST data set. The experimental results show that different frameworks have different performances on the same dataset. Our DWS-MKL algorithm obtains better classification results than the state-of-the-art kernel learning algorithms, as determined by a thorough comparison. The encouraging results demonstrate that our method has the potential to improve generalization performance of the model.

This paper develops a robust adaptive neural practical fixed-time tracking control scheme for Euler-Lagrange systems (ELSs) with unknown dynamics and external disturbances under input saturations. A novel auxiliary dynamic system governed by a smooth piecewise continuous function is constructed to handle the input saturation effect, while promoting to achieve the fixed-time convergence of tracking errors. Moreover, the unknown dynamics of ELSs and the bound vector of unknown external disturbances are synthesized into a compounded uncertain vector in this paper. Here, adaptive neural networks with the ∊-modification updating laws are employed to only approximate the compounded uncertain vector, rather than each dynamic matrix of ELSs, such that the computational burden of the developed control scheme is significantly reduced. It is theoretically proven that the trajectory tracking is able to be achieved in a fixed time under the developed adaptive neural tracking control scheme, while all signals in the Euler-Lagrange closed-loop tracking control system are bounded. The simulation results on a 2-link robotic manipulator are included to illuminate the effectiveness of our developed tracking control scheme and superiority to a finite-time control scheme.

This paper focuses on state estimation problem for discrete-time high-order neural networks with time-varying delays. First, the delay-dependent global exponential stability criterion of the error system is derived. Then, the state observer is designed by using the generalized inverse theory of matrices. Last, two numerical examples are given to illustrate the validity of the theoretical results. The method proposed in this paper has two advantages: (i) it is directly based on the definitions of global exponential stability and Moore–Penrose inverse of matrix, which avoids the construction of Lyapunov–Krasovskii functional; (ii) the obtained stability criteria contain only several simple matrix inequalities, which are easier to solve. More valuable, this paper fills in the gaps in designing state observers for discrete-time high-order neural network models.

In this paper, we study multi-agent systems with asymmetric information structure. Due to limited channel capacity in communication network, the information in routing path suffers a transmission delay. Instead of the game theoretic setting, we formulate the problem as an online quadratic optimization problem subject to stochastic systems involving input delay. Since the probability statistics of system noise is unknown, the decision-maker can not utilize the traditional optimal control strategies. Motivated by online convex optimization theory, we introduce the notion of regret, which measures the cumulative performance difference between the optimal statistics known (offline) index value and the statistics unknown (online) index value. The contributions of this paper are twofold. First, utilizing the linear minimum mean square biased estimate, we derive a learning based control policy and then characterize its behavior. Second, under some basic assumptions, we further prove that the regret grows at a sub-linear rate and it is explicitly bounded by O ( ln T ) .

Adversarial networks have been used to learn transferable representations in many domain adaptation methods. However, there is no theoretical guarantee that two distributions are identical, even if the discriminator is fully confused. Therefore, a more elaborate domain adversarial method to better align distributions is desirable. In this paper, we propose two groups of multiple adversarial networks for domain-invariant and class-distinguishable feature learning: i) class-wise domain adversarial networks based on sample locations and ii) sample adversarial networks. We analyze the impact of the sample’s intra-class distribution on transfer learning and reveal that the distance between a sample and its cluster center affects the role of that sample in transfer learning. Domain adversarial learning is conducted separately on samples located near the cluster center (central samples) and samples located far away from cluster center (non-central samples) in order to align the distributions of the source domain and target domain better. However, separate domain adversarial learning on central and non-central samples ignores the relationship between them, because all these samples belong to the same class. We therefore propose a method called sample adversarial learning to convert the distribution of non-central samples to the distribution of central samples. In this way, the relationship between central samples and non-central samples is rebuilt. Sample adversarial learning solves the problem that arises in the sperate domain adversarial learning. Sample adversarial learning also enables us to obtain a class-distinguishable feature representation because of the reduction in intra-class distance. Experimental results show that our method extracts more transferable and class-distinguishable features than existing methods and achieves start-of-the-art results on several datasets. The significant contribution of this paper is to show how separate domain adversarial learning based on sample locations and sample adversarial learning together enhance positive transfer by maximally matching the multimodal structures underlying the data distributions across domains.

Person reidentification (ReID) refers to the task of verifying the identity of a pedestrian observed from nonoverlapping views in a surveillance camera network. It has recently been validated that reranking can achieve remarkable performance improvements in person ReID systems. However, current reranking approaches either require feedback from users or suffer from burdensome computational costs. In this paper, we propose to exploit a density-adaptive smooth kernel technique to achieve efficient and effective reranking. Specifically, we adopt a smooth kernel function to formulate the neighbor relationships among data samples with a density-adaptive parameter. Based on this new formulation, we present two simple yet effective reranking methods, termed \emph{inverse} density-adaptive kernel based reranking (inv-DAKR) and \emph{bidirectional} density-adaptive kernel based reranking (bi-DAKR), in which the local density information in the vicinity of each gallery sample is elegantly exploited. Moreover, we extend the proposed inv-DAKR and bi-DAKR methods to incorporate the available extra probe samples and demonstrate that when and why these extra probe samples are able to improve the local neighborhood and thus further refine the ranking results. Extensive experiments are conducted on six benchmark datasets, including: PRID450s, VIPeR, CUHK03, GRID, Market-1501 and Mars. The experimental results demonstrate that our proposals are effective and efficient., 39 pages, 18 figures and 12 tables. This paper is an extended version of our preliminary work on ICPR 2018

This paper addresses global Mittag-Leffler lag quasi-synchronization (GMLQS) of fractional-order memristor-based neural networks (FMNNs). Firstly, for a general class of fractional-order nonlinear systems with interval uncertainties, a kind of linear feedback pinning controller, which works by feeding back partial state errors to the partial controlled variables, is designed to achieve global Mittag-Leffler ultimate boundedness (GMUB). Correspondingly, a GMUB criterion in the form of linear matrix inequality (LMI) is derived with the aid of a Lyapunov function and a newly established fractional-order differential inequality. Then, the linear feedback pinning controller is employed for GMUB of the synchronization error system, which is equivalent to GMLQS of FMNNs. Since there exists the propagation delay between drive-response FMNNs and the synchronization error system can not be obtained straightforwardly, an identical equation about Caputo’s fractional derivatives is established to overcome this difficulty. Moreover, the detailed pinning control scheme design procedures for a prescribed GMLQS performance are presented, where the performance involves both ultimate error bound and transient behavior. In the control scheme, an auxiliary LMI and an optimization objective function are introduced, which can significantly reduce control cost. Finally, a numerical example is presented to show the feasibility of the control scheme. The results obtained in this paper have improved the existing criterion on quasi-synchronization of FMNNs, and will also provide a novel insight into pinning control of fractional-order nonlinear systems.

This paper investigates fault-tolerant tracking control problem for autonomous underwater vehicle (AUV) with rudders faults and ocean current disturbance. The adaptive dynamic programming (ADP) method is adopted to transform the fault-tolerant tracking control problem into an optimal control problem. Two neural-network estimators (NNEs) are designed to estimate rudders faults and ocean current disturbance respectively. The estimated rudders faults and the estimated ocean current disturbance are utilized to construct the performance index function. By using policy iteration (PI), critic neural network and action neural network are constructed to solve the Hamilton-Jacobi-Bellman (HJB) equation. The error tracking system of AUV is guaranteed to be uniformly ultimately bounded (UUB) based on the Lyapunov stability theorem. Simulation results are given to verify the effectiveness of the control scheme proposed in this paper.

The explosive growth of data leads researchers to waste time and energy to search for papers they need. Context-aware citation recommendation aims to solve this problem by analyzing a citation context and provides a list of recommended papers. In this paper, we propose a context-aware citation recommendation model based on end to end memory network. The model learns the representations of papers and citation contexts respectively based on bidirectional long short-term memory (Bi-LSTM). In particular, we jointly integrate author information and citation relationship in the distributed vector representations of citation contexts and papers. Then calculates the continuous relevance between them based on a computational multilayers memory network. We also conduct experiments on three real-world datasets to evaluate the performance of our model.

Face stands out as a preferable biometric trait for automatic human authentication as it is intuitive and non-intrusive. This paper investigates various feature-based automatic face recognition approaches in detail. High degree of freedom in head movement and human emotion leads a face recognition system to face critical challenges in terms of pose, illumination and expression. Human face also undergoes irreversible changes due to aging. These factors makes the process of face recognition non trivial and hard. This paper also provides a review of the facial recognition approaches individually dealing with these issues. Applications of face recognition in the forensic domain sometimes needs identification using a scanned facial image. The scenario is quite useful to get investigative leads. Important approaches for the same are also been discussed in the manuscript. Recent developments in the low-cost image capturing devices has flooded the facial image databases with a lot of images, at the same time availability of GPU based compute power has helped develop deep learning approaches to handle the face recognition at a very accurate and massive level. The same has also been surveyed and analyzed in the manuscript.

The property value assessment in the real estate market still remains as a challenges due to incomplete and insufficient information, as well as the lack of efficient algorithms. House attributes, such as size and number of bedrooms, are currently being employed to perform the estimation by professional appraisers and researchers. Numerous algorithms have been proposed; however, a better assessment performance is still expected by the market. Nowadays, there are more available relevant data from various sources in urban areas, which have a potential impact on the house value. In this paper, we propose to fuse urban data, i.e., metadata and imagery data, with house attributes to unveil the market value of the property in Philadelphia. Specifically, two deep neural networks, i.e., metadata fusion network and image appraiser, are proposed to extract the representations, i.e., expected levels, from metadata and street-view images, respectively. A boosted regression tree (BRT) is adapted to estimate the market values of houses with the fused metadata and expected levels. The experimental results with the data collected from the city of Philadelphia demonstrate the effectiveness of the proposed model. The research presented in this paper also provides the real estate industry a new reference to the property value assessment with the data fusion methodology.

In a localization environment based on wireless sensor networks, the non-line-of-sight (NLOS) propagation of wireless signal can greatly degrade the performance of the localization system. In this paper, a novel semidefinite-relaxation-based target localization method is presented by utilizing an adaptive threshold correction scheme. First, whether the measurement is in NLOS propagation is identified according to the prediction stage of extended Kalman filtering (EKF) algorithm. Then, the objective function and constraints are, respectively, constructed according to the measurement model of time of arrival (TOA) and received signal strength indicator (RSSI) ranging method. By employing the semidefinite relaxation method, the original problem is converted into the SDP problem, in which the corrected measurement information is obtained and thus the accuracy is improved. In addition, a correction method for NLOS propagation threshold is proposed by which an optimal threshold is obtained quickly. Different from the traditional simulation environment without the consideration of obstacles, in this paper, obstacles are set so as to make it closer to the engineering practice. Finally, the simulation results are given to show the superior performance of the proposed method.

Vision is the main way for people to perceive and recognize the world. In this paper, four categories of the redundant information of video encoding, spatial redundancy, time redundancy, visual redundancy and statistical redundancy, are first introduced. Spatial redundancy is redundant information existing in static frames, time redundancy is the luminance and chrominance correlation between adjacent frames in the video sequence, visual redundancy is information that the human visual system cannot perceive, statistical redundancy is the expression redundancy of the information source symbols. Then the performance assessment of video coding are introduced. And the future development of video coding and conclusion are finally discussed in this paper.

Manual annotation of video segmentation datasets requires an immense amount of human effort, thus, reduction of human annotation costs is an active topic of research. While many papers deal with the propagation of masks through frames of a video, only a few results attempt to optimize annotation task selection. In this paper we present a deep learning based solution to the latter problem and train it using Reinforcement Learning. Our approach utilizes a modified version of the Dueling Deep Q-Network sharing weight parameters across the temporal axis of the video. This technique enables the trained agent to select annotation tasks from the whole video. We evaluate our annotation task selection method by means of a hierarchical supervoxel segmentation based mask propagation algorithm.

Face recognition recently has achieved remarkable success in many fields, especially in mobile payment, authentication, criminal investigation, and city management. However, face occlusion is still the key problem in person identification, such as in the field of anti-terrorism, criminal cases and public security. To solve this problem, an improved end-to-end deep generative adversarial network (named EyesGAN) has been proposed to synthesize human face from human eyes in this paper, which can be used as a potential scheme for masked face recognition. BicycleGAN is chosen as the baseline and effective improvements have been achieved. First, the self-attentional mechanism is introduced so that the improved model can more effectively learn about the internal mapping between human eyes and face. Second, the perceptual loss is applied to guide the model cyclic training and help with updating the network parameters so that the synthesized face can be of higher-similarity to the ground truth face. Third, EyesGAN has been designed by getting the utmost out of the performance of the perceptual loss and the self-attentional mechanism in GANs. A dataset of eyes-to-face synthesis has been reconstructed based on the public face datasets for training and testing. Finally, the faces synthesized by EyesGAN have been quantitatively and qualitatively compared with the results of existing methods. Extensive experiments demenstrate that our proposed method has performed better than the state-of-the-art methods in terms of Average Euclidean Distance, Average Cosine Similarity, Synthesis Accuracy Percentage, Frechet Inception Distance, and Baidu face recognition rate (the accuracy achieved 96.1 % on 615 test data of CelebA database). In this paper, the feasibility of synthesizing human face from human eyes has been explored, and the attention map shows that our network can predict other parts of the face from eyes.

Since the multiobjective evolutionary algorithm based on decomposition (MOEA/D) was proposed by Zhang and Li in 2007, this interesting framework has attracted a considerable attention from researchers. In MOEA/D, a multiobjective optimization problem is decomposed into a series of aggregated subproblems, which are optimized simultaneously in a collaborative way by using the information from their neighboring subproblems. The decomposition approach has significant impact on MOEA/D as it directs the evolutionary search. Many improved MOEA/D variants proposed various kinds of decomposition approaches and have shown promising performance for different kinds of problems. In this paper, we give a survey of decomposition approaches, which are classified into five categories, i.e., the tradition decomposition, the modified Tchebycheff decomposition, the modified penalty-based boundary intersection decomposition, the constrained decomposition, and other special cases of decomposition. Moreover, discussions are further given in this paper to analyze the performance of different decomposition approaches. One clarifies the difference between Tchebycheff decomposition and Pareto-based domination. The other one compares the performance of various decomposition approaches on different benchmark problems. Experiments results have demonstrated that the Tchebycheff decomposition and its varieties are robust on solving most problems while some specific decomposition approaches are very effective for some problems with special features.

Cross-modal person re-identification(Re-id) under infrared light and visible light (RGB-IR) is of great significance for modern video surveillance, especially nighttime surveillance. The existing research results in the single-mode person re-identification field have reached a high level. Cross-model person re-identification, however, is rather challenging for the tremendous cross-modality and intra-modality difference in addition to common issues such as lighting conditions, human posture, camera angle, and etc..The Cross-modal Multi-granularity Attention Network (CMGN) proposed by this paper enables network to learn the common features of different modalities and map them to the same feature space. Major contributions made by this paper includes:1) A new ”butterfly” attention module that can be used for cross-modal tasks is designed to constrain the network attention to common areas of different modes. And in the RegDB and SYSU-MM01 dataset reached the effect of State-of-the-art(SOA). 2) An end-to-end multi-granularity feature fusion network dedicated to processing cross-modal problems is proposed.

CAPTCHA, Completely Automated Public Turing test to tell Computers and Humans Apart, is widely used as a security mechanism to classify human and computer. This security mechanism is based on the Turing Test, which has been conceived to ensure network security. Usability is another fundamental issue, which can avoid human users proceeding tedious and time-consuming operation. CAPTCHA design should consider security and usability simultaneously. This paper provides a review on the development of CAPTCHA technologies for human and computer classification, along with their applications and instantiations. Different from previous CAPTCHA survey, this review discusses the CAPTCHA mechanism from usability and security aspects, therefore attacking (anti-classification) and defending (classification) technologies towards current CAPTCHA are both reviewed. Besides, recent emerging CAPTCHA and the attacking techniques are also introduced in this paper, such as game CAPTCHA, deep learning-based attacking, and etc.

Hashing methods have been widely applied to approximate nearest neighbor search in large-scale image retrieval due to its fast search speed and efficient storage space. In practice, most images are with multiple category-aware objects, i.e., multi-label images. This paper focuses on hash code learning for multi-label image retrieval. Most existing hashing methods directly extract one patch such as a downsized crop from each image as a training example, which ignores the multi-label characteristic of images and leads to suboptimal representations for multi-label images. Some researches have proved that each multi-label image follows a multi-instance assumption, where each image is represented as a bag of category-aware proposals (instances). However, existing multiple-instance learning methods use predefined statistical functions with limited learning capability to construct bag features, and they are designed for classification or pairwise-similarity preserving. Thus, directly applying existing multiple-instance learning methods into deep hashing framework still leads to suboptimal hash codes for retrieval. In this paper, we pose hashing learning for multi-label image retrieval as a problem of multiple-instance ranking learning. To solve this problem, we present an end-to-end deep hashing framework, referred to as Deep Multiple-Instance Ranking based Hashing (DMIRH). In DMIRH, we design a category-aware bag feature construction module, which jointly assigns the learned instances into categories and aggregates the selected instance features into a bag feature representation that can capture the multi-label information of each image. In addition, we propose a novel learning objective, which consists of an Inner Product distance based quantization loss to control the hash quality and a listwise ranking loss to preserve the ranking relationships. Experimental results on public benchmarks show the superiority of DMIRH over several state-of-the-art hashing methods.

This paper is mainly concerned with fixed-time synchronization control for a class of Cohen–Grossberg neural networks (CGNNs) with nonlinear coupling and time-varying delay based on synchronization dynamics. First, by using a derived sufficient condition of fixed-time synchronization (FTS) for nonlinear coupled CGNNs (NCCGNNs) with time-varying delay, a novel fixed-time synchronization controller with time-varying delay is designed. Second, by combining the synchronization dynamic viewpoint and the obtained fixed-time synchronization control rule, several useful fixed-time synchronization controllers (FTSCs) are derived. Third, comparisons with known conclusions are provided to show the innovation and feasibility of the proposed fixed-time synchronization control methods. Finally, two examples are given to verify the effectiveness of the theoretical results. Compared with related works, the advantages of this paper are as follows: (1) The designed novel FTSCs can scientifically and efficiently process the time-varying delay of the addressed coupled CGNNs; (2) The derived settling time of the FTS built on FTSCs can reflect the effect of the proposed system’s parameters on the synchronization convergence time.

Brain–machine interface (BMI) is a useful technology which creates a new way for disable people to communicate with the world, but experimenting with human brains is risky. Hence, a precise mathematical model of the information transmission in the process of limb movement is necessary to be established. In this paper, firstly, we improve the classical single-joint information transmission (SJIT) model through introducing several neuron models, and the improved model is closer to the true single-joint movements. Secondly, a closed-loop system with a Wiener filter-based decoder, an auxiliary controller based on model predictive control (MPC) and a network of Izhikevich neurons is formulated based on the improved model, and the used network of Izhikevich neurons is more time efficient than the existing one. Finally, in this closed-loop system, the intracortical micro-stimulation (ICMS) technology is introduced to feedback the information from the MPC controller in real time. The auxiliary controller assist the brain to control artificial arm by changing the frequency of stimulation current. In this way, the computational complexity of the optimization problem proposed in this paper is greatly reduced, and the closed-loop BMI system designed in this paper can well track the desired trajectory.

Siamese network is highly regarded in the visual object tracking filed because of its unique advantages of pairwise input and pairwise training. It can measure the similarity between two image patches, which coincides with the principle of the matching-based tracking algorithm. In this paper, a variant Siamese network based tracker is proposed to introduce attention module into traditional Siamese network, and relocate the object with some auxiliary relocation methods, when the proposed tracker runs under an untrusted state. Firstly, a novel attention shake layer is proposed to replace the max pooling layer in Siamese network. This layer could introduce and train two different kinds of attention modules at the same time, which means the proposed attention shake layer could also help to improve the expression power of Siamese network without increasing the depth of the network. Secondly, an auxiliary relocation branch is proposed to assist in object relocation and tracking. According to the prior assumptions of visual object tracking, some weights are involved in the auxiliary relocation branch, such as structure similarity weight, motion similarity weight, motion smoothness weight and object saliency weight. Thirdly, a novel response map based switch function is proposed to monitor the tracking process and control the effect of auxiliary relocation branch. Furthermore, in order to discuss the effect of pooling layer in Siamese network, 9 pooling and attention architectures are proposed and discussed in this paper. Some empirical results are shown in the experiment part. Comparing with the state-of-the-art trackers, the proposed tracker could achieve comparable performance in multiple benchmarks.

In this paper, we first established the fractional order memristive multidirectional associative memory neural networks (FMMAMNNs) model, and then considered its fixed-time synchronization control problem. On the basis of sliding model control and Lyapunov stability theorem, a fractional order sliding mode controller is constructed. By adding this controller to the response system, the error of the driver-response systems gradually converges to 0 in a fixed time. Compared with the previous researches, this paper considers a more complex model, and the proposed control theories can ensure that the setting time is only related to the model and controller, but not to the initial states of the system. Besides, the control theories are also applicable to the integer order models. Finally, two numerical simulations are given, the results show the validity of the theories.

It is well known that weighted sum of node states plays an essential role in function implementation of neural networks. Therefore, this paper proposes a new weighted sum synchronization model for memristive neural networks. Unlike the existing synchronization models of memristive neural networks which control each network node to reach synchronization, the proposed model treats the networks as dynamic entireties by weighted sum of node states and makes the entireties instead of each node reach expected synchronization. In this paper, weighted sum complete synchronization and quasi-synchronization are both investigated by designing feedback controller and aperiodically intermittent controller, respectively. Meanwhile, a flexible control scheme is designed for the proposed model by utilizing some switching parameters and can improve anti-interference ability of control system. By applying Lyapunov method and some differential inequalities, some effective criteria are derived to ensure the synchronizations of memristive neural networks. Moreover, the error level of the quasi-synchronization is given. Finally, numerical simulation examples are used to certify the effectiveness of the derived results.

This paper introduces a new procedure to train Minimal Learning Machines (MLM) for regression tasks. Besides that, we propose a new prediction process in MLM. A well-known drawback concerning the (original) MLM model formulation is the lack of sparseness.The most recent efforts on this problem strongly rely on the selection of reference points before training and prediction steps in MLM, all based on some supposition regarding the data. In the opposite direction, here, we explore another formulation of MLM in which we do not rely on any assumption regarding the data for prior selection. Instead, our proposal, named Lightweight Minimal Learning Machine (LW-MLM), builds a regularized system that imposes sparseness. We thrive in such a sparse criterion, not by selection but instead using a piece of weighted information into the model. We validate the contributions of this paper through four types of experiments to evaluate different aspects of our proposal: the prediction error performance, the goodness-of-fit of estimated vs. measured values, the norm values which are related to the sparsity, and finally, the prediction error in high dimensional settings. Based on the results, we show that LW-MLM is a valid alternative since achieved similar or higher accuracy rates against other variants being all seen as statistically equivalent.

This paper is concerned with event-triggered generalized dissipative filtering for delayed neural networks under aperiodic denial-of-service (DoS) attacks. Note that DoS attacks impede the wireless communications on measurement from time to time. This paper aims at designing resilient filters against DoS attacks to estimate neuronal states in the sense of dissipative. For this goal, a switched filter is introduced to cope with DoS attacks and unavailability of state information. In order to save precious communication resources, an event-triggered communication scheme is devised to transmit only necessary information to the filter. With such setting, the filtering error system is modeled as a switched system with time-delay. By employing the piecewise Lyapunov–Krasovskii functional approach and linear matrix inequality techniques, some criteria on the existence of suitable filters are presented against aperiodic DoS attacks while suitable filtering performance can be ensured. It should be mentioned that since a generalized dissipative performance index is introduced, several kinds of resilient event-based filtering issues, such as H∞ filtering, passive filtering, mixed H∞ and passive filtering, (Q, S, R)-dissipative filtering are solved in a unified framework in the presence of aperiodic DoS attacks. Finally, a numerical example is given to illustrate the effectiveness of the proposed method.

In this paper, the H∞ filtering problem is addressed for a class of nonlinear stochastic discrete-time systems subject to Round-Robin protocol, measurement outliers, randomly occurring parameter uncertainties and randomly occurring nonlinearities. First of all, the considered system is influenced by the parameter uncertainties, nonlinear dynamics and external disturbances. Next, mutually independent Bernoulli-distributed white sequences are employed to describe the phenomena of randomly occurring parameter uncertainties and nonlinearities, respectively. Besides, the Round-Robin protocol is introduced to prevent the occurrence of data collisions during the signal transmission. Moreover, a filter with adaptive saturation is constructed to weaken the impact of the measurement outliers. Through constructing a suitable Lyapunov function, sufficient conditions are established to ensure that the error system dynamics is exponentially mean-square stable and satisfies the H∞ performance. Subsequently, the filter gains are designed by solving a set of linear matrix inequalities. Finally, a simulation example is given to show the effectiveness of the filtering scheme proposed in this paper.

An adaptive dynamic programming (ADP) based event-triggered control method is established in this paper to solve the optimal control problem of unknown continuous-time nonlinear systems with input constraints. First, the unknown system is identified using two neural networks (NNs). Second, the threshold for event-triggering condition is designed, which guarantees the system stability. Then, a critic NN is employed to approximate the value function and the closed-loop system is proved to be uniformly ultimately bounded. Finally, the simulation results demonstrate the feasibility of the developed ADP method. The main contributions of this paper are that the developed ADP-based event-triggered control method avoids the Zeno phenomenon effectively and updates the weights of three NNs simultaneously in the process of implementation. Meanwhile, an improved critic NN weight updating criterion is adopted, which does not require an initial admissible control.

Intelligent transportation is an indispensable part of the smart city and the primary development direction of the future transportation systems. Vehicle detection and recognition, which is one of the most important aspects of intelligent transportation, plays a very important role in various areas of our daily life; one such important area is criminal investigation. In the fine-grained vehicle type detection and recognition, several difficult issues such as problems in data acquisition and tagging, dramatic variance in the data of different vehicle types, and challenges in identifying vehicles of the same brand with highly similar appearances remain unsolved. For the problems of data acquisition and tagging, this paper presents a strategy for automatic data acquisition and tagging based on object detection that can label the vehicle images efficiently while rapidly acquiring all types of fine-grained models. Considering the problem of data imbalance in the training process, this paper proposes a Faster-RCNN based data equalizing strategy (Faster-BRCNN), thereby improving the performance of object detection. In view of the severe information attenuation caused by the feature information transfer obstruct between layers in the traditional deep learning network, the lack of mutual dependency of these features, and the inability of the network to focus on the important region and characteristics, we propose an intensive dense attention network (DA-Net). Through its intensive connection and attention unit, we enhance the model's detection ability. The proposed method achieves mAP of 94.5% and 95.8% in the Stanford Cars and FZU Cars datasets, respectively, thereby verifying its effectiveness.

This paper proposes an automatic visual inspection method for the fracture detection of clevises in the catenary systems of high-speed railways, using images of catenaries captured by an inspection vehicle. First, the clevises are extracted from the catenary image using a convolutional neural network based algorithm, known as the faster region-based convolutional neural network. Because the structure of catenary systems does not have many variations and the contextual information near a catenary fitting may have strong correlation with its category, the architecture of the original faster region-based convolutional neural network is modified to make use of the contextual information of the regions of interest in the images for object recognition. A crack detection process is then used to recognize the fractures of clevises. To detect the cracks, the edge map of the clevis sub-image is generated using a region-scalable fitting model. Areas where the cracks are most likely to occur are projected from a standard clevis image to the clevis sub-image by shape context matching and affine transformation matrix computation. The cracks are then recognized by calculating the wavelet entropy inside these areas followed by morphological filtering. Experimental results show that the modified faster region-based convolutional neural network architecture achieves better results in clevis extraction than the original architecture as well as some other state-of-art object detection models. The detection is not affected by the scaling, texture and grayscale changes of the clevises caused by the variation of shooting distance, shooting angle and illumination variations. The fractures of the clevises can be accurately and reliably detected using the fracture detection method proposed in this paper and the performance of this visual inspection method meets the strict requirements for catenary system maintenance.

The Cognitive Packet Network (CPN) bases its routing decisions and flow control on the Random Neural Network (RNN) Reinforcement Learning algorithm; this paper proposes the addition of a Deep Learning (DL) Cluster management structure to the CPN for Quality of Service metrics (Delay Loss and Bandwidth), Cyber Security keys (User, Packet and Node) and Management decisions (QoS, Cyber and CEO). The RNN already models how neurons transmit information using positive and negative impulsive signals whereas the proposed additional Deep Learning structure emulates the way the brain learns and takes decisions; this paper presents a brain model as the combination of both learning algorithms, RNN and DL. The proposed model has been simulated under different network sizes and scenarios and it has been validated against the CPN itself without DL clusters. The simulation results are promising; the presented CPN with DL clusters as a mechanism to transmit, learn and make packet routing decisions is a step closer to emulate the way the brain transmits information, learns the environment and takes decisions.

Facial landmarks are highly correlated with each other since a certain landmark can be estimated by its neighboring landmarks. Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks. In this paper, we propose a novel deep learning framework named Multi-Center Learning with multiple shape prediction layers for face alignment. In particular, each shape prediction layer emphasizes on the detection of a certain cluster of semantically relevant landmarks respectively. Challenging landmarks are focused firstly, and each cluster of landmarks is further optimized respectively. Moreover, to reduce the model complexity, we propose a model assembling method to integrate multiple shape prediction layers into one shape prediction layer. Extensive experiments demonstrate that our method is effective for handling complex occlusions and appearance variations with real-time performance. The code for our method is available at https://github.com/ZhiwenShao/MCNet-Extension., This paper has been accepted by Neurocomputing

This paper proposes a Neurocomputing application that reorders the Web results obtained from different Web Search Engines emulating the way our brain takes decisions. The proposed application is based on the Random Neural Network with Deep Learning Clusters that evaluates and adapts Web result relevance by associating independently each Deep Learning Cluster to a specific Web Search Engine. In addition, this paper presents a Deep Learning Cluster to perform as a Management Cluster that decides the final result relevance based on the inputs from each independent Deep Learning cluster. The performance of the proposed Management Cluster is evaluated when included as an additional layer to the Deep Learning Clusters. On average; the proposed Deep Learning cluster structure improves Smart Search performance.

This paper discusses a multi-player mixed-zero-sum (MZS) differential games with completely unknown dynamics. Based on off-policy integral reinforcement learning (IRL), a novel algorithm is proposed to obtain the optimal control. First, a policy iteration algorithm is put forward to obtain the optimal solution for deterministic system. Next, the case that the system dynamics is completely unknown is considered. And an IRL-based off-policy algorithm is presented. Meanwhile, the convergence of the presented algorithms is proved in this paper. At the end, the effectiveness of the proposed algorithm is shown by a simulation.

Feature selection plays an important role in reducing irrelevant and redundant features, while retaining the underlying semantics of selected ones. An effective feature selection method is expected to result in a significantly reduced subset of the original features without sacrificing the quality of problem-solving (e.g., classification). In this paper, a non-unique decision measure is proposed that captures the degree of a given feature subset being relevant to different categories. This helps to represent the uncertainty information in the boundary region of a granular model, such as rough sets or fuzzy-rough sets in an efficient manner. Based on this measure, the paper further introduce a differentiation entropy as an evaluator of feature subsets to implement a novel feature selection algorithm. The resulting feature selection method is capable of dealing with either nominal or real-valued data. Experimental results on both benchmark data sets and a real application problem demonstrate that the features selected by the proposed approach outperform those attained by state-of-the-art feature selection techniques, in terms of both the size of feature reduction and the classification accuracy.

The problem of event-triggered guaranteed cost consensus for nonlinear multi-agent systems with time delay and uncertain parameters is solved in this paper. First, a distributed event-triggered strategy is presented, by which control protocol is updated only at the triggering time instants, leading to significant saving of communication resources. Second, based on the Lyapunov method and the proposed event-triggered strategy, some criteria are obtained to ensure that guaranteed cost consensus can be achieved. Moreover, it is proved that the Zeno behavior is excluded under the proposed event-triggered scheme. Third, an algorithm is given to design suitable control gains in terms of linear matrix inequalities. Finally, the validity of the proposed results in this paper is verified via numerical simulation.

In this paper, the H ∞ state estimation problem of Markov jump memristive neural networks with fading channels is concerned by virtue of the hidden Markov model approach. The measurement transmission between the sensor and the filter is completed through fading channels which are described by a modified Rice fading model. The objective of the paper is to design a memristive filter such that, in the presence of fading channels, the effect of external disturbances on the error system is attenuated at a certain level and quantified by the H ∞ -norm in the mean square sense. By employing a mode-dependent Lyapunov-Krasovskii functional, some sufficient conditions are obtained to determine the gain matrices of the filter. Finally, a numerical example is provided to demonstrate the effectiveness of the main results.

In this paper, we discuss the cooperative output regulation problem for a class of heterogeneous linear multi-agent systems under undirected communication topological graph. First, an adaptive event-triggered protocol is introduced to achieve the consensus problem for leader-following system. Then, two fully distributed event-triggered adaptive control protocols are designed. That is, the state feedback and dynamic output feedback controllers, which does not need global information about network topology of system. Under the proposed two control protocols, the cooperative output regulation problem can be solved and no Zeno behavior happens for each agent. Finally, a numerical simulation is used to corroborate the validity of the conclusions under two control laws. Moreover, a comparative experiment is carried out to highlight the advantages of the control protocol designed in this paper.

Facial expressions play an important role during communications, allowing information regarding the emotional state of an individual to be conveyed and inferred. Research suggests that automatic facial expression recognition is a promising avenue of enquiry in mental healthcare, as facial expressions can also reflect an individual's mental state. In order to develop user-friendly, low-cost and effective facial expression analysis systems for mental health care, this paper presents a novel deep convolution network based emotion analysis framework to support mental state detection and diagnosis. The proposed system is able to process facial images and interpret the temporal evolution of emotions through a new solution in which deep features are extracted from the Fully Connected Layer 6 of the AlexNet, with a standard Linear Discriminant Analysis Classifier exploited to obtain the final classification outcome. It is tested against 5 benchmarking databases, including JAFFE, KDEF,CK+, and databases with the images obtained ‘in the wild’ such as FER2013 and AffectNet. Compared with the other state-of-the-art methods, we observe that our method has overall higher accuracy of facial expression recognition. Additionally, when compared to the state-of-the-art deep learning algorithms such as Vgg16, GoogleNet, ResNet and AlexNet, the proposed method demonstrated better efficiency and has less device requirements. The experiments presented in this paper demonstrate that the proposed method outperforms the other methods in terms of accuracy and efficiency which suggests it could act as a smart, low-cost, user-friendly cognitive aid to detect, monitor, and diagnose the mental health of a patient through automatic facial expression analysis.

Two new hybrid neural architectures combining morphological neurons and perceptrons are introduced in this paper. The first architecture, called Morphological - Linear Neural Network (MLNN) consists of a hidden layer of morphological neurons and an output layer of classical perceptrons has the capability of extracting features. The second architecture, called Linear-Morphological Neural Network (LMNN) is composed of one or several perceptron layers as a feature extractor, it is then followed by an output layer of morphological neurons for non-linear classification. Both architectures are trained by stochastic gradient descent. One of the main contributions of this paper is to show that the morphological layer offers a greater capacity to extract features than the perceptron layer. This claim is supported both theoretically and experimentally. We prove that the morphological layer possesses a greater capacity per computation unit to segment the 2D input space than the perceptron layer. In other words, adding more hyper-boxes produces more response regions than adding hyperplanes. From an empirical point of view, we test the two new models on 25 standard datasets at low dimensionality and one big data dataset. The result is that MLNN requires a lesser number of learning parameters than the other tested architectures while achieving better accuracies.

This paper targets for the ordinal regression/classification, which objective is to learn a rule to predict labels from a discrete but ordered set. For instance, the classification for medical diagnosis usually involves inherently ordered labels corresponding to the level of health risk. Previous multi-task classifiers on ordinal data often use several binary classification branches to compute a series of cumulative probabilities. However, these cumulative probabilities are not guaranteed to be monotonically decreasing. It also introduces a large number of hyper-parameters to be fine-tuned manually. This paper aims to eliminate or at least largely reduce the effects of those problems. We propose a simple yet efficient way to rephrase the output layer of the conventional deep neural network. Besides, in order to alleviate the effects of label noise in ordinal datasets, we propose a unimodal label regularization strategy. It also explicitly encourages the class predictions to distribute on nearby classes of ground truth. We show that our methods lead to the state-of-the-art accuracy on the medical diagnose task (e.g., Diabetic Retinopathy and Ultrasound Breast dataset) as well as the face age prediction (e.g., Adience face and MORPH Album II) with very little additional cost.

Hand gestures are quite suitable for space human-robot interaction (SHRI) because of their natural and convenient features. While the detection and localization of hands are the premise and foundation for SHRI based on hand gestures. But hand gestures are very complicated and hand sizes are very small in some images. These problems make the robust real-time hand detection and local- ization very difficult. In this paper, a feature-map-fused single shot multibox detector (FF-SSD) which is a deep learning network is designed to deal with the problems of hand detection and localization in SHRI. First, the background of the method is introduced in this paper, including an astronaut assistant robot platform, the difficulties of hand detection and localization, and introduction of the state-of-the-art deep learning networks for object detection and localiza- tion. Then, the FF-SSD is proposed for detecting and localizing hands especially pony-size hands. This network magentatakes into consideration both accuracy and speed with balanced performance. And in the experiment part, the FF-SSD is trained and tested on hand databases which include a homemade database and two public databases. At last, the superiority of the proposed method is demonstrated compared with the state-of-the-art methods.

Proximal algorithms are popular class of methods for handling sparsity structure in the datasets due to their low iteration costs and faster convergence. In this paper, we consider the framework of the sum of two convex functions, one of which is a smooth function with a Lipschitz gradient, while the other may be a non-smooth function. The usages of such non-smooth functions for identifying complex sparsity-structures in datasets in form of non-smooth regularizers has been an active research direction in the recent past. In this paper, we present the convergence analysis for the extragradient-based fixed-point method with an inertial component, based on which recently a new accelerated proximal extragradient algorithm is designed. In addition, extending the application areas of this algorithm, we applied it to solve (i) the logistic regression problem with complex l1-based penalties, namely, overlapping group lasso and fused lasso frameworks, and (ii) a recently proposed structurally-regularized learning problem for representation selection where the objective function consists of a reconstruction error and structured regularizers as combination of group sparsity regularizer, diversity regularizer, and locality-sensitivity regularizer. With the help of extensive experiments on several publicly available real-world datasets, the efficacy of the inertial-based extragradient methods has been demonstrated for solving the extended lasso and representation selection problems of machine learning.

The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed network capacity that cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of the discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol., This paper has been accepted for publication in Neurocomputing 2019. arXiv admin note: substantial text overlap with arXiv:1809.09081

In this paper, we address a challenging task in real-word applications, i.e., automatic reading recognition for pointer meters, called PRM. 1 This application is valuable in the fields of military, industry, and aerospace. However, the accuracy of recognizing the readings of pointer meters by machine vision is, oftentimes, affected by several factors, such as uneven illumination in each image, large range variation of illumination in different images, complex backgrounds, tilting of pointer meters, image blur, and scale change, resulting in the recognized readings with unacceptable accuracy. In this paper, a new robust approach to reading recognition of pointer meters is proposed. The proposed method consists of three main contributions: (1) constructing a novel deep learning algorithm in which the PrRoIPooling is used in lieu of the RoiAlign in the existing Mask-RCNN, (2) classifying the type of pointer meters while fitting the pointer binary mask, and (3) calculating the readings of pointer meters by the proposed angle method. In addition, we also report and release a new dataset for the community. Experiments show that the new algorithm can significantly improve the accuracy of the recognized readings of pointer meters, meanwhile, the proposed approach is also robust to the natural environments and computationally efficient.

Person re-identification refers to matching people across non-overlapping camera views on different locations and at different times. In the case of changes in perspective, light, background, veil, and person's clothing, traditional method cannot achieve person recognition effectively and reliably. In this paper, we propose a novel biometric metric learning method named Human Skeleton Mutual Learning person re-identification (HSMLP-Reid). The purpose of HSML person re-identification method (HSMLP-Reid) largely aims to use the new pedestrian local segmentation method proposed in this paper combined with the global skeleton information to solve the influence of background and local posture change. Firstly, bottom-up method is used to estimate the pedestrian posture and skeleton and the joint points of the pedestrians will be marked in this process. A new local segmentation method proposed in this paper named joint segmentation is used to locally segment pedestrians and perform local block matching. Furthermore, we learn the global skeleton information by defined joint distances from the pedestrian 2D skeleton estimation by the bottom-up method and use global skeleton information to global skeleton matching. Finally, we use local match and global skeleton match for mutual learning. Local match based on pedestrian nodes and global skeleton match based on pedestrian skeleton are based on biometrics. We learn the classification loss and metric learning loss to train model. Metric loss includes global skeletal distance and local block metric distance. Extensive experimental results on the large-scale Market1501, CUHK03 and CUHK-SYSU data sets demonstrate that the proposed method achieves consistently superior performance and outperforms most of the state-of-the-art methods.

Matrix completion is extensively studied due to its wide applications in science and technology. In this paper, we concentrate our study on the matrix completion problem for image analysis tasks due to their immense importance and pervasive use in many fields. A rich collection of models has been proposed to capture both linear and nonlinear relationships latent in a matrix. Even though nonlinear models possess more powerful matrix completion capabilities than their linear counterparts, these models generally carry higher model complexity and tuning difficulties. To take advantage of the superior discriminative power offered by nonlinear models while curbing its deployment overheads, this paper proposes a novel nonlinear matrix completion model utilizing a deep learning-based approach. In contrast to existing nonlinear models, the new model carefully explores and exploits spatial locality among adjacent matrix elements exhibited in patches of various sizes and locations in a target matrix. Building upon this idea, a new patch-based nonlinear matrix completion algorithm is designed. The algorithm leverages a convolutional neural network to learn the predictive relationship between a matrix element and its surrounding elements through an end-to-end trainable fashion, leading to a capable and easy-to-deploy nonlinear matrix completion solution. To identify an optimal patch size suited for tackling a given matrix completion task without exhaustively enumerating all candidate patch sizes, the new algorithm is coupled with a fast stochastic search procedure, yielding a good trade-off between computational efficiency and accuracy. Extensive experiments are conducted to validate the effectiveness and advantages of the proposed algorithm for nonlinear matrix completion problem in comparison with a series of state-of-the-art algorithms. Experimental results consistently demonstrate the superiority of the new algorithm in completing images with a variety of random and textual noises.