• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-05-15
Li Li; Dongdong Yu; Yuanqing Xia; Hongjiu Yang

This paper concentrates on the remote state estimation problem for nonlinear systems over a communication-limited wireless sensor network. Because of the non-Gaussian property caused by nonlinear transformation, the unscented transformation technique is exploited to obtain approximate Gaussian probability distributions of state and measurement. To reduce excessive data transmission, uncontrollable and controllable stochastic event-triggered scheduling schemes are developed to decide whether the current measurement should be transmitted. Compared with some existing deterministic event-triggered scheduling schemes, the newly developed ones possess a potential superiority in maintaining Gaussian property of innovation process. Under the proposed schemes, two nonlinear state estimators are designed based on the unscented Kalman filter. Stability and convergence conditions of these two estimators are established by analyzing behaviors of estimation error and error covariance. It is shown that an expected compromise between communication rate and estimation quality can be achieved by properly tuning event-triggered parameter matrix. Numerical examples are provided to testify the validity of the proposed results.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2017-12-22
Anis Yazidi; Hugo Hammer

We present a novel lightweight incremental quantile estimator which possesses far less complexity than the Tierney’s estimator and its extensions. Notably, our algorithm relies only on tuning one single parameter which is a plausible property which we could only find in the discretized quantile estimator Frugal. This makes our algorithm easy to tune for better performance. Furthermore, our algorithm is multiplicative which makes it highly suitable to handle quantile estimation in systems in which the underlying distribution varies with time. Unlike Frugal and our legacy work which are randomized algorithms, we suggest deterministic updates where the step size is adjusted in a subtle manner to ensure the convergence. The deterministic algorithm is more efficient since the estimate is updated at every iteration. The convergence of the proposed estimator is proven using the theory of stochastic learning. Extensive experimental results show that our estimator clearly outperforms legacy works.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-30
Dan Ye; Meng-Meng Chen; Hai-Jiao Yang

In this paper, the distributed adaptive event-triggered fault-tolerant consensus of general linear multiagent systems (MASs) is considered. First, in order to deal with multiplicative fault, a distributed event-triggered consensus protocol is designed. Using distributed adaptive online updating strategies, the computation of the minimum eigenvalue of Laplacian matrix is avoided. Second, some adaptive parameters are introduced in trigger function to improve the self-regulation ability of event-triggered mechanism. The new trigger threshold is both state-dependent and time-dependent, which is independent of the number of agents. Then sufficient conditions are derived to guarantee the leaderless and leader-following consensus. On the basis of this, the results are extended to the case of actuator saturation. It is proved the Zeno-behavior of considered event-triggered mechanism is avoided. At last, the effectiveness of the proposed methods are demonstrated by three simulation examples.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-04
Frank M. Drop; Daan M. Pool; Marinus M. van Paassen; Max Mulder; Heinrich H. Bülthoff

The human controller (HC) in manual control of a dynamical system often follows a visible and predictable reference path (target). The HC can adopt a control strategy combining closed-loop feedback and an open-loop feedforward response. The effects of the target signal waveform shape and the system dynamics on the human feedforward dynamics are still largely unknown, even for common, stable, vehicle-like dynamics. This paper studies the feedforward dynamics through computer model simulations and compares these to system identification results from human-in-the-loop experimental data. Two target waveform shapes are considered, constant velocity ramp segments and constant acceleration parabola segments. Furthermore, three representative vehicle-like system dynamics are considered: 1) a single integrator (SI); 2) a second-order system; and 3) a double integrator. The analyses show that the HC utilizes a combined feedforward/feedback control strategy for all dynamics with the parabola target, and for the SI and second-order system with the ramp target. The feedforward model parameters are, however, very different between the two target waveform shapes, illustrating the adaptability of the HC to task variables. Moreover, strong evidence of anticipatory control behavior in the HC is found for the parabola target signal. The HC anticipates the future course of the parabola target signal given extensive practice, reflected by negative feedforward time delay estimates.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-03
Chao Ma; Ivor W. Tsang; Fumin Shen; Chuancai Liu

Most learning-based hashing algorithms leverage sample-to-sample similarities, such as neighborhood structure, to generate binary codes, which achieve promising results for image retrieval. This type of methods are referred to as instance-level encoding . However, it is nontrivial to define a scalar to represent sample-to-sample similarity encoding the semantic labels and the data structure. To address this issue, in this paper, we seek to use a class-level encoding method, which encodes the class-to-class relationship, to take the semantic information of classes into consideration. Based on these two encodings, we propose a novel framework, error correcting input and output (EC-IO) coding, which does class-level and instance-level encoding under a unified mapping space. Our proposed model contains two major components, which are distribution preservation and error correction. With these two components, our model maps the input feature of samples and the output code of classes into a unified space to encode the intrinsic structure of data and semantic information of classes simultaneously. Under this framework, we present our hashing model, EC-IO hashing (EC-IOH), by approximating the mapping space with the Hamming space. Extensive experiments are conducted to evaluate the retrieval performance, and EC-IOH exhibits superior and competitive performances comparing with popular supervised and unsupervised hashing methods.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-05
Xuegang Tan; Jinde Cao; Xiaodi Li

This paper investigates the leader-following consensus problem of multiagent systems using a distributed event-triggered impulsive control method. For each agent, the controller is updated only when some state-dependent errors exceed a tolerable bound. The control inputs will be carried out by actor only at event triggering impulsive instants. According to the Lyapunov stability theory and impulsive method, several sufficient criteria for leader-following consensus are derived. Also, it is shown that continuous communication of neighboring agents can be avoided, and Zeno-behavior can be excluded in our schema. The results are illustrated through several numerical simulation examples.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-08
Suman Deb; Samarendra Dandapat

In this paper, a novel multiscale amplitude feature is proposed using multiresolution analysis (MRA) and the significance of the vocal tract is investigated for emotion classification from the speech signal. MRA decomposes the speech signal into number of sub-band signals. The proposed feature is computed by using sinusoidal model on each sub-band signal. Different emotions have different impacts on the vocal tract. As a result, vocal tract responds in a unique way for each emotion. The vocal tract information is enhanced using pre-emphasis. Therefore, emotion information manifested in the vocal tract can be well exploited. This may help in improving the performance of emotion classification. Emotion recognition is performed using German emotional EMODB database, interactive emotional dyadic motion capture database, simulated stressed speech database, and FAU AIBO database with speech signal and speech with enhanced vocal tract information (SEVTI). The performance of the proposed multiscale amplitude feature is compared with three different types of features: 1) the mel frequency cepstral coefficients; 2) the Teager energy operator (TEO)-based feature (TEO-CB-Auto-Env); and 3) the breathinesss feature. The proposed feature outperforms the other features. In terms of recognition rates, the features derived from the SEVTI signal, give better performance compared to the features derived from the speech signal. Combination of the features with SEVTI signal shows average recognition rate of 86.7% using EMODB database.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-08
Mehmet Fatih Amasyali

The performance of the ensemble algorithms is related with the individual accuracy of the base learners and their results diversity. Individual accuracy of a base learner is directly related to the similarity between the original training set and the base learner’s training set. When a modified training set by randomly selecting features/classes/samples is given to the base learners, the diversity is created but the individual accuracy is decreased. From this point of view, different ensemble algorithms can be seen as a selection between having more accurate but less diverse base learners and having more diverse but less accurate base learners. We propose a meta ensemble method named as improved space forest which adds generated and (hopefully) more accurate features to the original features. The new features are obtained from randomly selected original features. When the new features are more distinctive than the original ones, they are selected by the learners. So, the ensemble may have more accurate base learners. However, a different improved space is generated for each learner to create diversity. The proposed method can be used with different ensemble methods. We compared original and improved space versions of bagging, random forest, and rotation forest algorithms. Improved space versions have generally better or comparable results than the original ones. We also present a theoretical framework to analyze the individual accuracies and diversities of the base learners.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-12
Liwei An; Guang-Hong Yang

Cyber-physical systems (CPSs) are naturally highly interconnected and complexly nonlinear. This paper investigates the problem of decentralized adaptive output feedback control for CPSs subject to intermittent denial-of-service (DoS) attacks. The considered CPSs are modeled as a class of nonlinear uncertain strict-feedback interconnected systems. When a DoS attack is active, all the state variables become unavailable and standard backstepping cannot be applied. To overcome this difficulty, a switching-type adaptive state estimator is constructed. Based on an improved average dwell time method incorporated by frequency and duration properties of DoS attacks, convex design conditions of controller parameters are derived in term of solving a set of linear matrix inequalities. The proposed controller guarantees that all closed-loop signals remain bounded, while the error signals converge to a small neighborhood of the origin. As an illustrative example, the proposed control scheme is applied to a power network system.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-30
Tong Zhang; Wenming Zheng; Zhen Cui; Yuan Zong; Yang Li

In this paper, we propose a novel deep learning framework, called spatial–temporal recurrent neural network (STRNN), to integrate the feature learning from both spatial and temporal information of signal sources into a unified spatial–temporal dependency model. In STRNN, to capture those spatially co-occurrent variations of human emotions, a multidirectional recurrent neural network (RNN) layer is employed to capture long-range contextual cues by traversing the spatial regions of each temporal slice along different directions. Then a bi-directional temporal RNN layer is further used to learn the discriminative features characterizing the temporal dependencies of the sequences, where sequences are produced from the spatial RNN layer. To further select those salient regions with more discriminative ability for emotion recognition, we impose sparse projection onto those hidden states of spatial and temporal domains to improve the model discriminant ability. Consequently, the proposed two-layer RNN model provides an effective way to make use of both spatial and temporal dependencies of the input signals for emotion recognition. Experimental results on the public emotion datasets of electroencephalogram and facial expression demonstrate the proposed STRNN method is more competitive over those state-of-the-art methods.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-30
He Jiang; Haibo He

This paper is concerned with a class of optimal output consensus control problems for discrete linear multiagent systems with the partially observable system state. Since the optimal control policy depends on the full system state which is not accessible for a partially observable system, traditionally, distributed observers are employed to recover the system state. However, in many situations, the accurate model of a real-world dynamical system might be difficult to obtain, which makes the observer design infeasible. Furthermore, the optimal consensus control policy cannot be analytically solved without system functions. To overcome these challenges, we propose a data-driven adaptive dynamic programming approach that does not require the complete system inner state. The key idea is to use the input and output sequence as an equivalent representation of the underlying state. Based on this representation, an adaptive dynamic programming algorithm is developed to generate the optimal control policy. For the implementation of this algorithm, we design a neural network-based actor-critic structure to approximate the local performance indices and the control polices. Two numerical simulations are used to demonstrate the effectiveness of our method.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-12
Proteek Chandan Roy; Kalyanmoy Deb; Md. Monirul Islam

Nondominated sorting is a key operation used in multiobjective evolutionary algorithms (MOEA). Worst case time complexity of this algorithm is ${O(MN^{2})}$ , where ${N}$ is the number of solutions and ${M}$ is the number of objectives. For stochastic algorithms like MOEAs, it is important to devise an algorithm which has better average case performance. In this paper, we propose a new algorithm that makes use of faster scalar sorting algorithm to perform nondominated sorting. It finds partial orders of each solution from all objectives and use these orders to skip unnecessary solution comparisons. We also propose a specific order of objectives that reduces objective comparisons. The proposed method introduces a weighted binary search over the fronts when the rank of a solution is determined. It further reduces total computational effort by a large factor when there is large number of fronts. We prove that the worst case complexity can be reduced to ${\Theta }({MNC}_{{max}}\mathrm {log}_{{2}} {(F+1)})$ , where the number of fronts is ${F}$ and the maximum number of solutions per front is ${C}_{\mathrm {max}}$ ; however, in general cases, our worst case complexity is still ${O(MN^{2})}$ . Our best case time complexity is ${O}({MN}\mathrm {log} {N})$ . We also achieve the best case complexity ${O}({MN}\mathrm {log} {N+N^{2}})$ , when all solutions are in a single front. This method is compared with other state-of-the-art algorithms—efficient nondomination level update, deductive sort, corner sort, efficient nondominated sort and divide-and-conquer sort—in four different datasets. Experimental results show that our method, namely, bounded best order sort, is computationally more efficient than all other competing algorithms.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-12
Fuwen Yang; Qing-Long Han; Yurong Liu

This paper is concerned with the distributed ${H_\infty }$ state estimation for a discrete-time target linear system over a filtering network with time-varying and switching topology and partial information exchange. Both filtering network topology switching and partial information exchange between filters are simultaneously considered in the filter design. The topology under consideration evolves not only over time but also by an event switch which is assumed to be subject to a nonhomogeneous Markov chain . The probability transition matrix of the nonhomogeneous Markov chain is time-varying . In the filter information exchange, partial state estimation information and channel noise are simultaneously considered. In order to design such a switching filtering network with partial information exchange, stochastic Markov stability theory is developed. The switching topology-dependent filters are derived to guarantee an optimal ${H_{\infty }}$ disturbance rejection attenuation level for the estimation disagreement of the filtering network. It is shown that the addressed ${H_\infty }$ state estimation problem is turned into a switching topology-dependent optimal problem. The distributed filtering problem with complete information exchanges from its neighbors is also investigated. An illustrative example is given to show the applicability of the obtained results.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-17
Min Xiao; Wei Xing Zheng; Guoping Jiang

It has been demonstrated in a large number of experimental results that small RNAs (sRNAs) play a vital role in gene regulation processes. Thus, the gene regulation process is dominated by sRNAs in addition to messenger RNAs and proteins. However, the regulation mechanism of sRNAs is not well understood and there are few models considering the effect of sRNAs. So it is of realistic biological background to include sRNAs when modeling gene networks. In this paper, sRNAs are incorporated into the process of gene expression and a new differential equation model is put forward to describe cyclic genetic regulatory networks with sRNAs and multiple delays. We mainly investigate the stability and bifurcation criteria for two cases: 1) positive cyclic genetic regulatory networks and 2) negative cyclic genetic regulatory networks. For a positive cyclic genetic regulatory network, it is revealed that there may exist more than one equilibrium and the multistability can appear. Sufficient conditions are established for the delay-independent stability and fold bifurcations. It is found that the dynamics of positive cyclic gene networks has no bearing on time delays, but depends on the biochemical parameters, the Hill coefficient and the equilibrium itself. For a negative cyclic genetic regulatory network, it is proved that there exists a unique equilibrium. Delay-dependent conditions for the stability are derived, and the existence of Hopf bifurcations is examined. Different from the delay-independent stability of positive gain networks, the stability of equilibrium is determined not only by the biochemical parameters, the Hill coefficient and the equilibrium itself, but also by the total delay. At last, three illustrative examples are provided to validate the major results.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-27
Tianrui Chen; Cong Wang; Guo Chen; Zhaoyang Dong; David J. Hill

In this paper, based on the deterministic learning (DL) theory, an approach for detection for small faults in a class of nonlinear closed-loop systems is proposed. First, the DL-based neural control approach and identification approach are employed to extract the knowledge of the control effort that compensates the fault dynamics (change of the control effort) and the fault dynamics (the change of system dynamics due to fault). Second, two types of residuals are constructed. One is to measure the change of system dynamics, another one is to measure change of the control effort. By combining these residuals, an enhanced residual is generated, in which the fault dynamics and the control effort are combined to diagnose the fault. It is shown that the major fault information is compensated by the control, and the major fault information is double in the enhanced residual. Therefore, the fault information in the diagnosis residual is enhanced. Finally, an analysis of the fault detectability condition of the diagnosis scheme is given. Simulation studies are included to demonstrate the effectiveness of the approach.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-17
Lingling Zhang; Minnan Luo; Zhihui Li; Feiping Nie; Huaxiang Zhang; Jun Liu; Qinghua Zheng

Semisupervised learning aims to leverage both labeled and unlabeled data to improve performance, where most of them are graph-based methods. However, the graph-based semisupervised methods are not capable for large-scale data since the computational consumption on the construction of graph Laplacian matrix is huge. On the other hand, the substantial unlabeled data in training stage of semisupervised learning could cause large uncertainties and potential threats. Therefore, it is crucial to enhance the robustness of semisupervised classification. In this paper, a novel large-scale robust semisupervised learning method is proposed in the framework of capped $\ell _{\boldsymbol {2,p}}$ -norm. This strategy is superior not only in computational cost because it makes the graph Laplacian matrix unnecessary, but also in robustness to outliers since the capped $\ell _{\boldsymbol {2,p}}$ -norm used for loss measurement. An efficient optimization algorithm is exploited to solve the nonconvex and nonsmooth challenging problem. The complexity of the proposed algorithm is analyzed and discussed in theory detailedly. Finally, extensive experiments are conducted over six benchmark data sets to demonstrate the effectiveness and superiority of the proposed method.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-23
Zhichen Gong; Huanhuan Chen; Bo Yuan; Xin Yao

A well-defined distance is critical for the performance of time series classification. Existing distance measurements can be categorized into two branches. One is to utilize handmade features for calculating distance, e.g., dynamic time warping, which is limited to exploiting the dynamic information of time series. The other methods make use of the dynamic information by approximating the time series with a generative model, e.g., Fisher kernel. However, previous distance measurements for time series seldom exploit the label information, which is helpful for classification by distance metric learning. In order to attain the benefits of the dynamic information of time series and the label information simultaneously, this paper proposes a multiobjective learning algorithm for both time series approximation and classification, termed multiobjective model-metric (MOMM) learning. In MOMM, a recurrent network is exploited as the temporal filter, based on which, a generative model is learned for each time series as a representation of that series. The models span a non-Euclidean space, where the label information is utilized to learn the distance metric. The distance between time series is then calculated as the model distance weighted by the learned metric. The network size is also optimized to learn parsimonious representations. MOMM simultaneously optimizes the data representation, the time series model separation, and the network size. The experiments show that MOMM achieves not only superior overall performance on uni/multivariate time series classification but also promising time series prediction performance.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-24
Tingjin Luo; Chenping Hou; Feiping Nie; Dongyun Yi

High-dimensional non-Gaussian data are ubiquitous in many real applications. Face recognition is a typical example of such scenarios. The sampled face images of each person in the original data space are more closely located to each other than to those of the same individuals due to the changes of various conditions like illumination, pose variation, and facial expression. They are often non-Gaussian and differentiating the importance of each data point has been recognized as an effective approach to process the high-dimensional non-Gaussian data. In this paper, to embed non-Gaussian data well, we propose a novel unified framework named adaptive discriminative analysis (ADA), which combines the sample’s importance measurement and subspace learning in a unified framework. Therefore, our ADA can preserve the within-class local structure and learn the discriminative transformation functions simultaneously by minimizing the distances of the projected samples within the same classes while maximizing the between-class separability. Meanwhile, an efficient method is developed to solve our formulated problem. Comprehensive analyses, including convergence behavior and parameter determination, together with the relationship to other related approaches, are as well presented. Systematical experiments are conducted to understand the work of our proposed ADA. Promising experimental results on various types of real-world benchmark data sets are provided to examine the effectiveness of our algorithm. Furthermore, we have also evaluated our method in face recognition. They all validate the effectiveness of our method on processing the high-dimensional non-Gaussian data.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-17
Lei Zhang; Xuehan Wang; Guang-Bin Huang; Tao Liu; Xiaoheng Tan

Electronic tongue (E-Tongue), as a novel taste analysis tool, shows a promising perspective for taste recognition. In this paper, we constructed a voltammetric E-Tongue system and measured 13 different kinds of liquid samples, such as tea, wine, beverage, functional materials, etc. Owing to the noise of system and a variety of environmental conditions, the acquired E-Tongue data shows inseparable patterns. To this end, from the viewpoint of algorithm, we propose a local discriminant preservation projection (LDPP) model, an under-studied subspace learning algorithm, that concerns the local discrimination and neighborhood structure preservation. In contrast with other conventional subspace projection methods, LDPP has two merits. On one hand, with local discrimination it has a higher tolerance to abnormal data or outliers. On the other hand, it can project the data to a more separable space with local structure preservation. Further, support vector machine, extreme learning machine (ELM), and kernelized ELM (KELM) have been used as classifiers for taste recognition in E-Tongue. Experimental results demonstrate that the proposed E-Tongue is effective for multiple tastes recognition in both efficiency and effectiveness. Particularly, the proposed LDPP-based KELM classifier model achieves the best taste recognition performance of 98%. The developed benchmark data sets and codes will be released and downloaded in http://www.leizhang.tk/ tempcode.html.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-23
Wei Wang; Shaocheng Tong; Dan Wang

The adaptive fuzzy containment control problem is discussed for high-order systems with unknown nonlinear dynamics and unmeasurable states guided by multiple dynamic leaders. A high gain observer is introduced to reconstruct the system states. Then, utilizing fuzzy logic systems to model followers’ dynamics, an observer-based adaptive fuzzy containment control approach is presented using only the relative position of the neighbors. It is shown that the uniformly ultimately bounded containment control is realized under the condition that, each follower can obtain the information from at least one leader through a directed path. As an extension, an observer-based containment control with prescribed performance is developed, which guarantees the relative position error to be bounded by a specified bound. The obtained theoretical results are validated by simulation examples.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-31
Jianshe Wu; Xing Shen; Kui Jiao

The minimum vertex cover (MVC) is a well-known combinatorial optimization problem. A game-based memetic algorithm (GMA-MVC) is provided, in which the local search is an asynchronous updating snowdrift game and the global search is an evolutionary algorithm (EA). The game-based local search can implement ( k,l )-exchanges for various numbers of ${k}$ and ${l}$ to remove ${k}$ vertices from and add ${l}$ vertices into the solution set, thus is much better than the previous (1,0)-exchange. Beyond that, the proposed local search is able to deal with the constraint, such that the crossover operator can be very simple and efficient. Degree-based initialization method is also provided which is much better than the previous uniform random initialization. Each individual of the GMA-MVC is designed as a snowdrift game state of the network. Each vertex is treated as an intelligent agent playing the snowdrift game with its neighbors, which is the local refinement process. The game is designed such that its strict Nash equilibrium (SNE) is always a vertex cover of the network. Most of the SNEs are only local optima of the problem. Then an EA is employed to guide the game to escape from those local optimal Nash equilibriums to reach a better Nash equilibrium. From comparison with the state of the art algorithms in experiments on various networks, the proposed algorithm always obtains the best solutions.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-23
Shirin Dora; Suresh Sundaram; Narasimhan Sundararajan

This paper presents a new learning algorithm developed for a three layered spiking neural network for pattern classification problems. The learning algorithm maximizes the interclass margin and is referred to as the two stage margin maximization spiking neural network (TMM-SNN). In the structure learning stage, the learning algorithm completely evolves the hidden layer neurons in the first epoch. Further, TMM-SNN updates the weights of the hidden neurons for multiple epochs using the newly developed normalized membrane potential learning rule such that the interclass margins (based on the response of hidden neurons) are maximized. The normalized membrane potential learning rule considers both the local information in the spike train generated by a presynaptic neuron and the existing knowledge (synaptic weights) stored in the network to update the synaptic weights. After the first stage, the number of hidden neurons and their parameters are not updated. In the output weights learning stage, TMM-SNN updates the weights of the output layer neurons for multiple epochs to maximize the interclass margins (based on the response of output neurons). Performance of TMM-SNN is evaluated using ten benchmark data sets from the UCI machine learning repository. Statistical performance comparison of TMM-SNN with other existing learning algorithms for SNNs is conducted using the nonparametric Friedman test followed by a pairwise comparison using the Fisher’s least significant difference method. The results clearly indicate that TMM-SNN achieves better generalization performance in comparison to other algorithms.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-30
Xiaomei Liu; Shuzhi Sam Ge; Cher-Hiang Goh; Yanan Li

In this paper, the formation tracking control is studied for a multiagent system (MAS) with communication limitations. The objective is to control a group of agents to track a desired trajectory while maintaining a given formation in nonomniscient constrained space. The role switching triggered by the detection of unexpected spatial constraints facilitates efficiency of event-triggered control in communication bandwidth, energy consumption, and processor usage. A coordination mechanism is proposed based on a novel role “coordinator” to indirectly spread environmental information among the whole communication network and form a feedback link from followers to the leader to guarantee the formation keeping. A formation scaling factor is introduced to scale up or scale down the given formation size in the case that the region is impassable for MAS with the original formation size. Controllers for the leader and followers are designed and the adaptation law is developed for the formation scaling factor. The conditions for asymptotic stability of MAS are discussed based on the Lyapunov theory. Simulation results are presented to illustrate the performance of proposed approaches.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-01-31
Dan Guo; Yaochu Jin; Jinliang Ding; Tianyou Chai

Gaussian processes (GPs) are the most popular model used in surrogate-assisted evolutionary optimization of computationally expensive problems, mainly because GPs are able to measure the uncertainty of the estimated fitness values, based on which certain infill sampling criteria can be used to guide the search and update the surrogate model. However, the computation time for constructing GPs may become excessively long when the number of training samples increases, which makes it inappropriate to use them as surrogates in evolutionary optimization. To address this issue, this paper proposes to use ensembles as surrogates and infill criteria for model management in evolutionary optimization. A heterogeneous ensemble consisting of a least square support vector machine and two radial basis function networks is constructed to enhance the reliability of ensembles for uncertainty estimation. In addition to the original decision variables, a selected subset of the decision variables and a set of transformed variables are used as inputs of the heterogeneous ensemble to further promote the diversity of the ensemble. The proposed heterogeneous ensemble is compared with a GP and a homogeneous ensemble for infill sampling criteria in evolutionary multiobjective optimization. Experimental results demonstrate that the heterogeneous ensemble is competitive in performance compared with GPs and much more scalable in computational complexity to the increase in search dimension.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-02
Peng Lin; Wei Ren; Hao Wang; Ubaid M. Al-Saggaf

This paper presents both algorithms and experimental results to solve a distributed rendezvous problem with shortest distance to convex regions. In a multiagent network, each agent is assigned to a certain convex region and has information about only its own region. All these regions might not have an intersection. Through local interaction with their neighbors, multiple agents collectively rendezvous at an optimal location that is a priori unknown to each agent and has the shortest total squared distance to these regions. First, a distributed time-varying algorithm is introduced, where a corresponding condition is given to guarantee that all agents rendezvous at the optimal location asymptotically for bounded convex regions. Then a distributed tracking algorithm combined with a distributed estimation algorithm is proposed. It is first shown that for general possibly unbounded convex regions, all agents rendezvous in finite time and then collectively slide to the optimal location asymptotically. Then it is shown that for convex regions with certain projection compressibility, all agents collectively rendezvous at the optimal location in finite time, even when the regions are time varying. The algorithms are experimentally implemented on multiple ground robots to illustrate the obtained theoretical results.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-02
Rui Yan; Zongying Shi; Yisheng Zhong

This paper considers a reach-avoid game on a rectangular domain with two defenders and one attacker. The attacker aims to reach a specified edge of the game domain boundary, while the defenders strive to prevent that by capturing the attacker. First, we are concerned with the barrier, which is the boundary of the reach-avoid set, splitting the state space into two disjoint parts: 1) defender dominance region (DDR) and 2) attacker dominance region (ADR). For the initial states lying in the DDR, there exists a strategy for the defenders to intercept the attacker regardless of the attacker’s best effort, while for the initial states lying in the ADR, the attacker can always find a successful attack strategy. We propose an attack region method to construct the barrier analytically by employing Voronoi diagram and Apollonius circle for two kinds of speed ratios. Then, by taking practical payoff functions into considerations, we present optimal strategies for the players when their initial states lie in their winning regions, and show that the ADR is divided into several parts corresponding to different strategies for the players. Numerical approaches, which suffer from inherent inaccuracy, have already been utilized for multiplayer reach-avoid games, but computational complexity complicates solving such games and consequently hinders efficient on-line applications. However, this method can obtain the exact formulation of the barrier and is applicable for real-time updates.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-19
Bin Xu; Zhongke Shi; Fuchun Sun; Wei He

This paper investigates a fault-tolerant control of the hypersonic flight vehicle using back-stepping and composite learning. With consideration of angle of attack (AOA) constraint caused by scramjet, the control laws are designed based on barrier Lyapunov function. To deal with the unknown actuator faults, a robust adaptive allocation law is proposed to provide the compensation. Meanwhile, to obtain good system uncertainty approximation, the composite learning is proposed for the update of neural weights by constructing the serial–parallel estimation model to obtain the prediction error which can dynamically indicate how the intelligent approximation is working. Simulation results show that the controller obtains good system tracking performance in the presence of AOA constraint and actuator faults.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-05
Li He; Nilanjan Ray; Yisheng Guan; Hong Zhang

We propose an efficient spectral clustering method for large-scale data. The main idea in our method consists of employing random Fourier features to explicitly represent data in kernel space. The complexity of spectral clustering thus is shown lower than existing Nyström approximations on large-scale data. With ${m}$ training points from a total of ${n}$ data points, Nyström method requires ${O(nmd+m^{3}+nm^{2})}$ operations, where ${d}$ is the input dimension. In contrast, our proposed method requires ${O(nDd+D^{3}+n'D^{2})}$ , where ${n}'$ is the number of data points needed until convergence and ${D}$ is the kernel mapped dimension. In large-scale datasets where ${n' \ll n}$ hold true, our explicitly mapping method can significantly speed up eigenvector approximation and benefit prediction speed in spectral clustering. For instance, on MNIST (60 000 data points), the proposed method is similar in clustering accuracy to Nyström methods while its speed is twice as fast as Nyström.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-02
Junbiao Pang; Anjing Hu; Qingming Huang; Qi Tian; Baocai Yin

Organizing webpages into interesting topics is one of the key steps to understand the trends from multimodal Web data. The sparse, noisy, and less-constrained user-generated content results in inefficient feature representations. These descriptors unavoidably cause that a detected topic still contains a certain number of the false detected webpages, which further make a topic be less coherent, less interpretable, and less useful. In this paper, we address this problem from a viewpoint interpreting a topic by its prototypes, and present a two-step approach to achieve this goal. Following the detection-by-ranking approach, a sparse Poisson deconvolution is proposed to learn the intratopic similarities between webpages. To find the prototypes, leveraging the intratopic similarities, top- ${k}$ diverse yet representative prototype webpages are identified from a submodularity function. Experimental results not only show the improved accuracies for the Web topic detection task, but also increase the interpretation of a topic by its prototypes on two public datasets.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-02
Mingsheng Fu; Hong Qu; Zhang Yi; Li Lu; Yongsheng Liu

The collaborative filtering (CF) based models are capable of grasping the interaction or correlation of users and items under consideration. However, existing CF-based methods can only grasp single type of relation, such as restricted Boltzmann machine which distinctly seize the correlation of user–user or item–item relation. On the other hand, matrix factorization explicitly captures the interaction between them. To overcome these setbacks in CF-based methods, we propose a novel deep learning method which imitates an effective intelligent recommendation by understanding the users and items beforehand. In the initial stage, corresponding low-dimensional vectors of users and items are learned separately, which embeds the semantic information reflecting the user–user and item–item correlation. During the prediction stage, a feed-forward neural networks is employed to simulate the interaction between user and item, where the corresponding pretrained representational vectors are taken as inputs of the neural networks. Several experiments based on two benchmark datasets (MovieLens 1M and MovieLens 10M) are carried out to verify the effectiveness of the proposed method, and the result shows that our model outperforms previous methods that used feed-forward neural networks by a significant margin and performs very comparably with state-of-the-art methods on both datasets.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-02
Deming Lei; Ming Li; Ling Wang

Flexible job shop scheduling problem (FJSP) has been extensively considered; however, multiobjective FJSP with energy consumption threshold is seldom investigated, the goal of which is to minimize makespan and total tardiness under the constraint that total energy consumption does not exceed a given threshold. Energy constraint is not always met and the threshold is difficult to be decided in advance. These features make it more difficult to solve the problem. In this paper, a two-phase meta-heuristic (TPM) based on imperialist competitive algorithm (ICA) and variable neighborhood search (VNS) is proposed. In the first phase, the problem is converted into FJSP with makespan, total tardiness and total energy consumption and the new FJSP is solved by an ICA, which uses some new methods to build initial empires and do imperialist competition. In the second phase, new strategies are provided for comparing solutions and updating the nondominated set of the first phase and a VNS is used for the original problem. The current solution of VNS is periodically replaced with member of the set $\Omega$ to improve solution quality. An energy consumption threshold is obtained by optimization. Extensive experiments are conducted to test the performance of TPM finally. The computational results show that TPM is a very competitive algorithm for the considered FJSP.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2018-02-08
Wei-Long Zheng; Wei Liu; Yifei Lu; Bao-Liang Lu; Andrzej Cichocki

In this paper, we present a multimodal emotion recognition framework called EmotionMeter that combines brain waves and eye movements. To increase the feasibility and wearability of EmotionMeter in real-world applications, we design a six-electrode placement above the ears to collect electroencephalography (EEG) signals. We combine EEG and eye movements for integrating the internal cognitive states and external subconscious behaviors of users to improve the recognition accuracy of EmotionMeter . The experimental results demonstrate that modality fusion with multimodal deep neural networks can significantly enhance the performance compared with a single modality, and the best mean accuracy of 85.11% is achieved for four emotions (happy, sad, fear, and neutral). We explore the complementary characteristics of EEG and eye movements for their representational capacities and identify that EEG has the advantage of classifying happy emotion, whereas eye movements outperform EEG in recognizing fear emotion. To investigate the stability of EmotionMeter over time, each subject performs the experiments three times on different days. EmotionMeter obtains a mean recognition accuracy of 72.39% across sessions with the six-electrode EEG and eye movement features. These experimental results demonstrate the effectiveness of EmotionMeter within and between sessions.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-14
Jiamiao Xu; Shujian Yu; Xinge You; Mengjun Leng; Xiao-Yuan Jing; C. L. Philip Chen

We present a novel cross-view classification algorithm where the gallery and probe data come from different views. A popular approach to tackle this problem is the multiview subspace learning (MvSL) that aims to learn a latent subspace shared by multiview data. Despite promising results obtained on some applications, the performance of existing methods deteriorates dramatically when the multiview data is sampled from nonlinear manifolds or suffers from heavy outliers. To circumvent this drawback, motivated by the Divide-and-Conquer strategy, we propose multiview hybrid embedding (MvHE), a unique method of dividing the problem of cross-view classification into three subproblems and building one model for each subproblem. Specifically, the first model is designed to remove view discrepancy, whereas the second and third models attempt to discover the intrinsic nonlinear structure and to increase the discriminability in intraview and interview samples, respectively. The kernel extension is conducted to further boost the representation power of MvHE. Extensive experiments are conducted on four benchmark datasets. Our methods demonstrate the overwhelming advantages against the state-of-the-art MvSL-based cross-view classification approaches in terms of classification accuracy and robustness.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-13
Xiaodi Li; Jinde Cao; Daniel W. C. Ho

Impulsive control of nonlinear delay systems is studied in this paper, where the time delays addressed may be the constant delay, bounded time-varying delay, or unbounded time-varying delay. Based on the impulsive control theory and some analysis techniques, a new theoretical result for global exponential stability is derived from the impulsive control point of view. The significance of the presented result is that the stability can be achieved via the impulsive control at certain impulse points despite the existence of impulsive perturbations which causes negative effect to the control. That is, the impulsive control provides a super performance to allow the existence of impulsive perturbations. In addition, we apply the theoretical result to the problem of impulsive control of delayed neural networks. Some results for global exponential stability and synchronization control of neural networks with time delays are derived via impulsive control. Three illustrated examples are given to show the effectiveness and distinctiveness of the proposed impulsive control schemes.

更新日期：2019-02-14
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-12
Yun Zhang; Xiaohang Su; Zhi Liu; C. L. Philip Chen

This paper investigates an event-triggered adaptive tracking control problem of multi-input and multi-output (MIMO) triangular structure nonlinear systems with nonparametric uncertainties. The implementation of this paper can be roughly classified into two steps: 1) solving the existing rate-limited communication constraints and 2) guaranteeing perfect tracking control performance. By using the relative threshold event-triggered strategy, the communication resource constraint is availably resolved, while the Zeno behavior can be avoided. In addition, by constructing a series of novel Lyapunov functions, an effective adaptive fuzzy control method is developed. The proposed fuzzy control scheme contains fewer calculations by the operation of addressing the square of the norm of the fuzzy weight vector for the entire MIMO system. It is proved that all of the closed-loop signals are global bounded, and the proposed method is not only capable of guaranteeing output tracking performance but is also available to ensure preserved transient performance. Simulation studies show the effectiveness of our approach and verify our established theory.

更新日期：2019-02-13
• IEEE Trans. Cybern. (IF 8.803) Pub Date :
Xingyu Chen; Junzhi Yu; Zhengxing Wu

Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithms have been developed for video detection task, yet very few approaches can achieve real-time online object detection in videos. In this paper, based on the attention mechanism and convolutional long short-term memory (ConvLSTM), we propose a temporal single-shot detector (TSSD) for real-world detection. Distinct from the previous methods, we take aim at temporally integrating pyramidal feature hierarchy using ConvLSTM, and design a novel structure, including a low-level temporal unit as well as a high-level one for multiscale feature maps. Moreover, we develop a creative temporal analysis unit, namely, attentional ConvLSTM, in which a temporal attention mechanism is specially tailored for background suppression and scale suppression, while a ConvLSTM integrates attention-aware features across time. An association loss and a multistep training are designed for temporal coherence. Besides, an online tubelet analysis (OTA) is exploited for identification. Our framework is evaluated on ImageNet VID dataset and 2DMOT15 dataset. Extensive comparisons on the detection and tracking capability validate the superiority of the proposed approach. Consequently, the developed TSSD-OTA achieves a fast speed and an overall competitive performance in terms of detection and tracking. Finally, a real-world maneuver is conducted for underwater object grasping.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date :
Van-Phong Vu; Wen-June Wang

This paper proposes a novel method to synthesize a controller for stabilizing the nonlinear large-scale system which is represented by a large-scale polynomial Takagi-Sugeno (T-S) fuzzy system. The large-scale system consists of a set of the uncertain polynomial T-S fuzzy system with interconnection terms. Modeling the large-scale nonlinear system under the framework of the polynomial form will decrease both the modeling errors and the number of fuzzy rules with respect to the conventional large-scale T-S fuzzy system. In addition, because of the existence of uncertainties, the synthesizing controller for the large-scale polynomial fuzzy system becomes much more challenging and has not been investigated in the previous studies. In this paper, a controller is synthesized to simultaneously eliminate the impact of the uncertainties and stabilize the system. With the aid of Lyapunov theory, sum-of-square technique, and S-procedure, the conditions for controller synthesis are derived in the main theorems. Finally, two examples are illustrated to show the effectiveness and merit of the proposed method.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date :
Xiaoyuan Zheng; Hao Zhang; Huaicheng Yan; Fuwen Yang; Zhuping Wang; Ljubo Vlacic

This paper is concerned with the adaptive backstepping control problem for a cloud-aided nonlinear active full-vehicle suspension system. A novel model for a nonlinear active suspension system is established, in which uncertain parameters, unknown friction forces, nonlinear springs and dampers, and performance requirements are considered simultaneously. In order to deal with the nonlinear characteristics, a backstepping control strategy is developed. Meanwhile, an adaptive control strategy is proposed to handle the uncertain parameters and unknown friction forces. In the cloud-aided vehicle suspension system framework, the adaptive backstepping controller is updated in a remote cloud based on the cloud storing information, such as road information, vehicle suspension information, and reference trajectories. Finally, simulation results for a full vehicle with 7-degree of freedom model are provided to demonstrate the effectiveness of the proposed control scheme, and it is shown that the addressed controller can improve the performances more than 80% compared with passive vehicle suspension systems.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date :
Hong-Xiang Hu; Guanghui Wen; Wenwu Yu; Jinde Cao; Tingwen Huang

In this paper, the finite-time coordination behavior of multiple Euler-Lagrange systems in cooperation-competition networks is investigated, where the coupling weights can be either positive or negative. Then, two auxiliary variables about the information exchange among agents are designed, and the finite-time distributed protocol is proposed based on the auxiliary variables and the property of the Euler-Lagrange system. By combining the approach of adding a power integrator with the homogeneous domination method, it is shown that finite-time bipartite consensus can be achieved if the cooperation-competition network is structurally balanced and the parameters of the distributed protocol are chosen appropriately; otherwise, finite-time distributed stabilization can be achieved. Furthermore, from the perspective of network decomposition, the finite-time coordination behavior is further considered, and some sufficient conditions about the cooperation subnetwork and the competition subnetwork are obtained. As an extension, finite-time coordination behavior only with partial state information of the neighbors is discussed, and some similar results are obtained. Finally, four numerical examples are shown for illustration.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date :
Guo Yu; Yaochu Jin; Markus Olhofer

In multiobjective optimization, it is nontrivial for decision makers to articulate preferences without a priori knowledge, which is particularly true when the number of objectives becomes large. Depending on the shape of the Pareto front, optimal solutions such as knee points may be of interest. Although several multi- and many-objective optimization test suites have been proposed, little work has been reported focusing on designing multiobjective problems whose Pareto front contains complex knee regions. Likewise, few performance indicators dedicated to evaluate an algorithm's ability of accurately locating all knee points in high-dimensional objective space have been suggested. This paper proposes a set of multiobjective optimization test problems whose Pareto front consists of complex knee regions, aiming to assess the capability of evolutionary algorithms to accurately identify all knee points. Various features related to knee points have been taken into account in designing the test problems, including symmetry, differentiability, and degeneration. These features are also combined with other challenges in solving the optimization problems, such as multimodality, linkage between decision variables, nonuniformity, and scalability of the Pareto front. The proposed test problems are scalable to both decision and objective spaces. Accordingly, new performance indicators are suggested for evaluating the capability of optimization algorithms in locating the knee points. The proposed test problems, together with the performance indicators, offer a new means to develop and assess preference-based evolutionary algorithms for solving multi- and many-objective optimization problems.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date :
Changqing Zhang; Ziwei Yu; Huazhu Fu; Pengfei Zhu; Lei Chen; Qinghua Hu

For real-world applications, multilabel learning usually suffers from unsatisfactory training data. Typically, features may be corrupted or class labels may be noisy or both. Ignoring noise in the learning process tends to result in an unreasonable model and, thus, inaccurate prediction. Most existing methods only consider either feature noise or label noise in multilabel learning. In this paper, we propose a unified robust multilabel learning framework for data with hybrid noise, that is, both feature noise and label noise. The proposed method, hybrid noise-oriented multilabel learning (HNOML), is simple but rather robust for noisy data. HNOML simultaneously addresses feature and label noise by bi-sparsity regularization bridged with label enrichment. Specifically, the label enrichment matrix explores the underlying correlation among different classes which improves the noisy labeling. Bridged with the enriching label matrix, the structured sparsity is imposed to jointly handle the corrupted features and noisy labeling. We utilize the alternating direction method (ADM) to efficiently solve our problem. Experimental results on several benchmark datasets demonstrate the advantages of our method over the state-of-the-art ones.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-08
Shuaibing Zhu; Jin Zhou; Guanrong Chen; Jun-An Lu

Topology identification of complex dynamical networks received extensive attention in the past decade. Most existing studies rely heavily on the linear independence condition (LIC). We find that a critical step in using this condition is not rigorous. Besides, it is difficult to verify this condition. Without regulating the original network, possible identification failure caused by network synchronization cannot be avoided. In this paper, we propose a new method to overcome these shortcomings. We add a regulation mechanism to the original network and construct an auxiliary network consisting of isolated nodes. Along with the outer synchronization between the regulated network and the auxiliary network, we show that the original network can be identified. Our method can avoid identification failure caused by network synchronization. Moreover, we show that there is no need to check the LIC. We finally provide some examples to demonstrate that our method is reliable and has good performances.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-08
Jin Zhang; Chen Peng; Xiangpeng Xie; Dong Yue

This paper investigates the output feedback stabilization problem for networked control systems under a stochastic scheduling protocol. First, an independent and identically distributed (i.i.d) scheduling protocol is introduced to orchestrate the signal transmission via a communication network. Taking into account the i.i.d protocol, network-induced delay, and packet dropout, a stochastic impulsive delayed model is presented for the studied system. Second, by use of the Lyapunov-Krasovskii functional approach, sufficient conditions for guaranteeing the stability of the studied system in the mean-square sense are obtained in the form of matrix inequalities. Moreover, an optimization algorithm is investigated to obtain the suitable dynamic output feedback controller and optimal i.i.d protocol parameters simultaneously. Finally, two numerical examples are presented to show the validity of the proposed method.

更新日期：2019-02-11
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-07
Runqi Chai; Al Savvaris; Antonios Tsourdos; Senchun Chai; Yuanqing Xia; Shuo Wang

The objective of this paper is to present an approximation-based strategy for solving the problem of nonlinear trajectory optimization with the consideration of probabilistic constraints. The proposed method defines a smooth and differentiable function to replace probabilistic constraints by the deterministic ones, thereby converting the chance-constrained trajectory optimization model into a parametric nonlinear programming model. In addition, it is proved that the approximation function and the corresponding approximation set will converge to that of the original problem. Furthermore, the optimal solution of the approximated model is ensured to converge to the optimal solution of the original problem. Numerical results, obtained from a new chance-constrained space vehicle trajectory optimization model and a 3-D unmanned vehicle trajectory smoothing problem, verify the feasibility and effectiveness of the proposed approach. Comparative studies were also carried out to show the proposed design can yield good performance and outperform other typical chance-constrained optimization techniques investigated in this paper.

更新日期：2019-02-08
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-07
Jing Na; Shubo Wang; Yan-Jun Liu; Yingbo Huang; Xuemei Ren

Although adaptive control design with function approximators, for example, neural networks (NNs) and fuzzy logic systems, has been studied for various nonlinear systems, the classical adaptive laws derived based on the gradient descent algorithm with σ-modification or e-modification cannot guarantee the parameter estimation convergence. These nonconvergent learning methods may lead to sluggish response in the control system and make the parameter tuning complex. The aim of this paper is to propose a new learning strategy driven by the estimation error to design the alternative adaptive laws for adaptive control of nonlinear servo systems. The parameter estimation error is extracted and used as a new leakage term in the adaptive laws. By using this new learning method, the convergence of both the estimated parameters and the tracking error can be achieved simultaneously. The proposed learning algorithm is further tailored to retain finite-time convergence. To handle unknown nonlinearities in the servomechanisms, an augmented NN with a new friction model is used, where both the NN weights and some friction model coefficients are estimated online via the proposed algorithms. Comparisons with the σ-modification algorithm are addressed in terms of convergence property and robustness. Simulations and practical experiments are given to show the superior performance of the suggested adaptive algorithms.

更新日期：2019-02-08
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-05
Bin Gu; Yingying Shan; Xin Quan; Guansheng Zheng

Sequential minimal optimization (SMO) is one of the most popular methods for solving a variety of support vector machines (SVMs). The shrinking and caching techniques are commonly used to accelerate SMO. An interesting phenomenon of SMO is that most of the computational time is wasted on the first half of iterations for building a good solution closing to the optimal. However, as we all know, the stochastic subgradient descent (SSGD) method is extremely fast for building a good solution. In this paper, we propose a generalized framework of accelerating SMO through SSGD for a variety of SVMs of binary classification, regression, ordinal regression, and so on. We also provide a deep insight about why SSGD can accelerate SMO. Experimental results on a variety of datasets and learning applications confirm that our method can effectively speed up SMO.

更新日期：2019-02-06
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-05
Guo-Ping Liu

This paper is concerned with the coordinated control problem of multiagent systems with communication constraints. A cost function of measuring the coordinated control between networked multiagents is presented. The networked proportional integral predictive control scheme is proposed so that not only the cost function is optimized but also simultaneous consensus and stability of networked multiagent systems is achieved and the communication constraints are actively compensated. The further analysis provides the necessary and sufficient conditions of reaching simultaneous stability and consensus. An example shows the proposed scheme works effectively.

更新日期：2019-02-06
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-02-01
Jianhui Wang; Zhi Liu; Yun Zhang; C. L. Philip Chen; Guanyu Lai

In this paper, an adaptive neural network control for stochastic nonlinear systems with uncertain disturbances is proposed. The neural network is considered to approximate an uncertain function in a nonlinear system. And computational burden in operation is reduced by handling the norm of the neural-network vector. However, it will arise chattering issue, which is a challenge to avoid it from the symbolic operation. Further, traditional schemes often view error of estimate as bounded constant, but it is a time-varying function exactly, which may lead control schemes cannot conform to practical situation and guarantee stability of systems. Thus, backstepping technology and the neural network technology combined to stabilize stochastic nonlinear systems together to handle the aforementioned issues. It is proved that the proposed control scheme can guarantee the satisfactory asymptotic convergence performance and predetermined transient tracking error performance. From simulation results, the proposed control scheme is verified that can guarantee the satisfactory effectiveness.

更新日期：2019-02-06
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-31
Hongjing Liang; Yanhui Zhang; Tingwen Huang; Hui Ma

This paper studies the quantized cooperative control problem for multiagent systems with unknown gains in the prescribed performance. Different from the finite-time control, a speed function is designed to realize that the tracking errors converge to a prescribed compact set in a given finite time for multiagent systems. Meanwhile, we consider the problem of unknown gains and input quantization, which can be addressed by using a lemma and Nussbaum function in cooperative control. Moreover, the fuzzy logic systems are proposed to approximate the nonlinear function defined on a compact set. A distributed controller and adaptive laws are constructed based on the Lyapunov stability theory and backstepping method. Finally, the effectiveness of the proposed approach is illustrated by some numerical simulation results.

更新日期：2019-02-06
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-30
Yafeng Li; Changchun Hua; Xinping Guan

In this paper, the distributed output feedback leader-following control is investigated for high-order nonlinear multiagent systems (MASs) using the dynamic gain method. The linear-like distributed output feedback controller is designed without using the recursive method to overcome the explosion of complexity'' problem and further relax the conditions on the nonlinear functions of the MASs. First, the distributed reduced order dynamic gain observer is constructed for the ith agent to estimate its unmeasured state variables, in which the output information of its neighbors are used. Second, the linear-like output feedback controller is designed such that the outputs of the followers track the leader's output, and the tracking error could be arbitrarily small. Finally, the simulation examples are given to illustrate the effectiveness of the proposed method.

更新日期：2019-01-31
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-30
Shengnan Wang; Chunguang Li; Hui-Liang Shen

Hashing-based approximate nearest neighbors search has attracted broad research interest, due to its low computational cost and fast retrieval speed. The hashing technique maps the data points into binary codes and, meanwhile, preserves the similarity in the original space. Generally, we need to solve a discrete optimization problem to learn the binary codes and hash functions, which is NP-hard. In the literature, most hashing methods choose to solve a relaxed problem by discarding the discrete constraints. However, such a relaxation scheme will cause large quantization error, which makes the learned binary codes less effective. In this paper, we present an equivalent continuous formulation of the discrete hashing problem. Specifically, we show that the discrete hashing problem can be transformed into a continuous optimization problem without any relaxations, while the transformed continuous optimization problem has the same optimal solutions and the same optimal value as the original discrete hashing problem. After transformation, the continuous optimization methods can be applied. We devise the algorithms based on the idea of DC (difference of convex functions) programming to solve this problem. The proposed continuous hashing scheme can be easily applied to the existing hashing models, including both supervised and unsupervised hashing. We evaluate the proposed method on several benchmarks and the results show the superiority of the proposed method compared with the state-of-the-art hashing methods.

更新日期：2019-01-31
• IEEE Trans. Cybern. (IF 8.803) Pub Date :
Fangyi Li; Ying Li; Changjing Shang; Qiang Shen

Fuzzy rule interpolation (FRI) facilitates approximate reasoning in fuzzy rule-based systems only with sparse knowledge available, remedying the limitation of conventional compositional rule of inference working with a dense rule base. Most of the existing FRI work assumes equal significance of the conditional attributes in the rules while performing interpolation. Recently, interesting techniques have been reported for achieving weighted interpolative reasoning. However, they are either particularly tailored to perform classification problems only or employ attribute weights that are obtained using additional information (rather than just the given rules), without integrating them with the associated FRI procedure. This paper presents a weighted rule interpolation scheme for performing prediction tasks by the use of fuzzy sparse knowledge only. The weights of rule conditional attributes are learned from a given rule base to discriminate the relative significance of each individual attribute and are integrated throughout the internal mechanism of the FRI process. This scheme is demonstrated using the popular scale and move transformation-based FRI for resolving prediction problems, systematically evaluated on 12 benchmark prediction tasks. The performance is compared with the relevant state-of-the-art FRI techniques, showing the efficacy of the proposed approach.

更新日期：2019-01-28
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-25
Ryoji Tanabe; Alex Fukunaga

Many differential evolution (DE) algorithms with various parameter control methods (PCMs) have been proposed. However, previous studies usually considered PCMs to be an integral component of a complex DE algorithm. Thus, the characteristics and performance of each method are poorly understood. We present an in-depth review of 24 PCMs for the scale factor and crossover rate in DE and a large-scale benchmarking study. We carefully extract the 24 PCMs from their original, complex algorithms and describe them according to a systematic manner. Our review facilitates the understanding of similarities and differences between existing, representative PCMs. The performance of DEs with the 24 PCMs and 16 variation operators is investigated on 24 black-box benchmark functions. Our benchmarking results reveal which methods exhibit high performance when embedded in a standardized framework under 16 different conditions, independent from their original, complex algorithms. We also investigate how much room there is for further improvement of PCMs by comparing the 24 methods with an oracle-based model, which can be considered to be a conservative lower bound on the performance of an optimal method.

更新日期：2019-01-28
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-25
Deqing Wang; Chenwei Lu; Junjie Wu; Hongfu Liu; Wenjie Zhang; Fuzhen Zhuang; Hui Zhang

The main challenge of cross-domain text classification is to train a classifier in a source domain while applying it to a different target domain. Many transfer learning-based algorithms, for example, dual transfer learning, triplex transfer learning, etc., have been proposed for cross-domain classification, by detecting a shared low-dimensional feature representation for both source and target domains. These methods, however, often assume that the word clusters matrix or the clusters association matrix as knowledge transferring bridges are exactly the same across different domains, which is actually unrealistic in real-world applications and, therefore, could degrade classification performance. In light of this, in this paper, we propose a softly associative transfer learning algorithm for cross-domain text classification. Specifically, we integrate two non-negative matrix tri-factorizations into a joint optimization framework, with approximate constraints on both word clusters matrices and clusters association matrices so as to allow proper diversity in knowledge transfer, and with another approximate constraint on class labels in source domains in order to handle noisy labels. An iterative algorithm is then proposed to solve the above problem, with its convergence verified theoretically and empirically. Extensive experimental results on various text datasets demonstrate the effectiveness of our algorithm, even with the presence of abundant state-of-the-art competitors.

更新日期：2019-01-28
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-25
R. Baranitha; Reza Mohajerpoor; R. Rakkiyappan

Communication time delays in a bilateral teleoperation system often carries a stochastic nature, particularly when we have multiple masters or slaves. In this paper, we tackle the problem for a single-master multislave (SMMS) teleoperation system by assuming an asymmetric and semi-Markovian jump protocol for communication of the slaves with the master under time-varying transition rates. A nonlinear robust controller is designed for the system that guarantees its global robust H∞ stochastic stability in the sense of the Lyapunov theory. Employing the nonlinear feedback linearization technique, the dynamics of the closed-loop teleoperator is decoupled into two interconnected subsystems: 1) master-slave tracking dynamics (coordination) and 2) multislave synchronization dynamics. Employing an improved reciprocally convex combination technique, the stability analysis of the closed-loop teleoperator is conducted using the Lyapunov-Krasovskii methodology, and the stability conditions are expressed in the form of linear matrix inequalities that can be solved efficiently using numerical algorithms. Numerical studies and simulation results validate the effectiveness of the proposed controller design algorithm in both tracking and synchronization performance of the SMMS system, and robustly handling the stochastic and nondifferentiable nature of communication delays.

更新日期：2019-01-28
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-25
Yi Jiang; Bahare Kiumarsi; Jialu Fan; Tianyou Chai; Jinna Li; Frank L. Lewis

This paper presents a model-free optimal approach based on reinforcement learning for solving the output regulation problem for discrete-time systems under disturbances. This problem is first broken down into two optimization problems: 1) a constrained static optimization problem is established to find the solution to the output regulator equations (i.e., the feedforward control input) and 2) a dynamic optimization problem is established to find the optimal feedback control input. Solving these optimization problems requires the knowledge of the system dynamics. To obviate this requirement, a model-free off-policy algorithm is presented to find the solution to the dynamic optimization problem using only measured data. Then, based on the solution to the dynamic optimization problem, a model-free approach is provided for the static optimization problem. It is shown that the proposed algorithm is insensitive to the probing noise added to the control input for satisfying the persistence of excitation condition. Simulation results are provided to verify the effectiveness of the proposed approach.

更新日期：2019-01-28
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-24
Xinghua Liu; Wee Peng Tay; Zhi-Wei Liu; Gaoxi Xiao

We consider the quasi-synchronization problem of a continuous time generalized Markovian switching heterogeneous network with time-varying connectivity, using pinned nodes that are event-triggered to reduce the frequency of controller updates and internode communications. We propose a pinning strategy algorithm to determine how many and which nodes should be pinned in the network. Based on the assumption that a network has limited control efficiency, we derive a criterion for stability, which relates the pinning feedback gains, the coupling strength, and the inner coupling matrix. By utilizing the stochastic Lyapunov stability analysis, we obtain sufficient conditions for exponential quasi-synchronization under our stochastic event-triggering mechanism, and a bound for the quasi-synchronization error. Numerical simulations are conducted to verify the effectiveness of the proposed control strategy.

更新日期：2019-01-25
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-24
Vittorio Latorre; David Yang Gao

This paper presents a new deterministic method and a polynomial-time algorithm for solving general huge-sized sensor network localization problems. The problem is first formulated as a nonconvex minimization, which was considered as an NP-hard based on conventional theories. However, by the canonical duality theory, this challenging problem can be equivalently converted into a convex dual problem. By introducing a new optimality measure, a powerful canonical primal-dual interior (CPDI) point algorithm is developed which can solve efficiently huge-sized problems with hundreds of thousands of sensors. The new method is compared with the popular methods in the literature. Results show that the CPDI algorithm is not only faster than the benchmarks but also much more accurate on networks affected by noise on the distances.

更新日期：2019-01-25
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-23
Parham M. Kebria; Abbas Khosravi; Saeid Nahavandi; Peng Shi; Roohallah Alizadehsani

This paper proposes a robust adaptive algorithm that effectively copes with time-varying delay and uncertainties in Internet-based teleoperation systems. Time-delay induced by the communication network, as a major problem in teleoperation systems, along with uncertainties in modeling of robotic manipulators and remote environment warn the stability and performance of the system. A robust adaptive control algorithm is developed to deal with the system uncertainties and to provide a smooth estimation of delayed reference signals. The proposed control algorithm generates chattering-free torques which is one of the practical considerations for robotic applications. In addition, the achieved input-to-state stability gains do not necessarily require high gain control torques to retain the system's stability. Experimental simulation studies validate the effectiveness of the proposed control strategy on a teleoperation system consisting of a Phantom Omni Haptic device and SimMechanics model of the industrial manipulator UR10. The validation of the proposed control methodology was executed through a real-time Internet-based communication established over 4G mobile networks between Australia and Scotland.

更新日期：2019-01-24
• IEEE Trans. Cybern. (IF 8.803) Pub Date : 2019-01-18
Clara Pizzuti; Annalisa Socievole

Methods for detecting the community structure in complex networks have mainly focused on network topology, neglecting the rich content information often associated with nodes. In the last few years, the compositional dimension contained in many real-world networks has been recognized fundamental to find network divisions which better reflect group organization. In this paper, we propose a multiobjective genetic framework which integrates the topological and compositional dimensions to uncover community structure in attributed networks. The approach allows to experiment different structural measures to search for densely connected communities, and similarity measures between attributes to obtain high intracommunity feature homogeneity. An efficient and efficacious post-processing local merge procedure enables the generation of high quality solutions, as confirmed by the experimental results on both synthetic and real-world networks, and the comparison with several state-of-the-art methods.

更新日期：2019-01-22
Some contents have been Reproduced with permission of the American Chemical Society.
Some contents have been Reproduced by permission of The Royal Society of Chemistry.