This page has only limited features, please log in for full access.

Unclaimed
Haibo He
Department of Electrical, Computer and Biomedical Engineering; University of Rhode Island; Kingston RI USA

Basic Info

Basic Info is private.

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 14 June 2021 in IEEE Transactions on Automatic Control
Reads 0
Downloads 0

In this paper, a type of intermittently coupled spatiotemporal networks (ICSNs) is proposed by means of partial differential equations, where the couplings among nodes are intermittent and the coupling weights are dependent of both time and space. By constructing piecewise auxiliary functions and developing a direct error method, several distributed intermittent adaptive protocols are designed to determine the space-time dependent weights of edges to realize synchronization of ICSNs. Particularly, based on spanning tree, an edge-based adaptive pinning scheme is proposed and it is demonstrated that the synchronization of ICSNs can be achieved by simply intermittently adjusting the weights of edges within a spanning tree. Lastly, the theoretical results are verified by means of some numerical examples.

ACS Style

Cheng Hu; Haibo He; Haijun Jiang. Edge-Based Adaptive Distributed Method for Synchronization of Intermittently Coupled Spatiotemporal Networks. IEEE Transactions on Automatic Control 2021, PP, 1 -1.

AMA Style

Cheng Hu, Haibo He, Haijun Jiang. Edge-Based Adaptive Distributed Method for Synchronization of Intermittently Coupled Spatiotemporal Networks. IEEE Transactions on Automatic Control. 2021; PP (99):1-1.

Chicago/Turabian Style

Cheng Hu; Haibo He; Haijun Jiang. 2021. "Edge-Based Adaptive Distributed Method for Synchronization of Intermittently Coupled Spatiotemporal Networks." IEEE Transactions on Automatic Control PP, no. 99: 1-1.

Journal article
Published: 19 March 2021 in IEEE Wireless Communications Letters
Reads 0
Downloads 0

In this letter, we propose a deep transfer cooperative sensing (DTCS) approach in cognitive radio networks, where multiple secondary users (SUs) cooperate to detect the presence of signals from a primary user (PU) in a shared frequency band. DTCS is a cooperative spectrum sensing (CSS) framework based on unsupervised deep transfer learning. It operates on energy vectors, whose each element is a sensing result by an energy detector from individual SU. It learns the knowledge by combining the sensing results from all SUs in one radio frequency environment and transfers it to another one. This approach is applicable for detecting the presence of arbitrary unknown signals, which enhances the generalization ability and robustness of the framework. Simulation results demonstrate the effectiveness of DTCS.

ACS Style

Lusi Li; He Jiang; Haibo He. Deep Transfer Cooperative Sensing in Cognitive Radio. IEEE Wireless Communications Letters 2021, 10, 1354 -1358.

AMA Style

Lusi Li, He Jiang, Haibo He. Deep Transfer Cooperative Sensing in Cognitive Radio. IEEE Wireless Communications Letters. 2021; 10 (6):1354-1358.

Chicago/Turabian Style

Lusi Li; He Jiang; Haibo He. 2021. "Deep Transfer Cooperative Sensing in Cognitive Radio." IEEE Wireless Communications Letters 10, no. 6: 1354-1358.

Journal article
Published: 02 February 2021 in IEEE Transactions on Automatic Control
Reads 0
Downloads 0

This paper addresses the problem of cooperative adaptive containment control for multi-agent systems, which specifies the objective of jointly achieving containment control and accurate adaptive learning/identification of unknown system parameters. We consider a class of linear uncertain multi-agent systems with multiple leaders subject to bounded unmeasurable inputs and multiple followers subject to unknown system dynamics. A novel cooperative adaptive containment control architecture is proposed, which consists of a discontinuous nonlinear state-feedback control law and a filter-based cooperative adaptation law. This new control architecture is compelling in the sense that exponential convergence of both containment tracking errors to zero and adaptation parameters to their true values can be achieved simultaneously under a mild cooperative finite-time excitation condition. This condition significantly relaxes existing ones (e.g., persistent excitation and finite-time excitation) for parameter identification in adaptive control systems. Effectiveness of the proposed approach has been demonstrated through both rigorous analysis and a case study.

ACS Style

Chengzhi Yuan; Paolo Stegagno; Haibo He; Wei Ren. Cooperative Adaptive Containment Control with Parameter Convergence via Cooperative Finite-Time Excitation. IEEE Transactions on Automatic Control 2021, PP, 1 -1.

AMA Style

Chengzhi Yuan, Paolo Stegagno, Haibo He, Wei Ren. Cooperative Adaptive Containment Control with Parameter Convergence via Cooperative Finite-Time Excitation. IEEE Transactions on Automatic Control. 2021; PP (99):1-1.

Chicago/Turabian Style

Chengzhi Yuan; Paolo Stegagno; Haibo He; Wei Ren. 2021. "Cooperative Adaptive Containment Control with Parameter Convergence via Cooperative Finite-Time Excitation." IEEE Transactions on Automatic Control PP, no. 99: 1-1.

Journal article
Published: 18 January 2021 in IEEE Access
Reads 0
Downloads 0

This article investigates the autonomous demand response (ADR) in a building microgrid incorporating photovoltaic (PV) generation and plug-in electric vehicles. Two operation models are introduced in this article to enhance the self-utilization of PV power: 1) mixed integer programming (MIP)-based optimization model; and 2) the game theoretic model. To avoid the disadvantages of MIP-based centralized optimization in a decentralized approach, a non-cooperative ADR game framework is formulated based on the proposed virtual cost mechanism for each player to help in selecting the optimal consumption strategy coordinately. The existence of the unique Nash equilibrium which coincides with the optimal solution of the MIP-based operation model is proved. In addition, an iterative algorithm is developed to determine the equilibrium solution for the ADR game. Simulation results verify that the non-cooperative game-based ADR program is effective in improving the utilization of PV energy and benefits to microgrid systems.

ACS Style

Xiaodong Yang; Youbing Zhang; Fan Zhang; Chongbo Xu; Biyi Yi. Enhancing Utilization of PV Energy in Building Microgrids via Autonomous Demand Response. IEEE Access 2021, 9, 23554 -23564.

AMA Style

Xiaodong Yang, Youbing Zhang, Fan Zhang, Chongbo Xu, Biyi Yi. Enhancing Utilization of PV Energy in Building Microgrids via Autonomous Demand Response. IEEE Access. 2021; 9 ():23554-23564.

Chicago/Turabian Style

Xiaodong Yang; Youbing Zhang; Fan Zhang; Chongbo Xu; Biyi Yi. 2021. "Enhancing Utilization of PV Energy in Building Microgrids via Autonomous Demand Response." IEEE Access 9, no. : 23554-23564.

Journal article
Published: 06 January 2021 in IEEE Transactions on Neural Networks and Learning Systems
Reads 0
Downloads 0

“Happy New Year!” As you open this January 2021 issue of IEEE T ransactions on N eural N etworks and L earning S ystems (IEEE TNNLS), I hope everyone enjoyed a healthy and happy holiday season!

ACS Style

Haibo He. Editorial: Staying Healthy and Strong Together. IEEE Transactions on Neural Networks and Learning Systems 2021, 32, 2 -3.

AMA Style

Haibo He. Editorial: Staying Healthy and Strong Together. IEEE Transactions on Neural Networks and Learning Systems. 2021; 32 (1):2-3.

Chicago/Turabian Style

Haibo He. 2021. "Editorial: Staying Healthy and Strong Together." IEEE Transactions on Neural Networks and Learning Systems 32, no. 1: 2-3.

Journal article
Published: 01 January 2021 in IEEE Transactions on Knowledge and Data Engineering
Reads 0
Downloads 0

Incomplete multi-view clustering (IMC) aims to integrate the complementary information from incomplete views to improve clustering performance. Most existing IMC methods try to fill the incomplete views or directly learn a common representation based on matrix factorization or subspace learning. The former may introduce useless even noisy information especially for data with a large missing ratio. The latter relies on the initialization and ignores the geometric structure of data. To address these issues, we propose a novel Joint Partition and Graph (JPG) learning method for IMC. Specifically, JPG jointly constructs local incomplete graph matrices, generates incomplete base partition matrices, stretches them to produce a unified partition matrix, and employs it to learn a consensus graph matrix. By this means, we transform incomplete multi-view data into a unified partition space and obtain the consensus graph in a mutual reinforcement manner. Moreover, a partition fusion strategy can allocate a large weight to the stretched base partition that is close to the unified matrix. The objective function is optimized in an alternating optimization fashion. Experimental results on several benchmark datasets demonstrate the effectiveness and superiority of JPG than the state-of-the-art baselines

ACS Style

Lusi Li; Zhiqiang Wan; Haibo He. Incomplete Multi-view Clustering with Joint Partition and Graph Learning. IEEE Transactions on Knowledge and Data Engineering 2021, PP, 1 -1.

AMA Style

Lusi Li, Zhiqiang Wan, Haibo He. Incomplete Multi-view Clustering with Joint Partition and Graph Learning. IEEE Transactions on Knowledge and Data Engineering. 2021; PP (99):1-1.

Chicago/Turabian Style

Lusi Li; Zhiqiang Wan; Haibo He. 2021. "Incomplete Multi-view Clustering with Joint Partition and Graph Learning." IEEE Transactions on Knowledge and Data Engineering PP, no. 99: 1-1.

Journal article
Published: 10 December 2020 in IEEE Transactions on Cybernetics
Reads 0
Downloads 0

This article presents a new command-filtered composite adaptive neural control scheme for uncertain nonlinear systems. Compared with existing works, this approach focuses on achieving finite-time convergent composite adaptive control for the higher-order nonlinear system with unknown nonlinearities, parameter uncertainties, and external disturbances. First, radial basis function neural networks (NNs) are utilized to approximate the unknown functions of the considered uncertain nonlinear system. By constructing the prediction errors from the serial-parallel nonsmooth estimation models, the prediction errors and the tracking errors are fused to update the weights of the NNs. Afterward, the composite adaptive neural backstepping control scheme is proposed via nonsmooth command filter and adaptive disturbance estimation techniques. The proposed control scheme ensures that high-precision tracking performances and NN approximation performances can be achieved simultaneously. Meanwhile, it can avoid the singularity problem in the finite-time backstepping framework. Moreover, it is proved that all signals in the closed-loop control system can be convergent in finite time. Finally, simulation results are given to illustrate the effectiveness of the proposed control scheme.

ACS Style

Jinlin Sun; Haibo He; Jianqiang Yi; Zhiqiang Pu. Finite-Time Command-Filtered Composite Adaptive Neural Control of Uncertain Nonlinear Systems. IEEE Transactions on Cybernetics 2020, PP, 1 -13.

AMA Style

Jinlin Sun, Haibo He, Jianqiang Yi, Zhiqiang Pu. Finite-Time Command-Filtered Composite Adaptive Neural Control of Uncertain Nonlinear Systems. IEEE Transactions on Cybernetics. 2020; PP (99):1-13.

Chicago/Turabian Style

Jinlin Sun; Haibo He; Jianqiang Yi; Zhiqiang Pu. 2020. "Finite-Time Command-Filtered Composite Adaptive Neural Control of Uncertain Nonlinear Systems." IEEE Transactions on Cybernetics PP, no. 99: 1-13.

Journal article
Published: 09 December 2020 in IEEE Transactions on Human-Machine Systems
Reads 0
Downloads 0

Sensor-based human activity recognition (HAR) aims to recognize a human's physical actions by using sensors attached to different body parts. As a user-specific application, HAR often suffers poor generalization from training on an individual to testing on another individual, or from one body part to another body part. To tackle this cross-domain HAR problem, this article proposes a domain adaptation (DA) method called local domain adaptation (LDA), whose core is to align cluster-to-cluster distributions between the source domain and the target domain. On the one hand, LDA differs from existing set-to-set alignment by reducing the distribution discrepancy at a finer granularity. On the other hand, LDA is superior to the class-to-class alignment because it can provide more accurate soft labels for the target domain. Specifically, LDA contains three main steps: 1) groups the activity class into several high-level abstract clusters; 2) maps the original data of each cluster in both domains into the same low-dimension subspace to align the intracluster data distribution; 3) predicts the class labels for target domain in the low-dimension subspace. Experimental results on two public HAR benchmark datasets show that LDA outperforms state-of-the-art DA methods for the cross-domain HAR.

ACS Style

Jiachen Zhao; Fang Deng; Haibo He; Jie Chen. Local Domain Adaptation for Cross-Domain Activity Recognition. IEEE Transactions on Human-Machine Systems 2020, 51, 12 -21.

AMA Style

Jiachen Zhao, Fang Deng, Haibo He, Jie Chen. Local Domain Adaptation for Cross-Domain Activity Recognition. IEEE Transactions on Human-Machine Systems. 2020; 51 (1):12-21.

Chicago/Turabian Style

Jiachen Zhao; Fang Deng; Haibo He; Jie Chen. 2020. "Local Domain Adaptation for Cross-Domain Activity Recognition." IEEE Transactions on Human-Machine Systems 51, no. 1: 12-21.

Journal article
Published: 01 December 2020 in IEEE Transactions on Industrial Informatics
Reads 0
Downloads 0

This article investigates distributed coordinated tracking problems of networked heterogeneous systems. Based on asynchronous sampling information, distributed sampled-data protocols are employed to realize leader-following synchronization and containment tracking in networked heterogeneous systems. In asynchronous sampled-data protocols, each node has different sampling instants with other nodes and only samples itself information at its own sampling instants. By utilizing the input-delay approach and Lyapunove-Krasovskii functional approach, some sufficient conditions for guaranteeing the coordinated tracking are presented. First, quasi-synchronization criteria are obtained for networked heterogeneous oscillator systems with a dynamic leader over the directed graph. Second, in the presence of multiple heterogeneous leaders for networked heterogeneous systems, sufficient conditions of quasi-containment tracking are derived. In a word, all followers can converge into a bounded level of convex hull spanned by the leader(s). The upper bounds of tracking errors are estimated for both quasi-synchronization and quasi-containment tracking. Finally, two numerical examples are given to verify the theoretical results.

ACS Style

Zhengxin Wang; Haibo He; Guo-Ping Jiang; Jinde Cao. Distributed Tracking in Heterogeneous Networks With Asynchronous Sampled-Data Control. IEEE Transactions on Industrial Informatics 2020, 16, 7381 -7391.

AMA Style

Zhengxin Wang, Haibo He, Guo-Ping Jiang, Jinde Cao. Distributed Tracking in Heterogeneous Networks With Asynchronous Sampled-Data Control. IEEE Transactions on Industrial Informatics. 2020; 16 (12):7381-7391.

Chicago/Turabian Style

Zhengxin Wang; Haibo He; Guo-Ping Jiang; Jinde Cao. 2020. "Distributed Tracking in Heterogeneous Networks With Asynchronous Sampled-Data Control." IEEE Transactions on Industrial Informatics 16, no. 12: 7381-7391.

Journal article
Published: 17 November 2020 in IEEE Transactions on Smart Grid
Reads 0
Downloads 0

This paper proposes a flexible event-triggered online scheduling (ETOS) method for residential multi-microgrid (MMG) systems integrating internal scheduling and external energy sharing levels. Our novelties lie in the flexible ETOS framework embedding customized functions and the fair energy sharing mechanism. Unlike time-triggered methods with a holistic controller and complex mechanisms, the presented ETOS framework achieves systematic management of MMG by simulating its real-life dynamics from the perspective of event-triggering. In the internal scheduling level, universal working logics are designed through active “demand response" interaction, which has high scalability and openness in function and makes event customization possible for future use. In the energy sharing level, the concept of energy level is introduced to organize a localized energy sharing, in which the sharing strategies can be decided through stimulation and transition with the advantages of fairness and low complexity. Moreover, we specify detailed function and algorithm for ETOS entities, helping to realize flexible online operation of MMG in a decentralized and natural way. Numerical simulations show that proposed ETOS is economically beneficial, computationally efficient, and is promising to facilitate the online scheduling of a practical real world MMG project.

ACS Style

Xiaodong Yang; Youbing Zhang; Hangfei Wu; Jinyu Wen; Shijie Cheng. Enabling Online Scheduling for Multi-Microgrid Systems: An Event-Triggered Approach. IEEE Transactions on Smart Grid 2020, 12, 1836 -1852.

AMA Style

Xiaodong Yang, Youbing Zhang, Hangfei Wu, Jinyu Wen, Shijie Cheng. Enabling Online Scheduling for Multi-Microgrid Systems: An Event-Triggered Approach. IEEE Transactions on Smart Grid. 2020; 12 (3):1836-1852.

Chicago/Turabian Style

Xiaodong Yang; Youbing Zhang; Hangfei Wu; Jinyu Wen; Shijie Cheng. 2020. "Enabling Online Scheduling for Multi-Microgrid Systems: An Event-Triggered Approach." IEEE Transactions on Smart Grid 12, no. 3: 1836-1852.

Journal article
Published: 30 October 2020 in IEEE Transactions on Smart Grid
Reads 0
Downloads 0

The uncertainty of distributed renewable energy brings significant challenges to economic operation of microgrids. Conventional online optimization approaches require a forecast model. However, accurately forecasting the renewable power generations is still a tough task. To achieve online scheduling of a residential microgrid (RM) that does not need a forecast model to predict the future PV/wind and load power sequences, this paper investigates the usage of reinforcement learning (RL) approach to tackle this challenge. Specifically, based on the recent development of Model-Based Reinforcement Learning, MuZero [1], we investigate its application to the RM scheduling problem. To accommodate the characteristics of the RM scheduling application, a optimization framework that combines the model-based RL agent with the mathematical optimization technique is designed, and long short-term memory (LSTM) units are adopted to extract features from the past renewable generation and load sequences. At each time step, the optimal decision is obtained by conducting Monte-Carlo tree search (MCTS) with a learned model and solving an optimal power flow sub-problem. In this way, this approach can sequentially make operational decisions online without relying on a forecast model. The numerical simulation results demonstrate the effectiveness of the proposed algorithm.

ACS Style

Hang Shuai; Haibo He. Online Scheduling of a Residential Microgrid via Monte-Carlo Tree Search and a Learned Model. IEEE Transactions on Smart Grid 2020, 12, 1073 -1087.

AMA Style

Hang Shuai, Haibo He. Online Scheduling of a Residential Microgrid via Monte-Carlo Tree Search and a Learned Model. IEEE Transactions on Smart Grid. 2020; 12 (2):1073-1087.

Chicago/Turabian Style

Hang Shuai; Haibo He. 2020. "Online Scheduling of a Residential Microgrid via Monte-Carlo Tree Search and a Learned Model." IEEE Transactions on Smart Grid 12, no. 2: 1073-1087.

Journal article
Published: 23 October 2020 in IEEE Transactions on Cybernetics
Reads 0
Downloads 0

Multiagent reinforcement learning (MARL) has recently attracted considerable attention from both academics and practitioners. Core issues, e.g., the curse of dimensionality due to the exponential growth of agent interactions and nonstationary environments due to simultaneous learning, hinder the large-scale proliferation of MARL. These problems deteriorate with an increased number of agents. To address these challenges, we propose an adversarial collaborative learning method in a mixed cooperative-competitive environment, exploiting friend-or-foe Q-learning and mean-field theory. We first treat neighbors of agent i as two coalitions (i's friend and opponent coalition, respectively), and convert the Markov game into a two-player zero-sum game with an extended action set. By exploiting mean-field theory, this new game simplifies the interactions as those between a single agent and the mean effects of friends and opponents. A neural network is employed to learn the optimal mean effects of these two coalitions, which are trained via adversarial max and min steps. In the max step, with fixed policies of opponents, we optimize the friends' mean action to maximize their rewards. In the min step, the mean action of opponents is trained to minimize the friends' rewards when the policies of friends are frozen. These two steps are proved to converge to a Nash equilibrium. Then, another neural network is applied to learn the best response of each agent toward the mean effects. Finally, the adversarial max and min steps can jointly optimize the two networks. Experiments on two platforms demonstrate the learning effectiveness and strength of our approach, especially with many agents.

ACS Style

Guiyang Luo; Hui Zhang; Haibo He; Jinglin Li; Fei-Yue Wang. Multiagent Adversarial Collaborative Learning via Mean-Field Theory. IEEE Transactions on Cybernetics 2020, 1 -14.

AMA Style

Guiyang Luo, Hui Zhang, Haibo He, Jinglin Li, Fei-Yue Wang. Multiagent Adversarial Collaborative Learning via Mean-Field Theory. IEEE Transactions on Cybernetics. 2020; (99):1-14.

Chicago/Turabian Style

Guiyang Luo; Hui Zhang; Haibo He; Jinglin Li; Fei-Yue Wang. 2020. "Multiagent Adversarial Collaborative Learning via Mean-Field Theory." IEEE Transactions on Cybernetics , no. 99: 1-14.

Journal article
Published: 07 October 2020 in IEEE Transactions on Cybernetics
Reads 0
Downloads 0

Recently, deep-learning-based feature extraction (FE) methods have shown great potential in hyperspectral image (HSI) processing. Unfortunately, it also brings a challenge that the training of the deep learning networks always requires large amounts of labeled samples, which is hardly available for HSI data. To address this issue, in this article, a novel unsupervised deep-learning-based FE method is proposed, which is trained in an end-to-end style. The proposed framework consists of an encoder subnetwork and a decoder subnetwork. The structure of the two subnetworks is symmetric for obtaining better downsampling and upsampling representation. Considering both spectral and spatial information, 3-D all convolution nets and deconvolution nets are used to structure the encoder subnetwork and decoder subnetwork, respectively. However, 3-D convolution and deconvolution kernels bring more parameters, which can deteriorate the quality of the obtained features. To alleviate this problem, a novel cost function with a sparse regular term is designed to obtain more robust feature representation. Experimental results on publicly available datasets indicate that the proposed method can obtain robust and effective features for subsequent classification tasks.

ACS Style

Mingyang Zhang; Maoguo Gong; Haibo He; Shengqi Zhu. Symmetric All Convolutional Neural-Network-Based Unsupervised Feature Extraction for Hyperspectral Images Classification. IEEE Transactions on Cybernetics 2020, 1 -13.

AMA Style

Mingyang Zhang, Maoguo Gong, Haibo He, Shengqi Zhu. Symmetric All Convolutional Neural-Network-Based Unsupervised Feature Extraction for Hyperspectral Images Classification. IEEE Transactions on Cybernetics. 2020; (99):1-13.

Chicago/Turabian Style

Mingyang Zhang; Maoguo Gong; Haibo He; Shengqi Zhu. 2020. "Symmetric All Convolutional Neural-Network-Based Unsupervised Feature Extraction for Hyperspectral Images Classification." IEEE Transactions on Cybernetics , no. 99: 1-13.

Journal article
Published: 31 August 2020 in IEEE Transactions on Smart Grid
Reads 0
Downloads 0

The conventional distributed secondary controller, consisting of a voltage controller and a power controller, is based on the parallel framework by exchanging two state variables and requires a voltage observer to regulate the voltage. In this paper, a cascaded control framework is proposed to achieve the voltage regulation and power sharing, in which only the power state variable is exchanged without the voltage observer. The secondary power controller is designed to adjust the reference value of the secondary voltage controller. And the output of the voltage controller is used to modify the input of the droop controller. Then a resilient cascaded controller is further proposed to enhance the controller resilience against time delays and disturbances. An extra information exchange block between the power controller and the voltage controller is introduced in the resilient cascaded controller. Moreover, the steady-state analysis is carried out to prove the effectiveness of proposed controllers. A small-signal model is also established to investigate the impact of controller parameter variation on the system dynamics. Finally, several case studies are conducted by simulations to demonstrate the performance of proposed controllers.

ACS Style

Jianyu Zhou; Mengxuan Shi; Xia Chen; Yin Chen; Jinyu Wen; Haibo He. A Cascaded Distributed Control Framework in DC Microgrids. IEEE Transactions on Smart Grid 2020, 12, 205 -214.

AMA Style

Jianyu Zhou, Mengxuan Shi, Xia Chen, Yin Chen, Jinyu Wen, Haibo He. A Cascaded Distributed Control Framework in DC Microgrids. IEEE Transactions on Smart Grid. 2020; 12 (1):205-214.

Chicago/Turabian Style

Jianyu Zhou; Mengxuan Shi; Xia Chen; Yin Chen; Jinyu Wen; Haibo He. 2020. "A Cascaded Distributed Control Framework in DC Microgrids." IEEE Transactions on Smart Grid 12, no. 1: 205-214.

Journal article
Published: 07 August 2020 in IEEE Transactions on Instrumentation and Measurement
Reads 0
Downloads 0

Bridge health assessment has been a challenging problem due to great evaluation errors caused by heterogeneous and different dimensional bridge factors. Most approaches employ monitoring data of one bridge factor to simplify the evaluation problem resulting in poor assessment performance. To address this issue, this paper proposes an end-to-end framework to evaluate the health of bridges by exploring objective features and correlations of multiple monitoring factors. This model aims to learn representative features from raw monitoring data of bridge factors (i.e., strain, temperature, traffic flow, and heavy vehicle number), and classify the comprehensive features into different health degrees in a single framework. Specifically, in terms of characteristics of bridge factors (e.g., time sequence and heterogeneity), a hierarchical learning structure with multiple convolutional, pooling, and dense layers is presented to learn the representations of the whole bridge monitoring data. The structure contributes to capturing rich information from different observed factors and improving feature learning ability through designing particular neural networks for each bridge factor in accordance with their corresponding data structure. Additionally, a classification scheme with multiple fully connection layers and support vector machine in the framework is designed to achieve higher evaluation accuracy. Experiments on real-world monitoring data of a specific bridge validate the superiority of the proposed model.

ACS Style

Jie Li; Hongli He; Haibo He; Lusi Li; Yi Xiang. An End-to-End Framework With Multisource Monitoring Data for Bridge Health Anomaly Identification. IEEE Transactions on Instrumentation and Measurement 2020, 70, 1 -9.

AMA Style

Jie Li, Hongli He, Haibo He, Lusi Li, Yi Xiang. An End-to-End Framework With Multisource Monitoring Data for Bridge Health Anomaly Identification. IEEE Transactions on Instrumentation and Measurement. 2020; 70 (99):1-9.

Chicago/Turabian Style

Jie Li; Hongli He; Haibo He; Lusi Li; Yi Xiang. 2020. "An End-to-End Framework With Multisource Monitoring Data for Bridge Health Anomaly Identification." IEEE Transactions on Instrumentation and Measurement 70, no. 99: 1-9.

Journal article
Published: 28 July 2020 in IEEE Transactions on Sustainable Energy
Reads 0
Downloads 0

This paper proposes a risk-averse time-series joint scheduling method to release inherent benefits for improvements on operational cost, voltage profile and risk control, through flexibility extraction from grid-storage-demand resources in ADNs. In particular, a flexibility analytical framework is developed to fully harness the controllability of various resources in both spatial and temporal scales, and is available for future analysis. The expected operational cost and the risk imposed by uncertainties are simultaneously addressed via conditional value at risk while satisfying physical and operating constraints, in which a sample weighted average approximation (SWAA) technique is employed for approximating the faced uncertainties. The resulting SWAAbased stochastic scheduling problem is further transformed into a second-order cone programming problem via linearization and conic relaxation. Numerical simulations on 33-bus and 123-bus test systems verify the effectiveness of the proposed method.

ACS Style

Xiaodong Yang; Chongbo Xu; Haibo He; Wei Yao; Jinyu Wen; Youbing Zhang. Flexibility Provisions in Active Distribution Networks With Uncertainties. IEEE Transactions on Sustainable Energy 2020, PP, 1 -1.

AMA Style

Xiaodong Yang, Chongbo Xu, Haibo He, Wei Yao, Jinyu Wen, Youbing Zhang. Flexibility Provisions in Active Distribution Networks With Uncertainties. IEEE Transactions on Sustainable Energy. 2020; PP (99):1-1.

Chicago/Turabian Style

Xiaodong Yang; Chongbo Xu; Haibo He; Wei Yao; Jinyu Wen; Youbing Zhang. 2020. "Flexibility Provisions in Active Distribution Networks With Uncertainties." IEEE Transactions on Sustainable Energy PP, no. 99: 1-1.

Journal article
Published: 30 June 2020 in Neural Networks
Reads 0
Downloads 0

Inspired by biological mechanisms and structures in neuroscience, many biologically inspired visual computational models have been presented to provide new solutions for visual recognition task. For example, convolutional neural network (CNN) was proposed according to the hierarchical structure of biological vision, which could achieve superior performance in large-scale image classification. In this paper, we propose a new framework called visual interaction networks (VIN-Net), which is inspired by visual interaction mechanisms. More specifically, self-interaction, mutual-interaction, multi-interaction, and adaptive interaction are proposed in VIN-Net, forming the first interactive completeness of the visual interaction model. To further enhance the representation ability of visual features, the adaptive adjustment mechanism is integrated into the VIN-Net model. Finally, our model is evaluated on three benchmark datasets and two self-built textile defect datasets. The experimental results demonstrate that the proposed model exhibits its efficiency on visual classification tasks. Furthermore, a textile industrial application shows that the proposed architecture outperforms the state-of-the-art approaches in classification performance.

ACS Style

Bing Wei; Haibo He; Kuangrong Hao; Lei Gao; Xue-Song Tang. Visual interaction networks: A novel bio-inspired computational model for image classification. Neural Networks 2020, 130, 100 -110.

AMA Style

Bing Wei, Haibo He, Kuangrong Hao, Lei Gao, Xue-Song Tang. Visual interaction networks: A novel bio-inspired computational model for image classification. Neural Networks. 2020; 130 ():100-110.

Chicago/Turabian Style

Bing Wei; Haibo He; Kuangrong Hao; Lei Gao; Xue-Song Tang. 2020. "Visual interaction networks: A novel bio-inspired computational model for image classification." Neural Networks 130, no. : 100-110.

Journal article
Published: 25 June 2020 in IEEE Transactions on Cybernetics
Reads 0
Downloads 0

This article addresses the team-triggered fixed-time consensus problems for a class of double-integrator agents subject to uncertain disturbance. Compared with the finite-time results, the convergence time of the fixed-time results is independent of the initial conditions. Furthermore, a novel team-triggered control (TTC) strategy is presented. This control strategy incorporates the event-triggered control (ETC) and self-triggered control (STC). The ETC and STC are proposed to achieve the fixed-time consensus of second-order multiagent systems (MASs), and no Zeno behavior occurs. The TTC scheme, derived by combining the ETC scheme and the STC scheme, is able to relax the requirement of continuous communication and thus lowering the energy consumption of communication while ensuring the performance of the system. The effectiveness of the proposed algorithms is validated by numerical simulations.

ACS Style

Jian Liu; Yao Yu; Haibo He; Changyin Sun. Team-Triggered Practical Fixed-Time Consensus of Double-Integrator Agents With Uncertain Disturbance. IEEE Transactions on Cybernetics 2020, 51, 3263 -3272.

AMA Style

Jian Liu, Yao Yu, Haibo He, Changyin Sun. Team-Triggered Practical Fixed-Time Consensus of Double-Integrator Agents With Uncertain Disturbance. IEEE Transactions on Cybernetics. 2020; 51 (6):3263-3272.

Chicago/Turabian Style

Jian Liu; Yao Yu; Haibo He; Changyin Sun. 2020. "Team-Triggered Practical Fixed-Time Consensus of Double-Integrator Agents With Uncertain Disturbance." IEEE Transactions on Cybernetics 51, no. 6: 3263-3272.

Journal article
Published: 12 June 2020 in Pattern Recognition
Reads 0
Downloads 0

Traditional manifold learning methods generally include a single projection stage that maps high-dimensional data into lower-dimensional space. However, these methods cannot guarantee that the projection matrix is optimal for classification, which limits their practical application. To address this issue, we propose a two-stage projection matrix optimization model termed self-adaptive manifold discriminant analysis (SAMDA). In pre-training projection stage, SAMDA obtains an initial projection matrix by constructing an interclass graph and an intraclass graph under the graph embedding (GE) framework. In weight optimization stage, a maximal manifold margin criterion is developed to further optimize the weights of projection matrix by feature similarity. A self-adaptive optimization process is introduced to increase the margins among different manifolds in low-dimensional space and extract discriminant features that are beneficial to classification. Experimental results on PaviaU, Indian Pines and Heihe data sets demonstrate that the proposed SAMDA method can achieve better classification results than some state-of-the-art methods.

ACS Style

Hong Huang; Zhengying Li; Haibo He; Yule Duan; Song Yang. Self-adaptive manifold discriminant analysis for feature extraction from hyperspectral imagery. Pattern Recognition 2020, 107, 107487 .

AMA Style

Hong Huang, Zhengying Li, Haibo He, Yule Duan, Song Yang. Self-adaptive manifold discriminant analysis for feature extraction from hyperspectral imagery. Pattern Recognition. 2020; 107 ():107487.

Chicago/Turabian Style

Hong Huang; Zhengying Li; Haibo He; Yule Duan; Song Yang. 2020. "Self-adaptive manifold discriminant analysis for feature extraction from hyperspectral imagery." Pattern Recognition 107, no. : 107487.

Journal article
Published: 11 June 2020 in IEEE Transactions on Cybernetics
Reads 0
Downloads 0

Unsupervised domain adaptation (DA) aims to perform classification tasks on the target domain by leveraging rich labeled data in the existing source domain. The key insight of DA is to reduce domain divergence by learning domain-invariant features or transferable instances. Despite its rapid development, there still exist several challenges to explore. At the feature level, aligning both domains only in a single way (i.e., geometrical or statistical) has limited ability to reduce the domain divergence. At the instance level, interfering instances often obstruct learning a discriminant subspace when performing the geometrical alignment. At the classifier level, only minimizing the empirical risk on the source domain may result in a negative transfer. To tackle these challenges, this article proposes a novel DA method, called discriminant geometrical and statistical alignment (DGSA). DGSA first aligns the geometrical structure of both domains by projecting original space into a Grassmann manifold, then matches the statistical distributions of both domains by minimizing their maximum mean discrepancy on the manifold. In the former step, DGSA only selects the density peaks to learn the Grassmann manifold and so to reduce the influences of interfering instances. In addition, DGSA exploits the high-confidence soft labels of target landmarks to learn a more discriminant manifold. In the latter step, a structural risk minimization (SRM) classifier is learned to match the distributions (both marginal and conditional) and predict the target labels at the same time. Extensive experiments on objection recognition and human activity recognition tasks demonstrate that DGSA can achieve better performance than the comparison methods.

ACS Style

Jiachen Zhao; Lusi Li; Fang Deng; Haibo He; Jie Chen. Discriminant Geometrical and Statistical Alignment With Density Peaks for Domain Adaptation. IEEE Transactions on Cybernetics 2020, 1 -14.

AMA Style

Jiachen Zhao, Lusi Li, Fang Deng, Haibo He, Jie Chen. Discriminant Geometrical and Statistical Alignment With Density Peaks for Domain Adaptation. IEEE Transactions on Cybernetics. 2020; ():1-14.

Chicago/Turabian Style

Jiachen Zhao; Lusi Li; Fang Deng; Haibo He; Jie Chen. 2020. "Discriminant Geometrical and Statistical Alignment With Density Peaks for Domain Adaptation." IEEE Transactions on Cybernetics , no. : 1-14.