Article
Computer Science, Artificial Intelligence
Hao Yu, Tongwen Chen
Summary: This article proposes an adaptive tracking controller based on radial basis function neural networks (RBFNNs) for nonlinear plants with unmatched uncertainties and smooth reference signals. Valid RBFNN adaptive control is introduced, ensuring that all closed-loop arguments of the involved RBFNNs remain inside their corresponding compact sets. A novel iterative design method is proposed and embedded into the traditional backstepping approach to obtain valid RBFNN adaptive controllers.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yongchao Liu, Qidan Zhu
Summary: In this article, the issue of adaptive neural network asymptotic tracking control for nonstrict feedback stochastic nonlinear systems is studied using the backstepping algorithm. Compared with previous research, the difficulty of unknown virtual control coefficients in control design is overcome. The recursive construction of the asymptotic tracking controller is achieved through the use of bound estimation scheme, smooth functions, and approximation-based neural network, ensuring asymptotic convergence character and stability with stochastic disturbance and unknown UVCC with the help of Lyapunov function and beneficial inequalities. This theoretical finding is verified through a simulation example.
Article
Computer Science, Artificial Intelligence
Yuxiao Lian, Jianwei Xia, Ju H. Park, Wei Sun, Hao Shen
Summary: This article focuses on the output feedback control of a nonlinear system with unknown control directions, unknown Bouc-Wen hysteresis, and unknown disturbances. The design obstacles caused by these unknown factors are eliminated through the use of linear state and coordinate transformations, avoiding the need for high-frequency oscillating Nussbaum function. A novel nonlinear disturbance observer is designed to handle unknown disturbances, which has a simple structure, low coupling, and easy implementation. An output feedback controller is devised using neural networks and backstepping technology, ensuring bounded closed-loop signals and convergence of system output, state observation error, and disturbance observation error. Simulation verification using numerical examples and a Nomoto ship model illustrates the effectiveness of the proposed scheme.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
P. Parsa, M-R Akbarzadeh-T, F. Baghbani
Summary: This study introduces a command-filtered backstepping H1 robust adaptive emotional controller for strict-feedback nonlinear systems with mismatched uncertainties. The controller utilizes command filters and compensating filters to handle matched/mismatched uncertainties and disturbances, requiring only the known and continuous reference signal and its first derivative.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Yanjun Shu, Yanhui Tong
Summary: This article proposes a novel robust neural tracking control scheme using backstepping technique for a class of discrete-time switched nonlinear uncertain systems. Radial basis function neural networks are used to approximate the unknown lumped function, simplifying the controller design process. Stability analysis demonstrates semi-globally uniformly ultimately bounded behavior of the closed-loop system, with tracking error converging to an arbitrarily small neighborhood of the origin.
Article
Automation & Control Systems
Qitian Yin, Hongyang Zhang, Quanqi Mu, Jianbai Yang, Qinghua Ma
Summary: This study presents an output backstepping control architecture based on command filter and Multilayer-Neural-Network Pre-Observer to achieve reference signal tracking of arbitrarily switching nonlinear systems. The proposed approach compensates for the chattering caused by the switching parameter and guarantees bounded states of the closed-loop system. The developed backstepping control method combines servo reconstruction and control, resulting in improved tracking performance.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Computer Science, Information Systems
Yan Zhang, Fang Wang, Feng Yan
Summary: This paper proposes a fast finite time adaptive neural network control scheme for a class of uncertain nonlinear systems, which introduces neural networks and dynamical signal functions to handle uncertainties. The scheme shows robustness to unmodeled dynamics and dynamical disturbances, and the feasibility is demonstrated through two simulation examples.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Dong Yang, Guangdeng Zong, Yanjun Liu, Choon Ki Ahn
Summary: This paper investigates the adaptive neural network output tracking control problem for a class of uncertain switched nonlinear systems. By relaxing the traditional multiple Lyapunov function conditions, an improved multiple Lyapunov function method is developed. A feasible state-dependent switching signal and an adaptive neural network output tracking switching controller are designed to ensure that the output tracking error converges to an arbitrarily small neighborhood of the origin, and all the signals in the closed-loop system remain within a bounded region. Numerical examples and an application example are provided to illustrate the effectiveness of the proposed algorithm.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Mingjie Cai, Peng Shi, Jinpeng Yu
Summary: This brief studies the control design method for a class of non-strict feedback nonlinear systems, taking into consideration uncertain nonlinearities and unknown non-symmetrical input dead-zone. By combining the finite-time command filtered backstepping technique with a neural network-based methodology, a novel finite-time adaptive control approach is proposed. The effectiveness of the control scheme is verified through numerical simulations.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Automation & Control Systems
Jianhui Wang, Peisen Zhu, Biaotao He, Guiyang Deng, Chunliang Zhang, Xing Huang
Summary: An adaptive neural sliding mode control with ESO is proposed to improve the stability of control systems. By combining sliding mode control and ESO, the system shows superior tracking performance and anti-interference ability in simulations.
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
(2021)
Article
Automation & Control Systems
Fanlin Jia, Xiao He
Summary: This paper discusses the problem of fault-tolerant tracking control for discrete-time nonstrict-feedback nonlinear systems in the presence of stochastic noises and actuator faults. A novel fault-tolerant tracking control strategy is proposed by integrating the properties of the backstepping framework and neural networks, and introducing an adaptive fault compensation term. The designed fault-tolerant controller ensures that the tracking error converges to an adjustable region regarding the origin and that all system signals are uniformly bounded concerning the mean-square sense.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Ke Xu, Huanqing Wang, Qiang Zhang, Ming Chen, Junfei Qiao, Ben Niu
Summary: The paper investigates the command-filter-based adaptive tracking control for a class of stochastic nonlinear systems with strict-feedback structure with input dead-zone. By introducing the control method of the command-filter and combining adaptive backstepping design algorithm and Lyapunov stability theorem, an adaptive neural command-filter controller is developed, ensuring closed-loop signals stability and tracking error convergence.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Huanqing Wang, Siwen Liu, Ding Wang, Ben Niu, Ming Chen
Summary: This paper presents an adaptive neural tracking control method for non-strict-feedback high-order nonlinear systems with quantized input signal. The introduced quantizer can avoid chattering problem, and dynamic surface control technique is used to solve the complexity issue. By utilizing the structural properties of RBF NNs, the design difficulty is simplified and an output tracking controller is designed to ensure system stability and tracking performance.
Article
Automation & Control Systems
Min Wang, Kunning Wang, Longwang Huang, Haotian Shi
Summary: In this article, a new output-feedback event-triggered (ET) tracking control strategy is proposed for discrete-time strict-feedback nonlinear systems. An effective state observer is designed to obtain current states information, removing the restriction of converting the system to the input-output model. The variable substitution technique is used to avoid time delays and calculation burden, and an adaptive critic design (ACD) structure is utilized to acquire the optimal control strategy.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Hao Yu, Tongwen Chen
Summary: This article investigates the application of neural network adaptive control in strict-feedback nonlinear systems with matched uncertainties and event-triggered communication. It proposes the concept of valid compact sets to ensure the effectiveness of control. It also introduces an event-triggering mechanism to avoid Zeno phenomenon and save communication resources. Simulation results demonstrate the effectiveness and feasibility of the proposed methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
David C. Chou, Houn-Gee Chen, Binshan Lin
Summary: This study aims to examine the role of corporate social responsibility and green information technology in achieving environmental sustainability. It proposes a value model that combines the operational procedures of CSR and Green IT to achieve desired value outcomes. The study illustrates the four-stage value creation process of this model through corporate experience analyses.
JOURNAL OF COMPUTER INFORMATION SYSTEMS
(2023)
Article
Automation & Control Systems
Siwen Liu, Huanqing Wang, Tieshan Li
Summary: This article discusses the design problem of an adaptive composite dynamic surface neural controller for nonlinear fractional-order systems (NFOSs) subject to delayed input. A fractional-order auxiliary system is first designed to solve the input-delay problem and the weights of radial basis function neural networks (RBFNNs) are determined based on prediction errors and the states of the error system using novel estimation models. The developed fractional-order filters address the complexity explosion problem when utilizing the classical backstepping control technique. Simulation results demonstrate the feasibility of the developed controller, which can also be applied to SISO nonlinear systems subject to a unitary input function.
Article
Automation & Control Systems
Dong Liu, Ning Liu, Tieshan Li
Summary: In this article, an original event-triggered model-free adaptive control is proposed for nonlinear systems with output constraints. A compact form dynamic linear model is established based on the output saturated data, and a pseudo partial derivative (PPD) parameter is designed to identify the linear model. A novel event-triggered mechanism is inserted into the controller to save communication resources by activating only when the event-triggered error satisfies the predefined condition. The article provides a convergence proof for the present algorithm and demonstrates its feasibility through simulation study.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2023)
Article
Automation & Control Systems
Ke He, Tieshan Li, Yue Long, Ju H. Park, C. L. Philip Chen
Summary: In this paper, the authors investigate the secure state estimation attack and reconstruction problems for linear cyber-physical systems (CPSs) under actuator attacks and unknown disturbances. A continuous sliding mode observer with an exponential reaching law strategy is introduced to improve the dynamic quality and eliminate chattering. The original system is transformed into a special attack channel separation form, and an improved sliding mode observer with disturbance compensation is obtained to solve the secure state estimation problem. Simulation results on a VTOL aircraft validate the effectiveness of the proposed scheme.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2023)
Article
Computer Science, Information Systems
David C. Chou, Binshan Lin
Summary: This study explores the support and importance of social mediating technologies for the success of social entrepreneurship. It utilizes a meta-analysis method to validate two research propositions and establishes a conceptual framework with three constructs: social mediating technologies, social network capabilities, and social entrepreneurship success. The results demonstrate the significant role of social mediating technologies and social network capabilities in achieving social entrepreneurial success.
JOURNAL OF COMPUTER INFORMATION SYSTEMS
(2023)
Article
Engineering, Mechanical
Tianpeng Huang, Tieshan Li
Summary: This paper addresses the problem of attitude control of quadrotor UAV, introducing a mathematical model of the system and developing a finite-time disturbance observer (FTDO) to compensate for external disturbance. A backstepping sliding mode control technique is proposed based on the FTDO to stabilize the quadrotor UAV's attitude angles, eliminating tracking errors asymptotically. The bound of transient attitude tracking error is derived in terms of L-2 norm by constructing an auxiliary equation. Comparative simulations demonstrate the effectiveness of the proposed control scheme.
NONLINEAR DYNAMICS
(2023)
Article
Engineering, Marine
Haoliang Wang, Liyu Lu, Tieshan Li, Anqing Wang
Summary: This article presents a design for three-dimensional path planning and secure event-triggered cooperative path following for multiple disk-type autonomous underwater gliders (AUGs), considering underwater obstacles and denial-of-service (DoS) attacks. The proposed method includes a collision-free path planning approach using quantum-behaved adaptive particle swarm optimization and artificial potential fields, a path variable update law based on a three-dimensional line-of-sight guidance mechanism for cooperative control, and an event-triggered mechanism for secure control under unreliable network conditions with DoS attacks. Simulation results and numerical analysis demonstrate the effectiveness of this integrated approach.
Article
Computer Science, Artificial Intelligence
Zhe Chen, Xiao-Jun Wu, Josef Kittler
Summary: This paper proposes a Fisher regularized e-dragging framework for image classification, which improves the intraclass compactness and interclass separability of relaxed labels. The Fisher criterion and e-dragging technique are integrated into a unified model, achieving superior performance compared to other classification methods.
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
(2023)
Article
Engineering, Marine
Yuxin Zhang, Yang Xiao, Qihe Shan, Tieshan Li
Summary: To reduce fuel-based energy consumption, it is crucial to investigate the optimal energy management for seaport integrated energy system in a fully distributed manner. A multi-objective energy management model is constructed, taking into account energy consumption, greenhouse gas emissions, and carbon trading to meet the sustainable development goals of the international shipping industry. Integrated carbon capture/storage devices are implemented to constrain the carbon emissions of the seaport. A fully distributed energy management strategy with dynamic-weighted coefficients is proposed to obtain the optimal solutions. Additionally, an event-triggered mechanism is designed to reduce communication resources, addressing the bandwidth limitation of the seaport. A rigorous mathematical analysis based on multi-agent theory and case studies demonstrates the effectiveness of the proposed method.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Marine
Yang Wang, Li-Ying Hao, Tieshan Li, C. L. Philip Chen
Summary: This paper investigates a fault-tolerant control problem for the dynamic positioning of unmanned marine vehicles based on a Takagi-Sugeno (T-S) fuzzy model using an integral sliding mode scheme. The T-S fuzzy model of an unmanned marine vehicle is established, and an integral sliding mode control scheme combined with the H & INFIN; performance index is developed. The unknown nonlinear function is approximated using a fuzzy logic system based on a representation of marine data. The fault estimation information is utilized to design the sliding mode surface, reducing conservatism.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Letter
Automation & Control Systems
Yalei Yu, Chen Guo, Tieshan Li
Summary: This letter addresses the path following of underactuated autonomous surface vessels (ASV) under surge velocity constraint, asymmetric saturation, and unknown dynamics. An adaptive finite-time sliding mode control scheme (AFTSM) is designed to cope with these constraints. The ASV's constraints are addressed by a novel rate and magnitude velocity guidance, projection-based finite-time auxiliary system, and parametric finite-time robust observer in this scheme. The effectiveness of the presented scheme is demonstrated through simulations and comparisons.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2023)
Article
Business
Garry Wei-Han Tan, Eugene Cheng-Xi Aw, Tat-Huei Cham, Keng-Boon Ooi, Yogesh K. Dwivedi, Ali Abdallah Alalwan, Janarthanan Balakrishnan, Hing Kai Chan, Jun-Jie Hew, Laurie Hughes, Varsha Jain, Voon Hsien Lee, Binshan Lin, Niprendra P. Rana, Teck Ming Tan
Summary: This article aims to provide valuable perspectives on six critical areas in which the metaverse could have a significant impact, including marketing ethics, marketing communication, relationship marketing, retail marketing, supply chain management, and transportation management. By gathering insights from various contributors, it explores the roles of the metaverse in each area and discusses the associated opportunities, challenges, and research agenda.
ASIA PACIFIC JOURNAL OF MARKETING AND LOGISTICS
(2023)
Article
Automation & Control Systems
Hongjing Liang, Dongni Li, Yingnan Pan, Tieshan Li
Summary: This article proposes a detect-switch-compensate mechanism based on fault-tolerant control strategy to solve the tracking control problem. By constructing a fault observer to recognize the occurrence time of faults and using a discontinuous compensation method, the algorithm achieves high efficiency. Furthermore, the fault observer also solves the problem of unmeasured states to ensure system stability.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Dan Zhang, C. L. Philip Chen, Tieshan Li, Yi Zuo, Nguyen Quang Duy
Summary: Target tracking is widely used in intelligent transportation, real-time monitoring, human-computer interaction, etc. The proposed method based on broad learning system improves the performance of Siamese networks by combining offline training with fast online learning of new features, achieving accurate and real-time tracking.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Yuanyuan Xu, Tieshan Li, Yue Yang, Qihe Shan, Shaocheng Tong, C. L. Philip Chen
Summary: In this article, an anti-attack event-triggered secure control scheme is developed for a class of nonlinear multi-agent systems with input quantization. The scheme utilizes neural networks to approximate unknown nonlinear functions, and employs an adaptive neural state observer to obtain unknown states. An event-triggered control strategy is introduced to save communication resources, and a quantizer is used to provide accuracy under low transmission rates. A predictor is designed to resist attacks in the multi-agent network. The proposed secure control protocol guarantees bounded closed-loop signals under attacks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.