Article
Computer Science, Artificial Intelligence
Aritz D. Martinez, Javier Del Ser, Eneko Osaba, Francisco Herrera
Summary: This paper introduces an adaptive multitask reinforcement learning algorithm called A-MFEA-RL, which improves performance by facilitating the exchange of genetic material through crossover and inheritance mechanisms. Experimental results show that A-MFEA-RL achieves high success rates when handling multiple tasks and enhances knowledge exchange among tasks.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Automation & Control Systems
Le Wang, Wei Sun, Shun-Feng Su, Xudong Zhao
Summary: This study presents an adaptive asymptotic tracking control scheme for flexible-joint (FJ) robot systems, which ensures that the output tracking error stays within the prescribed range during the initial stage of system operation and achieves asymptotic tracking as time approaches infinity. The control design introduces both a prescribed performance function and a positive integrable time-varying function for the first time. The control scheme is based on the adaptive backstepping method and command filtered technique, effectively addressing the problem of complexity explosion. Radial basis function neural networks are employed to handle unknown uncertainties, and adaptive laws are designed to approximate the norms of weight vectors and approximation errors. Simulation and experiments on a 2-link FJ robot on the Quanser platform demonstrate the feasibility of the proposed scheme.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Engineering, Industrial
Xingda Qu, Xinyao Hu, Jun Zhao, Zhong Zhao
Summary: The study aimed to investigate the roles of lower-limb joint proprioception in postural control during gait. Results showed that hip proprioception played the most important role in postural control during gait among the components, and the mechanisms for the effects of hip proprioception were different between age groups.
APPLIED ERGONOMICS
(2022)
Article
Engineering, Mechanical
Tandong Li, Junxing Zhang, Shaobo Li, Peng Zhou, Dongchao Lv
Summary: In this paper, a fixed-time prescribed performance fault-tolerant control scheme is proposed for the n-link flexible joint robot with actuator failures. The modified prescribed performance control method is used to enhance the robustness of the system and ensure convergence of the tracking error within a predetermined time. An adaptive-based passive fault-tolerant controller is constructed to counteract actuator failures, and the uncertainty problem is solved by incorporating neural networks and adaptive techniques. The proposed control scheme is validated through simulations on two different robots under different actuator failure scenarios.
NONLINEAR DYNAMICS
(2023)
Article
Computer Science, Artificial Intelligence
Hao Xu, A. K. Qin, Siyu Xia
Summary: Evolutionary Multitask Optimization (EMTO) uses evolutionary algorithms (EAs) to solve multiple optimization tasks simultaneously, utilizing knowledge transfer to improve performance. The proposed adaptive EMTO (AEMTO) framework adjusts knowledge transfer in a synergistic way, effectively addressing negative knowledge transfer and enhancing overall performance.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Dong Wang, Chanyue Wu, Yunpeng Bai, Ying Li, Changjing Shang, Qiang Shen
Summary: This paper proposes a multitask network (MTNet) to achieve joint multispectral (MS) pansharpening for images acquired by different satellites. The MTNet shares generic knowledge between datasets via a task-agnostic subnetwork (TASNet) and adapts this knowledge to specific satellites using task-specific subnetworks (TSSNets). It also introduces band-aware dynamic convolutions (BDConvs) to accommodate various ground scenes and bands. Experimental results demonstrate that the proposed approach outperforms existing state-of-the-art (SOTA) techniques across different datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Ye Li, Kangning Yin, Jie Liang, Zhuofu Tan, Xinzhong Wang, Guangqiang Yin, Zhiguo Wang
Summary: This article proposes a multitask joint framework (MJF) to address the issues of person detection, feature extraction, and identity comparison in person search, optimizing the performance of these three components. Specifically, the article introduces the use of the YOLOv5-GS model for person detection, a model adaptation architecture for feature extraction, and a 3D pooled table and matching strategy for identity comparison. Experimental results demonstrate that this framework enables real-time person search.
MULTIMEDIA SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Ming Zhao, Xin Zhang, Andre Kaup
Summary: This article proposes a multitask learning framework for ship detection in SAR images, which includes object detection, speckle suppression, and target segmentation tasks. Various techniques, such as angle classification loss, dual-feature fusion attention, and rotated Gaussian mask, are utilized to improve the accuracy, robustness, and efficiency of ship detection in SAR images. Extensive experiments on SAR ship detection datasets demonstrate the effectiveness and superiority of the proposed method.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Engineering, Electrical & Electronic
Junbing Cheng, Yunfei Gao, Jie Wu
Summary: This paper proposes an intelligent integrated navigation method based on multitask heterogeneous deep learning and adaptive Kalman filter, which can improve vehicle positioning accuracy in urban complex environments and effectively solve the problem of GNSS signal blockage.
IEEE SENSORS JOURNAL
(2023)
Article
Automation & Control Systems
Hui Ma, Qi Zhou, Hongyi Li, Renquan Lu
Summary: An adaptive fuzzy control strategy is proposed for a single-link flexible-joint robotic manipulator with prescribed performance. The strategy effectively identifies unknown nonlinearity using a fuzzy-logic system and ensures transient performance of the control system. Dynamic signals are applied to handle unmodeled dynamics, while an event-triggered control law is developed to reduce communication load. The control method guarantees Lyapunov stability, backstepping technique, and semiglobal ultimately uniformly boundedness for all signals in the closed-loop system.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Electrical & Electronic
Sheng Cheng, Han Hu, Xinggong Zhang
Summary: This article proposes ABRF, a QoE-oriented adaptive bitrate-FEC joint control algorithm. ABRF predicts the network loss pattern in the future and calculates the optimal bitrate-FEC decision based on a QoE model for real-time video streaming. Moreover, ABRF is equipped with a fast adaptation method to generalize across diverse network environments.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Automation & Control Systems
Raja Fawad Afsar Khan, Kamal Rsetam, Zhenwei Cao, Zhihong Man
Summary: This article proposes an adaptive integral sliding mode controller (AISMC) based on a singular perturbation method and two state observers for the flexible joint robot (FJR) to achieve high performance. The proposed controller effectively reduces noise amplification and achieves the desired tracking performance without requiring velocity and acceleration measurements. Additionally, adaptive laws for switching gains are proposed to remove the requirements of knowing the up-bound of the disturbances and uncertainties in the FJR system. The simulation and experimental results demonstrate the superiority of the proposed control in terms of less tracking error, significant noise suppression, and strong robustness in comparison with existing controllers.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
Xiaoqin Yang, Wei Sun, Huixuan Dong, Xueqi Wu
Summary: This paper considers the problem of adaptive prescribed performance tracking control for the n-link flexible-joint robot system with actuator failures. The provided adaptive fault-tolerant control scheme can effectively compensate for the influence of unknown actuator failures by designing applicable adaptive laws, and the communication burden is reduced by implementing the event-triggered control strategy. The command filtered technique and the presented adaptive fuzzy control method are used to avoid complexity explosion and handle unknown nonlinear terms, respectively. Based on Lyapunov stability analysis, it is proven that each tracking error converges to a prescribed small neighborhood of the origin in a finite time and remains within the prescribed boundary, and all signals in the closed-loop system are bounded. The effectiveness of the proposed control algorithm is verified through simulation examples.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2023)
Article
Automation & Control Systems
Yang Zhou, Shubo Wang
Summary: This paper investigates asymptotic tracking control of nonlinear robotic systems with prescribed performance. The control strategy is developed based on a modified prescribed performance function (PPF) and fuzzy logic system (FLS) to approximate the unknown dynamics. A robust integral of the sign of the error (RISE) term is incorporated into the control design to achieve asymptotic convergence. Numerical simulation and experimental results validate the effectiveness of the proposed control scheme.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Computer Science, Information Systems
Qing Shi, Feng Chen, Xinyu Li, Shukai Duan
Summary: This paper proposes an adaptive clustering learning approach based on an event triggered scheme for time-varying multitask networks, aiming to improve the estimation accuracy of agents. It also analyzes the mean-square of the proposed algorithm and evaluates the error probability of false alarms and false detections of the clustering mechanism. Extensive simulation is used to validate the analytical performance of the distributed learning strategy over time-varying multitasks.
INFORMATION SCIENCES
(2021)
Article
Physiology
Wen-Chieh Yang, Chih-Hsiu Cheng, Hsing-Kuo Wang, Kwan-Hwa Lin, Wei-Li Hsu
EUROPEAN JOURNAL OF APPLIED PHYSIOLOGY
(2015)
Article
Clinical Neurology
Andy Chien, Dar-Ming Lai, Shwu-Fen Wang, Chih-Hsiu Cheng, Wei-Li Hsu, Jaw-Lin Wang
EUROPEAN SPINE JOURNAL
(2015)
Article
Clinical Neurology
Chih-Hsiu Cheng, Andy Chien, Wei-Li Hsu, Dar-Ming Lai, Shwn-Fen Wang, Jaw-Lin Wang
EUROPEAN SPINE JOURNAL
(2016)
Article
Neurosciences
Wen-Chieh Yang, Wei-Li Hsu, Ruey-Meei Wu, Tung-Wu Lu, Kwan-Hwa Lin
Article
Clinical Neurology
Andy Chien, Dar-Ming Lai, Shwu-Fen Wang, Wei-Li Hsu, Chih-Hsiu Cheng, Jaw-Lin Wang
Article
Clinical Neurology
Wen-Chieh Yang, Wei-Li Hsu, Ruey-Meei Wu, Kwan-Hwa Lin
JOURNAL OF NEUROLOGIC PHYSICAL THERAPY
(2016)
Article
Engineering, Biomedical
Cheng-Hua Wu, Hui-Fen Mao, Jwu-Sheng Hu, Ting-Yun Wang, Yi-Jeng Tsai, Wei-Li Hsu
JOURNAL OF NEUROENGINEERING AND REHABILITATION
(2018)
Article
Multidisciplinary Sciences
Chih-Hsiu Cheng, Andy Chien, Wei-Li Hsu, Carl Pai-Chu Chen, Hsin-Yi Kathy Cheng
Article
Multidisciplinary Sciences
Jo-En Chien, Wei-Li Hsu
SCIENTIFIC REPORTS
(2018)
Article
Clinical Neurology
Wei-Jin Wong, Dar-Ming Lai, Shwu-Fen Wang, Jaw-Lin Wang, Wei-Li Hsu
Article
Engineering, Biomedical
Iu-Shiuan Lin, Dar-Ming Lai, Jian-Jiun Ding, Andy Chien, Chih-Hsiu Cheng, Shwu-Fen Wang, Jaw-Lin Wang, Chi-Lin Kuo, Wei-Li Hsu
JOURNAL OF NEUROENGINEERING AND REHABILITATION
(2019)
Article
Multidisciplinary Sciences
Chih-Hsiu Cheng, Dar-Ming Lai, Phooi Yee Lau, Shwu-Fen Wang, Andy Chien, Jaw-Lin Wang, Wei-Li Hsu
SCIENTIFIC REPORTS
(2020)
Article
Engineering, Biomedical
Chi-Ying Lee, Shih Chieh Lan, Jung-Ji Lin, Yu-Ting Lin, Po-Shen Chiang, Wei-Li Hsu, Kuo-Kuang Jen, Andy Y. S. Huang, Jia-Yush Yen
Summary: The study modeled natural human motion using a biped robot simulator and examined the effects of exoskeleton assistance and energy consumption. Virtual parallel bars were found to effectively assist the robot in simulating a natural walking gait.
JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING
(2021)
Review
Health Policy & Services
Phunsuk Kantha, Jiu-Jenq Lin, Wei-Li Hsu
Summary: This study investigates the effects of interactive virtual reality (iVR) on pain, psychological distress, and functional disability in patients with chronic musculoskeletal disorders compared with no rehabilitation and conventional rehabilitation. The results suggest that iVR can reduce pain and improve psychological distress.
GAMES FOR HEALTH JOURNAL
(2023)
Article
Engineering, Biomedical
Phunsuk Kantha, Shiow-Chwen Tsai, Chien-Wen Hou, Rong-Sen Yang, Pei-Yu Su, Wei-Li Hsu
Summary: In older adults with hyperkyphosis, bone mineral content (BMC) and muscle mass are correlated with walking and forward reach, while BMI and fat mass show no significant correlation with balance performance.
JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING
(2021)