Article
Automation & Control Systems
Xiaonan Liu, Minghui Song, Yonggui Kao
Summary: This paper investigates the synchronization between two hyperbolic coupled networks (HCNs) with time-varying delays using aperiodically intermittent pinning control (AIPC). Sufficient criteria for HCNs with internal delays only and with hybrid delays are obtained based on a Lyapunov function with a piecewise continuous function. It is found that HCNs with hybrid delays have a slower convergence speed compared to those with internal delays only. Additionally, two simulation results are presented to validate the theoretical findings.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Engineering, Multidisciplinary
K. Udhayakumar, S. Shanmugasundaram, Ardak Kashkynbayev, K. Janani, R. Rakkiyappan
Summary: This paper explores the synchronization of inertial neural networks (INNs) with time-varying delay and coupling delays using control systems with saturated and asymmetrically saturated impulses. Theoretical discussions introduce mixed delays for INNs, and the addressed model is transformed into first-order differential equations using variable transformation and dead-zone function. Adequate conditions for exponential synchronization are derived, and an asymmetric saturated impulsive control approach is proposed for achieving exponential synchronization in the leader-following synchronization pattern of INNs. Simulation results validate the theoretical findings.
APPLIED MATHEMATICAL MODELLING
(2023)
Article
Computer Science, Artificial Intelligence
Hongfei Li, Chuandong Li, Deqiang Ouyang, Sing Kiong Nguang
Summary: This article considers impulsive synchronization for inertial neural networks with unbounded delay and actuator saturation via sampled-data control. Theoretical analysis and numerical simulations demonstrate the effectiveness of the proposed approach. Additionally, a new image encryption algorithm based on hybrid control synchronization theory is presented and validated through experiments.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Mathematics, Applied
Chao Zhou, Chunhua Wang, Wei Yao, Hairong Lin
Summary: This article investigates the synchronization issue of memristive neural networks (MNNs) under denial-of-service (DoS) attacks and actuator saturation using an observer-based controller. The study considers the effect of actuator saturation in the controller design and explores DoS attacks in the communication channel connecting master and slave MNNs. The proposed observer-based control approach estimates the MNNs states and ensures synchronization in the presence of DoS attacks and actuator saturation, with sufficient synchronization conditions derived using the Lyapunov method and stochastic analysis technique.
APPLIED MATHEMATICS AND COMPUTATION
(2022)
Article
Mathematics, Applied
Zhilong He, Chuandong Li, Yi Li, Zhengran Cao, Xiaoyu Zhang
Summary: This paper investigates the local synchronization problem of a class of nonlinear dynamical networks under hybrid impulsive control with actuator saturations. The challenges caused by impulsive effects and saturation nonlinearities are addressed using mathematical induction and sector nonlinear model methods. Sufficient conditions for exponential stability and controller designs are derived, and numerical examples demonstrate the effectiveness of the obtained results.
APPLIED MATHEMATICS AND COMPUTATION
(2021)
Article
Mathematics
Yuxiao Zhao, Linshan Wang
Summary: This paper examines the practical exponential stability of an impulsive stochastic food chain system with time-varying delays. The existence of global positive solutions to the suggested system is discussed by constructing an auxiliary system equivalent to the original system and comparison theorem. Furthermore, the sufficient conditions for the exponential stability and practical exponential stability of the system are investigated using Razumikhin technique and the Lyapunov method. Additionally, the exponential stability and practical exponential stability of species are independent of time delay when Razumikhin's condition holds. The validity of the method is confirmed through numerical simulation.
Article
Mathematics, Applied
Tao Wu, Lianglin Xiong, Jinde Cao, Ju H. Park, Jun Cheng
Summary: This paper investigates the exponential synchronization issue for coupled reaction-diffusion stochastic neural networks with time-varying delay, proposing two new delay dependent impulsive pinning control mechanisms. Several sufficient criteria are established using the Lyapunov function approach, showing that exponential synchronization can be achieved by controlling a small number of network nodes with delayed impulses. The effectiveness and feasibility of the proposed method are demonstrated through numerical examples.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2021)
Article
Computer Science, Artificial Intelligence
Shuchen Wu, Xiaodi Li, Yanhui Ding
Summary: This paper investigates the synchronization problem for coupled neural networks with impulsive control, fully considering the saturation structure of impulse action. By introducing a new constraint of set inclusion and the corresponding sector condition, a sufficient condition for exponential synchronization is obtained by replacing saturation nonlinearity. Synchronization of coupled delayed neural networks is achieved in the framework of saturated impulses, and an optimization problem is solved to propose the estimating domain of attraction as large as possible.
Article
Mathematics, Applied
Yuxiao Zhao, Hong Lin, Xiaoyan Qiao
Summary: This paper investigates the persistence, extinction, and practical exponential stability of impulsive stochastic competition models with time-varying delays. The existence of global positive solutions is examined through the relationship between the original system and the equivalent system, and sufficient conditions for system persistence and extinction are provided. The study also reveals that impulsive perturbation has no impact on practical exponential stability under bounded pulse intensity, non-Markovian processes can be transformed into solving the stability of Markovian processes using Razumikhin inequality, and non-Markovian processes can sometimes produce Markovian effects. Numerical simulations further validate the importance and validity of the theoretical results for practical exponential stability.
Article
Physics, Multidisciplinary
Hongguang Fan, Kaibo Shi, Yi Zhao
Summary: This paper examines the pinning impulsive cluster synchronization problem in uncertain complex community networks with impulsive effects, internal delay, and coupling delay. By establishing a novel impulsive comparison principle and applying Lyapunov stability theory and pinning impulsive control techniques, sufficient conditions are derived to ensure the cluster synchronization of community networks. The validity of the results is demonstrated through numerical simulations.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Hongguang Fan, Kaibo Shi, Yanan Xu, Rui Zhang, Shuai Zhou, Hui Wen
Summary: This article investigates the mu-synchronization issues of non-dissipative coupled networks with bounded disturbances and mixed delays. By designing a hybrid non-delayed and time-delayed impulsive controller, the article provides novel sufficient conditions for achieving mu-synchronization in nonlinear complex networks. The theoretical achievements in this article are more general than previous works as the constraints on network topology and impulsive intervals are relaxed.
Article
Mathematics, Applied
Yuanyuan Xue, Yu Zhang, Jie Li
Summary: This paper investigates the exponential stabilization of genetic regulatory networks with time-varying delays using event-triggered impulsive control. An ETIC strategy is designed and sufficient conditions for the exponential stability of GRNs with time-varying delays under this strategy are established using Lyapunov functions and Razumikhin technique. The designed strategy is also shown to eliminate Zeno behavior. Two numerical examples are provided to demonstrate the effectiveness of the proposed results.
MATHEMATICAL METHODS IN THE APPLIED SCIENCES
(2023)
Article
Automation & Control Systems
Yanzhao Cheng, Yanchao Shi
Summary: This paper discusses the global exponential synchronization of quaternion-valued memristor-based neural networks with time-varying delays. Firstly, the discontinuous quaternion-valued memristive neural networks are transformed into an uncertain system with interval parameters using differential inclusion theory and set-valued map theory. A novel controller is designed to achieve the control goal. The criterion for global exponential synchronization of the quaternion-valued memristive neural networks is given using the ?-measure method and Halanay inequality. Numerical simulation is provided to prove the validity of the main results.
INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Xiaoyu Zhang, Chuandong Li, Hongfei Li, Jing Xu
Summary: This paper studies the synchronization problem of coupled neural networks with distributed delay coupling and nonlinear coupling. By introducing a novel array of delayed inequalities with mixed delays, some sufficient conditions ensuring exponential synchronization are obtained using linear matrix inequalities (LMIs) and Kronecker product. Furthermore, a delay-dependent distributed impulsive controller is proposed, and low-dimensional sufficient conditions are derived using the matrix decomposition technique.
Article
Mathematical & Computational Biology
Biwen Li, Xuan Cheng
Summary: This paper introduces and studies the complete synchronization and Mittag-Leffler synchronization problems of a kind of coupled fractional-order neural networks with time-varying delays. Sufficient conditions for complete synchronization of a controlled system are established using the Kronecker product technique and Lyapunov direct method under pinning control. An adaptive feedback controller is designed, which combines the Razumikhin-type method and Mittag-Leffler stability theory to achieve Mittag-Leffler synchronization. Numerical examples are provided to validate the theorems.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2023)
Article
Automation & Control Systems
Hongfei Li, Chuandong Li, Tingwen Huang, Deqiang Ouyang
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2017)
Article
Computer Science, Artificial Intelligence
Chengkun He, Jie Shao, Xing Xu, Deqiang Ouyang, Lianli Gao
Article
Computer Science, Artificial Intelligence
Deqiang Ouyang, Yonghui Zhang, Jie Shao
PATTERN RECOGNITION LETTERS
(2019)
Article
Computer Science, Artificial Intelligence
Deqiang Ouyang, Jie Shao, Cheng Hu
NEURAL COMPUTING & APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Liruo Zhang, Sing Kiong Nguang, Deqiang Ouyang, Shen Yan
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Hongfei Li, Chuandong Li, Deqiang Ouyang, Sing Kiong Nguang
Summary: This article considers impulsive synchronization for inertial neural networks with unbounded delay and actuator saturation via sampled-data control. Theoretical analysis and numerical simulations demonstrate the effectiveness of the proposed approach. Additionally, a new image encryption algorithm based on hybrid control synchronization theory is presented and validated through experiments.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Information Systems
Hongzhi Li, Dezhi Han, Mingdong Tang
Summary: This article proposes a decentralized and privacy-preserving charging scheme for EVs based on blockchain and fog computing to address the privacy issues of EVs charging systems. The scheme introduces fog computing to provide local computing services and employs a flexible consortium blockchain architecture to ensure privacy security during the charging process.
IEEE SYSTEMS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Hui Xu, Jiaxing Wang, Hao Li, Deqiang Ouyang, Jie Shao
Summary: This paper proposes an unsupervised meta-learning algorithm that learns from an unlabeled dataset and adapts to downstream human specific tasks with few labeled data. Experimental results show that the proposed method outperforms other tested unsupervised representation learning approaches and two recent unsupervised meta-learning baselines on two datasets.
PATTERN RECOGNITION
(2021)
Article
Automation & Control Systems
Hongfei Li, Chuandong Li, Deqiang Ouyang, Sing Kiong Nguang, Zhilong He
Summary: This article investigates the observer-based dissipativity control of Takagi-Sugeno (T-S) fuzzy neural networks with distributed time-varying delays. By establishing a new Lyapunov-Krasovskii functional and delay-dependent reciprocally convex inequality, the global asymptotical stability and strict (Q, S, R)-a-dissipativity are achieved. The effectiveness of the proposed results is demonstrated in numerical simulations.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Engineering, Electrical & Electronic
Xiaoyang Tian, Jie Shao, Deqiang Ouyang, Heng Tao Shen
Summary: The goal of cross-view image matching based on geo-localization is to determine the location of a ground-view image by matching it with a group of satellite-view images with geographic tags. Existing methods ignore the spatial correspondence between UAV-satellite views and only use brute force for feature matching, resulting in inferior performance. In this study, we propose an end-to-end cross-view matching method that integrates cross-view synthesis and geo-localization modules, improving performance by about 5%.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Anjie Zhu, Deqiang Ouyang, Shuang Liang, Jie Shao
Summary: This paper proposes a novel paradigm for knowledge graph reasoning by decomposing it into a two-level hierarchical decision process. It effectively controls the action space and enhances the rationality of reasoning. Additionally, a dynamic prospect mechanism is introduced to improve the effectiveness of the policy.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Anjie Zhu, Feiyu Chen, Hui Xu, Deqiang Ouyang, Jie Shao
Summary: Extracting temporal abstraction is a crucial challenge in hierarchical reinforcement learning. This study proposes methods to address the challenge through diversity and individuality perspectives.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Feiyu Chen, Jie Shao, Anjie Zhu, Deqiang Ouyang, Xueliang Liu, Heng Tao Shen
Summary: Approximating the uncertainty of an emotional AI agent is crucial for improving reliability and facilitating human-in-the-loop solutions. In this article, HU-Dialogue is presented, a model that incorporates hierarchical uncertainty for emotion recognition in conversation (ERC) task. Experimental results show that our model outperforms previous state-of-the-art methods on popular multimodal ERC datasets.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Information Systems
Xin Man, Deqiang Ouyang, Xiangpeng Li, Jingkuan Song, Jie Shao
Summary: This paper proposes a novel video captioning method that fully mines visual cues and considers scenario information, resulting in goal-directed and narrative coherent video descriptions.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.