Article
Automation & Control Systems
Taotao Hu, Zheng He, Xiaojun Zhang, Shouming Zhong, Xueqi Yao
Summary: This paper investigates the delay-dependent stability analysis of fractional-order systems with time-varying delay by proposing novel fractional-order integral inequalities and designing Lyapunov-Krasovskii functions to reduce conservatism, deriving delay-dependent criteria to achieve asymptotic stability of systems with time-varying delay.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2021)
Article
Mathematics, Interdisciplinary Applications
Xin Liu, Lili Chen, Yanfeng Zhao
Summary: This paper discusses the problem of uniform stability for a class of fractional-order fuzzy impulsive complex-valued neural networks with mixed delays in infinite dimensions for the first time. The uniqueness of the solution and criteria for uniform stability are derived using fixed-point theory, theory of differential inclusion, and set-valued mappings. Compared to related results, the approach does not require the construction of a complex Lyapunov function, reducing computational complexity.
FRACTAL AND FRACTIONAL
(2022)
Article
Computer Science, Artificial Intelligence
Hui Li, Yonggui Kao, Haibo Bao, Yangquan Chen
Summary: This paper discusses the complex-valued neural network based on CV parameters and variables, focusing on the fractional-order CVNN with linear impulses and fixed time delays. Criteria for uniform stability and existence and uniqueness of equilibrium solutions were derived using the sign function, Banach fixed point theorem, and two classes of activation functions. Three experimental simulations were presented to illustrate the correctness and effectiveness of the obtained results.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jianying Xiao, Jinde Cao, Jun Cheng, Shiping Wen, Ruimei Zhang, Shouming Zhong
Summary: This article focuses on the global synchronization and stability of fractional-order quaternion-valued neural networks, proposing multiple and flexible criteria based on the Lyapunov theory and new inequalities. The effectiveness of these criteria is demonstrated through numerical examples.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Yao Xu, Shang Gao, Wenxue Li
Summary: This article examines the exponential stability problem of fractional-order complex multi-links networks under aperiodically intermittent control, and provides the theoretical results on how control gain and fractional derivative order affect the exponential convergence rate. The practicality of the theoretical results is demonstrated through investigating the stability of fractional-order competitive neural networks with aperiodically intermittent control and establishing a stability criterion, which is further validated through a numerical example.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Automation & Control Systems
Yuanchu Shen, Song Zhu, Xiaoyang Liu, Shiping Wen
Summary: This article discusses the coexistence and dynamical behaviors of multiple equilibrium points in fractional-order complex-valued memristive neural networks with delays. The conditions for the existence of multiple equilibrium points are proposed, and the stability of these points is proven using the Lyapunov function. The effectiveness of the theoretical analysis is verified through computer simulations.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Mathematics, Applied
Mani Mallika Arjunan, Pratap Anbalagan, Qasem Al-Mdallal
Summary: This paper aims to establish the uniform stability criteria for fractional-order time-delayed gene regulatory networks with leakage delays (FOTDGRNL). The existence and uniqueness of the considered systems are established using the Banach fixed point theorem. The delay-dependent uniform stability and robust uniform stability of FOFGRNLT are investigated with the help of certain analysis techniques depending on equivalent norm techniques. Two numerical examples are provided to justify the applicability of the theoretical results.
MATHEMATICAL METHODS IN THE APPLIED SCIENCES
(2023)
Review
Computer Science, Artificial Intelligence
Jinde Cao, K. Udhayakumar, R. Rakkiyappan, Xiaodi Li, Jianquan Lu
Summary: This study provides an exhaustive review of the dynamical studies of multidimensional FONNs in continuous/discontinuous time. It covers various neural network models and their applications in different mathematical fields. Theoretical findings from multidimensional FONNs with different types of delays are thoroughly evaluated, and stability and synchronization requirements for fractional-order NNs without delays are mentioned.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Fanghai Zhang, Zhigang Zeng
Summary: This article investigates the multistability and stabilization of fractional-order competitive neural networks with unbounded time-varying delays, deriving conditions for coexistence of equilibrium points and multiple mu-stability through analytical methods. The results enrich and improve previous findings in the field, and are demonstrated to be effective through numerical examples.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Mathematics
Yilin Hao, Xiulan Zhang
Summary: This article discusses the adaptive control of uncertain fractional-order time-delay systems using a fuzzy adaptive method and robust controller design. Simulation examples demonstrate the effectiveness of the proposed method in stabilizing the system state and keeping the signals bounded within the FOTDS.
JOURNAL OF MATHEMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Chengdai Huang, Juan Wang, Xiaoping Chen, Jinde Cao
Summary: This paper investigates the bifurcation issue of a FOBAMNN with four different delays, finding that the stability of the network can be preserved by selecting smaller control delays, while Hopf bifurcation occurs once the delays exceed their critical values. The derived bifurcation results are numerically verified and the theoretical analysis is validated through simulation experiments.
Article
Mathematics, Interdisciplinary Applications
Ivanka Stamova, Trayan Stamov, Gani Stamov
Summary: In this paper, the concept of Lipschitz stability is introduced to impulsive delayed reaction-diffusion neural network models of fractional order. The stability analysis and criteria proposed in the paper extend existing results and are useful in numerous inverse problems.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Mathematics, Applied
Xiang Liu, Yongguang Yu
Summary: This paper introduces the discrete fractional-order Halanay inequality with distributed delays. Then, based on the generalized discrete fractional Halanay inequality and Lyapunov functional method, several novel Mittag-Leffler stability and synchronization conditions of discrete fractional-order neural network systems with distributed delays are derived. An example is given to illustrate one of the results.
FRACTIONAL CALCULUS AND APPLIED ANALYSIS
(2022)
Article
Mathematics, Applied
K. Udhayakumar, R. Rakkiyappan, Xiaodi Li, Jinde Cao
Summary: This paper investigates the multiple psi-type stability of fractional-order quaternion-valued neural networks and provides new conditions for the existence of multiple equilibrium points. The psi-type stability of the proposed neural networks is studied using fractional calculus theory and derivative techniques, and the effectiveness of the theoretical results is demonstrated through numerical simulations.
APPLIED MATHEMATICS AND COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Fanghai Zhang, Zhigang Zeng
Summary: This article discusses the multistability and attraction of fractional-order neural networks with unbounded time-varying delays. Multiple sufficient conditions are provided for the coexistence of equilibrium points with concave-convex activation functions. The criteria for Mittag-Leffler stability can be simplified to M-matrix and the extension of attraction basin is shown to be independent of the magnitude of delays. Three numerical examples are given to demonstrate the validity of the theoretical results.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Business, Finance
Chuangxia Huang, Yunke Deng, Xin Yang, Xiaoguang Yang, Jinde Cao
Summary: This paper aims to develop a novel network indicator for the rapid and accurate detection of financial crises. By constructing complex networks and extracting the Laplacian energy measure, this indicator successfully detects major financial events and outperforms traditional indicators in terms of accuracy and response speed.
EUROPEAN JOURNAL OF FINANCE
(2023)
Article
Computer Science, Artificial Intelligence
Ying Zhang, Rencan Nie, Jinde Cao, Chaozhen Ma
Summary: This paper proposes a self-supervised framework based on contrastive auto-encoding and convolutional information exchange for multi-modal medical fusion tasks. The proposed method constructs positive and negative result pairs and utilizes a novel contrastive loss to avoid information redundancy. It combines transformer and convolution neural networks in parallel to preserve both global and local features, and adopts a contribution estimation model for multi-modal medical image fusion. Experimental results show that the proposed method outperforms other state-of-the-art fusion approaches.
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
(2023)
Article
Automation & Control Systems
Muhammed Syed Ali, Muhammed Haneef Mubeen Tajudeen, Grienggrai Rajchakit, Porpattama Hammachukiattikul, Jinde Cao
Summary: This study addresses the problem of fault-tolerant control for a multi-agent system with input delay and sensor failures. The communication topology is an undirected subgraph with directed connections between the followers and leader. The Lyapunov approach is used to identify criteria for consensus control. A fault-tolerant controller based on observed descriptors is proposed to solve actuator problems, sensor faults, and state estimations. The Artstein-Kwon-Pearson reduction method is applied to minimize data size. Numerical examples are provided to demonstrate the theoretical results.
ASIAN JOURNAL OF CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Hao Shen, Xiaohui Hu, Jing Wang, Jinde Cao, Wenhua Qian
Summary: This work explores the $H_{infinity }$ synchronization issue for singularly perturbed coupled neural networks (SPCNNs) affected by both nonlinear constraints and gain uncertainties. A novel double-layer switching regulation containing Markov chain and persistent dwell-time switching regulation (PDTSR) is proposed to design a mode-dependent synchronization controller for the network. New sufficient conditions are established to ensure the mean-square exponential stability of the synchronization error systems with the specified level of the $H_{infinity }$ performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Mathematics, Interdisciplinary Applications
Peng Zhu, Min Xiao, Xia Huang, Fuchen Zhang, Zhen Wang, Jinde Cao
Summary: In recent years, the control of time evolution in ordinary differential systems has developed rapidly, while the control of spatiotemporal evolution dynamics in partial differential systems remains an open question. Turing pattern is a main spatiotemporal evolution behavior in mussel-algal ecosystems and controlling it can restore the ecosystem's stability. However, there has been limited research on the optimal control of Turing pattern in the mussel-algal system. This paper proposes a proportional-derivative (PD) control strategy for the reaction-diffusion mussel-algae model with time delays and demonstrates its efficiency and feasibility through numerical simulations.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Automation & Control Systems
Taixiang Zhang, Xiaodi Li, Jinde Cao
Summary: This article studies the finite-time stability of impulsive switched systems and proposes sufficient criteria based on multiple Lyapunov functions and dwell time condition. The results show that by effectively controlling the impulses and dwell time, the system can be stabilized in finite time.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
Article
Remote Sensing
Xianyue Wang, Longxia Qian, Jian Shi, Mei Hong, Jinde Cao
Summary: This article presents an efficient feature extraction framework, called the dual feature fusion model (DFFM), to address issues in hyperspectral image applications. The framework utilizes a novel two-order feature fusion and a valid three-order feature fusion method to maintain spatial structure integrity and save computing costs. It also automatically selects a suitable number of features and is robust to noise and training sets. Experimental results demonstrate that the framework outperforms state-of-the-art techniques in classification precision and execution time across various training sizes.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Lianglin Xiong, Li Cai, Jinde Cao, Tao Wu, Haiyang Zhang
Summary: In this paper, the authors address the issue of stability and stabilization for semi-Markov jump memristive neural networks (SMJMNNs) with stochastic quantized sampled-data control (QSDC) law. They establish a model of memristive neural network (MNN) with mixed semi-Markov jump and propose a stochastic QSDC scheme that considers the influence of transmission delay. They also develop a more general weak infinitesimal operator and construct stochastic Lyapunov functionals (LFs) to reduce conservatism and establish a stochastic stability criterion for SMJMNNs based on the constructed LFs.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yanbu Guo, Dongming Zhou, Xiaoli Ruan, Jinde Cao
Summary: The study presents a feature extraction model based on variational gated autoencoder for inferring potential disease-miRNA associations. Experimental results show that the proposed model achieves remarkable association prediction performance, validating the efficacy of the variational gate mechanism and contrastive cross-entropy loss for inferring disease-miRNA associations.
Article
Physics, Multidisciplinary
Yuwei Yang, Zhuoxuan Li, Jun Chen, Zhiyuan Liu, Jinde Cao
Summary: This paper proposes an extreme learning machine (ELM) algorithm based on residual correction and Tent chaos sequence (TRELM-DROP) for accurate prediction of traffic flow. The algorithm reduces the impact of randomness in traffic flow through the Tent chaos strategy and residual correction method, and avoids weight optimization using the iterative method. A DROP strategy is introduced to improve the algorithm's ability to predict traffic flow under varying conditions.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Computer Science, Information Systems
Yanyu Liu, Yongsheng Zang, Dongming Zhou, Jinde Cao, Rencan Nie, Ruichao Hou, Zhaisheng Ding, Jiatian Mei
Summary: Medical image fusion technology plays a crucial role in computer-aided diagnosis by extracting useful cross-modality cues and generating high-quality fused images. Existing methods mainly focus on fusion rules, leaving room for improvement in cross-modal information extraction. In this study, we propose a novel encoder-decoder architecture with three technical novelties, including attribute-based self-reconstruction tasks, a hybrid network combining CNN and transformer modules, and a self-adaptive weight fusion rule. Extensive experiments demonstrate satisfactory performance on medical image datasets and other multimodal datasets.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Automation & Control Systems
Xiaodi Li, Wenlu Liu, Sergey Gorbachev, Jinde Cao
Summary: This article investigates the event-triggered impulsive control (ETIC) problem for a class of nonlinear time-delay systems subject to exogenous disturbances. An original event-triggered mechanism (ETM) based on Lyapunov function approach is constructed, which utilizes the information of system state and external input. The article presents sufficient conditions for achieving input-to-state stability (ISS) of the considered system and establishes the relationship among ETM, exogenous input, and impulse action. The article also excludes possible Zeno behavior induced by the proposed ETM and provides the design criterion for ETM and impulse gain for impulsive control systems with delay.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Engineering, Electrical & Electronic
Hongling Qiu, Jun Shen, Jinde Cao, Heng Liu
Summary: This paper investigates the Loo-gain of incommensurate fractional-order delayed positive systems (FODPSs). It proposes necessary and sufficient criteria for achieving the positivity and stability of FODPSs with mixed delays. The validity of the theoretical results is demonstrated through numerical simulation.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Mathematics, Applied
Wenjie Li, Yajuan Guan, Jinde Cao, Fei Xu
Summary: This article establishes the global stability of the disease-free equilibrium in a degenerate diffusion system involving environmental transmission and spatial heterogeneity. It provides important insights into the transmission dynamics of avian influenza virus among avian, poultry, and human populations.
APPLIED MATHEMATICS LETTERS
(2024)
Article
Computer Science, Artificial Intelligence
Hanjie Liu, Jinde Cao, Wei Huang, Xinli Shi, Xingye Zhou, Zhuoxuan Li
Summary: A data-driven multidimensional framework is proposed to evaluate pavement condition by utilizing multilayer network representation learning. The method can capture the nonlinear interactions among performance attributes and provide a more in-depth understanding of pavement service condition. Experimental results demonstrate the effectiveness of this method in multi-attribute evaluation.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
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.