Article
Mathematics, Interdisciplinary Applications
Shilong Zhang, Feifei Du, Diyi Chen
Summary: This article investigates quasi-synchronization for a class of fractional-order delayed neural networks. By introducing a new fractional-order differential inequality and designing an adaptive controller, an effective criterion is proposed to ensure the quasi-synchronization.
FRACTAL AND FRACTIONAL
(2023)
Article
Mathematics, Interdisciplinary Applications
Qiu Peng, Jigui Jian
Summary: This paper focuses on global asymptotic synchronization of second-fractional-order fuzzy neural networks with delay and impulsive effects. Effective criteria are obtained using the fractional Lyapunov functional approach and the impulsive fractional-order delayed comparison principle. Two different control schemes are proposed to ensure synchronization by using the fractional derivative of states. The derived findings are validated through numerical simulations.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Computer Science, Artificial Intelligence
Lu Pang, Cheng Hu, Juan Yu, Leimin Wang, Haijun Jiang
Summary: This paper addresses the synchronization problem of impulsive complex networks with mismatched parameters, focusing on fixed-time (FT) and preassigned-time (PT) synchronization. The research first establishes more succinct conditions to achieve FT stability of impulsive systems and provides an improved estimation for the stable time. Building upon the improved FT stability results, FT synchronization criteria for ICNs with mismatched parameters are proposed by designing fixed-time controllers without the linear part. Correspondingly, the PT synchronization problem is also considered by developing innovative control protocols. The presented synchronization criteria are validated through numerical simulation.
Article
Mathematics, Interdisciplinary Applications
Yu Liu, Chao Zhang, Meixuan Li
Summary: The research aims to investigate the global dissipativity and quasi-synchronization of fractional-order neural networks (FNNs). A criterion for global dissipativity is established by creating an appropriate Lyapunov function and using fractional-order inequality techniques. Additionally, the issue of quasi-synchronization in drive-response FNNs is studied using linear state feedback control. The study demonstrates that the synchronization error converges to a bounded region by selecting an appropriate control parameter. The effectiveness of the research is validated through three numerical examples.
FRACTAL AND FRACTIONAL
(2023)
Article
Computer Science, Interdisciplinary Applications
Liguang Xu, Xiaoyan Chu, Hongxiao Hu
Summary: This paper investigates global exponential quasi-synchronization for fractional-order delayed dynamical networks with periodically intermittent pinning control. New fractional-order delayed differential inequalities are presented, and sufficient conditions for achieving global exponential quasi-synchronization are derived using the Lyapunov method and periodically intermittent pinning controller. Numerical simulations are provided to confirm the theoretical results.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2021)
Article
Mathematics, Interdisciplinary Applications
Fei Wang, Zhaowen Zheng, Yongqing Yang
Summary: This paper investigates the quasi-synchronization problem of a heterogeneous dynamical network with fractional order dynamical behavior and time-varying delay. It applies the distributed impulsive control strategy and discusses both synchronizing impulses and desynchronizing impulses.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoze Ni, Shiping Wen, Huamin Wang, Zhenyuan Guo, Song Zhu, Tingwen Huang
Summary: This article focuses on the observer-based quasi-synchronization problem of delayed dynamical networks with parameter mismatch under impulsive effect. State estimation strategy is proposed, appropriate synchronization controller is designed, and analysis is done using Lyapunov function to prove the boundedness of the system trajectory. A numerical simulation is presented to illustrate the validity of the obtained results.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Mathematics, Interdisciplinary Applications
Ruihan Chen, Tianfeng Zhao
Summary: This paper investigates the quasi-synchronization of nonidentical fractional-order memristive neural networks (FMNNs) via impulsive control. The study provides quasi-synchronization conditions, error convergence rates, and error boundaries for the networks, demonstrating their validity through a simulation example.
DISCRETE DYNAMICS IN NATURE AND SOCIETY
(2021)
Article
Automation & Control Systems
Dong Ding, Ze Tang, Ju H. Park, Yan Wang, Zhicheng Ji
Summary: This article investigates the synchronization of complex networks with nonlinear couplings and distributed time-varying delays. It analyzes a leader-following quasisynchronization issue using impulsive control due to the mismatched parameters of individual systems. A dynamic self-triggered impulsive controller is proposed to predict the available instants of impulsive inputs. The synchronization conditions within a specific bound are derived using the Lyapunov stability theorem and the comparison method.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Mathematics, Applied
Nanxiang Yu, Wei Zhu
Summary: This paper investigates the synchronization of fractional-order differential chaotic systems using event-triggered impulsive control, combining the advantages of impulsive control and event-triggered control. By reducing the update frequency of the controller, the consumption of communication bandwidth and computing resources can be further reduced, while excluding Zeno-behavior of the impulsive sequence. The theoretical results are validated through a numerical example with simulation.
APPLIED MATHEMATICS AND COMPUTATION
(2021)
Article
Mathematics, Interdisciplinary Applications
Lu Wang, Xujun Yang, Hongjun Liu, Xiaofeng Chen
Summary: This paper investigates the synchronization in finite time of fractional-order complex-valued gene networks with time delays. Several sufficient conditions for the synchronization in finite time of the relevant network models are explored using feedback controllers and adaptive controllers. The setting time of the response is then estimated using the theory of fractional calculus. Finally, a numerical example is presented to validate the theoretical results, demonstrating that the setting time based on the adaptive controller is shorter than that based on the feedback controller.
FRACTAL AND FRACTIONAL
(2023)
Article
Automation & Control Systems
Ankit Kumar, Sunny Singh, Subir Das, Yang Cao
Summary: This article investigates the projective quasi-synchronization problem of non-identical complex-valued recurrent neural networks (CVRNNs) with proportional delays and mismatched parameters. Nonlinear Lipschitz activation functions, Lyapunov stability criteria, and the matrix measure approach are employed. By designing a suitable controller, a sufficient condition for projective quasi-synchronization of the non-identical CVRNNs model is derived using the matrix measure approach. Important results for CVRNNs with mismatched parameters and proportional delays are provided. Numerical simulation results are presented to validate the theoretical results, and graphical representations are shown for different specific cases.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Mathematics, Applied
Zahra Moniri, Behrouz Parsa Moghaddam, Morteza Zamani Roudbaraki
Summary: This paper presents a computationally efficient and fast-running solver for fractional differential equations with impulsive effects. A B-spline version of interpolation by corresponding equal mesh points is used to approximate the fractional-order integral operator. An illustrative example compares the accuracy of the new solver results with those of a previous study. The performance of the proposed solver is evaluated using the fractional Rossler and susceptible-exposed-infectious impulsive systems, demonstrating the impact of impulsive behaviors for various impulsive values.
JOURNAL OF FUNCTION SPACES
(2023)
Article
Mathematics, Interdisciplinary Applications
Joel Perez Padron, Jose P. Perez, Jose Javier Perez Diaz, Carlos Astengo-Noguez
Summary: In this research, time-delay adaptive synchronization and adaptive anti-synchronization of chaotic fractional order systems are analyzed using the Caputo fractional derivative. The problem of synchronization and anti-synchronization of chaotic systems with variable fractional order is solved using the fractional order PID control law, adaptive laws of variable-order fractional calculus, and a control law derived from Lyapunov's theory extended to systems of time-delay variable-order fractional calculus. This research solves two important problems in the control area: synchronization of chaotic systems with adaptive fractional order and time delay using the fractional order PID control law and adaptive laws, and anti-synchronization of chaotic systems with adaptive fractional order and time delay using the fractional order PID control law and adaptive laws.
FRACTAL AND FRACTIONAL
(2023)
Article
Computer Science, Artificial Intelligence
N. Padmaja, P. Balasubramaniam
Summary: This work presents a novel delay-dependent LMI condition for analyzing the passivity of fractional-order neural networks with impulse, proportional delays, and state-dependent switching parameters. Additionally, a sufficient condition for impulse gain-dependent LMI condition is derived, along with passivity criteria for fractional-order systems with proportional delays.
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.