A5073242437- Distributed Control Multi-Agent Systems
- Neural Networks Stability and Synchronization
- Domain Adaptation and Few-Shot Learning
- Stability and Control of Uncertain Systems
- Complex Network Analysis Techniques
- Multimodal Machine Learning Applications
- Opinion Dynamics and Social Influence
- Nonlinear Dynamics and Pattern Formation
- COVID-19 diagnosis using AI
- GaN-based semiconductor devices and materials
- Adaptive Control of Nonlinear Systems
- Structural Behavior of Reinforced Concrete
- Mathematical and Theoretical Epidemiology and Ecology Models
- Structural Load-Bearing Analysis
- Semiconductor materials and devices
- Robotic Path Planning Algorithms
- Chaos control and synchronization
- Matrix Theory and Algorithms
- Semiconductor Quantum Structures and Devices
- Energy Efficient Wireless Sensor Networks
- Gene Regulatory Network Analysis
- Machine Learning and ELM
- Modular Robots and Swarm Intelligence
- Structural Engineering and Vibration Analysis
- Quantum chaos and dynamical systems
Mohamed bin Zayed University of Artificial Intelligence
2023-2024
Carnegie Mellon University
2023-2024
East China Jiaotong University
2015-2024
Tongji University
2005-2024
Huazhong University of Science and Technology
2006-2024
Henan University
2021-2022
Weatherford College
2021
Guizhou University
2021
Nanchang University
2021
China Academy of Space Technology
2019-2020
Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to over-coming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature extraction models trained on ImageNet alone, ignoring cross-dataset bias between GZSL benchmarks. Such a inevitably results in poor-quality visual features for tasks, which potentially limits recognition performance both seen unseen classes. In this paper, we...
This article focuses on scaled consensus tracking for a class of high-order nonlinear multiagent systems. Different from the existing results, systems with time delays and external disturbances, fully distributed protocol is designed to drive all agents achieve preassigned ratios. The control gains are varying updated by adaptive laws. As result, presented independent any global information, thus, could be implemented in manner. Simultaneously, using an <inline-formula...
The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, thus achieving a desirable transfer unseen classes. Prior works either simply align global an image with its associated class vector or utilize unidirectional attention learn limited representations, which could not effectively discover intrinsic (e.g., semantics) features. To solve above dilemma, we propose Mutually Semantic Distillation Network...
Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen unseen ones. Semantic is learned attribute descriptions shared between different classes, which are strong prior for localization of object representing discriminative region features enabling significant visual-semantic interaction. Although few attention-based models have attempted learn such in a single image, the transferability and visual typically neglected. In this paper, we propose...
Multiple chaotic attractors, implying several independent attractors generated simultaneously in a system from different initial values, are very interesting and important nonlinear phenomenon, but there few studies that have previously addressed it to our best knowledge. In this paper, we propose polynomial function method for generating multiple the Sprott B system. The extends number of index-2 saddle foci, which determines emergence analysis equilibria is presented. Two coexisting three...
This article is concerned with the event-triggered guaranteed cost control for a class of Markovian jump systems time-varying delays and partly unknown transition probabilities, which described by Takagi-Sugeno fuzzy model. For sake saving network bandwidth, an mechanism related to system modes developed in feedback channel, network-induced delay randomly occurs. The stability criterion index derived Lyapunov-Krasovskii functional. Moreover, sufficient conditions that ensure existence...
Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to ones. Typically, guarantee desirable transfer, a common (latent) space is adopted for associating visual and domains in ZSL. However, existing methods align by merely mitigating distribution disagreement through one-step adaptation. This strategy usually ineffective due heterogeneous nature of feature representations two domains, which intrinsically contain both...
This paper is concerned with the sliding mode control problem for a class of continuous-time switched neural networks mode-dependent average dwell time (MDADT). The considered are motivated by biological which contain nonlinear term and changeable signal. concept MDADT introduced, in every subsystem has its own before switching to another subsystem. Moreover, novel controller designed an event-triggered mechanism based on observer error system mode, where triggered condition can be more...
In this paper, the flocking behavior and targets consensus tracking problems of heterogeneous multiple inertial agents with limited communication ranges are investigated. Consider effect real agents, a distributed control protocol is designed such that can achieve stable group behaviors. Using decomposition approach, stability system proved. Combining themselves in charge searching choosing target an autonomous individual way according to relationship between velocities targets. An augmented...
This paper considers the problem of distributed H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> filtering for a class switched repeated scalar nonlinear systems with randomly occurred sensor nonlinearities and asynchronous switching due to practical reasons. The possibility is described by Bernoulli stochastic variable, means that mode plant different from designed filter possibly. A network used estimate system state instead improve...
In this paper, the scaled consensus of multiagent systems (MASs) with second-order nonlinear dynamics and time-varying delays is investigated, where agents are supposed to aperiodically communicate each other under a directed graph at some disconnected time intervals. Different from existing works, we consider case exist in both communication networks. First, address problem, propose novel protocol. Second, using Lyapunov theory theory, it proved that mild conditions, MASs exponentially...
This brief is concerned with the problem of observed-based asynchronous control for a class semi-Markov jump systems (SMJSs) in continuous-time domain. There exists an phenomenon between system modes and controller due to limitations actual environment. System are usually described as hidden observable modes, respectively. Their relationship can be exhibited by emission probabilities. In this brief, model used describe such phenomenon. A conventional approach employed improved result derived...
In this article, the consensus problem of linear multiagent systems (MASs) is investigated, where an event-triggered mechanism combined with sampler introduced to rationally utilize network bandwidth and communication energy. Different from most existing results on MASs, a time-varying delay (CD) more general form constructed in article. With help new class Lyapunov functional advanced inequalities, some novel criteria for achieving asymptotic considered MASs under different CD cases are...
In this article, we consider the cooperative output regulation for linear multiagent systems (MASs) via distributed event-triggered strategy in fixed time. A novel fixed-time control protocol is proposed using a dynamic compensator method. It shown that based on designed scheme, problem addressed time and agents communication network are subject to intermittent with their neighbors. Simultaneously, event-triggering mechanism, Zeno behavior can be ruled out by choosing appropriate parameters....
This article studies the stability problem of generalized neural networks (GNNs) with time-varying delay. The delay has two cases: first case is that delay's derivative only upper bound, other no information its or itself not differentiable. For both cases, we provide novel criteria based on Lyapunov-Krasovskii functionals (LKFs) and new negative definite conditions (NDCs) matrix-valued cubic polynomials. In contrast existing methods, in this article, proposed do need to introduce extra...
In this paper, the local flocking of multi-agent systems is investigated, which means all agents form some groups surrounding multiple targets with partial information exchange. For purpose realising multi-flocking, a control algorithm proposed, biologically inspired approach that assimilates key characteristics and anti-flocking. process mobile through algorithm, can adaptively choose between two work modes to depend on variation visual field number pursuing target. One mode pursue each...