Deep neural networks, especially face recognition models, have been shown to be vulnerable to adversarial examples. However, existing attack methods for face recognition systems either cannot attack black-box models, ...
详细信息
Signed networks refer to a class of network systems including not only cooperative but also antagonistic interactions among *** to the existence of antagonistic interactions in signed networks,the agreement of nodes m...
详细信息
Signed networks refer to a class of network systems including not only cooperative but also antagonistic interactions among *** to the existence of antagonistic interactions in signed networks,the agreement of nodes may not be established,instead of which disagreement behaviors generally *** paper reviews several different disagreement behaviors in signed networks under the single-integrator linear dynamics,where two classes of topologies,namely,the static topology and the dynamic topology,are *** the static signed networks with the adjacency weights as(time-varying)scalars,we investigate the convergence behaviors and the fluctuation behaviors with respect to fixed topologies and switching topologies,respectively,and give some brief introductions on the disagreement behaviors of general time-varying signed ***,several classes of behavior analysis approaches are also *** the dynamic signed networks with the adjacency weights as transfer functions or linear time-invariant systems,we show the specific descriptions and characteristics of them such that the disagreement behaviors can be obtained by resorting to the derived static signed ***,we give their applications to the behavior analysis of static signed networks in the presence of high-order dynamics or communication delays.
The paper proposes new ontologies for describing and diagnosing malfunctions of subsystems of autonomous underwater vehicles (AUV) as a part of the development of a previously created approach to the intelligent diagn...
详细信息
Zero-shot learning (ZSL) is an important but challenging task in computer vision that aims to identify unseen classes without matching training samples. Current cutting-edge ZSL methods based on locality focus on acqu...
In the electronics industry, PCB is crucial for ensuring the product quality. However, these defects of PCB generally have the characteristics of complex backgrounds, small sizes and similar features, resulting in the...
详细信息
The paper presents the results of developing a method for generating reference control signals that describe the desired law of movement of various mechatronic objects (unmanned aerial vehicles, mobile land and underw...
详细信息
The accurate prediction of behaviors of surrounding traffic participants is critical for autonomous vehicles (AV). How to fully encode both explicit (e.g., map structure and road geometry) and implicit scene context i...
详细信息
作者:
Zhang, ChunjieZheng, XiaolongBeijing Jiaotong University
Institute of Information Science Beijing100044 China Beijing Jiaotong University
Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China University of Chinese Academy of Sciences
State Key Laboratory of Multimodal Artificial Intelligence Systems The State of Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence Beijing100190 China
Most image classification methods are designed to either boost the classification accuracies with abundant supervision, or cope with the shortage of supervision information. This is often achieved by using the visual ...
详细信息
For the problem of fault tolerant trajectory tracking control for a large Flying-Wing (FW) aircraft with Linear Parameter-Varying (LPV) model, a gain scheduled H∞ controller is designed by dynamic output feedback. Ro...
详细信息
For the problem of fault tolerant trajectory tracking control for a large Flying-Wing (FW) aircraft with Linear Parameter-Varying (LPV) model, a gain scheduled H∞ controller is designed by dynamic output feedback. Robust synthesis of this gain scheduled H∞ control is carried out by an affine Parameter Dependent Lyapunov Function (PDLF). The problem of trajectory tracking control for the LPV plant is transformed into solving an infinite number of linear matrix inequalities by the PDLF design, and the linear matrix inequalities are solved by convex optimization techniques. To overcome model uncertainties due to linearization and external disturbances, a radial basis function neural network disturbance observer is proposed, and to estimate actuator faults, an LPV fault estimator is designed. Furthermore, a composite controller is proposed to realize fault tolerant trajectory tracking control, which combines the LPV control with the fault estimator and disturbance observer, as well as an active-set based control allocation to avoiding actuator saturation. The approach is tested by simulation of two scenarios that show responses of the altitude, speed and heading angle to (i) unknown disturbances and (ii) actuator faults. The results show that the proposed neural network observer based LPV control has better performances for both disturbance rejecting and fault-tolerant trajectory tracking. IEEE
The work is devoted to approbation of a methodology for constructing and verifying composite maps of sea surface temperature (SST) with the preservation of thermal fronts. The equatorial part of the Northwestern Pacif...
详细信息
暂无评论