检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 684-697页

作者： Chen, Sizhe Huang, Zhehao Tao, Qinghua Huang, Xiaolin Department of Automation and Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China MOE Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China ESAT-STADIUS Katholieke Universiteit Leuven Leuven3000 Belgium

Deep neural networks (DNNs) are acknowledged as vulnerable to adversarial attacks while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates. For query-efficiency, surrogate models of the victim are used to generate transferable adversarial examples (AEs) because of their gradient similarity (GS), i.e., surrogates' attack gradients are similar to the victim's ones. However, it is generally neglected to exploit their similarity on outputs, namely the prediction similarity (PS), to filter out inefficient queries by surrogates without querying the victim. To jointly utilize and also optimize surrogates' GS and PS, we develop QueryNet, a unified attack framework that can significantly reduce queries. QueryNet creatively attacks by multi-identity surrogates, i.e., crafts several AEs for one sample by different surrogates and also uses surrogates to decide on the most promising AE for the query. After that, the victim's query feedback is accumulated to optimize not only surrogates' parameters but also their architectures, enhancing both the GS and the PS. Although QueryNet has no access to pretrained surrogates' prior, it reduces queries by averagely about an order of magnitude compared to alternatives within an acceptable time, according to our comprehensive experiments: 11 victims (including two commercial models) on MNIST/CIFAR10/ImageNet, allowing only 8-b image queries, and no access to the victim's training data. The code is available at https://***/Sizhe-Chen/QueryNet. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Counter-swarm Splitting Strategy using Receding Horizon control Algorithm 41

A Counter-swarm Splitting Strategy using Receding Horizon Co...

引用

第41届中国控制会议

作者： Angwei Zhang Dewei Li Haibin Shao Lulu Pan Yaonan Guan the Department of Automation and the Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper proposes a model predictive control framework for the task of countering the swarm of autonomous *** on the Boids model,the neighbor selection mechanism and interaction model are further employed to characterize the formation of the target *** is assumed that individuals in the target swarm are equipped with a collision avoidance *** the perspective of the position and velocity of individuals in the target swarm,Lanchester's index and polarization index are employed to characterize the performance of the counter-swarm strategy,*** strategy of splitting the target swarm via attacking its geometric centroid is proposed and the model predictive control framework for the counter-swarm task is designed.A simulation is finally provided to illustrate the effectiveness of the proposed strategy.

关键词： counter swarm model predictive control autonomous systems Boids model collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Time-varying Output Formation control Based on a Reduced-order Output-feedback Protocol 41

Time-varying Output Formation Control Based on a Reduced-ord...

引用

第41届中国控制会议

作者： Zhuo Chen Xianwei Li Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper investigates time-varying output formation(TVOF) of homogeneous linear multi-agent systems based on a reduced-order output-feedback ***,a reduced-order output-feedback protocol using relative information of neighboring agents is *** this protocol,a necessary and sufficient condition for achieving TVOF is *** explicit expression of the time-varying formation reference function and a feasibility condition for TVOF are *** an algorithm is proposed for designing the protocol *** is shown that when the dynamics of each agent is stabilizable and detectable,the multi-agent system can achieve a desired TVOF under the protocol designed by the *** with existing results which only consider full-order protocols,the proposed protocol has a lower order and thus has lower implementation *** simulation is finally presented to demonstrate the effectiveness of the proposed protocol.

关键词： Time-varying output formation(TVOF) multi-agent systems output feedback reduced-order design

来源：评论

学校读者我要写书评

暂无评论

Lidar-Visual-Inertial Odometry with Online Extrinsic Calibration

引用

Journal of Shanghai Jiaotong university(Science) 2023年第1期28卷 70-76页

作者：茅天阳赵文韬王景川陈卫东 Department of Automation Institute of Medical RoboticsShanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China

To achieve precise localization,autonomous vehicles usually rely on a multi-sensor perception system surrounding the mobile *** is a time-consuming process,and mechanical distortion will cause extrinsic calibration ***,we propose a lidar-visual-inertial odometry,which is combined with an adapted sliding window mechanism and allows for online nonlinear optimization and extrinsic *** the adapted sliding window mechanism,spatial-temporal alignment is performed to manage measurements arriving at different *** nonlinear optimization with online calibration,visual features,cloud features,and inertial measurement unit(IMU)measurements are used to estimate the ego-motion and perform extrinsic *** experiments were carried out on both public datasets and real-world *** indicate that the proposed system outperforms state-of-the-art open-source methods when facing challenging sensor-degenerating conditions.

关键词： autonomous vehicles multi-sensor fusion online calibration

来源：评论

学校读者我要写书评

暂无评论

Robust Dual-Model Collaborative Broad Learning system for Classification Under Label Noise Environments

引用

IEEE Internet of Things Journal 2025年第12期12卷 21055-21067页

作者： Deng, Wu Shen, Jiuru Ding, Jianming Zhao, Huimin Civil Aviation University of China College of Electronic Information and Automation Tianjin300300 China Civil Aviation University of China Tianjin Key Laboratory for Advanced Signal Processing Tianjin300300 China Southwest Jiaotong University State Key Laboratory of Rail Transit Vehicle System Chengdu610031 China State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu610031 China

Broad Learning system (BLS) has shown remarkable results in various machine learning tasks, but the fragility of BLS based on the minimum mean square error criterion under the label noise environment in Internet of Things(IoT) limits its application. To solve these problems, a dual-model collaborative label adaptive correction BLS based on the collaboration of KRPBLS and SKBLS, namely SC-KSBLS is proposed to significantly improve the robustness of BLS under label noise environment. Firstly, a new broad learning system based on the Kernel risk-sensitive mean p-power(KRP) criterion, namely KRPBLS is developed to overcome the sensitivity by optimizing the output weight matrix and replacing the minimum mean square error criterion. Then, the label feature space is constructed, and the popular regularization strategy is designed to construct the SKBLS model with the collaborative training of KRP criterion and regularization to improve the learning ability of BLS. Finally, the interaction mechanism between KRPBLS and SKBLS is designed to effectively identify and correct label noise. The robustness theory of the SC-KSBLS has been analyzed and proven. The experimental results on nine datasets in IoT show that the SC-KSBLS significantly improves the robustness and performance, which provide an innovative solution under label noise environment. © 2014 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

GITANet: Group Interactive Threshold-based Attention Network for Hyperspectral Image Classification

引用

IEEE Transactions on Multimedia 2025年 27卷 3571-3584页

作者： Duan, Yule Chen, Chuang Fu, Maixia Gong, Xiuwen Niu, Yingying Luo, Fulin The University of Sydney Faculty of Engineering NSW2006 Australia Henan University of Technology Key Laboratory of Grain Information Processing and Control Ministry of Education Zhengzhou450001 China Henan University of Technology Key Laboratory of Grain Photoelectric Detection and Control Zhengzhou450001 China Chongqing University College of Computer Science Chongqing400044 China

Group convolution networks have shown great potential in hyperspectral image (HSI) classification because of their ability to divide total spectral bands into multiple groups and focus on fine discrimination within different spectral ranges. Most group convolution networks process parallel spectral groups independently;however, they neglect the important relevance of nearby spectral ranges. Moreover, the feature maps from different spectral groups are not considered for recalibration in the existing attention. To address these issues, we propose a novel group interactive threshold attention network (GITANet). In the network, a stratified-split-concatenation strategy, which not only splits all bands into multiple groups for intragroup convolution but also propagates the intergroup information via the stratified concatenation operation between different groups, is designed for bandwise group convolution. Relying on the high dependencies among nearby spectra, the cross-group interactive attention block is designed to encourage significant spectral features. Subsequently, from different spectral ranges, a learnable threshold generation block is built to estimate the information validity of each pixel. On the basis of this threshold, soft threshold spatial attention is developed in the bandwise encoderdecoder architecture, which emphasizes high-value spatial areas during the fusion of group convolutional features. Therefore, complementary and discriminative spectral-spatial features are obtained to improve the performance of HSI classification. The experimental results on three HSI datasets illustrate that GITANet is superior to several state-of-the-art networks. © 1999-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered control of Multiple Euler-Lagrange systems with Communication Time-Delays 41

Event-Triggered Control of Multiple Euler-Lagrange Systems w...

引用

第41届中国控制会议

作者： Xueqi Zhang Xianwei Li Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we study the consensus problem of multiple Euler-Lagrange systems subject to limited communication resources and parametric ***,an event-triggered communication scheme is proposed to achieve the leaderless consensus *** the proposed event-triggered mechanism,the state of each subsystem is transmitted at event instants which are aperiodic and asynchronous with respect to other ***,we consider the time-delay effects in *** consensus analysis of the proposed scheme is based on the small-gain *** simulation results on a network of robot manipulators are given to illustrate the effectiveness of the proposed control scheme.

关键词： Consensus event-triggered control Euler-Lagrange system communication delays

来源：评论

学校读者我要写书评

暂无评论

Containment control Protocol Design for PDE Agents Subject to External Disturbances 42

Containment Control Protocol Design for PDE Agents Subject t...

引用

42nd Chinese control Conference, CCC 2023

作者： Chen, Yining School of Artificial Intelligence Tiangong University Tianjin300387 China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai639798 China

ISBN: (纸本)9789887581543

This paper mainly solves the containment control issue for a network of infinite-dimensional agents described by wave equations. To eliminate influences caused by external disturbances, observers based on partial differential equations are proposed. A novel interaction protocol is then designed to reach containment control under a fixed directed communication topology. Different from the existing works, disturbances with unbounded derivatives are allowed in this paper. A proper Lyapunov function is constructed and the sufficient condition assuring containment control is obtained. Finally, the theoretical results are verified via numerical examples. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

A Novel FL-AoI-Based control and Event-Triggered Strategy Integrating Network Characteristics for ICPS 49

A Novel FL-AoI-Based Control and Event-Triggered Strategy In...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Lu, Xuanzhao Xu, Qimin Zhang, Jinglong Lin, Meihan Chen, Cailian Shanghai Jiao Tong University Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China China

ISBN: (纸本)9798350331820

The joint design of control and transmission has been demonstrated to be a successful technique for enhancing the performance of industrial cyber-physical systems (ICPS). In the majority of existing works, the control cost and the transmission cost are defined independently, followed by a weighted total calculation. This approach suffers from a dimension consistency issue, leading the results to diverge from the system's actual optimal performance. Hence, it is necessary to consider the overall information of the loop and characterize the coupling relationship between control and transmission to construct the overall system performance function. This paper proposes a full loop age of information (FL-AoI) based control and transmission joint design architecture for multi-subsystem ICPS integrating multi-hop network. The state delay, input delay, and event trigger are all taken into consideration by FL-AoI to more fully portray the freshness of the information. We provide a novel control performance based on FL-AoI where the network characteristics are incorporated into the control cost, which could tackle the dimensionality mismatch brought by the form of weighted summation of the control and transmission cost. We also provide the FL-AoI-based strategy for the controller and event-triggering mechanism and derive the cost's boundary. The evaluation results demonstrate that, in comparison to the conventional joint design strategy, our solution increases the stability of the control system while decreasing the network burden. © 2023 IEEE.

关键词： Cyber Physical system

来源：评论

学校读者我要写书评

暂无评论

Enhancing Resource Allocation and Performance in Multi-Layer Industrial IoT Through Adjustable Strategy Integrating Cooperative Communication and Edge Computing

引用

IEEE Internet of Things Journal 2025年第12期12卷 19732-19744页

作者： Sun, Mingyue Yuan, Yazhou Ma, Kai Chen, Cailian Zhang, Jianmin Luo, Xiaoyuan The Institute of electrical Engineering Yanshan University Qinhuangdao066004 China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The Automation Department of the Baosteel Research Institute Shanghai200240 China

Reliable bidirectional communication between the control center (CC) and manufacturing devices (MDs) along with efficient resource allocation are critical for the Industrial Internet of Things (IIoT). However, due to the limited network resources of IIoT devices and the intertwined nature of communication and computation resources, achieving efficient optimization of these resources presents significant challenges. In this paper, we propose a multi-layer communication architecture for the IIoT based on edge computing and cooperative communication technologies, where resource-constrained MDs upload data to edge servers (ESs) for processing. To address the issues of resource scarcity and coupling, we establish a bandwidth release model (BRM) to analyze and quantify the relationship between computation and communication resources. This elucidates the interaction mechanisms between ‘transmission-computation’ performance. Furthermore, to prevent excessive data upload to ESs, which could lead to node overload and network congestion, we employ game theory to develop a pricing mechanism for resource allocation, where ESs charge for computation services. Specifically, we construct a Lagrangian framework to determine a resource allocation scheme, aiming to maximize the utility of the factory. Simulation results indicate that compared to common methods employed in existing works, our strategy enhances factory utility by 29.79%. © 2014 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：