作者：Qiwen Li¹;，Tijin Yan²;，Huanhuan Yuan³;，Yuanqing Xia²; （¹School of Mathematics and Statistics,Beijing Institute of Technology；²School of Automation,Beijing Institute of Technology；³School of Astronautics,Northwestern Polytechnical University）

出处：第41届中国控制会议 2022

关键词：Adversarial；Autoencoder；Self-Attention；Mechanism；Cyber；Physical；Systems；Anomaly；Detection

摘要：Data-driven anomaly detection continues to be challenging due to the increased complexity of modern cyber physical systems（CPS s） and their temporal d ...

作者：Kai Liu¹;，Yuanqing Xia¹;，Chu-ge Wu¹;，Yufeng Zhan^1,2; （¹School of Automation,Beijing Institute of Technology；²Yangtze Delta Region Academy of Beijing Institute of Technology (Jiaxing)）

出处：第41届中国控制会议 2022

关键词：Cloud；Robotics；Platform；Micro-services；Proxy；ROS；CI/CD；Gmapping

摘要：Cloud robotics has become a strategic focus of the development of the information technology industry in recent years.More and more cloud robotics pla ...

作者：Yiran Li¹;，Qian Wang¹;，Zhongqi Sun^1,2;，Yuanqing Xia¹; （¹School of Automation,Beijing Institute of Technology；²Yangtze Delta Region Academy of Beijing Institute of Technology）

出处：第41届中国控制会议 2022

关键词：Model；predictive；control（MPC）；reinforcement；learning（RL）；data-driven；method；nonlinear；systems

摘要：Inspired by Willems and the co-authors’ idea that continuously excited system trajectories can be used to represent the input-output behavior of discr ...

作者：Hui Li¹;Liping Yan¹;CA1;Yuanqing Xia¹;Jinhui Zhang¹; （¹the Key Laboratory of Intelligent Control Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing, 100081, P. R. China）

出处：Journal of the Franklin Institute 2022

摘要：In this paper, we study a distributed state estimation problem for Markov jump systems (MJS) over sensor networks, in which each sensor node connects ...

作者：Yifan Chen¹;，Liping Yan¹;，Yuanqing Xia¹;，Bo Xiao²; （¹Key Laboratory of Intelligent Control and Decision of Complex Systems,School of Automation,Beijing Institute of Technology；²School of Artificial Intelligence,Beijing University of Posts and Telecommunications）

出处：第41届中国控制会议 2022

关键词：Semantic；Segmentation；Real-time；Semantic；Segmentation；Deep；Learning；Bilateral；Neural；Network

摘要：With the improvement of hardware performance,semantic segmentation based on convolutional neural network has achieved wide concern for its’ advantage ...

作者：Tayssir Bouraffa¹;，Zihang Feng¹;，Yuxuan Wang¹;，Liping Yan¹;，Yuanqing Xia¹;，Bo Xiao²; （¹Key Laboratory of Intelligent Control and Decision of Complex Systems,School of Automation,Beijing Institute of Technology；²School of Artificial Intelligence,Beijing University of Posts and Telecommunications）

出处：第34届中国控制与决策会议 2022

关键词：Visual；tracking；convolutional；neural；network；correlation；filters；hierarchical；features

摘要：Recently,convolutional neural network has been pervasively adopted in visual object tracking for its potential in discriminating the target from the s ...

作者：Guan Wang^1,2;，Yufeng Zhan¹;，Yuanqing Xia¹;，Liping Yan¹; （¹Key Laboratory of Intelligent Control and Decision of Complex Systems,School of Automation,Beijing Institute of Technology；²School of Information Science and Engineering,University of ZaoZhuang）

出处：第41届中国控制会议 2022

关键词：Cloud；control；systems；address；encoding；cloud-edge-device；cooperation

摘要：With the rapid development of cloud computing and control theory,a new paradigm of networked control systems named cloud control systems has been prop ...

作者：Huifang Li;Jianghang Huang;Jingwei Huang;Senchun Chai;Leilei Zhao;Yuanqing Xia （Key Laboratory of Complex System Intelligent Control and Decision, Beijing Institute of Technology, Beijing 100081, China）

出处：Journal of Beijing Institute of Technology 2021

关键词：fault diagnosis;deep learning;multimodal heterogeneous data;multimodal fused features

摘要：Industrial Internet of Things (IoT) connecting society and industrial systems represents a tremendous and promising paradigm shift. With IoT, multimod ...

作者：李慧芳，黄姜杭，徐光浩，夏元清 （北京理工大学复杂系统智能控制与决策国家重点实验室）

出处：自动化学报 2023

关键词：云数据中心；工作流；集成学习；特征融合；执行时间预测

摘要：任务执行时间估计是云数据中心环境下工作流调度的前提.针对现有工作流任务执行时间预测方法缺乏类别型和数值型数据特征的有效提取问题,提出了基于多维度特征融合的预测方法.首先,通过构建具有注意力机制的堆叠残差循环网络,将类别型数据从高维稀疏的特征空间映射到低维稠密的特征空间,以增强类别型数据的解析能力,有 ...

发明人：闫莉萍，周宇琴，夏元清，张金会，孙中奇，邹伟东

申请日期：2022.05.13

摘要：本发明公开了基于非对称alpha散度异步非均匀分布式多目标跟踪方法，用于异步非均匀分布式传感器网络下的多目标跟踪。通过设定时间变量作为时间触发融合结构的触发条件，并基于时间判断程序获得当前系统状态，再结合贝叶斯估计过程构建适用于异步非均匀传感器网络的时间触发融合TTF结构。其次，基于连续离散多目标动 ...