检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Daoshuai Wang Dewei Li Yaonan Guan Gang Wang Haibin Shao Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Skeleton-based human action reco gnition has attracted considerable research interest due to its robustness to dynamic environments and complex *** based on graph neural networks have achieved great success in this ***,most of these graph neural network based methods adopt a single-branch or two-stream structure with limited input *** to the separation of space and time,many methods cannot pay attention to the critical information of human skeleton sequence,and multi-scale spatial-temporal dependent attention modeling becomes the key to *** paper proposes a novel multi-branch Spatio-temporal attention graph convolutional neural network(MB-STAGCN) to recognize human actions from skeleton *** proposed model adopts a multi-branch structure,fuses three-stream features,and then inputs them into the backbone network to extract features from multiple perspectives to a greater ***,we design a new temporal convolutional block for multi-scale extraction of information in the backbone *** also propose an attention block named Spatio-temporal Concat Attention(STCatAtt) to capture critical *** on benchmark datasets show remarkable performance for human action reco gnition,demonstrating the effectiveness of our method.

关键词： Skeleton-based human action recognition MB-STAGCN STCatAtt

来源：评论

学校读者我要写书评

暂无评论

A Co-regularization Facial Emotion Recognition Based on Multi-Task Facial Action Unit Recognition 41

A Co-regularization Facial Emotion Recognition Based on Mult...

引用

第41届中国控制会议

作者： Chinonso Paschal Udeh Luefeng Chen Sheng Du Min Li Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Facial emotion recognition helps feed the growth of the future artificial intelligence with the development of emotion recognition,learning,and analysis of different angles of a human face and head *** worlds recent pandemic gave rise to the rapid installment of facial recognition for fewer applications,while emotion recognition is still within the experimental *** current challenges encountered with facial emotion recognition(FER) are the difference between background *** todays world shows us that humans soon need robotics in the most significant role of human perception,attention,memory,decision-making,and human-robot interaction(HRI) needs *** merging the head pose as a combination towards the FER to boost the robustness in understanding emotions using the convolutional neural networks(CNN).The stochastic gradient descent with a comprehensive model is adopted by applying multi-task learning capable of implicit parallelism,inherent and better global optimizer in finding better network *** executing a multi-task learning model using two independent datasets,the experiment with the FER and head pose learning multi-views co-regularization frameworks were subsequently merged with validation accuracy.

关键词： head pose facial expression convolution neural network deep learning emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Knowledge Evolution with Time Duration from Finer-Time-Granularity Temporal Knowledge Graph

Learning Knowledge Evolution with Time Duration from Finer-T...

引用

2023 China automation Congress, CAC 2023

作者： Du, Shaochong Chen, Kang Yang, Shijie Huo, Hong Fang, Tao Shanghai Jiao Tong University Department of Automation Shanghai China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai China Shanghai Engineering Research Centre of Intelligent Control and Management Shanghai China

ISBN: (纸本)9798350303759

How to represent the temporal information corresponding to each fact in temporal knowledge graphs (TKGs) effectively is always challenging. Most existing representation learning methods usually map the timelines of knowledges into multiple points and ignore the underlying continuous time property and periodic characteristics behind those dense timestamps in finer-time granularity temporal knowledge graphs. A novel Knowledge Evolution with Time Duration (KETD) model is proposed for knowledge representation of temporal knowledge graphs with finer-time granularities. It represents the entity embedding as a time-varying nonlinear function to find the specific continuous time property from dense timestamps. To the best of our knowledge, it is the first attempt to learn embeddings of time durations and combines them into embeddings of entities and relations to predict potential periodic facts. It also uses the temporal point process to capture the impact of historical facts on the current fact. The experiments on self-built finer-time granularity TKG of Satellite-to-Earth Communication (STEC) and two public datasets have demonstrated the superiority of KETD compared to some baseline approaches. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization of Heterogeneous Linear Multi-Agent systems with Unknown Disturbances 63

Distributed Optimization of Heterogeneous Linear Multi-Agent...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Duan, Mengmeng Zhu, Shanying Yang, Ziwen Chen, Cailian Guan, Xinping The authors are with the Department of Automation Shanghai Jiao Tong University Shanghai 200240 ChinaKey Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China and also Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240 China

ISBN: (纸本)9798350316339

In this paper, we investigate the distributed optimization problem for heterogeneous linear multi-agent systems with unknown disturbances. By applying the primal-dual method and the time-scale separation technique, a distributed dynamic controller without using any disturbance information is proposed. Based on the optimal condition, the relationship between the optimal solution and the equilibrium point of the system is established, and it is shown that the distributed optimization problem is solved provided that the closed-loop system is stable. Then, inspired by the nonsingular perturbation analysis, it is proved that the closed-loop system is exponentially input-to-state stable with respect to the derivative of the disturbance. Numerical examples are provided to illustrate the theoretical results. © 2024 IEEE.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

LiDAR Point Cloud Map Coding Framework Based on Quadric Surface Fitting and Scene Construction 5

LiDAR Point Cloud Map Coding Framework Based on Quadric Surf...

引用

5th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2024

作者： Sun, Xuebin Wang, Jinxi Yang, Xiaofei School of Electrical Automation and Information Engineering Tianjin University Tianjin China School of Information and Control Engineering China University of Mining and Technology Xuzhou China Shanghai Institute of Optics and Fine Mechanics Department of Aerospace Laser Technology and System Shanghai China

ISBN: (纸本)9798350355925

Due to rapid 3D acquisition advancements, LiDAR point clouds are prevalent in emerging applications like heritage preservation, mobile robotics, and remote sensing. Yet, the sheer data volume poses challenges for transmission and storage, especially in autonomous driving. This paper introduces an efficient coding framework for compressing large dense LiDAR point cloud maps. By recording timestamps and quaternion matrices during map construction, we reduce map compression to sequence compression. The scans are segregated into intra-frames and inter-frames. For intra-frames, a quadric surface fitting intra-prediction technique eliminates spatial redundancy. For inter-frames, by constructing the 3D scene using encoded intra-frames, the inter-frame can be simulated according to its posture and LiDAR intrinsic parameters. Coding focuses on the difference between actual and predicted point cloud data. Decoding reverses this process, reconstructing the point cloud map from the decoded sequence and quaternion matrices. KITTI dataset experiments show the point cloud map can be averagely compressed to 3.43% of its original size while maintaining centimeter-level precision. This outperforms both octree and Google Draco methods. © 2024 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Online Multi-Object Tracking Under Moving Unmanned Aerial Vehicle Platform Based on Object Detection and Feature Extraction Network

引用

Journal of Shanghai Jiaotong university(Science) 2024年第3期29卷 388-399页

作者：刘增敏王申涛姚莉秀蔡云泽 Department of Automation Shanghai 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 Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong UniversityShanghai 200240China JD Business Growth Department Beijing 100176China Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghai 200240China

In order to solve the problem of small object size and low detection accuracy under the unmanned aerial vehicle(UAV)platform,the object detection algorithm based on deep aggregation network and high-resolution fusion module is ***,a joint network of object detection and feature extraction is studied to construct a real-time multi-object tracking *** the problem of object association failure caused by UAV movement,image registration is applied to multi-object tracking and a camera motion discrimination model is proposed to improve the speed of the multi-object tracking *** simulation results show that the algorithm proposed in this study can improve the accuracy of multi-object tracking under the UAV platform,and effectively solve the problem of association failure caused by UAV movement.

关键词： moving unmanned aerial vehicle(UAV)platform small object feature extraction image registration multi-object tracking

来源：评论

学校读者我要写书评

暂无评论

Modal Fusion Sign Language Recognition Based on Swin Transformer Architecture 8

Modal Fusion Sign Language Recognition Based on Swin Transfo...

引用

8th International Conference on Image, Vision and Computing, ICIVC 2023

作者： Gao, Yujie Li, Yadong Liu, Bin Tian, Yifan Zhu, Minfeng Luo, Jian School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated System Tianjin China

ISBN: (纸本)9798350335231

Sign language plays an important role in information transmission and emotional communication between the hearing-impaired and the outside world. It is expressed through a rapid and complex combination of gestures, body postures and facial expressions. In this paper, Google's MediaPipe framework is used to extract and process key point information of hands. Depth features are used to supplement the RBG diagram. A framework of skeleton sensing multi-modal recognition suitable for complex scenes is proposed. This can be used to deal with the problem of sign language recognition of multi-modal information in different scenes. However, most of the existing sign language recognition methods are traditional convolutional networks and LSTM. Although they have excellent achievements in image recognition and video recognition, their application in sign language recognition does not conform to the characteristics of sign language. In this paper, a Swin Transformer model is used to process both depth information and RGB information. Finally, statistical data fusion method was used to fuse the depth prediction results with RGB prediction results. Experimental analysis shows that this method performs well in sign language recognition in complex scenes compared with existing methods. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Day-ahead Chance-constrained Energy Management of Energy Hubs:A Distributionally Robust Approach

引用

CSEE Journal of Power and Energy systems 2022年第3期8卷 812-825页

作者： Jiaxin Cao Bo Yang Shanying Zhu Chao Ning Xinping Guan Department of Automation Shanghai Jiao Tong UniversityShanghai200240China Key Laboratory of System Control and Information Processing Ministry of Education of China Robert Frederick Smith School of Chemical and Biomolecular Engineering Cornell UniversityIthacaNY 14853 USA

The day-ahead management schedules of hybrid energy hubs are intricate and usually exposed to various uncertainties with the penetration of renewable sources and different ***,it is difficult to access to precise probability distribution functions and exact moment information of uncertain *** cope with these issues,an energy management scheme based on the distributionally robust optimization approach is developed for the energy *** makes no assumptions of certain probability distributions and can be implemented with limited empirical data and partial information of underlying *** operational strategy can provide decision makers with a preliminary and robust optimal solution in the day-ahead *** results illustrate the economical benefit of the energy model,and the effectiveness of the proposed approach in chance-constrained energy management is demonstrated by comparing with other *** Terms-Chance constraint,distributionally robust optimization,energy hub,energy management.

关键词： Chance constraint distributionally robust optimization energy hub energy management

来源：评论

学校读者我要写书评

暂无评论

A Model Predictive control Approach for Virtually Coupled Train Set Based on Multi-Phase Trajectory Planning 21

A Model Predictive Control Approach for Virtually Coupled Tr...

引用

21st International Conference on Networking, Sensing and control, ICNSC 2024

作者： Li, Bosi Liu, Hongjie Lang, Yinghui Jia, Qingdong Zhang, Kun Li, Kaixuan School of Automation and Intelligence Beijing Jiaotong University Beijing100044 China Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing100044 China Traffic Control Technology Co. Ltd. Beijing100070 China

ISBN: (纸本)9798350365221

Virtual coupling (VC) is an emerging technology that enhances railway operations by dynamically and accurately matching line capacity with passenger demand. However, challenges arise in coordinating the virtually coupled train set (VCTS) during inter-station operations and maintaining accurate control of the VCTS. To address this issue, we propose a multi-phase trajectory planning control approach to generate the reference trajectories for VCTS to enhance the synchronicity of interstation operations. However, during speed-varying inter-station operations, it remains challenging to control VCTS accurately under disturbances while adhering to safety constraints. The control layer employs a model predictive control (MPC) approach to ensure precise reference tracking, based on the optimized reference trajectories for all train units. The effectiveness of this approach is validated through experimental results. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Validation of Delayed Anesthesia Model Using Identification Methods and Correlation Analysis

引用

IFAC-PapersOnLine 2024年第27期58卷 172-177页

作者： Bora Ayvaz Erhan Yumuk Clara M. Ionescu Ali Fuat Ergenç Control and Automation Engineering Department Istanbul Technical University Istanbul 34469 Turkey Department of Electromechanics System and Metal Engineering Ghent University 9052 Ghent Belgium

Many successful control strategies for anesthetic processes do not adequately consider time delays despite potential 30-second delays from biophase and bispectral index (BIS) monitoring. This study introduces linear delayed Pharmacokinetic-Pharmacodynamic (PK-PD) patient models that correlate more to real patient outputs than common non-delayed models. The delayed models are obtained for both effect-site concentration (Ce) and BIS outputs. The model structures are identified using autoregressive exogenous input (ARX) and delayed-ARX (DARX) polynomial models and least squares estimations (LSE) using the real surgical data of the open-access database VitalDB. Validation of delayed PK-PD patient models involves using correlation analysis. Results indicate that PK-PD patient models with output delays exhibit higher correlations with real patient data, particularly when considering BIS output.

关键词： Time Delay Models General Anesthesia system Identification Correlation Analysis Closed-Loop control

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：