检索结果-内蒙古大学图书馆

Depression Scale Dictionary Decomposition Framework for Multimodal Automatic Depression Level Prediction

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 6195-6210页

作者： Niu, Mingyue Wang, Xu Gong, Jibing Liu, Bin Tao, Jianhua Schuller, Bjorn W. Yanshan University School of Information Science and Engineering Hebei province Qinhuangdao066004 China Hebei Key Laboratory of Computer Virtual Technology and System Integration China Technology Co. Ltd Bejing100022 China Bejing100190 China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China University of Augsburg ZD.B. Chair of Embedded Intelligence for Health Care and Wellbeing Augsburg Germany Glam - Group on Language Audio and Music United Kingdom

Currently, many researchers aim to achieve automatic depression level prediction via speech and video behavior analysis. However, previous works have struggled to decompose audio and video sequences into the information related to and unrelated to depression scores, hindering the model's perception of depression cues. Besides, previous works implement multimodal fusion using attention mechanisms or linear layers, but failed to simultaneously consider the Euclidean relationship among tokens and the non-Euclidean relationship among channels, which bring limitations in capturing depression cues. In response to the above issues, we propose a depression scale dictionary decomposition framework, which mainly includes a Bidirectional Dictionary Decomposition (BDD) module and a Bidirectional Multimodal Fusion (BMF) module. The BDD module can use the dictionaries generated based on the depression scale to semantically decompose audio and video sequences into the information related to and unrelated to depression scores along token and channel dimensions for promoting depression cue perception. Moreover, considering the respective characteristics of tokens and channels, the BMF module uses linear layers and graph convolution to achieve cross-modal mixing, which is used to aggregate audio and video sequences for predicting depression levels. The validation on AVEC 2013, AVEC 2014 and DAIC-WOZ datasets demonstrates our method's superiority. © 1991-2012 IEEE.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

CEBRA Method: Decoding Brain Activity for Advanced Brain-Computer Interface technology 46

CEBRA Method: Decoding Brain Activity for Advanced Brain-Com...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Yang, Jingcheng Kulwa, Frank Liu, Xuanwei Lu, Yiqing Fu, Yufa Li, Guanglin Huai, Yaping Zhang, Xin Li, Yongcheng Shenzhen Dapeng New District Nanao People's Hospital Guangdong Shenzhen518000 China Shenzhen Longhua District Central Hospital Department of Rehabilitation Medicine Guangdong Shenzhen518000 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Brain Cognition and Brain-Computer Intelligence Integration Group Kunming650500 China Cas Key Laboratory of Human-Machine Intelligence Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen518055 China Shandong Zhongke Advanced Technology Co. Ltd. Jinan250014 China

ISBN: (纸本)9798350371499

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

SDP Security Control technology Based on Zero Trust 4

SDP Security Control Technology Based on Zero Trust

引用

4th IEEE International Conference on Civil Aviation Safety and Information technology, ICCASIT 2022

作者： Xu, Weipeng Xie, Yi Lv, Ming Sun, Han Li, Anran Zhao, Haimeng China Mobile Group Design Institute Co. Ltd. Beijing China China Mobile Communications Group Co. Ltd. Beijing China Capital Normal University Information Engineering College Beijing China Guilin University of Aerospace Technology School of Electronic Information and Automation Guilin China Peking University Beijing Key Lab of Spatial Information Integration and Its Applications Beijing China

ISBN: (数字)9781665467667

ISBN: (纸本)9781665467667

With the development of the Internet, cloud computing, big data, distributed and other technologies have been widely used, and the scale of the network continues to expend and increase in complexity. The traditional 4A system has limited management and control capabilities in the face of complex networks, and the existing security risks and information security issues are key issues that must be resolved. In the 4A system, the concept of zero trust is applied, and the characteristics of continuous authentication and dynamic authorization of the zero trust network are used to establish an efficient 4A system to meet the security requirements of managers for network security and resource management. This paper discusses the comparison between traditional security management and control methods and the introduction of zero trust/ Software Defined Perimeter (SDP), the system in terms of authentication and access control, and the specific practice of applying SDP security products to enhance protection capabilities. © 2022 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A Simultaneous Localization and Mapping Method for UAVs in Sparse Features Spaces

A Simultaneous Localization and Mapping Method for UAVs in S...

引用

Robotics, Control and automation (ICRCA), International Conference on

作者： Jintao Guo Zhengyu Xu Enjun Zhen Zongjin Li Ruoxuan Yu Mengfan Xu Franchise Operations Division China Energy Longyuan Environmental Protection Co. Ltd National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology Beijing China National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology Inner Mongolia First Machinery Group Co. Ltd Inner Mongolia China Franchise Operations Division China Energy Longyuan Environmental Protection Co. Ltd Beijing China School of Automation and Intelligence Beijing Jiaotong Universit Beijing China

ISBN: (数字)9798331544577

ISBN: (纸本)9798331544584

In large, dark, cylindrical confined spaces, conventional positioning methods, such as satellite and visual positioning, are not applicable. This type of space presents similar characteristics in the height direction in the vertical direction, making it impossible for lidar to complete simultaneous localization and mapping (SLAM). Therefore, this study proposes a three-dimensional laser SLAM algorithm for unmanned aerial vehicle (UAV) platforms in sparse feature space, called SPARSE-LIO. The algorithm is based on the tightly coupled SLAM framework of iterative Kalman filtering. The height information collected by the single-line laser module is designed to be used as the height constraint of the SLAM process, and the inertial measurement unit (IMU) is used as a state prediction to overcome the feature degradation phenomenon caused by the high similarity of the environment in the vertical direction. The simulation results verified the feasibility and accuracy of mapping, indicating that this method can be applied to achieve autonomous positioning and navigation of robots in cylindrical enclosures such as high towers and large pipelines.

关键词： Point cloud compression Degradation Simultaneous localization and mapping Laser radar Three-dimensional displays Simulation Poles and towers Autonomous aerial vehicles Iterative methods Kalman filters

来源：评论

学校读者我要写书评

暂无评论

CEBRA Method: Decoding Brain Activity for Advanced Brain-Computer Interface technology

CEBRA Method: Decoding Brain Activity for Advanced Brain-Com...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Jingcheng Yang Frank Kulwa Xuanwei Liu Yiqing Lu Yufa Fu Guanglin Li Yaping Huai Xin Zhang Yongcheng Li CAS Key Laboratory of Human-Machine Intelligence Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences (CAS) Shenzhen China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China Shenzhen Dapeng New District Nanao People’s Hospital Shenzhen China Department of Rehabilitation Medicine Shenzhen Longhua District Central Hospital Shenzhen China Brain Cognition and Brain-Computer Intelligence Integration Group Kunming University of Science and Technology Kunming China Shandong Zhongke Advanced Technology Co. Ltd. Jinan China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

The emerging neurorehabilitation technology, Brain-Computer Interface (BCI), provides a novel prospect for stroke recovery. However, decoding brain activity during the movement present substantial challenges, and feature extraction is crutial to build a better decoder. In this study the CEBRA method were employed to extract features first based on electroencephalogram(EEG) data during Motor Execution(ME) and Motor lmagery (Ml) tasks for 20 participants (including 10 stroke patients). The results revealed that, in MI tasks, CEBRA-RF (Random Forests) achieved an average classification accuracy of 91.33%, with an average F1-score of 91.19%, and CEBRA-SVM (Support Vector Machine) achieved an average classification accuracy of 91.32%, with an average F1-score of 90.83%. Compared to other conventional feature extraction methods, CEBRA shows significantly higher accuracy (t-test, p<0.01). However, in ME tasks, CEBRA-RF achieved an average classification accuracy of 75.67%, with an average F1-score of 75.39%, and CEBRA-SVM achieved an average classification accuracy of 76.13%, with an average F1-score of 75.80%. Nevertheless, no significant differences were observed compared to other feature extraction methods. These findings demonstrate the potential of CEBRA in decoding patients’ brain activity. The results of this study hold promise in addressing the current challenges of low decoding accuracy in BCI systems, offering a new approach for designing BCI-assisted rehabilitation systems for stroke patients.

关键词： Support vector machines Brain Accuracy Stroke (medical condition) Feature extraction Motors Brain-computer interfaces Neurorehabilitation Decoding Paralysis

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode Observation and Control for Overhead Cranes with Varying Rope Length

Sliding Mode Observation and Control for Overhead Cranes wit...

引用

2021 China automation Congress, CAC 2021

作者： Huan, Xuwei Niu, Dan Li, Qi Yang, Jun Liu, Guoyao Chen, Xisong Xiao, Xi Key Laboratory of Measurement and Control of CSE Ministry of Education Southeast University Nanjing China Department of Aeronautical and Automotive Engineering Loughborough University LoughboroughLE11 3TU United Kingdom Nanjing Sciyon Automation Group Co. Ltd Nanjing China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration Nanjing China

ISBN: (纸本)9781665426473

This paper proposes a state observer and controller based on the second-order sliding mode scheme for underactuated overhead cranes with load hoisting and lowering. The designed state observer can effectively estimate the uncertainly and unmodeled dynamics of crane systems, and provide appropriate driving force compensations for the sliding mode controller designed by coupling the load swing angle. This guarantees an accurate load positioning and residual swing elimination. Based on the Lyapunov stability criterion, the asymptotic stability of the control system is proved Several simulations are implemented to verify the effectiveness and robustness of the proposed controller for anti-sway and positioning controls. © 2021 IEEE

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode Observation and Control for Overhead Cranes with Varying Rope Length

Sliding Mode Observation and Control for Overhead Cranes wit...

引用

Chinese automation Congress (CAC)

作者： Xuwei Huan Dan Niu Qi Li Jun Yang Guoyao Liu Xisong Chen Xi Xiao Key Laboratory of Measurement and Control of CSE Ministry of Education Southeast University Nanjing China Loughborough University Loughborough UK Nanjing Sciyon Automation Group Co. Ltd Nanjing China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration Nanjing China

ISBN: (纸本)9781665426480

This paper proposes a state observer and controller based on the second-order sliding mode scheme for under-actuated overhead cranes with load hoisting and lowering. The designed state observer can effectively estimate the uncertainty and unmodeled dynamics of crane systems, and provide appropriate driving force compensations for the sliding mode controller designed by coupling the load swing angle. This guarantees an accurate load positioning and residual swing elimination. Based on the Lyapunov stability criterion, the asymptotic stability of the control system is proved. Several simulations are implemented to verify the effectiveness and robustness of the proposed controller for anti-sway and positioning controls.

关键词： Cranes Uncertainty Force Dynamics Observers Robustness Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Vision-Guided Grasping Policy Learning from Demonstrations for Robotic Manipulators

International Journal of Artificial Intelligence and Robotic...

引用

International Journal of Artificial Intelligence and Robotics Research 2024年第2期01卷

作者： Lei Jiang Feiyan Wang Yueyue Liu Zhejiang Industry Polytechnic College Shaoxing Zhejiang Province P. R. China Chinese Academy of Agricultural Mechanization Sciences Group Co. Ltd. No. 1 Beishatan Desheng Gate Chaoyang District Beijing 100101 P. R. China Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education 2 Weigongcun Road Haidian District Beijing 100039 P. R. China School of Management China University of Mining and Technology-Beijing No. 11 Xueyuan Road Haidian District Beijing 100083 P. R. China School of Internet of Things Engineering Institute of Automation Jiangnan University Wuxi 214122 P. R. China

The integration of robotics into domestic environments poses significant challenges due to the dynamic and varied nature of these settings. This paper introduces a new framework that combines vision-guided object recognition with adaptive grasping policies learned from human demonstrations. By harnessing computer vision technology, our system employs deep learning algorithms, particularly Convolutional Neural Networks (CNNs), to precisely detect and classify household objects. Simultaneously, the system uses imitation learning to refine grasping policies, enabling the robotic manipulator to dynamically adapt to new target objects. We validated our framework through a series of experimental setups that simulate typical kitchen tasks, such as manipulating utensils and preparing ingredients. These tasks, which primarily involve picking up and placing objects, served as practical tests for our system. The results demonstrate the system’s ability to effectively recognize a broad array of objects and adapt its grasping policies, thereby enhancing operational efficiency.

关键词： Deep learning learning from demonstrations robotic grasping

来源：评论

学校读者我要写书评

暂无评论

Self-Awareness for Autonomous Systems

引用

PROCEEDINGS OF THE IEEE 2020年第7期108卷 971-975页

作者： Dutt, Nikil Regazzoni, Carlo S. Rinner, Bernhard Yao, Xin Nikil Dutt (Fellow IEEE) received the Ph.D. degree from the University of Illinois at Urbana–Champaign Champaign IL USA in 1989.""He is currently a Distinguished Professor of computer science (CS) cognitive sciences and electrical engineering and computer sciences (EECS) with the University of California at Irvine Irvine CA USA. He is a coauthor of seven books. His research interests include embedded systems electronic design automation (EDA) computer architecture distributed systems healthcare Internet of Things (IoT) and brain-inspired architectures and computing.""Dr. Dutt is a Fellow of ACM. He was a recipient of the IFIP Silver Core Award. He has received numerous best paper awards. He serves as the Steering Committee Chair of the IEEE/ACM Embedded Systems Week (ESWEEK). He is also on the steering organizing and program committees of several premier EDA and embedded system design conferences and workshops. He has served on the Editorial Boards for the IEEE Transactions on Very Large Scale Integration (VLSI) Systems and the ACM Transactions on Embedded Computing Systems and also previously served as the Editor-in-Chief (EiC) for the ACM Transactions on Design Automation of Electronic Systems. He served on the Advisory Boards of the IEEE Embedded Systems Letters the ACM Special Interest Group on Embedded Systems the ACM Special Interest Group on Design Automationt and the ACM Transactions on Embedded Computing Systems. Carlo S. Regazzoni (Senior Member IEEE) received the M.S. and Ph.D. degrees in electronic and telecommunications engineering from the University of Genoa Genoa Italy in 1987 and 1992 respectively.""He is currently a Full Professor of cognitive telecommunications systems with the Department of Electrical Electronics and Telecommunication Engineering and Naval Architecture (DITEN) University of Genoa and a Co-Ordinator of the Joint Doctorate on Interactive and Cognitive Environments (JDICE) international Ph.D. course started initially as EU Erasmus Mundus Project and

Autonomous systems are able to make decisions and potentially take actions without direct human intervention, which requires some knowledge about the system and its environment as well as goal-oriented reasoning. In computer systems, one can derive such behavior from the concept of a rational agent with autonomy (“control over its own actions”), reactivity (“react to events from the environment”), proactivity (“act on its own initiative”), and sociality (“interact with other agents”) as fundamental properties \n[1]\n. Autonomous systems will undoubtedly pervade into our everyday lives, and we will find them in a variety of domains and applications including robotics, transportation, health care, communications, and entertainment to name a few. \nThe articles in this month’s special issue cover concepts and fundamentals, architectures and techniques, and applications and case studies in the exciting area of self-awareness in autonomous systems.

关键词： Special issues and sections Autonomous systems Self-aware Robot sensing systems Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Wafer-scale automation of electron beam induced depositions

Wafer-scale automation of electron beam induced depositions

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Patrick Elfert Malte Bartenwerfer Sergej Fatikow Group Automation and Integration Technology Institute for Information Technology Oldenburg Germany Division Micro-robotics and Control Engineering University of Oldenburg Oldenburg Germany

ISBN: (纸本)9781509020669

The electron beam induced deposition process is a versatile and promising technology to improve and build a variety of different targets. The technique works in scanning electron microscope environment and is applicable from the micro-down to the nanometer scale. The fundamental working principle is well known and investigated. However, its application as standard process is still lacking, since repeatability and throughput are infancy. Especially, as this technique is performed manually. An automation and stabilization of the EBID process is desirable but challenging, since the SEM working environment is accompanied with many disturbing effects. Therefore, this work outlines automation strategies to handle those effects and achieve high repeatability and high throughput. These strategies are validated on an external off-the-shelf computer that is connected with the scanning electron microscope via self-developed scan generator. Analyzing these strategies show high repeatability and a reasonable throughput. An outlook is given about the possibilities on extending the scan generator to be able to do an online control of the electron beam induced depositions process.

关键词： automation Electron beams Generators Scanning electron microscopy Throughput Robot kinematics

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：