检索结果-内蒙古大学图书馆

Anomaly Detection of Predicted Frames Based on U-Net Feature Vector Reconstruction

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第1期1627卷

作者： Yong Qiang Shumin Fei Yiping Jiao Liuwen Li Key Laboratory of Measurement and Control of CSE (Ministry of Education) School of Automation Southeast University Nanjing 210096 China School of Computer Engineering Jinling Institute of Technology Nanjing 211169 China

Anomaly detection in surveillance video scenes is one of the current research hotspots. Due to the small sample collection of anomalous events, the lack of negative sample labeling data training in anomaly detection research adds a lot of difficulties. Therefore, we adopt the method of unsupervised training and improve the method of anomaly detection based on the reconstruction of the potential features of the predicted frame and ground truth based on u-net. We reduce the reconstruction error between the potential features of u-net in the predicted frame and the potential features of the real frame. Then through other constraints, the reconstruction error of the entire predicted frame is minimized according to the generative adversarial training. Due to the use of normal behavior sample training, when the abnormal behavior is detected, the reconstruction error value exceeds the set threshold to judge whether abnormal behavior occurs in the surveillance video. Experiments prove that our improved method is effective and accurate.

关键词：

Abnormal Behavior Detection Based on the Potential Field Forces in Surveillance Scenarios

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第1期1487卷

作者： Yong Qiang Shumin Fei Liuwen Li Key Laboratory of Measurement and Control of CSE (Ministry of Education) School of Automation Southeast University Nanjing 210096 China School of Computer Engineering Jinling Institute of Technology Nanjing 211169 China

In a social environment, there is a natural mutual force between people. This paper proposes a method for detecting group abnormal behavior based on the potential field method. The movement of a pedestrian is described as the movement towards the target under the combined action of several forces. Forces on pedestrians include the attractive force for themselves and the repulsive force between pedestrians. By calculating the resultant force between them, the behavior of pedestrians is judged according to a set threshold. It is verified through experiments on public data sets that our method has high accuracy and robustness.

关键词：

A Study of Discharge Cavity Optimization in Hollow-Cathode Electron Beam Source

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： He, Weiguo Huo, Weijie Duan, Xinxin Gu, Jun Zhu, Kangwu School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou310024 China Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province Taiji Laboratory for Gravitational Wave Universe Hangzhou310024 China Shanghai Aerospace Electronic Technology Institute Shanghai201109 China Shanghai SastSpace Technology Co. Ltd Shanghai201109 China Shanghai Aerospace Control Technology Institute Shanghai201109 China

Improving the high-voltage resistance of the discharge cavity is essential to enhancing the performance of the hollow-cathode electron source. In this work, a discharge cavity of the hollow-cathode electron beam source is designed and optimized by stacking and isolating the insulating sheets. The experimental results indicate that the optimized design not only improves the overall high-voltage resistance of the device but also improves the stability of the discharge. Meanwhile, it is found that when the amplitude of the discharge breakdown voltage is increased from 12 kV to 20 kV, the resistance of the discharge cavity varies within the range of 3.8–3.7 Ω, with a slight change in the amplitude, and the inductance decreases from 356 nH to 323.1 nH. The experimental study of the high-pressure gas discharge characteristics in the discharge cavity reveals that the change in gas pressure leads to a significant change in the discharge pattern, and compared with the glow discharge, the hollow-cathode discharge significantly improves the discharge current and shortens the breakdown time of the discharge. Under the same air pressure, the breakdown voltage of the discharge decreases and then increases with the increase in cathode cavity length. © 2023, The Authors. All rights reserved.

关键词： Glow discharges

Decision-Making in Driver-automation Shared control: A Review and Perspectives

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Wenshuo Na, Xiaoxiang Cao, Dongpu Gong, Jianwei Xi, Junqiang Xing, Yang Wang, Fei-Yue CA94720 United States Department of Engineering University of Cambridge Trumpington Street CambridgeCB2 1PZ United Kingdom Mechanical and Mechatronics Engineering University of Waterloo 200 University Ave. West Waterloo ONN2L3G1 Canada Department of Mechanical Engineering Beijing Institute of Technology Beijing100081 China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore639798 Singapore State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology Changsha410073 China

Shared control schemes allow a human driver to work with an automated driving agent in driver-vehicle systems while retaining the driver’s abilities to control. The human driver, as an essential agent in the driver-vehicle shared control systems, should be precisely modeled regarding their cognitive processes, control strategies, and decision-making processes. The interactive strategy design between drivers and automated driving agents brings an excellent challenge for human-centric driver assistance systems due to the inherent characteristics of humans. Many open-ended questions arise, such as what proper role of human drivers should act in a shared control scheme? How to make an intelligent decision capable of balancing the benefits of agents in shared control systems? Due to the advent of these attentions and questions, it is desirable to present a survey on the decision-making between human drivers and highly automated vehicles, to understand their architectures, human driver modeling, and interaction strategies under the driver-vehicle shared schemes. Finally, we give a further discussion on the key future challenges and opportunities. They are likely to shape new potential research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Decision making

Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Liu, Yinqiu Wang, Jiacheng Lin, Yijing Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Ai, Bo Zhou, Haibo Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Shenzhen China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electronic Science and Engineering Nanjing University Jiangsu Nanjing210093 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex data distributions and generate high-quality samples has made GDMs particularly effective in tasks such as image generation and reinforcement learning. Furthermore, their iterative nature, which involves a series of noise addition and denoising steps, is a powerful and unique approach to learning and generating data. This paper serves as a comprehensive tutorial on applying GDMs in network optimization tasks. We delve into the strengths of GDMs, emphasizing their wide applicability across various domains, such as vision, text, and audio generation. We detail how GDMs can be effectively harnessed to solve complex optimization problems inherent in networks. The paper first provides a basic background of GDMs and their applications in network optimization. This is followed by a series of case studies, showcasing the integration of GDMs with Deep Reinforcement Learning (DRL), incentive mechanism design, Semantic Communications (SemCom), Internet of Vehicles (IoV) networks, etc. These case studies underscore the practicality and efficacy of GDMs in real-world scenarios, offering insights into network design. We conclude with a discussion on potential future directions for GDM research and applications, providing major insights into how they can continue to shape the future of network optimization. © 2023, CC BY.

关键词： Reinforcement learning

Active disturbance rejection control design with suppression of sensor noise effects in application to DC-DC buck power converter

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lakomy, Krzysztof Madonski, Rafal Dai, Bin Yang, Jun Kicki, Piotr Ansari, Maral Li, Shihua The Poznaá Universitńy of Technology Poznan60-965 Poland The Energy Electricity Research Center International Energy College Jinan University Zhuhai519070 China The School of Automation Southeast University Key Laboratory of Measurement and Control of CSE Ministry of Education Nanjing210096 China The Institute of Robotics and Machine Intelligence Poznań University of Technology Poznań60-965 Poland The Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia

The performance of active disturbance rejection control (ADRC) algorithms can be limited in practice by high-frequency measurement noise. In this work, this problem is addressed by transforming the high-gain extended state observer (ESO), which is the inherent element of ADRC, into a new cascade observer structure. Set of experiments, performed on a DC-DC buck power converter system, show that the new cascade ESO design, compared to the conventional approach, effectively suppresses the detrimental effect of sensor noise over-amplification while increasing the estimation/control performance. The proposed design is also analyzed with a low-pass filter at the converter output, which is a common technique for reducing measurement noise in industrial applications. Copyright © 2020, The Authors. All rights reserved.

关键词： Spurious signal noise

P-94:Distinguished Student Poster: Three Dimensional Lenticular Display Rendering Based on Light Field Acquisition

学校读者我要写书评

暂无评论

SID Symposium Digest of Technical Papers 2017年第1期48卷

作者： Renjing Pei Zheng Geng Kui Ma Zhang Mei Wang Rong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences East Zhongguanchun Road No. 95 Haidian District Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 101408 China

Crosstalk is a critical defect affecting quality in 3D displays. Existing methods require tedious computations or device-specific optical measurements and results are often sub-optimal for 3D productions. We propose a method based on light field acquisition and optimization for crosstalk reduction. Algorithms were developed and experimental results showed superior performance.

关键词： lenticular 3D display crosstalk optimization light field light field capture

Entropy feature extraction on flow pattern of gas/liquid two-phase flow based on cross-section measurement

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2009年第1期147卷

作者： J Han F Dong Y Y Xu Tianjin Key Laboratory of Process Measurement and Control School of Electrical Engineering & Automation Tianjin University Tianjin 300072 CHINA Department of Educational Technology Capital Normal University Beijing 100037 CHINA

This paper introduces the fundamental of cross-section measurement system based on Electrical Resistance Tomography (ERT). The measured data of four flow regimes of the gas/liquid two-phase flow in horizontal pipe flow are obtained by an ERT system. For the measured data, five entropies are extracted to analyze the experimental data according to the different flow regimes, and the analysis method is examined and compared in three different perspectives. The results indicate that three different perspectives of entropy-based feature extraction are sensitive to the flow pattern transition in gas/liquid two-phase flow. By analyzing the results of three different perspectives with the changes of gas/liquid two-phase flow parameters, the dynamic structures of gas/liquid two-phase flow is obtained, and they also provide an efficient supplementary to reveal the flow pattern transition mechanism of gas/liquid two-phase flow. Comparison of the three different methods of feature extraction shows that the appropriate entropy should be used for the identification and prediction of flow regimes.

关键词：

Machine discovery of partial differential equations from spatiotemporal data

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yuan, Ye Li, Junlin Li, Liang Jiang, Frank Tang, Xiuchuan Zhang, Fumin Liu, Sheng Goncalves, Jorge Voss, Henning U. Li, Xiuting Kurths, Jürgen Ding, Han School of Artificial Intelligence and Automation State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta30332 United States School of Power and Mechanical Engineering Wuhan University Wuhan430074 China Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Luxembourg Centre for Systems Biomedicine University of Luxembourg BelvauxL-4367 Luxembourg Citigroup Biomedical Imaging Center Weill Cornell Medical College New York10021 United States Research Domain IV - Transdisciplinary Concepts & Methods Potsdam Institute for Climate Impact Research Potsdam14473 Germany School of Mechanical Science and Engineering State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China

The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data. The method, called Sparse Spatiotemporal System Discovery (S3d), decides which physical terms are necessary and which can be removed (because they are physically negligible in the sense that they do not affect the dynamics too much) from a pool of candidate functions. The method is built on the recent development of Sparse Bayesian Learning;which enforces the sparsity in the to-be-identified PDEs, and therefore can balance the model complexity and fitting error with theoretical guarantees. Without leveraging prior knowledge or assumptions in the discovery process, we use an automated approach to discover ten types of PDEs, including the famous Navier-Stokes and sine-Gordon equations, from simulation data alone. Moreover, we demonstrate our data-driven discovery process with the complex Ginzburg-Landau Equation (CGLE) using data measured from a traveling-wave convection experiment. Our machine discovery approach presents solutions that has the potential to inspire, support and assist physicists for the establishment of physical laws from measured spatiotemporal data, especially in notorious fields that are often too complex to allow a straightforward establishment of physical law, such as biophysics, fluid dynamics, neuroscience or nonlinear optics. Copyright © 2019, The Authors. All rights reserved.

关键词： Nonlinear optics