检索结果-内蒙古大学图书馆

A Complementary Modularized Ramp Metering Approach Based on Iterative Learning control and ALINEA

IEEE Transactions on Intelligent Transportation Systems 2011年第4期12卷 1305-1318页

作者： Zhongsheng Hou Xin Xu Jingwen Yan Jian-Xin Xu Gang Xiong Advanced Control Systems Laboratory School of Electronic and Information Engineering Beijing Jiaotong University BJTU Beijing China Institute of Automation College of Mechatronics and Automation National University of Defense Technology Changsha China Department of Electrical and Computer Engineering National University of Singapore Singapore Automation Institute Chinese Academy of Sciences (CAS) Beijing China

Ramp metering is an effective tool for traffic management on freeway networks. In this paper, we apply iterative learning control (ILC) to address ramp metering in a macroscopic-level freeway environment. By formulating the original ramp metering problem as an output regulating and disturbance rejection problem, ILC has been applied to control the traffic response. The learning mechanism is further combined with Asservissement Linéaire d'Entrée Autoroutière (ALINEA) in a complementary manner to achieve the desired control performance. The ILC-based ramp metering strategy and the modified modularized ramp metering approach based on ILC and ALINEA in the presence of input constraints are also analyzed to highlight the advantages and the robustness of the proposed methods. Extensive simulations are given to verify the effectiveness of the proposed approaches.

关键词： Traffic control Mathematical model Convergence Learning systems Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancing Ultra-Short-Term Wind Power Forecasting with Multi-Channel ML Techniques

Advancing Ultra-Short-Term Wind Power Forecasting with Multi...

引用

Energy Systems and Electrical Power (ICESEP), International Conference on

作者： Jiapin Ren Chenlin Zhu Zeyu Huang Ruihan Chen Shurui Xu Peng You Department of Information and Electrical Engineering Xuhai College China University of Mining and Technology Xuzhou China Metropolitan College Boston University Boston USA School of Information Engineering China Jiliang University Hangzhou China School of Mathematical Sciences Zhejiang Normal University Jinhua China Cognitive Neuroscience Laboratory Beijing Meishi Cha Technology Co. Ltd. Beijing China National and Local Joint Engineering Laboratory of Internet Applied Technology on Mines China University of Mining and Technology School of Information and Control Engineering China University of Mining and Technology Xuhai College China University of Mining and Technology Xuzhou China

ISBN: (数字)9798350353563

ISBN: (纸本)9798350353570

To address the inherent unpredictability of wind speeds and directions, which significantly affect wind turbine output, this paper presents a multi-channel feature combination strategy for ultra-short term wind power prediction. The research utilises a number of data sources, including meteorological observations, historical power data and geographical inputs, to create a robust feature set for prediction models. By using advanced machine learning techniques, in particular deep learning models such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, the study effectively captures the complex dynamics of wind power generation. The novel approach of reclassifying data sets and refining model features through task-specific channels significantly improves prediction accuracy. Experimental results show significant improvements in prediction accuracy, highlighting the potential of the proposed method to optimise grid operation and energy management in real-time scenarios.

关键词： Accuracy Wind power generation Predictive models Feature extraction Data models Wind turbines Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Swarm aggregations of heterogeneous multi-agent systems

引用

International Journal of control 2014年第12期87卷 2594页

作者： Liang, Haili Su, Housheng Wang, Xiaofan Chen, Michael Z.Q. [a] Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China[b] School of Automation Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Luoyu Road 1037 Wuhan 430074 China[c] Department of Mechanical Engineering The University of Hong Kong Hong Kong

This paper investigates the problem of swarm aggregations of heterogeneous multi-agent systems. Comparing with the existing studies on swarm aggregations of homogeneous multi-agent systems, this paper is much more resembling the practical situations, where the agents have different dynamics. We show that the heterogeneous agents will gather with a certain error under some assumptions and conditions. The stability properties have been proven by theoretical analysis and verified via numerical simulation. The stability of the heterogeneous multi-agent systems has been achieved based on matrix theory and the Lyapunov stability theorem. Numerical simulation is given to demonstrate the effectiveness of the theoretical result. [PUBLICATION ABSTRACT]

关键词： swarm multi-agent systems heterogeneous systems stability

来源：评论

学校读者我要写书评

暂无评论

Temporal wheeler’s delayed-choice experiment based on cold atomic quantum memory

arXiv

引用

arXiv 2019年

作者： Dong, Ming-Xin Ding, Dong-Sheng Yu, Yi-Chen Ye, Ying-Hao Zhang, Wei-Hang Li, En-Ze Zeng, Lei Zhang, Kan Li, Da-Chuang Guo, Guang-Can Shi, Bao-Sen Key Laboratory of Quantum Information University of Science and Technology of China Hefei Anhui230026 China Synergetic Innovation Center of Quantum Information and Quantum Physics University of Science and Technology of China Hefei Anhui230026 China Department of Fundamental Education Anhui Institute of Information Technology Wuhu Anhui241002 China Institute for Quantum Control and Quantum Information and School of Physics and Materials Engineering Hefei Normal University Hefei Anhui230601 China

Nowadays the most intriguing features of wave-particle complementarity of single photon is exemplified by the famous Wheeler’s delayed choice experiment in linear optics, nuclear magnetic resonance and integrated photonic device systems. Studying the wave-particle behavior in light and matter interaction at single photon level is challenging and interesting, which gives how single photons complement in light and matter interaction. Here, we demonstrate a Wheeler’s delayed choice experiment in an interface of light and atomic memory, in which the cold atomic memory makes the heralded single photon divided into a superposition of atomic collective excitation and leaked pulse, thus acting as memory beam-splitters. We observe the morphing behavior between particle and wave of a heralded single photon by changing the relative proportion of quantum random number generator, the second memory efficiency, and the relative storage time of two memories. The reported results exhibit the complementarity behavior of single photon under the interface of light-atom interaction. Copyright © 2019, The Authors. All rights reserved.

关键词： Particle beams

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

Computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Xiuen Wu Tao Wang Yuanzheng Cai Lingyu Liang George Papageorgiou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Data Science Fuzhou University Fuzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians’ future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method.

关键词： Deep learning Pedestrians Computational modeling Predictive models Prediction algorithms Vectors Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation

arXiv

引用

arXiv 2023年

作者： Cao, Yuxue Zhao, Wenbo Wang, Shengjie Zheng, Xiang Ma, Wenke Wang, Zhaolei Zhang, Tao Beijing Institute of Control Engineering China Department of Automation Tsinghua University China Institute for Interdisciplinary Information Sciences Tsinghua University China Department of Computer Science City University of Hong Kong Hong Kong Qian Xuesen Laboratory of Space Technology China Beijing Aerospace Automatic Control Institute China

Symmetric bi-manual manipulation is an essential skill in on-orbit operationsdue to its potent load capacity. Previous works have applied compliant controlto maintain the stability of manipulations. However, traditional methods haveviewed motion planning and compliant control as two separate modules, which canlead to conflicts with the simultaneous change of the desired trajectory andimpedance parameters in the presence of external forces and ***, the joint usage of these two modules requires experts to manuallyadjust parameters. To achieve high efficiency while enhancing adaptability, wepropose a novel Learning-based Adaptive Compliance algorithm (LAC) thatimproves the efficiency and robustness of symmetric bi-manual ***, the algorithm framework integrates desired trajectory generationand impedance-parameter adjustment under a unified framework to mitigatecontradictions and improve efficiency. Second, we introduce a centralizedActor-Critic framework with LSTM networks preprocessing the force states,enhancing the synchronization of bi-manual manipulation. When evaluated indual-arm peg-in-hole assembly experiments, our method outperforms baselinealgorithms in terms of optimality and robustness. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Tongue image segmentation via color decomposition and thresholding

Tongue image segmentation via color decomposition and thresh...

引用

作者： Li, Zuoyong Yu, Zhaochai Liu, Weixia Xu, Yong Zhang, Daoqiang Cheng, Yong Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China The Fujian College's Research Base of Humanities and Social Science for Internet Innovation Research Center Minjiang University Fuzhou350121 China Straits Institute Minjiang University Fuzhou350121 China Bio-Computing Research Center Shenzhen Graduate School Harbin Institute of Technology Shenzhen518055 China Department of Computer Science and Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Communication Engineering Nanjing Institute of Technology Nanjing211167 China

Tongue image segmentation is a crucial step in developing an automatic tongue diagnosis system. After exploring characteristics of image thresholding in different color spaces, we propose a simple and effective tongue image segmentation method. Specifically, the proposed method first extracts an initial tongue body region by performing image thresholding on the transformed hue component in HSI (Hue, Saturation, and Intensity) color space. Then, one of two image thresholding results on the red component of an original tongue image is adaptively selected to find the gap region between the tongue body root and the upper lip. Finally, the initial tongue body region is refined by removing fake object regions such as the upper lip to obtain final tongue image segmentation result. Experimental results on a tongue image dataset containing 200 subjects demonstrate the effectiveness of the proposed method. © 2018 John Wiley & Sons, Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Edge detection algorithm in image processing based on point-by-point threshold segmentation

引用

Guangdianzi Jiguang/Journal of Optoelectronics Laser 2008年第10期19卷 1383-1387页

作者： Zhu, Shi-Ping Xia, Xi Zhang, Qing-Rong Department of Measurement Control and Information Technology School of Instrumentation Science and Optoelectronics Engineering Beihang University Beijing 100191 China

A new segmentation algorithm in which each pixel in the image has its own threshold is proposed. The threshold of a pixel in an image is estimated by calculating the mean of the grayscale values of the neighborhood pixels of the pixel, and the square deviation of the grayscale values of the neighborhood pixels is also calculated as an additional judge condition, so that the result of the proposed algorithm is the edge of the image. Experimental results demonstrate that the proposed algorithm could get the precise edge of the image, while it is reasonable to estimate the threshold of a pixel through the statistic information of its neighborhood pixels.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Time-Efficient Trajectory Optimization in Patrolling Problems with Non-prespecified Depots and Robots

Time-Efficient Trajectory Optimization in Patrolling Problem...

引用

Mediterranean Conference on control and Automation

作者： Walaaeldin Ghadiry Jalal Habibi Amir G. Aghdam Youmin Zhang Department of Electrical and Computer Engineering Concordia University Montreal Quebec Canada Faculty of Engineering McGill University 817 Rue Sherbrooke Ouest Montral Qubec H3A 0C3 Canada Department of Information and Control Engineering Xi'an University of Technology Xi'an Shaanxi 710048 China

ISBN: (纸本)9781467383479

Two new formulations are presented in this paper for the minimum-time trajectories in the patrolling problem, where a number of robots are desired to patrol a given set of viewpoints in the shortest possible time. In the first problem, it is assumed that the starting depots and their corresponding robots are non-prespecified. In the second problem, it is desired to obtain the minimum-distance trajectories among all the possible minimum-time trajectories that could be the output of the first problem. The problem is considered to be a variant of the well-known Traveling Salesman Problem (TSP), namely, Minimum-Time Multidepot multiple Traveling Salesmen Problem (MTMmTSP). The distinguishing features of the proposed problem statement is that first of all the initial depots and their corresponding assigned number of robots are not prespecified. Secondly, the cost function to be minimized is total travel time of robots as opposed to the travel distance or waiting time of the salesmen at the visited nodes for a given TSP with time windows (TSPTW).

关键词： Minimum-Time Multidepot multiple Traveling Salesman Problem (MTMmTSP) Patrolling operation Non-prespecified starting depot Return trip

来源：评论

学校读者我要写书评

暂无评论

Submerged Zone and Vegetation Drive Distribution of Heavy Metal Fractions and Microbial Community Structure: Insights into Stormwater Biofiltration System

SSRN

引用

SSRN 2022年

作者： Honge, Yusheng Wan, Zeyi Kim, Youngchul Yu, Jianghua Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control School of Environmental Science and Engineering Nanjing University of Information Science & Technology Nanjing210044 China Department of Environmental Engineering Hanseo University Seosan 356-706 Korea Republic of

Biofiltration system is a widely used stormwater treatment option which is effective at removing heavy metals. The concentration and distribution of heavy metal fractions in biofiltration filter media, as well as the microbiota composition affected by the design parameters, are relatively new concepts that require further research. A laboratory-scale column study was conducted to investigate the microbial community and the fractionation of heavy metals (Pb, Cu, Cr, and Cd) extracted from filter media samples, subjected to the presence of vegetation, submerged zone (SZ), and major environmental parameters (pH, water content). Sequential extractions revealed that, compared to the three other fractions (exchangeable fraction, reducible fraction and oxidizable fraction), the residual fraction was the most represented for each metal (between 41% and 82%). As a result, vegetation was found to reduce pH value, significantly decrease the concentration of the exchangeable fraction of Pb in the middle layer, and the oxidizable fraction of Pb, Cu, Cd, and Cr in the middle and bottom layers (p © 2022, The Authors. All rights reserved.

关键词： Biofilters

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：