检索结果-内蒙古大学图书馆

China Communications 2023年第2期 3-6页

作者： Yuan Wu Xu Chen Feng Lyu Xianfu Chen Xumin Huang Jie Gao Yueyue Dai Tony Q.S.Quek Yan Zhang the State Key Laboratory of Internet of Things for Smart City University of Macau the Department of Computer and Information Science University of Macau Sun Yat-sen University Sun Yat-sen University Institute of Advanced Networking and Computing Systems Sun Yat-sen University National and Local Joint Engineering Laboratory the School of Computer Science and Engineering Central South University the VTT Technical Research Centre of Finland the School of Automation Guangdong University of Technology the School of Information Technology Carleton University Huazhong University of Science and Technology Singapore University of Technology and Design(SUTD) the IEEE Communications Society Technical Committee on Green Communications and Computing(TCGCC)

With the growing maturity of the advanced edge-cloud collaboration and integrated sensing-communication-computing systems, edge intelligence has been envisioned as one of the enabling technologies for ubiquitous and l...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Circular Formation Control for Networked Dynamic Autonomous Underwater Vehicles: Estimator-Based Approaches

引用

IEEE Transactions on Control of Network Systems 2025年

作者： Xie, Jingjing Lan, Weiyao Tong, Feng Yu, Xiao Xiamen University Department of Automation China Xiamen University College of Ocean and Earth Sciences The National and Local Joint Engineering Research Center for Navigation and Location Service Technology Xiamen361005 China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China The Institute of Artificial Intelligence Xiamen361005 China

This paper investigates the circular formation control problem of networked dynamic autonomous underwater vehicles (AUVs) in a directed network. The objective is to make dynamic AUVs encircle a given target with specific radius and velocity. The network topology among all AUVs is modeled by a directed graph containing a spanning tree, and the target is only known to one AUV. Estimator-based approaches with the backstepping technique are proposed for cases with or without communication. First, in communication-based networks, AUVs are allowed to transmit information via communication devices. A dynamic control law consisting of a distributed estimator is proposed. By analyzing with perturbed system method, the multi-vehicle system achieves global exponential stability instead of asymptotic stability. Second, in communication-denied networks, AUVs depend only on the relative measurements from the onboard sensors. A dynamic control law consisting of a decentralized estimator is proposed. By small-gain analysis, the global asymptotic stability for the multi-vehicle system is established. To demonstrate effectiveness, simulation results are presented. © 2014 IEEE.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

MPTA-Net: Multi-Scale Perception Network with Triple-View Attention for Polyp Segmentation 4

MPTA-Net: Multi-Scale Perception Network with Triple-View At...

引用

4th International Conference on Neural Networks, Information and Communication engineering, NNICE 2024

作者： Chen, Zhihong Yao, Lisha Liu, Yue Qiu, Bingjiang Han, Chu Tang, Haoyang Du, Yujia Liu, Zaiyi Fang, Gang Guangzhou University Institute of Computing Science and Technology Guangzhou China Guangdong Prov. Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China South China University of Technology School of Medicine Guangzhou China Department of Radiology Guangzhou China Jiangxi College of Applied Technology School of Information Engineering Ganzhou China Guangdong Provincial People's Hospital Guangdong Academy of Sciences Guangdong Cardiovascular Institute Guangzhou China Southern Medical University Medical Research Institute Guangzhou China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350394375

Accurate segmentation of polyps in endoscopic images is pivotal for the early detection and diagnosis of colorectal cancer (CRC). Nonetheless, the varied appearance of polyp foregrounds and the intricate background interference significantly diminish the efficacy of pixel-level predictions. To address this issue, we propose a multi-scale perception network with triple-view attention (MPTA-Net) for polyp segmentation. The model primarily revolves around two core principles. The first integrates multiscale spatial information into the network's hierarchical encoding process to better preserve detailed polyp semantic information. The second introduces a triple-view attention mechanism that analyzes feature maps from three distinct perspectives to focus on and localize semantically relevant areas, thereby enhancing segmentation accuracy. Experimental results reveal that the proposed model outperforms existing mainstream segmentation models, effectively addressing under-segmentation, over-segmentation, and edge blurriness issues in polyp segmentation, thereby achieving better identification of challenging areas. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第6期36卷 9737-9757页

作者： Yuji Cao Huan Zhao Yuheng Cheng Ting Shu Yue Chen Guolong Liu Gaoqi Liang Junhua Zhao Jinyue Yan Yun Li Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong SAR China Department of Building Environment and Energy Engineering The Hong Kong Polytechnic University Hong Kong China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Center for Crowd Intelligence Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Electrical and Electronic Engineering Nanyang Technological University Jurong West Singapore School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China i4AI Ltd. London U.K.

With extensive pretrained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects, such as multitask learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared with conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs’ functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated and provide insights into future directions. Finally, the comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications, such as robotics, autonomous driving, and energy systems.

关键词： Taxonomy Surveys Visualization Reviews Planning Reinforcement learning Games Transformers Natural language processing Large language models

来源：评论

学校读者我要写书评

暂无评论

ICE Vehicle Energy Consumption Measurement and Calculation Methodology for the Purpose of EV Battery Pack Design 35

ICE Vehicle Energy Consumption Measurement and Calculation M...

引用

35th International Conference on Power Electronics and Electrical Drives, EDPE 2021

作者： Peršić, Antonio Kristek, Hrvoje Peršić, Vladimir Vražić, Mario Department of Electric Machines Drives and Automation Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Novatec D.o.o. Labin Croatia

This paper presents a standard vehicle's energy consumption calculation for the purpose of an electric vehicle (EV) battery pack design procedure. The vehicle dynamics parameters were measured on a route located on a mountainous terrain with a standard driving profile. Vehicle used to conduct the measurements, was a standard internal combustion engine (ICE) vehicle. Afterwards the measured parameters have been used as inputs to a vehicle dynamics model to calculate the resistive forces "on the wheels"that the vehicle had to overcome to achieve the desired driving profile on the specified route. Those forces are then used to calculate the average energy consumption of the vehicle on the mentioned route, only to be scaled to the battery pack with the use of the powertrain model. Furthermore, the consumptions of the vehicle's onboard electrical devices are added to receive the complete energy consumption of the vehicle on the specified route with the desired driving profile. The before mentioned average energy consumption (in kWh/km), can be then used for further application of this vehicle model in different scenarios. ©2021 IEEE.

关键词： Auxiliary on board devices Battery pack Electric vehicle Energy consumption Gps module Powertrain Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Text Recognition for Station Equipment Troubleshooting Based on BERT-BiLSTM-CRF Models

Text Recognition for Station Equipment Troubleshooting Based...

引用

Chinese automation Congress (CAC)

作者： Wei Bai Xiaosu Wang Bo Liang Guoyuan Yang Hanyu Zhi Yinwei Qiao Institute of Computing Technology China Academy of Railway Sciences co. Ltd. Beijing China Postgraduate Department China Academy of Railway Sciences Beijing China School of Automation and Software Engineering Shanxi University Taiyuan China

The excessive length and high semantic complexity of station equipment fault handling report texts are addressed to the extent that effective text recognition is difficult to achieve. A station equipment fault handling dataset is formulated and a text recognition system for station fault reports based on the BERT-BiLSTM-CRF model is designed. The method first preprocesses the data using the BERT pre-trained language model to generate word vectors, which are then fed into BiLSTM to obtain the embedded contextual information, which is passed through the CRF model to obtain the global optimal solution, and finally outputs the textual results of the station equipment fault handling. The experimental results show that the model outperforms the other five comparative models by more than 2% in terms of precision, recall, and $F$ 1 value (checking accuracy) for intelligent recognition over the five entities predicted by the other five comparative models. This brings a new direction of thinking for the analysis of equipment troubleshooting texts in railway stations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analog One-Cycle Control Based Scheme for Battery Charging in Photovoltaic Systems

Analog One-Cycle Control Based Scheme for Battery Charging i...

引用

IEEE Annual Southern Power Electronics Conference (SPEC)

作者： João T. de Carvalho Neto Andrés O. Salazar Natal-East Side Campus Federal Institute of Education Science and Technology of Rio Grande do Norte Natal-RN Brazil Department of Computing Engineering and Automation Federal University of Rio Grande do Norte Natal-RN Brazil

In recent years, the use of photovoltaic systems has getting more attention because radiation is converted directly into electricity without the use of inverters. A major scientific challenge in this theme consists of clean energy storage systems, widely researched for charging electric vehicles (EVs). Batteries are one of the most common ways to store the generated energy directly from photovoltaic systems. Current literature proposes several challenges in charging batteries using photovoltaic systems, especially when it comes to increasing their lifetime, since sudden changes in irradiation cause voltage overshoots in the batteries. This article presents a control strategy based in One-Cycle Control to prevent damages in the batteries adapting its voltage to varying input voltages. The main purpose of this paper is to present applicability of One-Cycle Control based control scheme used for battery charging. The experimental results present the power and controller signal analysis in steady state conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-task Optimization Based Co-training for Electricity Consumption Prediction

arXiv

引用

arXiv 2022年

作者： Song, Hui Qin, A.K. Yan, Chenggang School of Engineering RMIT University Melbourne Australia Department of Computing Technologies Swinburne University of Technology Hawthorn Australia School of Automation Hangzhou Dianzi University Hangzhou China

Real-world electricity consumption prediction may involve different tasks, e.g., prediction for different time steps ahead or different geo-locations. These tasks are often solved independently without utilizing some common problem-solving knowledge that could be extracted and shared among these tasks to augment the performance of solving each task. In this work, we propose a multi-task optimization (MTO) based co-training (MTO-CT) framework, where the models for solving different tasks are co-trained via an MTO paradigm in which solving each task may benefit from the knowledge gained from when solving some other tasks to help its solving process. MTO-CT leverages long short-term memory (LSTM) based model as the predictor where the knowledge is represented via connection weights and biases. In MTO-CT, an inter-task knowledge transfer module is designed to transfer knowledge between different tasks, where the most helpful source tasks are selected by using the probability matching and stochastic universal selection, and evolutionary operations like mutation and crossover are performed for reusing the knowledge from selected source tasks in a target task. We use electricity consumption data from five states in Australia to design two sets of tasks at different scales: a) one-step ahead prediction for each state (five tasks) and b) 6-step, 12-step, 18-step, and 24-step ahead prediction for each state (20 tasks). The performance of MTO-CT is evaluated on solving each of these two sets of tasks in comparison to solving each task in the set independently without knowledge sharing under the same settings, which demonstrates the superiority of MTO-CT in terms of prediction accuracy. Copyright © 2022, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Efficient Twin Migration in Vehicular Metaverses: Multi-Agent Split Deep Reinforcement Learning with Spatio-Temporal Trajectory Generation

引用

IEEE Transactions on Mobile computing 2025年

作者： Chen, Junlong Kang, Jiawen Xu, Minrui Wu, Fan Zhang, Hongliang Huang, Huawei Niyato, Dusit Mao, Shiwen Guangdong University of Technology School of Automation Guangzhou China Nanyang Technological University School of Computing and Data Science Singapore Singapore Central South University School of Computer Science and Engineering Changsha China Peking University School of Electronics Beijing China Sun Yat-Sen University School of Data and Computer Science Guangzhou China Auburn University Department of Electrical and Computer Engineering Auburn United States

Vehicle Twins (VTs) as digital representations of vehicles can provide users with immersive experiences in vehicular metaverse applications, e.g., Augmented Reality (AR) navigation and embodied intelligence. VT migration is an effective way that migrates the VT when the locations of physical entities keep changing to maintain seamless immersive VT services. However, an efficient VT migration is challenging due to the rapid movement of vehicles, dynamic workloads of Roadside Units (RSUs), and heterogeneous resources of the RSUs. To achieve efficient migration decisions and a minimum latency for the VT migration, we propose a multi-agent split Deep Reinforcement Learning (DRL) framework combined with spatio-temporal trajectory generation. In this framework, multiple split DRL agents utilize split architecture to efficiently determine VT migration decisions. Furthermore, we propose a spatio-temporal trajectory generation algorithm based on trajectory datasets and road network data to simulate vehicle trajectories, enhancing the generalization of the proposed scheme for managing VT migration in dynamic network environments. Finally, experimental results demonstrate that the proposed scheme not only enhances the Quality of Experience (QoE) by 29% but also reduces the computational parameter count by approximately 25% while maintaining similar performances, enhancing users' immersive experiences in vehicular metaverses. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PREFACE: 3^rd International Conference on Robotics, Intelligent automation and Control Technologies (RIACT 2022)

引用

AIP Conference Proceedings 2023年第1期2946卷

作者： Arockia Doss, Arockia Selvakumar Short, Michael Schilberg, Daniel Design and Automation Research Group School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Chennai India School of Computing Engineering and Digital Technologies Teesside University United Kingdom Department of Mechatronics and Mechanical Engineering University of Applied Sciences Bochum Germany

Preface: 3rd International Conference on Robotics, Intelligent automation and Control Technologies (RIACT 2022), AIP Conference Proceedings, Volume 2946, Issue

关键词：

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：