检索结果-内蒙古大学图书馆

Transportation engineering 2023年 13卷

作者： Xu, Y. Kersten, A. Klacar, S. Ban, B. Hellsing, J. Sedarsky, D. AB Göteborg Sweden Chalmers University of Technology Division of Energy Conversion and Propulsion Systems Mechanics and Maritime Sciences Göteborg Sweden Bundeswehr University Munich Department of Electrical Engineering Neubiberg Germany Infimotion Technology Europe AB Göteborg Sweden Torquery Consulting Göteborg Sweden University of Zagreb Faculty of Electrical Engineering and Computing Department of Electric Machines and Automation Zagreb Croatia

Front and rear axle independently driven (FRID) powertrains are becoming a popular solution for electric vehicles (EVs) due to torque distribution capability which can enhance powertrain energy efficiency. Typically, permanent magnet synchronous machines (PMSMs) are used for FRID powertrains due to their high torque, and power density. However, the drive-cycle efficiency of FRID powertrains with PMSMs is typically reduced in comparison to single motor drives. This is due to the unwanted no-load losses of PMSMs in the field weakening region. To overcome this drawback of PMSM FRIDs, this paper proposes an adaptive front- and rear-axle independently driven (AFRID) powertrain, utilizing two dog clutches, so that the powertrain can be operated in different modes (rear, front, and all-wheel drive) by adaptively connecting and disconnecting the front and/or rear electric drive unit (EDU). A rule-based mode selection strategy is developed to utilize the flexibility of different powertrain operating modes of the powertrain for maximizing the energy efficiency of the EDU. The simulation results show that the suggested AFRID powertrain, in comparison to a common FRID powertrain, can improve the WLTC drive-cycle consumption from 22.17 kWhh to 20.50 kWhh per 100 km. Based on the route and road-load information, the energy-saving potential of the AFRID powertrain can be further improved to 20.37 kWhh per 100 km by a suggested predictive mode selection strategy, achieving an optimal mode selection. © 2023 The Author(s)

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimal AoI-based Block Propagation and Incentive Mechanism for Blockchain Networks in Web 3.0

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Wen, Jinbo Kang, Jiawen Xiong, Zehui Du, Hongyang Yang, Zhaohui Niyato, Dusit Shen, Meng Jiao, Yutao Zhang, Yang Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China Guangdong University of Technology School of Automation China Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore Hong Kong University Department of Electrical and Electronic Engineering Hong Kong Zhejiang University College of Information Science and Electronic Engineering China Nanyang Technological University College of Computing and Data Science Singapore Beijing Institute of Technology School of Cyberspace Science and Technology China Army Engineering University of PLA College of Communications Engineering China

Web 3.0 is regarded as a revolutionary paradigm that enables users to securely manage data without a centralized authority. Blockchains, which enable data to be managed in a decentralized and transparent manner, are key technologies for achieving Web 3.0 goals. However, blockchain-based Web 3.0 is still in its infancy, such as ensuring block freshness and optimizing block propagation to improve blockchain performance. In this paper, we develop a freshness-aware block propagation optimization framework for Web 3.0. We first propose a novel metric called Age of Block Information (AoBI) based on the concept of age of information to quantify block freshness. AoBI measures the time elapsed from the freshest transaction generation to the completion of block consensus. To make block propagation optimization tractable, we classify miners into five different states and propose a block propagation model for public blockchains inspired by epidemic models. Moreover, considering that the miners are bounded rational, we propose an incentive mechanism based on the evolutionary game for block propagation to improve block propagation efficiency. Numerical results demonstrate that compared with other block propagation mechanisms in public blockchains, the proposed scheme has a higher block forwarding probability, which improves block propagation efficiency and decreases the minimum value of average AoBI. © 2015 IEEE.

关键词： age of information block propagation evolutionary game Web 3.0 wireless networks

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropy

arXiv

引用

arXiv 2023年

作者： Xiao, Jiaren Dai, Quanyu Shen, Xiao Xie, Xiaochen Dai, Jing Lam, James Kwok, Ka-Wai Department of Mechanical Engineering The University of Hong Kong Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong School of Computer Science and Technology Hainan University Haikou China Department of Automation Harbin Institute of Technology Shenzhen China Institute for Automatic Control and Complex Systems University of Duisburg-Essen Duisburg Germany

Label scarcity in a graph is frequently encountered in real-world applications due to the high cost of data labeling. To this end, semi-supervised domain adaptation (SSDA) on graphs aims to leverage the knowledge of a labeled source graph to aid in node classification on a target graph with limited labels. SSDA tasks need to overcome the domain gap between the source and target graphs. However, to date, this challenging research problem has yet to be formally considered by the existing approaches designed for cross-graph node classification. This paper proposes a novel method called SemiGCL to tackle the graph Semi-supervised domain adaptation with Graph Contrastive Learning and minimax entropy training. SemiGCL generates informative node representations by contrasting the representations learned from a graph’s local and global views. Additionally, SemiGCL is adversarially optimized with the entropy loss of unlabeled target nodes to reduce domain divergence. Experimental results on benchmark datasets demonstrate that SemiGCL outperforms the state-of-the-art baselines on the SSDA tasks. © 2023, CC BY-NC-ND.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

FOF-X: Towards Real-time Detailed Human Reconstruction from a Single Image

arXiv

引用

arXiv 2024年

作者： Feng, Qiao Liu, Yebin Lai, Yu-Kun Yang, Jingyu Li, Kun College of Intelligence and Computing Tianjin University Tianjin300350 China Department of Automation Tsinghua University Beijing100084 China School of Computer Science and Informatics Cardiff University CardiffCF24 4AG United Kingdom School of Electrical and Information Engineering Tianjin University Tianjin300072 China

We introduce FOF-X for real-time reconstruction of detailed human geometry from a single image. Balancing real-time speed against high-quality results is a persistent challenge, mainly due to the high computational demands of existing 3D representations. To address this, we propose Fourier Occupancy Field (FOF), an efficient 3D representation by learning the Fourier series. The core of FOF is to factorize a 3D occupancy field into a 2D vector field, retaining topology and spatial relationships within the 3D domain while facilitating compatibility with 2D convolutional neural networks. Such a representation bridges the gap between 3D and 2D domains, enabling the integration of human parametric models as priors and enhancing the reconstruction robustness. Based on FOF, we design a new reconstruction framework, FOF-X, to avoid the performance degradation caused by texture and lighting. This enables our real-time reconstruction system to better handle the domain gap between training images and real images. Additionally, in FOF-X, we enhance the interconversion algorithms between FOF and mesh representations with a Laplacian constraint and an automaton-based discontinuity matcher, improving both quality and robustness. We validate the strengths of our approach on different datasets and real-captured data, where FOF-X achieves new state-of-the-art results. The code will be released for research purposes at https://***/faculty/likun/projects/FOFX/***. © 2024, CC BY.

关键词： Fourier series

来源：评论

学校读者我要写书评

暂无评论

Instruction-Following Long-Horizon Manipulation by LLM-Empowered Symbolic Planner

Instruction-Following Long-Horizon Manipulation by LLM-Empow...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Zhihao Li Junjia Liu Zhuo Li Minghao Yu Tao Teng Shunbo Zhou Miao Li Tin Lun Lam Fei Chen Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong SAR Hong Kong Center for Logistics Robotics Hong Kong SAR Computing Technologies Co. Ltd. Shenzhen China Institute of Technological Sciences Wuhan University Wuhan China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

One of the grand goals in robotics is to develop a versatile robot capable of executing a wide array of tasks based on language instructions. These tasks often involve long-horizon manipulation due to the complexity of the real-world tasks and the high-dimensional action space of the dual-arm mobile robots. This work proposes a generalizable framework that combines a Large Language Model, a Visual-language Model, and symbolic planning to address long-horizon bimanual mobile manipulation tasks. We use the Large Language Model as the commonsense reasoner to break down the task into a set of subgoals and generate goal-oriented state queries. Subsequently, we fine-tune a Visual-language Model to obtain answers to queries. Finally, we propose a Planning Domain Definition Language translator that translates the subgoal and the goal-oriented states into a symbolic planning problem that can be solved by search-based planners. The experiments show that the proposed method has generalization ability in novel objects and instruction. It outperforms the baseline methods across all the configurations. Moreover, our approach exhibits competence in increasingly complex tasks, encompassing those that demand upward of 10 planning steps.

关键词： Translation Large language models Scalability Humanoid robots Detectors Search problems Generators Planning Complexity theory Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Generative AI-aided Reinforcement Learning for Computation Offloading and Privacy Protection in VR-based Multi-Access Edge computing

Generative AI-aided Reinforcement Learning for Computation O...

引用

Smart World Congress (SWC), IEEE

作者： Feiran You Hongyang Du Jiawen Kang Wei Ni Dusit Niyato Abbas Jamalipour School of Electrical and Computer Engineering The University of Sydney Sydney NSW Australia Data61 Commonwealth Scientific and Industrial Research Organization (CSIRO) Sydney NSW Australia Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong School of Automation Guangdong University of Technology China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

The rapid growth of Artificial Intelligence-Generated Content (AIGC) services has led to increased mobile user participation in related computations and interactions. This development has enabled AI-generated characters to interact with Virtual Reality (VR) users in real time, making the VR experience more interactive and personalized. In this paper, we consider an MEC system where VR users engage in AIGC services, focusing on the Generative Diffusion Model (GDM)based image generation tasks. Specifically, VR users initiate requests for computing resources, while computation offloading distributes the processing load across the MEC system. To manage AIGC edge computation offloading and cloudlet-VR user connections jointly, a Data Center Operator (DCO) employs a centralized Proximal Policy Optimization (PPO) algorithm. To protect VR users’ privacy while preserving PPO functionality, we employ the Generative Diffusion Model (GDM), specifically the Denoising Diffusion Implicit Model (DDIM), which first introduces noise to the PPO state, then conducts a denoising process to recover the state information. We further employ Inverse Reinforcement Learning (IRL) to infer rewards for the recovered states, using expert demonstrations trained by the PPO. The similarity between PPO-generated rewards and IRL-inferred rewards is then computed. Simulation results demonstrate that our proposed approach successfully achieves computation offloading while protecting VR users’ privacy within the PPO centralized management framework.

关键词： Privacy Solid modeling Simulation Noise reduction Noise Virtual reality Reinforcement learning Diffusion models Protection Optimization

来源：评论

学校读者我要写书评

暂无评论

Finite-time asynchronous dissipative filtering of conic-type nonlinear Markov jump systems

引用

Science China(Information Sciences) 2021年第5期64卷 151-162页

作者： Xiang ZHANG Shuping HE Vladimir STOJANOVIC Xiaoli LUAN Fei LIU Key Laboratory of Intelligent Computing and Signal Processing (Ministry of Education) School of Electrical Engineering and Automation Anhui University Department of Automatic Control Robotics and Fluid Technique Faculty of Mechanical and Civil EngineeringUniversity of Kragujevac Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) Institute of AutomationJiangnan University

In the present study, the finite-time asynchronous dissipative filter design problem for the Markov jump systems with conic-type nonlinearity is studied. The hidden Markov model can describe the asynchronism embodied in the system modes and the filter modes reasonably. Moreover, a suitable LyapunovKrasovskii function is utilized and linear matrix inequalities are applied to obtain adequate conditions. These techniques guarantee the finite-time boundedness and strict dissipativity of the filtering error dynamic system. Furthermore, the design problems of the passive filter and the H∞ filter are studied by adjusting the three parameters U, G and V. Finally, the filter gains and the optimal index α*are obtained and the correctness and feasibility of the designed approach are verified by a simulation example.

关键词： dissipative filtering hidden Markov model finite-time boundedness Markov jump systems conic-type nonlinearity

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Sustainable Multi-User Computation Offloading for Mobile Edge-Quantum computing

Learning-Based Sustainable Multi-User Computation Offloading...

引用

IEEE International Conference on Communications (ICC)

作者： Minrui Xu Dusit Niyato Jiawen Kang Zehui Xiong Mingzhe Chen School of Computer Science and Engineering Nanyang Technological University Singapore School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Singapore Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral Gables FL USA

In this paper, a novel paradigm of mobile edgequantum computing (MEQC) is proposed, which brings quantum computing capacities to mobile edge networks that are closer to mobile users (i.e., edge devices). First, we propose an MEQC system model where mobile users can offload computational tasks to scalable quantum computers via edge servers with cryogenic components and fault-tolerant schemes. Second, we show that it is NP-hard to obtain a centralized solution to the partial offloading problem in MEQC in terms of the optimal latency and energy cost of classical and quantum computing. Third, we propose a multi-agent hybrid discrete-continuous deep reinforcement learning using proximal policy optimization to learn the long-term sustainable offloading strategy without prior knowledge. Finally, experimental results demonstrate that the proposed algorithm can reduce at least 30% of the cost compared with the existing baseline solutions under different system settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics

arXiv

引用

arXiv 2025年

作者： Tang, Jialiang Chen, Shuo Gong, Chen Zhang, Jing Tao, Dacheng School of Computer Science and Engineering Nanjing University of Science and Technology China College of Computing and Data Science Nanyang Technological University Singapore School of Intellgence Science and Technology Nanjing University China Department of Automation Institute of Image ProceProceedingssing and Pattern Recognition Shanghai Jiao Tong University China School of Computer Science Wuhan University China

Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Recent studies have revealed that Large Language Models (LLMs), with their powerful in-contextual modeling capabilities, hold significant potential for TSF. However, existing LLM-based methods usually perform suboptimally because they neglect the inherent characteristics of time series data. Unlike the textual data used in LLM pre-training, the time series data is semantically sparse and comprises distinctive temporal patterns. To address this problem, we propose LLM-PS to empower the LLM for TSF by learning the fundamental Patterns and meaningful Semantics from time series data. Our LLM-PS incorporates a new multi-scale convolutional neural network adept at capturing both short-term fluctuations and long-term trends within the time series. Meanwhile, we introduce a time-to-text module for extracting valuable semantics across continuous time intervals rather than isolated time points. By integrating these patterns and semantics, LLM-PS effectively models temporal dependencies, enabling a deep comprehension of time series and delivering accurate forecasts. Intensive experimental results demonstrate that LLM-PS achieves state-of-the-art performance in both short- and long-term forecasting tasks, as well as in few- and zero-shot settings. © 2025, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Design and Development of an Experimental Photovoltaic System

Design and Development of an Experimental Photovoltaic Syste...

引用

Energy Efficiency and Agricultural engineering (EE&AE), International Conference on

作者： Ventsislav Keseev Nicolay Mihailov Boris Evstatiev Tsvetelina Mladenova Vladislav Hinkov Nikolay Valov Department of Telecommunications University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Electrical Power Engineering University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Electronics University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Computer Systems and Technologies University of Ruse “Angel Kanchev” Ruse Bulgaria Center for Computing and Information Services University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Automation and Mechatronics University of Ruse “Angel Kanchev” Ruse Bulgaria

ISBN: (数字)9798350369380

ISBN: (纸本)9798350369397

The world faces many challenges today and the distributed photovoltaic (PV) systems for local high-efficiency generation of electricity from sunlight seem to be one of the good solutions, but most of the population live in crowded urban environments, which creates a number of limiting factors. This study focuses on the design and implementation of an experimental photovoltaic installation in Ruse, Bulgaria, which allows the investigation of the impact of these factors on the efficiency of urban PV plants for optimization and education purposes. Initially, the goals towards the research facility are defined and the design and implementation of the installation is presented, including the orientation and positioning of the PV park, its schematic, and the key characteristics of the equipment used. Next, the first full year of operation of the research facility is analyzed by examining its energy generation profile. The winter months have about 6 times lower energy yields than the best summer ones and about 4-5 times lower on average compared to those for the other 3 seasons. This is due to the nearby buildings and trees, which create different shadows over the different seasons. The daily energy generation period during the winter is more than twice as short in comparison to that for the other seasons, while the peak daily winter energy yield is about $30 \%$ lower. The yearly energy yield per 1 kW peak installed PV panels is $1131.75 \mathrm{kWh} / \mathrm{kW}$, while the Global Solar Atlas suggests that the specific photovoltaic power output for Ruse is $1360.2 \mathrm{kWh} / \mathrm{kWp}$. The obtained exploitation results indicate that the experimental installation fully complies with the stated goals and allows investigating a number of urban scenarios.

关键词： Photovoltaic systems Azimuth Electricity Urban areas Buildings Production Solar power generation

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：