检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chen, Dingshuo Zhu, Yanqiao Zhang, Jieyu Du, Yuanqi Li, Zhixun Liu, Qiang Wu, Shu Wang, Liang Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences China Department of Computer Science University of California Los Angeles United States The Paul G. Allen School of Computer Science and Engineering University of Washington United States Department of Computer Science Cornell University United States Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong

Molecular Representation Learning (MRL) has emerged as a powerful tool for drug and materials discovery in a variety of tasks such as virtual screening and inverse design. While there has been a surge of interest in advancing model-centric techniques, the influence of both data quantity and quality on molecular representations is not yet clearly understood within this field. In this paper, we delve into the neural scaling behaviors of MRL from a data-centric viewpoint, examining four key dimensions: (1) data modalities, (2) dataset splitting, (3) the role of pre-training, and (4) model capacity. Our empirical studies confirm a consistent power-law relationship between data volume and MRL performance across these dimensions. Additionally, through detailed analysis, we identify potential avenues for improving learning efficiency. To challenge these scaling laws, we adapt seven popular data pruning strategies to molecular data and benchmark their performance. Our findings underline the importance of data-centric MRL and highlight possible directions for future research. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Collaborative Aggregation Networks for Multi-Site Brain Disorder Diagnosis

Personalized Federated Learning with Collaborative Aggregati...

引用

Industrial automation, Robotics and Control engineering (IARCE), International Conference on

作者： Qian Si Yang Li School of Cyber Science and Technology Beihang University Beijing China Department of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Virtual Reality Technology and Systems Advanced Institute of Information Technology Peking University Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

In multi-site brain disease diagnosis studies, traditional centralized training methods necessitate sharing medical data, posing significant privacy risks. Federated learning (FL) offers a privacy-preserving solution by enabling global model training through aggregating locally trained models from multiple data centers without sharing raw data. However, current FL approaches rely on a server-based network topology, where central server failure disrupts training. Additionally, data heterogeneity across sites often slows convergence and reduces accuracy. To overcome these issues, we introduce a decentralized personalized federated learning collaborative aggregation network (pFedCAN). This framework has two core components: (1) separating local models into shared and personalized layers, and (2) forming a collaborative aggregation network via similarity detection in the shared layers. Specifically, each center trains its local model, then separates it into shared and personalized layers. The shared layer is exchanged with other centers, while the personalized layer remains local. Data centers analyze similarities in received shared layers to build a collaborative network, where shared layers from similar centers are aggregated to refine the model. This approach flexibly adapts to varying levels of data heterogeneity, enhancing model training efficiency. Validation on public datasets, ABIDE I and ADHD, shows that the proposed method outperforms current leading techniques.

关键词： Training Adaptation models Data centers Federated learning Service robots Collaboration Brain modeling Data models Servers Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Physical Layer Communication Security through Generative AI with Mixture of Experts

arXiv

引用

arXiv 2024年

作者： Zhao, Changyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui In Kim, Dong Shen, Xuemin Letaief, Khaled B. CNRS@CREATE 1 Create Way 08-01 Create Tower 138602 Singapore College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Hong Kong University of Science and Technology Hong Kong

AI technologies have become more widely adopted in wireless communications. As an emerging type of AI technologies, the generative artificial intelligence (GAI) gains lots of attention in communication security. Due to its powerful learning ability, GAI models have demonstrated superiority over conventional AI methods. However, GAI still has several limitations, including high computational complexity and limited adaptability. Mixture of Experts (MoE), which uses multiple expert models for prediction through a gate mechanism, proposes possible solutions. Firstly, we review GAI model’s applications in physical layer communication security, discuss limitations, and explore how MoE can help GAI overcome these limitations. Furthermore, we propose an MoE-enabled GAI framework for network optimization problems for communication security. To demonstrate the framework’s effectiveness, we provide a case study in a cooperative friendly jamming scenario. The experimental results show that the MoE-enabled framework effectively assists the GAI algorithm, solves its limitations, and enhances communication security. © 2024, CC BY.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Distributed formation trajectory planning for multi-vehicle systems

Distributed formation trajectory planning for multi-vehicle ...

引用

American Control Conference (ACC)

作者： Binh Nguyen Truong Nghiem Linh Nguyen Tung Nguyen Hung La Mehdi Sookhak Thang Nguyen Department of Engineering Texas A&M University–Corpus Christi Corpus Christi TX USA School of Informatics Computing and Cyber Systems Northern Arizona University Flagstaff AZ USA School of Engineering Information Technology and Physical Sciences Federation University Australia Churchill VIC Australia Department of Information Technology Uppsala University Uppsala Sweden Department of Computer Science and Engineering Advanced Robotics and Automation (ARA) Lab University of Nevada Reno NV USA Department of Computing Sciences Texas A&M University–Corpus Christi Corpus Christi TX USA

This paper addresses the problem of distributed formation trajectory planning for multi-vehicle systems with collision avoidance among vehicles. Unlike some previous distributed formation trajectory planning methods, our proposed approach offers great flexibility in handling computational tasks for each vehicle when the global formation of all the vehicles changes. It affords the system the ability to adapt to the computational capabilities of the vehicles. Furthermore, global formation constraints can be handled at any selected vehicles. Thus, any formation change can be effectively updated without recomputing all local formations at all the vehicles. To guarantee the above features, we first formulate a dynamic consensus-based optimization problem to achieve desired formations while guaranteeing collision avoidance among vehicles. Then, the optimization problem is effectively solved by ADMM-based or alternating projection-based algorithms, which are also presented. Theoretical analysis is provided not only to ensure the convergence of our method but also to show that the proposed algorithm can surely be implemented in a fully distributed manner. The effectiveness of the proposed method is illustrated by a numerical example of a 9-vehicle system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Accuracy of Thermographic Inspections of Photovoltaic Modules

Investigation of the Accuracy of Thermographic Inspections o...

引用

International Symposium for Design and Technology of Electronics Packages (SIITME)

作者： Boris Evstatiev Nikolay Valov Katerina Gabrovska-Evstatieva Tsvetelina Mladenova Nicolay Mihailov Department of Electronics University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Automation and Mechatronics University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Computer Science University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Computing University of Ruse “Angel Kanchev” Ruse Bulgaria Department of Electrical Power Engineering University of Ruse “Angel Kanchev” Ruse Bulgaria

Remote inspections of photovoltaic installations are an important factor for taking timely measures to increase their efficiency and reduce degradation. This study deals with the accuracy and uncertainty of thermal measurements of PV cells. An experiment is organized in order to compare the measured temperatures with means of contact sensor and contactless infrared cameras from different distance. The obtained results indicate significant difference in the measured peak temperatures with the different means. Furthermore, the temperature gradient of an affected cell depends strongly on the soiling area and could surpass $40^{\circ}\mathrm{C}$, which is a precondition for significant errors in the measured temperatures, i.e. it creates a significant uncertainty. Another important observation is that for the investigated polycrystalline module no hotspot was created if 6% or less of a cell’s area is covered.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved efficiency with adaptive front and rear axle independently driven powertrain and disconnect functionality

Transportation Engineering

引用

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

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：