检索结果-内蒙古大学图书馆

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Yin, Jianhua Zhan, Xianyuan Ji, Tianying Xu, Bingrong He, Yi Zhang, Daqing Li, Lingxi Wuhan University of Technology Intelligent Transportation Systems Research Center Wuhan430063 China Engineering Research Center of Transportation Information and Safety Ministry of Education Wuhan430063 China Chongqing Research Institute Wuhan University of Technology Chongqing China Institute for Ai Industry Research Tsinghua University Beijing100084 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Tsinghua University Department of Computer Science and Technology Beijing100084 China School of Automation Wuhan University of Technology Wuhan430070 China College of Mechanical and Electrical Engineering Hunan Agricultural University Changsha410128 China Sunward Intelligent Equipment Co. Ltd. Changsha410100 China Elmore Family School of Electrical and Computer Engineering College of Engineering Purdue University IN46202 United States

ISBN: (纸本)9798331505929

Off-road autonomous ground vehicles (AGVs) work in unstructured environments with varied elevation and deformable ground, where vehicle-terrain interactions are more complex resulting in unpredictable dynamics behavior. Current sensor-based hazards/obstacle identification methods mainly focus on geometric hazards/obstacles with explicit geometry, which might be adequate for vehicles in on-road conditions. However, in the off-road environment, vehicle-terrain interactions could introduce non-geometric hazards that cannot be detected by current geometric hazards-oriented sensing techniques, e.g. vehicle stuck in mud. To enable AGVs to traverse the target terrain and meet the goal while avoiding non-geometric hazards, this work proposes a motion planning method integrated with coupled vehicle-terrain dynamics response. Specifically, terramechanics-based modeling and simulation (M&S) is utilized to characterize vehicle-terrain interactions. Based on the dynamics response, a reinforcement learning (RL) algorithm with a specialized reward function is used to navigate the AGV to find the goal with high mobility and safety. We demonstrate the proposed method with two case studies, 1) high mobility is the foremost concern with less safety requirement, and 2) both high mobility and safety are required. The results show that the proposed motion planning method is effective for navigating the AGV in off-road terrains. © 2024 IEEE.

关键词： Off road vehicles

来源：评论

学校读者我要写书评

暂无评论

GSLB: The Graph Structure Learning Benchmark

arXiv

引用

arXiv 2023年

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Low-Overhead Channel Estimation via 3D Extrapolation for TDD mmWave Massive MIMO systems Under High-Mobility Scenarios

arXiv

引用

arXiv 2024年

作者： Zhou, Binggui Yang, Xi Ma, Shaodan Gao, Feifei Yang, Guanghua School of Intelligent Systems Science and Engineering Jinan University Zhuhai519070 China State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau 999078 China Department of Automation Tsinghua University Beijing100084 China School of Intelligent Systems Science and Engineering Guangdong International Cooperation Base of Science and Technology for GBA Smart Logistics Jinan University Zhuhai519070 China

In time division duplexing (TDD) millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, downlink channel state information (CSI) can be obtained from uplink channel estimation thanks to channel reciprocity. However, under high-mobility scenarios, frequent uplink channel estimation is needed due to channel aging. Additionally, large amounts of antennas and subcarriers result in high-dimensional CSI matrices, aggravating pilot training overhead. To address this, we propose a three-domain (3D) channel extrapolation framework across spatial, frequency, and temporal domains. First, considering the effectiveness of traditional knowledge-driven channel estimation methods and the marginal effects of pilots in the spatial and frequency domains, a knowledge- and-data driven spatial-frequency channel extrapolation network (KDD-SFCEN) is proposed for uplink channel estimation via joint spatial-frequency channel extrapolation to reduce spatial-frequency domain pilot overhead. Then, leveraging channel reciprocity and temporal dependencies, we propose a temporal uplink-downlink channel extrapolation network (TUDCEN) powered by generative artificial intelligence for slot-level channel extrapolation, aiming to reduce the tremendous temporal domain pilot overhead caused by high mobility. Numerical results demonstrate the superiority of the proposed framework in significantly reducing the pilot training overhead by 16 times and improving the system’s spectral efficiency under high-mobility scenarios compared with state-of-the-art channel estimation/extrapolation methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of oracle character recognition: challenges, benchmarks, and beyond

arXiv

引用

arXiv 2024年

作者： Li, Jing Chi, Xueke Wang, Qiufeng Huang, Kaizhu Wang, Da-Han Liu, Yongge Liu, Cheng-Lin College of Science & Technology Ningbo University Ningbo China School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China Duke Kunshan University Suzhou China Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computer and Information Engineering Xiamen University of Technology Xiamen China Anyang Normal University Anyang China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Oracle character recognition—an analysis of ancient Chinese inscriptions found on oracle bones—has become a pivotal field intersecting archaeology, paleography, and historical cultural studies. Traditional methods of oracle character recognition have relied heavily on manual interpretation by experts, which is not only labor-intensive but also limits broader accessibility to the general public. With recent breakthroughs in pattern recognition and deep learning, there is a growing movement towards the automation of oracle character recognition (OrCR), showing considerable promise in tackling the challenges inherent to these ancient scripts. However, a comprehensive understanding of OrCR still remains elusive. Therefore, this paper presents a systematic and structured survey of the current landscape of OrCR research. We commence by identifying and analyzing the key challenges of OrCR. Then, we provide an overview of the primary benchmark datasets and digital resources available for OrCR. A review of contemporary research methodologies follows, in which their respective efficacies, limitations, and applicability to the complex nature of oracle characters are critically highlighted and examined. Additionally, our review extends to ancillary tasks associated with OrCR across diverse disciplines, providing a broad-spectrum analysis of its applications. We conclude with a forward-looking perspective, proposing potential avenues for future investigations that could yield significant advancements in the field. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

User Experience Evaluation in Virtual Reality based on Subjective Feelings and Physiological Signals

User Experience Evaluation in Virtual Reality based on Subje...

引用

2020 Engineering Reality of Virtual Reality Conference, ERVR 2020

作者： Niu, Yunfang Wang, Danli Wang, Ziwei Sun, Fan Yue, Kang Zheng, Nan State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Information Technology Liaoning Normal University Dalian China

At present, the research on emotion in the virtual environment is limited to the subjective materials, and there are very few studies based on objective physiological signals. In this article, the authors conducted a user experiment to study the user emotion experience of virtual reality (VR) by comparing subjective feelings and physiological data in VR and two-dimensional display (2D) environments. First, they analyzed the data of self-report questionnaires, including Self-assessment Manikin (SAM), Positive And Negative Affect Schedule (PANAS) and Simulator Sickness Questionnaire (SSQ). The result indicated that VR causes a higher level of arousal than 2D, and easily evokes positive emotions. Both 2D and VR environments are prone to eye fatigue, but VR is more likely to cause symptoms of dizziness and vertigo. Second, they compared the differences of electrocardiogram (ECG), skin temperature (SKT) and electrodermal activity (EDA) signals in two circumstances. Through mathematical analysis, all three signals had significant differences. Participants in the VR environment had a higher degree of excitement, and the mood fluctuations are more frequent and more intense. In addition, the authors used different machine learning models for emotion detection, and compared the accuracies on VR and 2D datasets. The accuracies of all algorithms in the VR environment are higher than that of 2D, which corroborated that the volunteers in the VR environment have more obvious skin electrical signals, and had a stronger sense of immersion. This article effectively compensated for the inadequacies of existing work. The authors first used objective physiological signals for experience evaluation and used different types of subjective materials to make contrast. They hope their study can provide helpful guidance for the engineering reality of virtual reality. c Society for Imaging Science and Technology 2019

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

arXiv

引用

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EDOLAB: An Open-Source Platform for Education and Experimentation with Evolutionary Dynamic Optimization Algorithms

arXiv

引用

arXiv 2023年

作者： Peng, Mai Yazdani, Delaram She, Zeneng Yazdani, Danial Luo, Wenjian Li, Changhe Branke, Juergen Nguyen, Trung Thanh Gandomi, Amir H. Yang, Shengxiang Jin, Yaochu Yao, Xin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Research Institute Faculty of Engineering and Technology Liverpool John Moores University United Kingdom School of Computer Science and Technology Harbin Institute of Technology China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Peng Cheng Laboratory China School of Artificial Intelligence Anhui University of Sciences & Technology China Information Systems Management and Analytics in Warwick Business School University of Warwick United Kingdom Faculty of Engineering & Information Technology University of Technology Sydney Australia Obuda University Hungary School of Computer Science and Informatics De Montfort University United Kingdom Department of Artificial Intelligence School of Engineering Westlake University China School of Computer Science University of Birmingham United Kingdom

Many real-world optimization problems exhibit dynamic characteristics, posing significant challenges for traditional optimization techniques. Evolutionary Dynamic Optimization Algorithms (EDOAs) are designed to address these challenges effectively. However, in existing literature, the reported results for a given EDOA can vary significantly. This inconsistency often arises because the source codes for many EDOAs, which are typically complex, have not been made publicly available, leading to error-prone re-implementations. To support researchers in conducting experiments and comparing their algorithms with various EDOAs, we have developed an open-source MATLAB platform called the Evolutionary Dynamic Optimization laboratory (EDOLAB). This platform not only facilitates research but also includes an educational module designed for instructional purposes. The education module allows users to observe: a) a 2-dimensional problem space and its morphological changes following each environmental change, b) the behaviors of individuals over time, and c) how the EDOA responds to environmental changes and tracks the moving optimum. The current version of EDOLAB features 25 EDOAs and four fully parametric benchmark generators. © 2023, CC BY-NC-SA.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

ICSGD-Momentum: SGD Momentum Based on Inter-gradient Collision

ICSGD-Momentum: SGD Momentum Based on Inter-gradient Collisi...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weidong Zou Weipeng Cao Yuanqing Xia Bineng Zhong Dachuan Li School of Automation Beijing Institute of Technology Beijing China Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Deep neural networks (DNNs) are widely used in fields like computer vision and natural language processing. A key component of DNN training is the optimizer. SGD-Momentum is popular in many DNN methodologies, such as ResNet and DenseNet, due to its simplicity and effectiveness. However, its slow convergence rate limits its use. To overcome this, we introduce inter-gradient collision into SGD-Momentum, inspired by the elastic collision model in physics. This new method, called ICSGD-Momentum, aims to improve convergence. We provide theoretical proof of convergence and establish a regret bound for ICSGD-Momentum. Experiments on benchmarks including function optimization, CIFAR-100, ImageNet, Penn Treebank, COCO, and YCB-Video show that ICSGD-Momentum accelerates training and enhances the generalization performance of DNNs compared to optimizers like SGD-Momentum, Adam, Radam, Adabound, and AdaBelief.

关键词： Training computer vision Artificial neural networks Benchmark testing Natural language processing Informatics Physics Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing systems

arXiv

引用

arXiv 2024年

作者： Yang, Jing Zhao, Yu Yang, Linyao Wang, Xiao Chen, Long Wang, Fei-Yue Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha410000 China Zhejiang Lab Hangzhou311121 China School of Artificial Intelligence Anhui University Hefei266114 China Department of Computer and Information Science University of Macau 999078 China Faculty of Innovation Engineering Macau University of Science and Technology 999078 China

Temporal relation extraction (TRE) aims to grasp the evolution of events or actions, and thus shape the workflow of associated tasks, so it holds promise in helping understand task requests initiated by requesters in crowdsourcing systems. However, existing methods still struggle with limited and unevenly distributed annotated data. Therefore, inspired by the abundant global knowledge stored within pre-trained language models (PLMs), we propose a multi-task prompt learning framework for TRE (TemPrompt), incorporating prompt tuning and contrastive learning to tackle these issues. To elicit more effective prompts for PLMs, we introduce a task-oriented prompt construction approach that thoroughly takes the myriad factors of TRE into consideration for automatic prompt generation. In addition, we design temporal event reasoning in the form of masked language modeling as auxiliary tasks to bolster the model’s focus on events and temporal cues. The experimental results demonstrate that TemPrompt outperforms all compared baselines across the majority of metrics under both standard and few-shot settings. A case study on designing and manufacturing printed circuit boards is provided to validate its effectiveness in crowdsourcing scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Slicing4Meta: An Intelligent Integration Framework with Multi-dimensional Network Resources for Metaverse-as-a-Service in Web 3.0

arXiv

引用

arXiv 2022年

作者： Liu, Yi-Jing Du, Hongyang Niyato, Dusit Feng, Gang Kang, Jiawen Xiong, Zehui The School of Computer Science and Engineering Nanyang Technological University Singapore The National Laboratory of Communications University of Electronic Science and Technology of China 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

As the next-generation Internet paradigm, Web 3.0 encapsulates the expectations of user-centric immersion and interaction experiences in a decentralized manner. Metaverse, a virtual world interacting with the physical world, is becoming one of the most potential technology to push forward with Web 3.0. In the Metaverse, users expect to tailor immersive and interactive experiences by customizing real-time Metaverse services (e.g., augmented/virtual reality and digital twin) in the three-dimensional virtual world. Nevertheless, there are still no unified solutions for the Metaverse services in terms of orchestration and management. It is calling for a continuous and seamless evolution of mobile systems to support Metaverse services, and thus bring Metaverse into reality. In this paper, to provide scalable subscription solutions for Metaverse services, we propose a new concept, named Metaverse-as-a-Service (MaaS), in which various physical-virtual components and technologies in the Metaverse can be delivered as services. Furthermore, to unify the orchestration and management of MaaS, we propose a novel framework, called Slicing4Meta, to customize Metaverse services by intelligently integrating MaaS models and the associated multi-dimensional resources on the components and technologies. Additionally, we propose the classification for typical Metaverse services based on the quality of experience (QoE) requirements and illustrate how to fulfill the QoE requirements under the Slicing4Meta framework. We then illustrate a virtual travel study case, in which we examine the relationship between the QoE and the multi-dimensional resources by quantitatively modeling the QoE of Metaverse users. Finally, we discuss some open challenges of Slicing4Meta and propose potential solutions to address the challenges. © 2022, CC BY.

关键词： Virtual reality

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：