检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Junzhou Huang, Heqiang Zhang, Ronghui Lyu, Nengchao Guo, Yanyong Dai, Hong-Ning Yan, Hong Guangdong Provincial Key Laboratory of Intelligent Transport System School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510275 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430063 China School of Transportation Southeast University Nanjing210097 China Department of Computer Science Hong Kong Baptist University Hong Kong Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

Ensuring safety in both autonomous driving and advanced driver-assistance systems (ADAS) depends critically on the efficient deployment of traffic sign recognition technology. While current methods show effectiveness, they often compromise between speed and accuracy. To address this issue, we present a novel real-time and efficient road sign detection network, YOLO-TS. This network significantly improves performance by optimizing the receptive fields of multi-scale feature maps to align more closely with the size distribution of traffic signs in various datasets. Moreover, our innovative feature-fusion strategy, leveraging the flexibility of Anchor-Free methods, allows for multiscale object detection on a high-resolution feature map abundant in contextual information, achieving remarkable enhancements in both accuracy and speed. To mitigate the adverse effects of the grid pattern caused by dilated convolutions on the detection of smaller objects, we have devised a unique module that not only mitigates this grid effect but also widens the receptive field to encompass an extensive range of spatial contextual information, thus boosting the efficiency of information usage. Evaluation on challenging public datasets, TT100K and CCTSDB2021, demonstrates that YOLO-TS surpasses existing state-of-the-art methods in terms of both accuracy and speed. The code for our method will be available. Copyright © 2024, The Authors. All rights reserved.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluations for RIS-Aided Satellite Aerial Terrestrial Integrated Networks with Link Selection Scheme and Practical Limitations

引用

IEEE Transactions on Network and Service Management 2024年

作者： Zhou, Feng Guo, Kefeng Huang, Gaojian Li, Xingwang Markakis, Evangelos K. Politis, Ilias Asif, Muhammad Yancheng Institute of Technology School of Information Technology Yancheng224051 China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing210016 China Space Engineering University School of Space Information Beijing101407 China Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454000 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Hellenic Mediterranean University Electrical and Computer Engineering Department Heraklion71410 Greece Industrial Systems Institute / Research Center 'ATHENA' Patras26504 Greece InQbit Innovations Srl Bucharest041386 Romania Jiangsu University School of Computer Science and Communication Engineering Zhenjiang China

This paper researches the system evaluations of the reconfigurable intelligent surface (RIS)-assisted satellite aerial terrestrial integrated systems. To ensure the stability of the regarded network, a link selection scheme is presented to get the balance between the system performance and the system efficiency. Besides, in order to build a practical environment of the transmission networks, the imperfect hardware, channel estimation errors and co-channel interference are both considered in the networks. Relied on the above considerations, the detailed analysis for the outage behaviors is shown along with the asymptotic outage probability in high signal-to-noise ratio scenarios. Moreover, the diversity order and coding gain are also provided to give fast methods to confirm the system evaluation. Finally, some re-presentative simulations are provided to confirm the efficiency and advantage of analytical results and the proposed link selection scheme. © 2004-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Design in STAR-RIS Assisted Communication System with Antenna Selection

Energy-Efficient Design in STAR-RIS Assisted Communication S...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Guangyang Zhang Yang Lu Bo Ai Zhangdui Zhong Zhiguo Ding Tony Q. S. Quek School of Electronic and Information Engineering Beijing Jiaotong University Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China Key Laboratory of Railway Industry of Broadband Mobile Information Communications Beijing Jiaotong University Beijing China Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE Department of Electrical and Electronic Engineering University of Manchester Manchester UK Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

This paper investigates the energy-efficient beamforming design in a simultaneous transmission and reflection-reconfigurable intelligent surface (STAR-RIS) assisted wireless communication system, where the antenna selection scheme is adopted. An energy efficiency (EE) maximization problem is formulated by optimizing the transmit beamformers and the phase shift vectors subject to the power budget constraint of the base station (BS), the maximum transmit power constraint per antenna and the users' data rate requirements. An alternating optimization-based algorithm is proposed to tackle the coupled variables, and the quadratic transform is used to deal with the fractional formulations. Simulation results demonstrate that the antenna selection scheme can significantly improve the EE performance by suppressing the energy consumption due to massive antennas. With the assistance of the STAR-RIS, the EE performance is further enhanced.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model

arXiv

引用

arXiv 2024年

作者： Qian, Xinyuan Gao, Jiaran Zhang, Yaodan Zhang, Qiquan Liu, Hexin Garcia, Leibny Paola Li, Haizhou The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Electrical Engineering and Telecommunications The University of New South Wales Sydney2052 Australia The College of Computing and Data Science Nanyang Technological University Singapore The Center for Language and Speech Processing Johns Hopkins University United States The Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen51872 China

Speech enhancement plays an essential role in various applications, and the integration of visual information has been demonstrated to bring substantial advantages. However, the majority of current research concentrates on the examination of facial and lip movements, which can be compromised or entirely inaccessible in scenarios where occlusions occur or when the camera view is distant. Whereas contextual visual cues from the surrounding environment have been overlooked: for example, when we see a dog bark, our brain has the innate ability to discern and filter out the barking noise. To this end, in this paper, we introduce a novel task, i.e. Scene-aware AudioVisual Speech Enhancement (SAV-SE). To our best knowledge, this is the first proposal to use rich contextual information from synchronized video as auxiliary cues to indicate the type of noise, which eventually improves the speech enhancement performance. Specifically, we propose the VC-S2E method, which incorporates the Conformer and Mamba modules for their complementary strengths. Extensive experiments are conducted on public MUSIC, AVSpeech and AudioSet datasets, where the results demonstrate the superiority of VC-S2E over other competitive methods. We will make the source code publicly available. Project demo page: https://***/ © 2024, CC BY.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Recent advances on data-driven services for smart energy systems optimization and pro-active management

Recent advances on data-driven services for smart energy sys...

引用

Metrology for Living Environment (MetroLivEn), IEEE International Workshop on

作者： Tancredi Testasecca Marilena Lazzaro Elissaios Sarmas Stathis Stamatopoulos Dipartimento di Ingegneria Università degli Studi di Palermo Palermo Italy Research & Innovation Department Engineering Ingegneria Informatica S.p.A. Palermo Italy Decision Support Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Athens Greece

Optimization and proactive management of energy systems are crucial for achieving sustainability, efficiency and resilience in future smart energy networks. Data-driven approaches offer promising solutions for tackling the complex and dynamic challenges of energy systems, such as uncertainty, variability, and heterogeneity. Meanwhile, recent advances in decreasing hardware costs and improving data accessibility have allowed for the collection of high-quality data, leading to the development of more accurate and robust data-driven models of different energy systems. In this study, a comprehensive overview of current and future trends in data-driven optimization for smart energy systems is presented. After introducing the motivation and the background of this research field, the potential applications and benefits of optimization in various domains is discussed, such as electric vehicles charge, district heating networks and energy districts. Subsequently this review focuses on different methods and techniques for data-driven optimization and proactive management, ranging from scientific models to machine learning algorithms. Finally, the novel European project, DigiBUILD, is introduced, where different case studies are tested in several pilots, including electric vehicle charging management for increasing renewable energy source consumption, district heating network operative costs optimization and building energy and comfort management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flexible Humidity Sensors with Electrodes Composed of Laser-Induced Graphene and Sputtered Sensitive Films All Derived from Poly(Ether-Ether-Ketone)

SSRN

引用

SSRN 2022年

作者： Wang, Junjie Wang, Nan Xu, Da Tang, Lei Sheng, Bin a School of Optical Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai 200093 China. b Shanghai Key Laboratory of Modern Optical Systems Engineering Research Center of Optical Instruments and Systems Shanghai 200093 China.

Currently, there are still challenges in the practical applications of flexible, efficient, and large-scale production humidity sensors. In the work, we put forward a type of convenient, efficient, durable, and flexible wearable method to prepare humidity sensors. Flexible substrates based on laser direct writing technology in poly(ether-ether-ketone) (PEEK) film was used for the preparation of laser-induced graphene interdigital electrode (LIG-IDE) , which did not require high investment costs and could be implemented for the large-scale preparation of a flexible base. A flexible impedance hygroscopic element based on poly(ether-ether-ketone) sputtered and polymerized (PEEK-SP) as a hygroscopic layer with high sensitivity was obtained, with a fast response/recovery time (4.2/6.8 s,) and a wide operating range of relative humidity (11% RH~97% RH). These advantages extended the sensor's versatility, from contactless humidity sensing to breath detection for human applications. Therefore, a high-performance flexible humidity sensor based entirely on the PEEK polymer material is reported here, which provides a new approach for the development of flexible gas and humidity sensors. © 2022, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network Enabled Fluid Antenna systems: A Two-Stage Approach

arXiv

引用

arXiv 2025年

作者： He, Changpeng Lu, Yang Chen, Wei Ai, Bo Wong, Kai-Kit Niyato, Dusit State Key Laboratory of Advanced Rail Autonomous Operation China School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China School of Electronics and Information Engineering Beijing Jiaotong University Beijing100044 China Department of Electronic and Electrical Engineering University College London LondonWC1E 6BT United Kingdom Yonsei Frontier Laboratory The School of Integrated Technology Yonsei University Seoul03722 Korea Republic of College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

An emerging fluid antenna system (FAS) brings a new dimension, i.e., the antenna positions, to deal with the deep fading, but simultaneously introduces challenges related to the transmit design. This paper proposes an "unsupervised learning to optimize" paradigm to optimize the FAS. Particularly, we formulate the sum-rate and energy efficiency (EE) maximization problems for a multiple-user multiple-input single-output (MU-MISO) FAS and solved by a two-stage graph neural network (GNN) where the first stage and the second stage are for the inference of antenna positions and beamforming vectors, respectively. The outputs of the two stages are jointly input into a unsupervised loss function to train the two-stage GNN. The numerical results demonstrates that the advantages of the FAS for performance improvement and the two-stage GNN for real-time and scalable optimization. Besides, the two stages can function separately. © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time Workflow Scheduling in Hybrid Clouds with Privacy Protection

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time ...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Long Cheng Haoyang He Yan Gu Qingzhi Liu Zhiming Zhao Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Information Technology Group Wageningen University and Research Netherlands Research Group of Multi-Scale Networked Systems University of Amsterdam Netherlands

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Scheduling workflows in hybrid cloud environments presents significant challenges due to the inherent complexity of workflows and the dynamic nature of cloud resources. This complexity is further increased when attempting to balance workflow performance with privacy protection. Recent efforts have leveraged deep reinforcement learning (DRL) to address these challenges. However, most of these approaches rely on single-agent models, which can lead to security issues and scalability problems due to their centralized processing. Specifically, the properties of workflows are transferred to the single agent, which risks leaking privacy information. Our paper addresses these issues by introducing MARS, a real-time workflow scheduling method that prioritizes privacy protection in hybrid clouds. MARS leverages multi-agent deep reinforcement learning (MADRL) to optimize the workflow scheduling of cloud virtual machines (VMs). The benefit of our solution is that it relies on the collaborative learning of multi-agents on multiple VMs, which could assign user data to specific cloud servers for privacy protection while sharing training experiences between agents. In our implementation, MARS aims to reduce workflow completion time and operational costs while complying with strict privacy protection guidelines. The experimental results demonstrate that MARS can significantly surpass existing methods, reducing makespan by an average of $53.18 \%$ and costs by $61.98 \%$ compared to basic techniques, and achieving $20.26 \%$ and $25.71 \%$ improvements over the latest advanced methods, respectively.

关键词： Training Cloud computing Privacy Costs Scalability Deep reinforcement learning Dynamic scheduling Real-time systems Complexity theory Protection

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network Enabled Fluid Antenna systems: A Two-Stage Approach

引用

IEEE Transactions on Vehicular Technology 2025年

作者： He, Changpeng Lu, Yang Chen, Wei Ai, Bo Wong, Kai-Kit Niyato, Dusit State Key Laboratory of Advanced Rail Autonomous Operation China Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China Beijing Jiaotong University School of Electronics and Information Engineering Beijing100044 China University College London Department of Electronic and Electrical Engineering LondonWC1E 6BT United Kingdom Yonsei University Yonsei Frontier Laboratory School of Integrated Technology Seoul03722 Korea Republic of Nanyang Technological University College of Computing and Data Science 639798 Singapore

An emerging fluid antenna system (FAS) brings a new dimension, i.e., the antenna positions, to deal with the deep fading, but simultaneously introduces challenges related to the transmit design. This paper proposes an "unsupervised learning to optimize" paradigm to optimize the FAS. Particularly, we formulate the sum-rate and energy efficiency (EE) maximization problems for a multiple-user multiple-input single-output (MU-MISO) FAS and solved by a two-stage graph neural network (GNN) where the first stage and the second stage are for the inference of antenna positions and beamforming vectors, respectively. The outputs of the two stages are jointly input into an unsupervised loss function to train the two-stage GNN. The numerical results demonstrate that the advantages of the FAS for performance improvement and the two-stage GNN for real-time and scalable optimization. Besides, the two stages can function separately. © 1967-2012 IEEE.

关键词： Graph neural networks

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：