检索结果-内蒙古大学图书馆

FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kou, Wei-Bin Zhu, Guangxu Cheng, Bingyang Wang, Shuai Tang, Ming Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Shenzhen International Center For Industrial And Applied Mathematics Shenzhen Research Institute of Big Data Shenzhen China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a promising paradigm for enhancing the generalization of AD models through privacy-preserving distributed learning. However, these FL AD models face significant temporal catastrophic forgetting when deployed in dynamically evolving environments, where continuous adaptation causes abrupt erosion of historical knowledge. This paper proposes Federated Exponential Moving Average (FedEMA), a novel framework that addresses this challenge through two integral innovations: (I) Server-side model’s historical fitting capability preservation via fusing current FL round’s aggregation model and a proposed previous FL round’s exponential moving average (EMA) model;(II) Vehicle-side negative entropy regularization to prevent FL models’ possible overfitting to EMA-introduced temporal patterns. Above two strategies empower FedEMA a dual-objective optimization that balances model generalization and adaptability. In addition, we conduct theoretical convergence analysis for the proposed FedEMA. Extensive experiments both on Cityscapes dataset and Camvid dataset demonstrate FedEMA’s superiority over existing approaches, showing 7.12% higher mean Intersection-over-Union (mIoU). © 2025, CC BY-NC-ND.

关键词：

The effect of pooling parameters on the performance of convolution neural network

学校读者我要写书评

暂无评论

Artificial Intelligence Review 2025年第9期58卷

作者： Shadoul, Inas Al-Hmouz, Rami Hossen, Abdulnasir Mesbah, Mostefa Deveci, Muhammet Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman UNESCO Chair on Artificial Intelligence Communication and Information Research Center Sultan Qaboos University Muscat Oman Department of Industrial Engineering Turkish Naval Academy National Defence University Tuzla Istanbul34942 Turkey Department of Computer Science and Engineering College of Informatics Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of Department of Information Technologies Western Caspian University Baku1001 Azerbaijan

Pooling is a crucial aspect of Convolutional Neural Networks (CNNs), a prominent machine learning technique. It plays an essential role in the learning process by reducing the spatial dimensions of feature maps and minimizing computational costs. Common pooling methods, such as Max Pooling (MaxPool) and Average Pooling (AvgPool), have notable limitations. While MaxPool efficiently extracts important features, it often discards useful information, which can negatively impact CNN performance. In contrast, AvgPool preserves background information (maintaining global detail) but treats all inputs equally (assigning the same importance to every pixel in a region of an image), potentially leading to inefficiencies. We propose enhancing pooling adaptability by introducing learnable parameters to address these issues. These parameters (pooling kernels) are incorporated into the pooling methods to make them learnable. The study also explores how this modification affects the image classification performance of CNNs across various widely used datasets. The findings suggest that integrating parameters into the pooling process produces better results compared to the traditional pooling techniques previously discussed. © The Author(s) 2025.

关键词： Convolutional neural networks

REAL-TIME GEOINFORMATION SYSTEMS TO IMPROVE THE QUALITY, SCALABILITY, AND COST OF INTERNET OF THINGS FOR AGRI-ENVIRONMENT research

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Runck, Bryan C. Schulz, Bobby Bishop, Jeff Carlson, Nathan Chantigian, Bryan Deters, Gary Erdmann, Jesse Ewing, Patrick M. Felzan, Michael Fu, Xiao Greyling, Jan Hogan, Christopher J. Hollman, Andrew Joglekar, Ali Junker, Kris Kantar, Michael Kaunda, Lumbani Krishna, Mohana Lynch, Benjamin Marchetto, Peter Marsolek, Megan McKay, Troy Morris, Brad Niaghi, Ali Rashid Pamulaparthy, Keerthi Pardey, Philip Piotrowski, Ann Poudyal, Christina Prather, Tom Raghavan, Barath Reiter, Maggie Rosen, Lucas Salazar, Benjamin Scobbie, Andrew Sharma, Vasudha Silverstein, Kevin A.T. Singh, Gurparteet Strock, Jeff Subedi, Samikshya Tang, Evan Turturillo, Gianna Watkins, Eric Webster, Blake Wilgenbusch, James GEMS Informatics Center University of Minnesota Twin Cities United States Department of Geography Environment and Society University of Minnesota Twin Cities United States Minnesota Supercomputing Institute University of Minnesota United States Department of Electrical Engineering University of Minnesota Twin Cities United States Department of Applied Economics University of Minnesota Twin Cities United States Department of Horticultural Science University of Minnesota Twin Cities United States Department of Computer Science University of Southern California United States Sensing Inc. Conservify Graphspan LLC USDA-ARS Food Systems Research Unit BurlingtonVT05405 United States Amazon United States Department of Soil Water and Climate University of Minnesota Twin Cities United States Department of Computer Science and Engineering University of Minnesota Twin Cities United States Departmnet of Agricultural Education Communication and Marketing University of Minnesota Twin Cities United States Benson Hill United States Southwest Research and Outreach Center University of Minnesota Twin Cities United States Code Weavers Department of Mechanical Engineering University of Minnesota Twin Cities United States University of Hawaii at Manoa HonoluluHI United States Minnesota Agricultural Experiment Station University of Minnesota Twin Cities United States Sunday Stellenbosch AgroInformatics Initiative Stellenbosch University South Africa Ameriprise Financial Services LLC Optum University of Minnesota Twin Cities United States

With the increasing emphasis on machine learning and artificial intelligence to drive knowledge discovery in the agricultural sciences, spatial internet of things (IoT) technologies have become increasingly important for collecting real-time, high resolution data for these models. However, managing large fleets of devices while maintaining high data quality remains an ongoing challenge as scientists iterate from prototype to mature end-to-end applications. Here, we provide a set of case studies using the framework of technology readiness levels for an open source spatial IoT system. The spatial IoT systems underwent 3 major and 14 minor system versions, had over 2,727 devices manufactured both in academic and commercial contexts, and are either in active or planned deployment across four continents. Our results show the evolution of a generalizable, open source spatial IoT system designed for agricultural scientists, and provide a model for academic researchers to overcome the challenges that exist in going from one-off prototypes to thousands of internet-connected devices. © 2024, CC BY-NC-ND.

关键词： Internet of things

All-Dielectric Meta-optics for High-Efficiency Independent Amplitude and Phase Manipulation

学校读者我要写书评

暂无评论

Research Square

research Square 2021年

作者： Raeker, Brian O. Zheng, Hanyu Zhou, You Kravchenko, Ivan I. Valentine, Jason Grbic, Anthony Vanderbilt University United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Department of Electrical Engineering and Computer Science Vanderbilt University NashvilleTN37212 United States Photonics Initiative Advanced Science Research Center City University of New York New YorkNY10031 United States Center for Nanophase Materials Sciences Oak Ridge National Laboratory Oak RidgeTN37831 United States Department of Mechanical Engineering Vanderbilt University NashvilleTN37212 United States

Metasurfaces, composed of subwavelength scattering elements, have demonstrated remarkable control over the transmitted amplitude, phase, and polarization of light. However, manipulating the amplitude upon transmission has required loss if a single metasurface is used. Here, we describe high-efficiency independent manipulation of the amplitude and phase of a beam using two lossless phase-only metasurfaces separated by a distance. With this configuration, we experimentally demonstrate optical components such as combined beam-forming and splitting devices, as well as those for forming complex-valued, three-dimensional holograms. The compound meta-optic platform provides a promising approach for achieving high performance optical holographic displays and compact optical components, while exhibiting a high overall efficiency. © 2021, CC BY.

关键词： Holographic displays

Beamforming Design and Association Scheme for Multi-RIS Multi-User mmWave Systems Through Graph Neural Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Wireless Communications 2025年

作者： Liu, Mengbing Huang, Chongwen Alhammadi, Ahmed Renzo, Marco Di Debbah, Merouane Yuen, Chau Nanyang Technological University School of Electrical and Electronics Engineering 639798 Singapore Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing Hangzhou310027 China Technology Innovation Institute Masdar City Abu Dhabi United Arab Emirates Université Paris-Saclay CNRS Laboratoire des Signaux et Systèmes CentraleSupélec 3 Rue Joliot-Curie Gif-sur-Yvette91192 France King’s College London Centre for Telecommunications Research – Department of Engineering LondonWC2R 2LS United Kingdom Khalifa University KU6G. Research Center Department of Computer and Information Engineering Abu Dhabi127788 United Arab Emirates University Paris-Saclay CentraleSupelec Gif-sur-Yvette91192 France

Reconfigurable intelligent surface (RIS) is emerging as a promising technology for next-generation wireless communication networks, offering a variety of merits such as the ability to tailor the communication environment. Moreover, deploying multiple RISs helps mitigate severe signal blocking between the base station (BS) and users, providing a practical and efficient solution to enhance the service coverage. However, fully reaping the potential of a multi-RIS aided communication system requires solving a non-convex optimization problem. This challenge motivates the adoption of learning-based methods for determining the optimal policy. In this paper, we introduce a novel heterogeneous graph neural network (GNN) to effectively leverage the graph topology of a wireless communication environment. Specifically, we design an association scheme that selects a suitable RIS for each user. Then, we maximize the weighted sum rate (WSR) of all the users by iteratively optimizing the RIS association scheme, and beamforming designs until the considered heterogeneous GNN converges. Based on the proposed approach, each user is associated with the best RIS, which is shown to significantly improve the system capacity in multi-RIS multi-user millimeter wave (mmWave) communications. Specifically, simulation results demonstrate that the proposed heterogeneous GNN closely approaches the performance of the high-complexity alternating optimization (AO) algorithm in the considered multi-RIS aided communication system, and it outperforms other benchmark schemes. Moreover, the performance improvement achieved through the RIS association scheme is shown to be of the order of 30%. © 2002-2012 IEEE.

关键词： Beamforming

Aerial reconfigurable intelligent surface-aided wireless communication systems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Do, Tri Nhu Kaddoum, Georges Nguyen, Thanh Luan da Costa, Daniel Benevides Haas, Zygmunt J. Department of Electrical Engineering ÉTS University of Québec MontrealQC Canada HCMC Viet Nam Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Computer Science Department University of Texas at Dallas RichardsonTX United States

In this paper1, we propose and investigate an aerial reconfigurable intelligent surface (aerial-RIS)-aided wireless communication system. Specifically, considering practical composite fading channels, we characterize the air-to-ground (A2G) links by Namkagami-m small-scale fading and inverse-Gamma large-scale shadowing. To investigate the delay-limited performance of the proposed system, we derive a tight approximate closed-form expression for the end-to-end outage probability (OP). Next, considering a mobile environment, where performance analysis is intractable, we rely on machine learning-based performance prediction to evaluate the performance of the mobile aerial-RIS-aided system. Specifically, taking into account the three-dimensional (3D) spatial movement of the aerial-RIS, we build a deep neural network (DNN) to accurately predict the OP. We show that: (i) fading and shadowing conditions have strong impact on the OP, (ii) as the number of reflecting elements increases, aerial-RIS achieves higher energy efficiency (EE), and (iii) the aerial-RIS-aided system outperforms conventional relaying systems. © 2021, CC BY.

关键词： Deep neural networks

GRADIENTS OF BRAIN ORGANIZATION: SMOOTH SAILING FROM METHODS DEVELOPMENT TO USER COMMUNITY

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Royer, Jessica Paquola, Casey Valk, Sofie L. Kirschner, Matthias Hong, Seok-Jun Park, Bo-Yong Bethlehem, Richard A.I. Leech, Robert Yeo, B.T. Thomas Jefferies, Elizabeth Smallwood, Jonathan Margulies, Daniel Bernhardt, Boris C. Montreal Neurological Institute and Hospital McGill University MontrealQC Canada Forschungszentrum Julich Julich Germany Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Division of Adult Psychiatry Department of Psychiatry University Hospitals of Geneva Thonex Switzerland Center for Neuroscience Imaging Research Institute for Basic Science Suwon Korea Republic of Center for the Developing Brain Child Mind Institute New York United States Department of Biomedical Engineering Sungkyunkwan University Suwon Korea Republic of Department of Data Science Inha University Incheon Korea Republic of Department of Statistics and Data Science Inha University Incheon Korea Republic of Department of Psychology University of Cambridge Cambridge United Kingdom Centre for Neuroimaging Science King's College London London United Kingdom Centre for Sleep áCognition Centre for Translational Magnetic Resonance Research Yong Loo Lin School of Medicine National University of Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Institute for Health Institute for Digital Medicine National University of Singapore Singapore Singapore National University of Singapore Singapore Singapore Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Department of Psychology University of York York United Kingdom Department of Psychology Queens University KingstonON Canada Universite de Paris Paris France

Multimodal neuroimaging grants a powerful in vivo window into the structure and function of the human brain. Recent methodological and conceptual advances have enabled investigations of the interplay between large-scale spatial trends - or gradients - in brain structure and function, offering a framework to unify principles of brain organization across multiple scales. Strong community enthusiasm for these techniques has been instrumental in their widespread adoption and implementation to answer key questions in neuroscience. Following a brief review of current literature on this framework, this perspective paper will highlight how pragmatic steps aiming to make gradient methods more accessible to the community propelled these techniques to the forefront of neuroscientific inquiry. More specifically, we will emphasize how interest for gradient methods was catalyzed by data sharing, open-source software development, as well as the organization of dedicated workshops led by a diverse team of early career researchers. To this end, we argue that the growing excitement for brain gradients is the result of coordinated and consistent efforts to build an inclusive community and can serve as a case in point for future innovations and conceptual advances in neuroinformatics. We close this perspective paper by discussing challenges for the continuous refinement of neuroscientific theory, methodological innovation, and real-world translation to maintain our collective progress towards integrated models of brain organization. © 2024, CC BY.

关键词： Gradient methods

The Realization Factors of Taiwan's Low Altitude Airspace Economy and UAM: Analysis and Evaluation

学校读者我要写书评

暂无评论

The Realization Factors of Taiwan's Low Altitude Airspace Ec...

IEEE International Conference on e-Business engineering (ICEBE)

作者： Tung-Ling Wu Chih-Ming Kung Guan-Ting Lin Kuen-Yu Tsai Guang-Yun Meng Yu-Che Huang Wan-Shu Cheng Institute of Transportation at Ministry of Transportation and Communications Taiwan R.O.C. Dep. Of Information Technology&Communication Shin Chin Univeristy Kaohsiung Campus Taiwan R.O.C. Dep. of Computer Science and Information Management Providence University Taichung Taiwan R.O.C. Department of Electrical Engineering National Taiwan Univeristy Taipei Taiwan R.O.C. Executive Officer Center for Research on High-Performance Remote Sensing and Urban Informatics NTU Taiwan R.O.C.

ISBN: (数字)9798350365856

ISBN: (纸本)9798350365863

Low altitude airspace economy applications will be of highly effective in a wide range of civil activities and will be a critical element in the smart cities of the future. In view of the main features of unmanned aerial vehicle (UAV), such as automatic piloting system, access to uninhabited areas, low cost compared to road and manned aircraft, shorter delivery time, and the ability to carry heavy payloads, it is important to recognize that UAVs can be used for a wide range of civil activities. With the development of these applications in full swing around the world, in addition to advanced communications technology and other related infrastructure, business demand and a favorable investment climate, clarity, definiteness and feasible regulations in the Taiwanese environment are also essential. Based on the premise of local economic strength, the technical level of the telecommunication industry, and commercial demands, Taiwan should establish a rational standard for the UAV regulatory system as soon as possible, so as to facilitate the development of UAM and to ensure the international competitiveness of the related technologies for market development,

关键词： Industries Technological innovation Transportation Autonomous aerial vehicles Regulation Communications technology Aircraft Standards Drones Investment

Achromatic metasurfaces by dispersion customization for ultra-broadband acoustic beam engineering

学校读者我要写书评

暂无评论

National Science Review 2022年第12期 185-195页

作者：董浩文沈宸赵胜东邱维宝郑海荣张传增 Steven A.Cummer 汪越胜方岱宁成利 Institute of Advanced Structure Technology Beijing Institute of Technology Department of Mechanical Engineering The Hong Kong Polytechnic University Department of Electrical and Computer Engineering Duke University Department of Mechanical Engineering Rowan University School of Mathematics and Statistics Qingdao University Paul C.Lauterbur Research Center for Biomedical Imaging Institute of Biomedical and Health Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Department of Civil Engineering University of Siegen Deparment of Mechanics School of Mechanical Engineering Tianjin University

Metasurfaces,the ultra-thin media with extraordinary wavefront modulation ability,have shown great promise for many potential ***,most of the existing metasurfaces are limited by narrow-band and strong dispersive modulation,which complicates their real-world applications and,therefore require strict customized *** address this issue,we report a general methodology for generating ultra-broadband achromatic metasurfaces with prescribed ultra-broadband achromatic properties in a bottom-up inverse-design *** demonstrate three ultra-broadband functionalities,including acoustic beam deflection,focusing and levitation,with relative bandwidths of 93.3%,120% and 118.9%,*** addition,we reveal a relationship between broadband achromatic functionality and element *** metasurface elements have anisotropic and asymmetric geometries with multiple scatterers and local cavities that synthetically support internal resonances,bi-anisotropy and multiple scattering for ultra-broadband customized *** study opens new horizons for ultra-broadband highly efficient achromatic functional devices,with promising extension to optical and elastic metamaterials.

关键词：