检索结果-内蒙古大学图书馆

To talk or to work: Flexible communication compression for energy efficient federated learning over heterogeneous mobile edge devices

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Liang Shi, Dian Hou, Ronghui Li, Hui Pan, Miao Han, Zhu School of Cyber Engineering Xidian University Xi’an China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China Department of Electrical and Computer Engineering University of Houston HoustonTX United States

Recent advances in machine learning, wireless communication, and mobile hardware technologies promisingly enable federated learning (FL) over massive mobile edge devices, which opens new horizons for numerous intelligent mobile applications. Despite the potential benefits, FL imposes huge communication and computation burdens on participating devices due to periodical global synchronization and continuous local training, raising great challenges to battery constrained mobile devices. In this work, we target at improving the energy efficiency of FL over mobile edge networks to accommodate heterogeneous participating devices without sacrificing the learning performance. To this end, we develop a convergence-guaranteed FL algorithm enabling flexible communication compression. Guided by the derived convergence bound, we design a compression control scheme to balance the energy consumption of local computing (i.e., "working") and wireless communication (i.e., "talking") from the long-term learning perspective. In particular, the compression parameters are elaborately chosen for FL participants adapting to their computing and communication environments. Extensive simulations are conducted using various datasets to validate our theoretical analysis, and the results also demonstrate the efficacy of the proposed scheme in energy saving. © 2020, CC BY.

关键词： Wireless networks

A scholarly backcasting approach to a novel model for smart sustainable cities of the future: strategic problem orientation

学校读者我要写书评

暂无评论

City, Territory and architecture 2019年第1期6卷 1页

作者： Bibri, Simon Elias Krogstie, John Department of Computer Science The Norwegian University of Science and Technology Sem Saelands veie 9 Trondheim 7491 Norway Department of Architecture and Planning Alfred Getz vei 3 Sentralbygg 1 5th Floor Trondheim 7491 Norway

Sustainable cities have, since the early 1990s, been the leading global paradigm of urban planning and development thanks to the different models of sustainable urban form proposed as new frameworks for redesigning and restructuring urban places to achieve sustainability. Indeed, huge advances in some areas of sustainability knowledge and a multitude of exemplary practical initiatives have been realized, thereby raising the profile of sustainable cities worldwide. The change is still inspiring and the challenge continues to induce scholars and practitioners to enhance existing, and propose new, models. Especially, sustainable urban forms have been problematic, whether in theory or practice, so is yet knowing to what extent progress has been made towards sustainable cities. They are associated with a number of problems, issues, and challenges and thus much more needs to be done considering the very fragmented, conflicting picture that arises of change on the ground in the face of the expanding urbanization. This involves the question of how they should be monitored, understood, analyzed, planned, and even integrated so as to improve, advance, and maintain their contribution to sustainability. This brings us to the issue of sustainable cities and smart cities being extremely fragmented as landscapes and weakly connected as approaches, despite the proven role and untapped potential of advanced ICT, especially big data technology, for advancing sustainability under what is labeled ‘smart sustainable cities.’ Essentially, there are multiple visions of, and pathways to achieving, such cities, which depends on how they can be conceptualized. This paper details the two parts of strategic problem orientation by answering the guiding questions for Steps 1 and 2 of the futures study being conducted. This study aims to analyze, investigate, and develop a novel model for smart sustainable cities of the future using backcasting as a scholarly approach. It involves a series of pap

关键词： Backcasting Big data science and analytics Compact cities Design principles and strategies Eco-cities Futures study Planning practices Smart cities Smart sustainable cities Sustainable cities Sustainable development

The Role of Open-Source LLMs in Shaping the Future of GeoAI

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Xiao Tu, Zhengzhong Ye, Xinyue Goodchild, Michael Department of Environmental Sciences Emory University AtlantaGA30322 United States Department of Computer Science and Engineering Texas A&M University College StationTX77840 United States Department of Landscape Architecture and Urban Planning Center for Geospatial Sciences Applications and Technology Texas A&M University College StationTX77840 United States Department of Geography University of California Santa BarbaraCA93106 United States

Large Language Models (LLMs) are transforming geospatial artificial intelligence (GeoAI), offering new capabilities in data processing, spatial analysis, and decision support. This paper examines the open-source paradigm's pivotal role in this transformation. While proprietary LLMs offer accessibility, they often limit the customization, interoperability, and transparency vital for specialized geospatial tasks. Conversely, open-source alternatives significantly advance Geographic Information Science (GIScience) by fostering greater adaptability, reproducibility, and community-driven innovation. Open frameworks empower researchers to tailor solutions, integrate cutting-edge methodologies (e.g., reinforcement learning, advanced spatial indexing), and align with FAIR principles. However, the growing reliance on any LLM necessitates careful consideration of security vulnerabilities, ethical risks, and robust governance for AI-generated geospatial outputs. Ongoing debates on accessibility, regulation, and misuse underscore the critical need for responsible AI development strategies. This paper argues that GIScience advances best not through a single model type, but by cultivating a diverse, interoperable ecosystem combining open-source foundations for innovation, bespoke geospatial models, and interdisciplinary collaboration. By critically evaluating the opportunities and challenges of open-source LLMs within the broader GeoAI landscape, this work contributes to a nuanced discourse on leveraging AI to effectively advance spatial research, policy, and decision-making in an equitable, sustainable, and scientifically rigorous manner. © 2025, CC BY-NC-ND.

关键词： Indexing (of information)

Linearization-based quantized stabilization of nonlinear systems under DoS attacks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kato, Rui Cetinkaya, Ahmet Ishii, Hideaki Department of Computer Science Tokyo Instutite of Technology Yokohama226-8502 Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo101-8430 Japan

Motivated by recent security issues in cyber-physical systems, this technical note studies the stabilization problem of networked control systems under Denial-of-Service (DoS) attacks. In particular, we consider to stabilize a nonlinear system with limited data rate via linearization. We employ a deterministic DoS attack model constrained in terms of attacks’ frequency and duration, allowing us to cover a large class of potential attacks. To achieve asymptotic stabilization, we propose a resilient dynamic quantizer in the sense that it does not saturate in the presence of packet losses caused by DoS attacks. A sufficient condition for stability is derived by restricting the average DoS frequency and duration. In addition, because of the locality of linearization, we explicitly investigate an estimate of the region of attraction, which can be expected to be reduced depending on the strength of DoS attacks. A simulation example is presented for demonstration of our results. Copyright © 2020, The Authors. All rights reserved.

关键词： Denial-of-service attack

Generative adversarial networks (GANs) in networking: A comprehensive survey & Evaluation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Navidan, Hojjat Moshiri, Parisa Fard Nabati, Mohammad Shahbazian, Reza Ghorashi, Seyed Ali Shah-Mansouri, Vahid Windridge, David School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran14395-515 Iran Cognitive Telecommunication Research Group Department of Telecommunications Faculty of Electrical Engineering Shahid Beheshti University Tehran19839-69411 Iran Department of Electrical Engineering Faculty of Technology and Engineering Standard Research Institute Alborz31745-139 Iran School of Architecture Computing and Engineering University of East London LondonE16 2RD United Kingdom Department of Computer Science School of Science and Technology Middlesex University LondonNW4 4BT United Kingdom

Despite the recency of their conception, Generative Adversarial Networks (GANs) constitute an extensively-researched machine learning sub-field for the creation of synthetic data through deep generative modeling. GANs have consequently been applied in a number of domains, most notably computer vision, in which they are typically used to generate or transform synthetic images. Given their relative ease of use, it is therefore natural that researchers in the field of networking (which has seen extensive application of deep learning methods) should take an interest in GAN-based approaches. The need for a comprehensive survey of such activity is therefore urgent. In this paper, we demonstrate how this branch of machine learning can benefit multiple aspects of computer and communication networks, including mobile networks, network analysis, internet of things, physical layer, and cybersecurity. In doing so, we shall provide a novel evaluation framework for comparing the performance of different models in non-image applications, applying this to a number of reference network datasets. © 2021, CC BY-NC-ND.

关键词： Generative adversarial networks

Identifying Users with Wearable Sensors based on Activity Patterns

学校读者我要写书评

暂无评论

Procedia computer Science 2020年 177卷 8-15页

作者： Muhammad Ehatisham-ul-Haq Maryam Naseer Malik Muhammad Awais Azam Usman Naeem Asra Khalid Mustansar Ali Ghazanfar Department of Computer Engineering University of Engineering and Technology Taxila Punjab 47050 Pakistan Whitecliffe Technologies Wellington New Zealand School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom School of Engineering & Computer Science Victoria University of Wellington New Zealand School of Architecture Computing and Engineering University of East London United Kingdom

We live in a world where ubiquitous systems surround us in the form of automated homes, smart appliances and wearable devices. These ubiquitous systems not only enhance productivity but can also provide assistance given a variety of different scenarios. However, these systems are vulnerable to the risk of unauthorized access, hence the ability to authenticate the end-user seamlessly and securely is important. This paper presents an approach for user identification given the physical activity patterns captured using on-body wearable sensors, such as accelerometer, gyroscope, and magnetometer. Three machine learning classifiers have been used to discover the activity patterns of users given the data captured from wearable sensors. The recognition results prove that the proposed scheme can effectively recognize a user’s identity based on his/her daily living physical activity patterns.

关键词： Activity recognition machine learning user identification wearable sensors

When creators meet the metaverse: A survey on computational arts

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lee, Lik-Hang Lin, Zijun Hu, Rui Gong, Zhengya Kumar, Abhishek Li, Tangyao Li, Sijia Hui, Pan Augmented Reality and Media Lab KAIST Korea Republic of Department of Economics University College London United Kingdom Computational Media & Arts The Hong Kong University of Science and Technology Hong Kong Center for Ubiquitous Computing University of Oulu Finland Department of Computer Science University of Helsinki Finland School of Mathematical Sciences Queen Mary University of London United Kingdom Department of Architecture Inha University Korea Republic of

The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity. This article conducts a comprehensive survey on computational arts, in which seven critical topics are relevant to the metaverse, describing novel artworks in blended virtual-physical realities. The topics first cover the building elements for the metaverse, e.g., virtual scenes and characters, auditory, textual elements. Next, several remarkable types of novel creations in the expanded horizons of metaverse cyberspace have been reflected, such as immersive arts, robotic arts, and other user-centric approaches fuelling contemporary creative outputs. Finally, we propose several research agendas: democratising computational arts, digital privacy, and safety for metaverse artists, ownership recognition for digital artworks, technological challenges, and so on. The survey also serves as introductory material for artists and metaverse technologists to begin creations in the realm of surrealistic cyberspace. © 2021, CC BY-NC-SA.

关键词： Surveys

Rolling stock shunt operation planning in urban rail transit depots with maintenance consideration

学校读者我要写书评

暂无评论

Transportation Research Part B: Methodological 2025年 199卷

作者： Wang, Dian Yao, Ling D'Ariano, Andrea Zhan, Shuguang Wang, Lisha School of Automotive and Transportation Engineering Hefei University of Technology Anhui Hefei230009 China Department of Civil Computer Science and Aeronautical Technologies Engineering Roma Tre University Rome00146 Italy School of Traffic and Transportation Beijing Jiaotong University Beijing100044 China School of Architecture and Urban Planning Chongqing University Chongqing400030 China

This study investigates the daily rolling stock shunt operation planning in a rail depot. Given the layout of a depot and the rolling stocks (that arrive at and depart from this depot within an operation day) with given maintenance schedule, the studied problem lies in determining: 1) the position where each rolling stock is parked, outside washed, and/or maintained, and 2) the conflict-free shunting plan of rolling stocks to move within a depot. We transform the track-circuits in the depot into different multi-layer directed graphs to illustrate the shunting processes of rolling stocks. By means of these graphs, we formulate the studied problem as a mixed integer linear programming model by considering a more general variant of four requirements that make sense in practice but are not or rarely considered in previous works and by presenting a flexible technique to model the track capacity, to reduce the additional shunting movements of rolling stocks. Besides, we design a two-stage decomposition manner to efficiently solve real-life problem instances, wherein the problem in each stage is addressed by a presented logic-based Benders decomposition algorithm enhanced by customized acceleration mechanisms. Finally, a set of realistic and real-life instances with different scales (derived from the largest depot of the Chongqing Rail Transit Line 3 in China) are investigated. Computational results demonstrate that our best algorithm solves a real-life instance to optimality in approximately 8 s that is considerably shorter than the time of rail staffs to solve this instance manually, thus our approach can provide strong automatical computer-aided decision supports. Our approach is also very efficient in optimizing another objective that is also widely used, and can provide management insights to rail staffs. © 2025 Elsevier Ltd

关键词： Urban transportation

ZETA: a library for Zonotope-based EsTimation and fAult diagnosis of discrete-time systems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Rego, Brenner S. Scott, Joseph K. Raimondo, Davide M. Terra, Marco H. Raffo, Guilherme V. Department of Electrical and Computer Engineering University of São Paulo SP São Carlos13566-590 Brazil Department of Chemical and Biomolecular Engineering Georgia Institute of Technology 311 Ferst Dr. AtlantaGA30318 United States Department of Engineering and Architecture University of Trieste Trieste34127 Italy Department of Electronics Engineering Graduate Program in Electrical Engineering Federal University of Minas Gerais MG Belo Horizonte31270-901 Brazil

This paper introduces ZETA, a new MATLAB library for Zonotope-based EsTimation and fAult diagnosis of discrete-time systems. It features user-friendly implementations of set representations based on zonotopes, namely zonotopes, constrained zonotopes, and line zonotopes, in addition to a basic implementation of interval arithmetic. This library has capabilities starting from the basic set operations with these sets, including propagations through nonlinear functions using various approximation methods. The features of ZETA allow for reachability analysis and state estimation of discrete-time linear, nonlinear, and descriptor systems, in addition to active fault diagnosis of linear systems. Efficient order reduction methods are also implemented for the respective set representations. Some examples are presented in order to illustrate the functionalities of the new library. © 2025, CC BY.

关键词： Digital arithmetic