检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Wu, Jia Dai, Tingyi Guan, Peiyuan Chen, Ziru Gou, Fangfang Taherkordi, Amir The Department of Informatics University of Oslo Oslo0316 Norway The Department of Electrical and Computer Engineering Illinois Institute of Technology Chicago United States The School of Computer Science and Technology GuiZhou University Guiyang550025 China The Research Center for Artificial Intelligence Faculty of IT Monash University MelbourneVIC3800 Australia

As the 5G era develops quickly, there has been a significant growth in the amount of network data. Concurrently, traditional routing algorithms are encountering growing challenges. Traditional routing algorithms typically rely on maintaining stable end-to-end paths to facilitate smooth data transmission. However, in wireless multi-hop networks, the mobility of nodes and the dynamic nature of network topology make maintaining stable end-to-end paths exceedingly difficult, if not impossible. Consequently, data transmission efficiency decreases while network overhead increases. To address these challenges, opportunistic routing has emerged. Opportunistic routing is self-organizing networks that rely on chance encounters between nodes to transmit messages, and the store-and-carry forwarding technique is used for data transmission between nodes. Typically, most traditional opportunistic routing algorithms divide nodes into communities. However, such approaches often overlook node characteristics, potentially leading to disparate nodes being assigned to separate communities despite positive correlations. Thus, accurately dividing communities remains a significant challenge. To address this, we propose the Efficient Community Detection Data Transmitting (ECDDT) algorithm. During community division, ECDDT combines social attributes and network topology using mobile edge computing. Subsequently, to expedite task execution, we schedule these tasks in a reasonable manner. Through simulation experiments across four diverse real datasets, we evaluate the algorithm's efficacy. Our findings demonstrate favorable performance in delivery rate and routing overhead. © 2024, The Authors. All rights reserved.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

TinyQMIX: Distributed Access Control for mMTC via Multi-agent Reinforcement Learning

TinyQMIX: Distributed Access Control for mMTC via Multi-agen...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Tien Thanh Le Yusheng Ji John C.S. Lui Department of Informatics The Graduate University for Advanced Studies SOKENDAI Tokyo Japan National Institute of Informatics Tokyo Japan Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781665454698

Distributed access control is a crucial component for massive machine type communication (mMTC). In this communication scenario, centralized resource allocation is not scalable because resource configurations have to be sent frequently from the base station to a massive number of devices. We investigate distributed reinforcement learning for resource selection without relying on centralized control. Another important feature of mMTC is the sporadic and dynamic change of traffic. Existing studies on distributed access control assume that traffic load is static or they are able to gradually adapt to the dynamic traffic. We minimize the adaptation period by training TinyQMIX, which is a lightweight multi-agent deep reinforcement learning model, to learn a distributed wireless resource selection policy under various traffic patterns before deployment. Therefore, the trained agents are able to quickly adapt to dynamic traffic and provide low access delay. Numerical results are presented to support our claims.

关键词： Access control Deep learning Wireless communication Training Vehicular and wireless technologies Reinforcement learning Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Generative AI for Lyapunov Optimization Theory in UAV-based Low-Altitude Economy Networking

arXiv

引用

arXiv 2025年

作者： Liu, Zhang Niyato, Dusit Wang, Jiacheng Sun, Geng Huang, Lianfen Gao, Zhibin Wang, Xianbin Department of Informatics and Communication Engineering Xiamen University Fujian361102 China College of Computing and Data Science Nanyang Technological University Singapore College of Computer Science and Technology Jilin University Changchun130012 China Navigation Institute Jimei University Fujian Xiamen361021 China Department of Electrical and Computer Engineering Western University LondonONN6A 5B9 Canada

Lyapunov optimization theory has recently emerged as a powerful mathematical framework for solving complex stochastic optimization problems by transforming long-term objectives into a sequence of real-time short-term decisions while ensuring system stability. This theory is particularly valuable in unmanned aerial vehicle (UAV)-based low-altitude economy (LAE) networking scenarios, where it could effectively address inherent challenges of dynamic network conditions, multiple optimization objectives, and stability requirements. Recently, generative artificial intelligence (GenAI) has garnered significant attention for its unprecedented capability to generate diverse digital content. Extending beyond content generation, in this paper, we propose a framework integrating generative diffusion models with reinforcement learning to address Lyapunov optimization problems in UAV-based LAE networking. We begin by introducing the fundamentals of Lyapunov optimization theory and analyzing the limitations of both conventional methods and traditional AI-enabled approaches. We then examine various GenAI models and comprehensively analyze their potential contributions to Lyapunov optimization. Subsequently, we develop a Lyapunov-guided generative diffusion model-based reinforcement learning framework and validate its effectiveness through a UAV-based LAE networking case study. Finally, we outline several directions for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Cloud-based Distributed Computing Approach for Extracting Molecular Descriptors 22

A Cloud-based Distributed Computing Approach for Extracting ...

引用

Proceedings of the 6th International Conference on Algorithms, Computing and Systems

作者： Christos Didachos Dionisis Panagiotis Kintos Manolis Fousteris Vassilis C. Gerogiannis Le Hoang Son Andreas Kanavos Department of Computer Engineering & Informatics University of Patras Greece Department of Pharmacy Laboratory of Medicinal Chemistry University of Patras Greece Department of Digital Systems University of Thessaly Greece VNU Information Technology Institute Vietnam National University Vietnam Department of Informatics Ionian University Greece

ISBN: (纸本)9781450397407

Feature extraction is an initial and essential part for the development of accurate predictive machine learning classifiers. In the research field of drug discovery and development, the usage of molecular descriptors, which can be defined as mathematical representations of molecules’ chemical properties, is a challenging task not only for machine learning studies but even for "classical wet lab" approaches. However, a high diversity of these descriptors is required in order to exploit all the available knowledge and, consequently, to maximize the potentially predictive power of approaches that could be applied for the discovery of new bioactive compounds against one or more molecular targets. Furthermore, the representation and normalization of these information is considered a rather time-consuming process. Herein, we present an approach that employs the power of cloud and distributing computing for the extraction, processing and representation of big datasets, leading to the generation of molecular descriptors in a reasonable time frame.

关键词： Coiled Computing Performance Computational Drug Design Dask Molecular Descriptors Chemical Big Data

来源：评论

学校读者我要写书评

暂无评论

Utilizing low-cost optical sensor for the measurement of particulate matter and calculating Pearson's correlation coefficient 16

Utilizing low-cost optical sensor for the measurement of par...

引用

16th International Conference on Correlation Optics, COR 2023

作者： Kirešová, Simona Rusyn, Volodymyr Guzan, Milan Vorobets, George Sobota, Branislav Vorobets, Oleksandr Dept. of Theoretical and Industrial Electrical Engineering Technical University of Košice Letná 9 Košice042 00 Slovakia Dept. of Radio Engineering and Information Security Yuriy Fedkovych Chernivtsi National University 2 Kotsjubynskyi Str. Chernivtsi58000 Ukraine Dept. of Computer Systems and Networks Yuriy Fedkovych Chernivtsi National University 2 Kotsjubynskyi Str. Chernivtsi58000 Ukraine Dept. of Computers and Informatics Technical University of Košice Letná 9 Košice042 00 Slovakia

ISBN: (纸本)9781510671829

This article discusses the possibilities of measuring Particulate Matter using optical low-cost sensors. Depending on the sensor used, not only can there be problems with the positioning of the sensor with respect to the incoming sunlight, but it may also be possible to measure ultrafine particles. While PM2.5 and PM10 are commonly used to characterize air quality, in this paper we point out the need to pay more attention to smaller particles up to 0.1 μm in size (also referred to as ultrafine particulates) due to their highly negative effects on the human health. Attention is also paid to the correlation between particulate matter and meteorological factors like pressure, temperature, and humidity. However, the sudden change in Pearson's correlation coefficient unveiled a need to look into the effect of the wind on particulate matter. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Effects of Mobility Restrictions during COVID-19 on Land Surface Temperature with GIS and Satellite Data

Evaluating the Effects of Mobility Restrictions during COVID...

引用

International Conference on informatics and Computing (ICIC)

作者： Herlawati Herlawati Rahmadya Trias Handayanto Ika Dewi Sartika Saimima Muhammad Khaerudin M. Hadi Prayitno Prio Kustanto Ismaniah Ismaniah Ajif Yunizar Pratama Yusuf Arman Andrian Informatics Universitas Bhayangkara Jakarta Raya Jakarta Indonesia Computer Engineering Universitas Islam 45 Bekasi Indonesia Law Universitas Bhayangkara Jakarta Raya Jakarta Indonesia Industrial Engineering Universitas Bhayangkara Jakarta Raya Jakarta Indonesia

In order to analyze specific occurrences, such as the COVID-19 pandemic’s effects, experts from a variety of professions might work together. The majority of study, such as those on economics, health, spread projections, and similar topics, focuses on just one area of the field. Therefore, several multidisciplinary teams need to collaborate in analyzing the occurring phenomena. The method employed in this research involves using Remote Sensing and Geographic Information Systems (RS-GIS) to observe the impact of the pandemic phenomenon on environmental conditions, specifically surface temperature warming in Bekasi Regency, Indonesia. This is due to its impact not only on health but also on other aspects. This study converts Landsat 7 and Landsat 8 images using (RS-GIS) technologies to extract thermal sensors (Band 10 and Band 11). The test results indicate that the temperature rises annually, but that it falls during the COVID-19 pandemic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the generalization of stochastic gradient descent with momentum

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 1132-1187页

作者： Ali Ramezani-Kebrya Kimon Antonakopoulos Volkan Cevher Ashish Khisti Ben Liang Department of Informatics University of Oslo and Visual Intelligence Centre Integreat Norwegian Centre for Knowledge-driven Machine Learning Oslo Norway Laboratory for Information and Inference Systems (LIONS) EPFL EPFL STI IEL LIONS Lausanne Switzerland Department of Electrical and Computer Engineering University of Toronto Toronto ON Canada

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that there exists a convex loss function for which the stability gap for multiple epochs of SGD with standard heavy-ball momentum (SGDM) becomes unbounded. Then, for smooth Lipschitz loss functions, we analyze a profiles momentum-based update rule, i.e., SGD with early momentum (SGDEM) under a broad range of step-sizes, and show that it can train machine learning models for multiple epochs with a guarantee for generalization. Finally, for the special case of strongly convex loss functions, we find a range of momentum such that multiple epochs of standard SGDM, as a special form of SGDEM, also generalizes. Extending our results on generalization, we also develop an upper bound on the expected true risk, in terms of the number of training steps, sample size, and momentum. Our experimental evaluations verify the consistency between the numerical results and our theoretical bounds. SGDEM improves the generalization error of SGDM when training ResNet-18 on ImageNet in practical distributed settings.

关键词： uniform stability generalization error heavy-ball momentum stochastic gradient descent non-convex

来源：评论

学校读者我要写书评

暂无评论

Multi-View 2D to 3D Lifting Video-Based Optimization: A Robust Approach for Human Pose Estimation with Occluded Joint Prediction*

Multi-View 2D to 3D Lifting Video-Based Optimization: A Robu...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Daniela Rato Miguel Oliveira Vítor Santos Angel Sappa Bogdan Raducanu Department of Mechanical Engineering Institute of Electronics and Informatics Engineering of Aveiro Campus Universitário de Santiago University of Aveiro Aveiro Portugal LASI - Intelligent System Associate Laboratory Portugal Edificio O Computer Vision Center Barcelona Spain ESPOL Polytechnic University Guayaquil Ecuador

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In the context of robotics, accurate 3D human pose estimation is essential for enhancing human-robot collaboration and interaction. This manuscript introduces a multi-view 2D to 3D lifting optimization-based method designed for video-based 3D human pose estimation, incorporating temporal information. Our technique addresses key challenges, namely robustness to 2D joint detection error, occlusions, and varying camera perspectives. We evaluate the performance of the algorithm through extensive experiments on the MPI-INF-3DHP dataset. Our method demonstrates very good robustness up to 25 pixels of 2D joint error and shows resilience in scenarios involving several occluded joints. Comparative analyses against existing 2D to 3D lifting and multi-view methods showcase good performance of our approach.

关键词： Three-dimensional displays Accuracy Pose estimation Robot vision systems Human-robot interaction Cameras Robustness Intelligent robots Resilience

来源：评论

学校读者我要写书评

暂无评论

Evaluating Data Augmentation Techniques for Coffee Leaf Disease Classification

arXiv

引用

arXiv 2024年

作者： Gheorghiu, Adrian Tăiatu, Iulian-Marius Cercel, Dumitru-Clementin Marin, Iuliana Pop, Florin Computer Science and Engineering Department National University of Science and Technology POLITEHNICA Bucharest Romania Faculty of Engineering in Foreign Languages National University of Science and Technology POLITEHNICA Bucharest Romania National Institute for Research and Development in Informatics - ICI Bucharest Romania Academy of Romanian Scientists Bucharest Romania

The detection and classification of diseases in Robusta coffee leaves are essential to ensure that plants are healthy and the crop yield is kept high. However, this job requires extensive botanical knowledge and much wasted time. Therefore, this task and others similar to it have been extensively researched subjects in image classification. Regarding leaf disease classification, most approaches have used the more popular PlantVillage dataset while completely disregarding other datasets, like the Robusta Coffee Leaf (RoCoLe) dataset. As the RoCoLe dataset is imbalanced and does not have many samples, fine-tuning of pre-trained models and multiple augmentation techniques need to be used. The current paper uses the RoCoLe dataset and approaches based on deep learning for classifying coffee leaf diseases from images, incorporating the pix2pix model for segmentation and cycle-generative adversarial network (CycleGAN) for augmentation. Our study demonstrates the effectiveness of Transformer-based models, online augmentations, and CycleGAN augmentation in improving leaf disease classification. While synthetic data has limitations, it complements real data, enhancing model performance. These findings contribute to developing robust techniques for plant disease detection and classification. © 2024, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Peculiarities of Supporting Anti-Crisis Decision-Making in the Conditions of the Epidemic Danger of the Spread of COVID-19 9

Peculiarities of Supporting Anti-Crisis Decision-Making in t...

引用

9th IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2022

作者： Tiutiunyk, Olha Ruban, Igor Tiutiunyk, Vadym Simon Kuznets Kharkiv National University of Economics Department of Informatics and Computer Engineering Kharkov Ukraine Kharkiv National University of Radio Electronics Department of Electronic Computers Kharkov Ukraine National University of Civil Defence of Ukraine Department of Management and Organization of Civil Defence Kharkov Ukraine

ISBN: (纸本)9798350398915

The work examines the peculiarities of the functioning of situational centers in the event of an epidemic danger of the spread of COVID-19. A procedure has been developed to support the adoption of anti-crisis decisions at the regional management level regarding the implementation of targeted actions aimed at minimizing the consequences of medical and biological emergency situations in the conditions of the epidemic danger of the spread of COVID-19. © 2022 IEEE.

关键词： COVID-19

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：