在支持雾的无人机即服务中构建可持续的联邦学习模型,用于航空图像分类

IF 3.8 3区 计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE
Raju Imandi , Arijit Roy , Yong-Guk Kim , Pavan Kumar B.N.
{"title":"在支持雾的无人机即服务中构建可持续的联邦学习模型,用于航空图像分类","authors":"Raju Imandi ,&nbsp;Arijit Roy ,&nbsp;Yong-Guk Kim ,&nbsp;Pavan Kumar B.N.","doi":"10.1016/j.suscom.2025.101133","DOIUrl":null,"url":null,"abstract":"<div><div>The Fog-enabled UAV-as-a-Service (FU-Serve) platform leverages distributed fog nodes to enable real-time data processing for multiple concurrent applications. However, the computational limitations of these fog nodes significantly hamper the execution of resource-intensive deep learning (DL) algorithms, compromising both operational performance and energy sustainability. To address these challenges, we integrated Federated Learning (FL) within the FU-Serve platform, coupled with the development of three specialized FL-based models tailored for on-device image classification. First, we introduced a sustainable adaptation of MobileNetV2 that synergizes Transfer Learning (TL) with FL principles. This model achieves 97.68% accuracy with an 8.64 MB footprint by distributing pre-trained weights to optimize bandwidth efficiency. To further address resource constraints of fog nodes, we designed FUSERNet—a lightweight DL architecture employing separable convolutions and skip connections, which reduces computational overhead while preserving critical feature representations. This model achieves 97.47% accuracy with an ultra-compact footprint of 237 KB, demonstrating a 98.59% reduction in size compared to state-of-the-art models. Finally, our third model, FusionNet, combines the strengths of MobileNetV2 and FUSERNet to deliver a balanced solution, achieving 97.75% accuracy with moderate resource requirements (8.86 MB). We evaluated our models on the AIDER and NDD disaster response datasets, our models demonstrate superior performance in classifying critical natural disaster scenarios. Notably, FusionNet matches SOTA accuracy levels while reducing memory consumption by 50%, and FUSERNet’s 0.23 MB size enables deployment on even the most resource-constrained UAVs. These contributions enhance the FU-Serve platform’s real-time decision-making capabilities, balancing computational efficiency and mission-critical accuracy for sustainable disaster response.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101133"},"PeriodicalIF":3.8000,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Building sustainable federated learning models in Fog-enabled UAV-as-a-Service for aerial image classification\",\"authors\":\"Raju Imandi ,&nbsp;Arijit Roy ,&nbsp;Yong-Guk Kim ,&nbsp;Pavan Kumar B.N.\",\"doi\":\"10.1016/j.suscom.2025.101133\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The Fog-enabled UAV-as-a-Service (FU-Serve) platform leverages distributed fog nodes to enable real-time data processing for multiple concurrent applications. However, the computational limitations of these fog nodes significantly hamper the execution of resource-intensive deep learning (DL) algorithms, compromising both operational performance and energy sustainability. To address these challenges, we integrated Federated Learning (FL) within the FU-Serve platform, coupled with the development of three specialized FL-based models tailored for on-device image classification. First, we introduced a sustainable adaptation of MobileNetV2 that synergizes Transfer Learning (TL) with FL principles. This model achieves 97.68% accuracy with an 8.64 MB footprint by distributing pre-trained weights to optimize bandwidth efficiency. To further address resource constraints of fog nodes, we designed FUSERNet—a lightweight DL architecture employing separable convolutions and skip connections, which reduces computational overhead while preserving critical feature representations. This model achieves 97.47% accuracy with an ultra-compact footprint of 237 KB, demonstrating a 98.59% reduction in size compared to state-of-the-art models. Finally, our third model, FusionNet, combines the strengths of MobileNetV2 and FUSERNet to deliver a balanced solution, achieving 97.75% accuracy with moderate resource requirements (8.86 MB). We evaluated our models on the AIDER and NDD disaster response datasets, our models demonstrate superior performance in classifying critical natural disaster scenarios. Notably, FusionNet matches SOTA accuracy levels while reducing memory consumption by 50%, and FUSERNet’s 0.23 MB size enables deployment on even the most resource-constrained UAVs. These contributions enhance the FU-Serve platform’s real-time decision-making capabilities, balancing computational efficiency and mission-critical accuracy for sustainable disaster response.</div></div>\",\"PeriodicalId\":48686,\"journal\":{\"name\":\"Sustainable Computing-Informatics & Systems\",\"volume\":\"46 \",\"pages\":\"Article 101133\"},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2025-05-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Sustainable Computing-Informatics & Systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S221053792500054X\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sustainable Computing-Informatics & Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S221053792500054X","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0

摘要

支持雾的无人机即服务(FU-Serve)平台利用分布式雾节点为多个并发应用程序实现实时数据处理。然而,这些雾节点的计算限制严重阻碍了资源密集型深度学习(DL)算法的执行,从而影响了操作性能和能源可持续性。为了应对这些挑战,我们将联邦学习(FL)集成到FU-Serve平台中,并开发了三种专门用于设备上图像分类的基于FL的模型。首先,我们介绍了MobileNetV2的可持续适应,它将迁移学习(TL)与FL原则协同起来。该模型通过分配预训练的权重来优化带宽效率,以8.64 MB的内存占用实现97.68%的准确率。为了进一步解决雾节点的资源约束问题,我们设计了fusernet——一种采用可分离卷积和跳过连接的轻量级深度学习架构,在保留关键特征表示的同时减少了计算开销。该模型的精度达到97.47%,占用空间超紧凑,为237 KB,与最先进的模型相比,尺寸缩小了98.59%。最后,我们的第三个模型,FusionNet,结合了MobileNetV2和FUSERNet的优势,提供了一个平衡的解决方案,在适度的资源要求(8.86 MB)下实现了97.75%的准确率。我们在AIDER和NDD灾害响应数据集上对我们的模型进行了评估,我们的模型在关键自然灾害情景分类方面表现出优异的性能。值得注意的是,FusionNet与SOTA精度水平相当,同时减少了50%的内存消耗,而FUSERNet的0.23 MB大小甚至可以部署在资源最有限的无人机上。这些贡献增强了FU-Serve平台的实时决策能力,平衡了计算效率和关键任务的准确性,以实现可持续的灾害响应。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Building sustainable federated learning models in Fog-enabled UAV-as-a-Service for aerial image classification
The Fog-enabled UAV-as-a-Service (FU-Serve) platform leverages distributed fog nodes to enable real-time data processing for multiple concurrent applications. However, the computational limitations of these fog nodes significantly hamper the execution of resource-intensive deep learning (DL) algorithms, compromising both operational performance and energy sustainability. To address these challenges, we integrated Federated Learning (FL) within the FU-Serve platform, coupled with the development of three specialized FL-based models tailored for on-device image classification. First, we introduced a sustainable adaptation of MobileNetV2 that synergizes Transfer Learning (TL) with FL principles. This model achieves 97.68% accuracy with an 8.64 MB footprint by distributing pre-trained weights to optimize bandwidth efficiency. To further address resource constraints of fog nodes, we designed FUSERNet—a lightweight DL architecture employing separable convolutions and skip connections, which reduces computational overhead while preserving critical feature representations. This model achieves 97.47% accuracy with an ultra-compact footprint of 237 KB, demonstrating a 98.59% reduction in size compared to state-of-the-art models. Finally, our third model, FusionNet, combines the strengths of MobileNetV2 and FUSERNet to deliver a balanced solution, achieving 97.75% accuracy with moderate resource requirements (8.86 MB). We evaluated our models on the AIDER and NDD disaster response datasets, our models demonstrate superior performance in classifying critical natural disaster scenarios. Notably, FusionNet matches SOTA accuracy levels while reducing memory consumption by 50%, and FUSERNet’s 0.23 MB size enables deployment on even the most resource-constrained UAVs. These contributions enhance the FU-Serve platform’s real-time decision-making capabilities, balancing computational efficiency and mission-critical accuracy for sustainable disaster response.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Sustainable Computing-Informatics & Systems
Sustainable Computing-Informatics & Systems COMPUTER SCIENCE, HARDWARE & ARCHITECTUREC-COMPUTER SCIENCE, INFORMATION SYSTEMS
CiteScore
10.70
自引率
4.40%
发文量
142
期刊介绍: Sustainable computing is a rapidly expanding research area spanning the fields of computer science and engineering, electrical engineering as well as other engineering disciplines. The aim of Sustainable Computing: Informatics and Systems (SUSCOM) is to publish the myriad research findings related to energy-aware and thermal-aware management of computing resource. Equally important is a spectrum of related research issues such as applications of computing that can have ecological and societal impacts. SUSCOM publishes original and timely research papers and survey articles in current areas of power, energy, temperature, and environment related research areas of current importance to readers. SUSCOM has an editorial board comprising prominent researchers from around the world and selects competitively evaluated peer-reviewed papers.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信