Building Lightweight Deep learning Models with TensorFlow Lite for Human Activity Recognition on Mobile Devices

IF 1.8 4区 计算机科学 Q3 TELECOMMUNICATIONS Annals of Telecommunications Pub Date : 2023-07-15 DOI:10.1007/s12243-023-00962-x
Sevda Özge Bursa, Özlem Durmaz İncel, Gülfem Işıklar Alptekin
{"title":"Building Lightweight Deep learning Models with TensorFlow Lite for Human Activity Recognition on Mobile Devices","authors":"Sevda Özge Bursa,&nbsp;Özlem Durmaz İncel,&nbsp;Gülfem Işıklar Alptekin","doi":"10.1007/s12243-023-00962-x","DOIUrl":null,"url":null,"abstract":"<div><p>Human activity recognition (HAR) is a research domain that enables continuous monitoring of human behaviors for various purposes, from assisted living to surveillance in smart home environments. These applications generally work with a rich collection of sensor data generated using smartphones and other low-power wearable devices. The amount of collected data can quickly become immense, necessitating time and resource-consuming computations. Deep learning (DL) has recently become a promising trend in HAR. However, it is challenging to train and run DL algorithms on mobile devices due to their limited battery power, memory, and computation units. In this paper, we evaluate and compare the performance of four different deep architectures trained on three datasets from the HAR literature (WISDM, MobiAct, OpenHAR). We use the TensorFlow Lite platform with quantization techniques to convert the models into lighter versions for deployment on mobile devices. We compare the performance of the original models in terms of accuracy, size, and resource usage with their optimized versions. The experiments reveal that the model size and resource consumption can significantly be reduced when optimized with TensorFlow Lite without sacrificing the accuracy of the models.</p></div>","PeriodicalId":50761,"journal":{"name":"Annals of Telecommunications","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Telecommunications","FirstCategoryId":"94","ListUrlMain":"https://link.springer.com/article/10.1007/s12243-023-00962-x","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}
引用次数: 1

Abstract

Human activity recognition (HAR) is a research domain that enables continuous monitoring of human behaviors for various purposes, from assisted living to surveillance in smart home environments. These applications generally work with a rich collection of sensor data generated using smartphones and other low-power wearable devices. The amount of collected data can quickly become immense, necessitating time and resource-consuming computations. Deep learning (DL) has recently become a promising trend in HAR. However, it is challenging to train and run DL algorithms on mobile devices due to their limited battery power, memory, and computation units. In this paper, we evaluate and compare the performance of four different deep architectures trained on three datasets from the HAR literature (WISDM, MobiAct, OpenHAR). We use the TensorFlow Lite platform with quantization techniques to convert the models into lighter versions for deployment on mobile devices. We compare the performance of the original models in terms of accuracy, size, and resource usage with their optimized versions. The experiments reveal that the model size and resource consumption can significantly be reduced when optimized with TensorFlow Lite without sacrificing the accuracy of the models.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
使用TensorFlow Lite构建轻量级深度学习模型,用于移动设备上的人类活动识别
人类活动识别(HAR)是一个研究领域,它可以为各种目的持续监测人类行为,从辅助生活到智能家居环境中的监控。这些应用程序通常使用智能手机和其他低功耗可穿戴设备生成的丰富传感器数据集。收集的数据量很快就会变得巨大,需要进行耗时和消耗资源的计算。深度学习(DL)最近成为HAR的一个有前途的趋势。然而,由于移动设备的电池电量、内存和计算单元有限,在移动设备上训练和运行深度学习算法是具有挑战性的。在本文中,我们评估和比较了在来自HAR文献(WISDM, mobact, OpenHAR)的三个数据集上训练的四种不同深度架构的性能。我们使用TensorFlow Lite平台和量化技术将模型转换为更轻的版本,以便部署在移动设备上。我们将原始模型在精度、大小和资源使用方面的性能与优化版本进行比较。实验表明,在不牺牲模型精度的前提下,使用TensorFlow Lite进行优化可以显著减少模型大小和资源消耗。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Annals of Telecommunications
Annals of Telecommunications 工程技术-电信学
CiteScore
5.20
自引率
5.30%
发文量
37
审稿时长
4.5 months
期刊介绍: Annals of Telecommunications is an international journal publishing original peer-reviewed papers in the field of telecommunications. It covers all the essential branches of modern telecommunications, ranging from digital communications to communication networks and the internet, to software, protocols and services, uses and economics. This large spectrum of topics accounts for the rapid convergence through telecommunications of the underlying technologies in computers, communications, content management towards the emergence of the information and knowledge society. As a consequence, the Journal provides a medium for exchanging research results and technological achievements accomplished by the European and international scientific community from academia and industry.
期刊最新文献
Editorial of 6GNet 2023 special issue On the (in)efficiency of fuzzing network protocols Mixed $$\mathcal {H}_{2}$$/$$\mathcal {H}_{\infty }$$ fault detection and control for uncertain delta operator systems with mixed random delays and multiple data packet dropouts Investigation of LDPC codes with interleaving for 5G wireless networks Opportunistic data gathering in IoT networks using an energy-efficient data aggregation mechanism
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1