利用知识提炼技术在可穿戴设备上高效识别人类活动

IF 2.6 3区 工程技术 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS
Paulo H. N. Gonçalves, Hendrio Bragança, Eduardo Souto
{"title":"利用知识提炼技术在可穿戴设备上高效识别人类活动","authors":"Paulo H. N. Gonçalves, Hendrio Bragança, Eduardo Souto","doi":"10.3390/electronics13183612","DOIUrl":null,"url":null,"abstract":"Mobile and wearable devices have revolutionized the field of continuous user activity monitoring. However, analyzing the vast and intricate data captured by the sensors of these devices poses significant challenges. Deep neural networks have shown remarkable accuracy in Human Activity Recognition (HAR), but their application on mobile and wearable devices is constrained by limited computational resources. To address this limitation, we propose a novel method called Knowledge Distillation for Human Activity Recognition (KD-HAR) that leverages the knowledge distillation technique to compress deep neural network models for HAR using inertial sensor data. Our approach transfers the acquired knowledge from high-complexity teacher models (state-of-the-art models) to student models with reduced complexity. This compression strategy allows us to maintain performance while keeping computational costs low. To assess the compression capabilities of our approach, we evaluate it using two popular databases (UCI-HAR and WISDM) comprising inertial sensor data from smartphones. Our results demonstrate that our method achieves competitive accuracy, even at compression rates ranging from 18 to 42 times the number of parameters compared to the original teacher model.","PeriodicalId":11646,"journal":{"name":"Electronics","volume":null,"pages":null},"PeriodicalIF":2.6000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Efficient Human Activity Recognition on Wearable Devices Using Knowledge Distillation Techniques\",\"authors\":\"Paulo H. N. Gonçalves, Hendrio Bragança, Eduardo Souto\",\"doi\":\"10.3390/electronics13183612\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Mobile and wearable devices have revolutionized the field of continuous user activity monitoring. However, analyzing the vast and intricate data captured by the sensors of these devices poses significant challenges. Deep neural networks have shown remarkable accuracy in Human Activity Recognition (HAR), but their application on mobile and wearable devices is constrained by limited computational resources. To address this limitation, we propose a novel method called Knowledge Distillation for Human Activity Recognition (KD-HAR) that leverages the knowledge distillation technique to compress deep neural network models for HAR using inertial sensor data. Our approach transfers the acquired knowledge from high-complexity teacher models (state-of-the-art models) to student models with reduced complexity. This compression strategy allows us to maintain performance while keeping computational costs low. To assess the compression capabilities of our approach, we evaluate it using two popular databases (UCI-HAR and WISDM) comprising inertial sensor data from smartphones. Our results demonstrate that our method achieves competitive accuracy, even at compression rates ranging from 18 to 42 times the number of parameters compared to the original teacher model.\",\"PeriodicalId\":11646,\"journal\":{\"name\":\"Electronics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electronics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.3390/electronics13183612\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3390/electronics13183612","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

移动和可穿戴设备彻底改变了用户连续活动监控领域。然而,对这些设备的传感器捕获的大量复杂数据进行分析是一项重大挑战。深度神经网络在人类活动识别(HAR)中表现出了非凡的准确性,但其在移动和可穿戴设备上的应用却受到有限计算资源的限制。为解决这一限制,我们提出了一种名为 "人类活动识别知识蒸馏(KD-HAR)"的新方法,利用知识蒸馏技术压缩深度神经网络模型,从而使用惯性传感器数据进行人类活动识别。我们的方法将获得的知识从高复杂度的教师模型(最先进的模型)转移到复杂度更低的学生模型。这种压缩策略使我们能够在保持性能的同时降低计算成本。为了评估我们的方法的压缩能力,我们使用两个流行的数据库(UCI-HAR 和 WISDM)对其进行了评估,这两个数据库包含来自智能手机的惯性传感器数据。结果表明,即使压缩率为原始教师模型参数数量的 18 到 42 倍,我们的方法也能达到具有竞争力的精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Efficient Human Activity Recognition on Wearable Devices Using Knowledge Distillation Techniques
Mobile and wearable devices have revolutionized the field of continuous user activity monitoring. However, analyzing the vast and intricate data captured by the sensors of these devices poses significant challenges. Deep neural networks have shown remarkable accuracy in Human Activity Recognition (HAR), but their application on mobile and wearable devices is constrained by limited computational resources. To address this limitation, we propose a novel method called Knowledge Distillation for Human Activity Recognition (KD-HAR) that leverages the knowledge distillation technique to compress deep neural network models for HAR using inertial sensor data. Our approach transfers the acquired knowledge from high-complexity teacher models (state-of-the-art models) to student models with reduced complexity. This compression strategy allows us to maintain performance while keeping computational costs low. To assess the compression capabilities of our approach, we evaluate it using two popular databases (UCI-HAR and WISDM) comprising inertial sensor data from smartphones. Our results demonstrate that our method achieves competitive accuracy, even at compression rates ranging from 18 to 42 times the number of parameters compared to the original teacher model.
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
Electronics
Electronics Computer Science-Computer Networks and Communications
CiteScore
1.10
自引率
10.30%
发文量
3515
审稿时长
16.71 days
期刊介绍: Electronics (ISSN 2079-9292; CODEN: ELECGJ) is an international, open access journal on the science of electronics and its applications published quarterly online by MDPI.
×
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