Continual Activity Recognition with Generative Adversarial Networks

IF 3.5 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS ACM Transactions on Internet of Things Pub Date : 2021-03-01 DOI:10.1145/3440036
Juan Ye, Pakawat Nakwijit, Martin Schiemer, Saurav Jha, F. Zambonelli
{"title":"Continual Activity Recognition with Generative Adversarial Networks","authors":"Juan Ye, Pakawat Nakwijit, Martin Schiemer, Saurav Jha, F. Zambonelli","doi":"10.1145/3440036","DOIUrl":null,"url":null,"abstract":"Continual learning is an emerging research challenge in human activity recognition (HAR). As an increasing number of HAR applications are deployed in real-world environments, it is important and essential to extend the activity model to adapt to the change in people’s activity routine. Otherwise, HAR applications can become obsolete and fail to deliver activity-aware services. The existing research in HAR has focused on detecting abnormal sensor events or new activities, however, extending the activity model is currently under-explored. To directly tackle this challenge, we build on the recent advance in the area of lifelong machine learning and design a continual activity recognition system, called HAR-GAN, to grow the activity model over time. HAR-GAN does not require a prior knowledge on what new activity classes might be and it does not require to store historical data by leveraging the use of Generative Adversarial Networks (GAN) to generate sensor data on the previously learned activities. We have evaluated HAR-GAN on four third-party, public datasets collected on binary sensors and accelerometers. Our extensive empirical results demonstrate the effectiveness of HAR-GAN in continual activity recognition and shed insight on the future challenges.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Internet of Things","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3440036","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 8

Abstract

Continual learning is an emerging research challenge in human activity recognition (HAR). As an increasing number of HAR applications are deployed in real-world environments, it is important and essential to extend the activity model to adapt to the change in people’s activity routine. Otherwise, HAR applications can become obsolete and fail to deliver activity-aware services. The existing research in HAR has focused on detecting abnormal sensor events or new activities, however, extending the activity model is currently under-explored. To directly tackle this challenge, we build on the recent advance in the area of lifelong machine learning and design a continual activity recognition system, called HAR-GAN, to grow the activity model over time. HAR-GAN does not require a prior knowledge on what new activity classes might be and it does not require to store historical data by leveraging the use of Generative Adversarial Networks (GAN) to generate sensor data on the previously learned activities. We have evaluated HAR-GAN on four third-party, public datasets collected on binary sensors and accelerometers. Our extensive empirical results demonstrate the effectiveness of HAR-GAN in continual activity recognition and shed insight on the future challenges.
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
基于生成对抗网络的持续活动识别
持续学习是人类活动识别(HAR)领域一个新兴的研究挑战。随着越来越多的HAR应用部署在现实环境中,扩展活动模型以适应人们活动常规的变化是非常重要和必要的。否则,HAR应用程序可能会过时,无法交付活动感知服务。HAR的现有研究主要集中在检测异常传感器事件或新活动,然而,扩展活动模型目前尚未得到充分探索。为了直接应对这一挑战,我们基于终身机器学习领域的最新进展,设计了一个持续的活动识别系统,称为HAR-GAN,以随着时间的推移发展活动模型。HAR-GAN不需要预先了解新的活动类别,也不需要通过使用生成对抗网络(GAN)来存储历史数据,以生成先前学习过的活动的传感器数据。我们在二进制传感器和加速度计上收集的四个第三方公开数据集上评估了HAR-GAN。我们广泛的实证结果证明了HAR-GAN在持续活动识别中的有效性,并对未来的挑战提供了见解。
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
CiteScore
5.20
自引率
3.70%
发文量
0
期刊最新文献
FLAShadow: A Flash-based Shadow Stack for Low-end Embedded Systems CoSense: Deep Learning Augmented Sensing for Coexistence with Networking in Millimeter-Wave Picocells CASPER: Context-Aware IoT Anomaly Detection System for Industrial Robotic Arms Collaborative Video Caching in the Edge Network using Deep Reinforcement Learning ARIoTEDef: Adversarially Robust IoT Early Defense System Based on Self-Evolution against Multi-step Attacks
×
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