利用集合深度学习框架识别过渡感知的人类活动

IF 9 1区 心理学 Q1 PSYCHOLOGY, EXPERIMENTAL Computers in Human Behavior Pub Date : 2024-09-10 DOI:10.1016/j.chb.2024.108435
Saad Irfan Khan , Hussain Dawood , M.A. Khan , Ghassan F. Issa , Amir Hussain , Mrim M. Alnfiai , Khan Muhammad Adnan
{"title":"利用集合深度学习框架识别过渡感知的人类活动","authors":"Saad Irfan Khan ,&nbsp;Hussain Dawood ,&nbsp;M.A. Khan ,&nbsp;Ghassan F. Issa ,&nbsp;Amir Hussain ,&nbsp;Mrim M. Alnfiai ,&nbsp;Khan Muhammad Adnan","doi":"10.1016/j.chb.2024.108435","DOIUrl":null,"url":null,"abstract":"<div><p>Understanding human activities in daily life is of utmost importance, especially in the context of personalized and adaptive ubiquitous learning. Although existing HAR systems perform well-identifying activities based on their inter-spatial and temporal relationships, they lack in identifying the importance of accurately detecting postural transitions that not only enhance the activity recognition rate and reduced the error rate but also provides added motivation to explore and develop hybrid models. It's in this context we propose an ensemble approach of 1D-CNN and LSTM for the task of postural transition recognition, facilitated by wireless computing and wearable sensors. The proliferation of achieving ubiquitous learning will ultimately lead to the creation of adaptive devices enabled by various data analysis and relation learning techniques. Our approach is one of the methods that can be incorporated to enable seamless learning and acquire correlations with adaptive learning techniques. The experimental results on testing datasets including newly produced HAPT (Human Activities and Postural Transitions) show better classification accuracy than existing state-of-the-art HAR approaches (97.84% for transitional activities and 99.04% for dynamic human activities) indicating the capability of the model in ubiquitous learning scenarios and personalized and adaptive human learning environments.</p></div>","PeriodicalId":48471,"journal":{"name":"Computers in Human Behavior","volume":"162 ","pages":"Article 108435"},"PeriodicalIF":9.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0747563224003030/pdfft?md5=8aaa469f57822eaae80ceea614b5c0e9&pid=1-s2.0-S0747563224003030-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Transition-aware human activity recognition using an ensemble deep learning framework\",\"authors\":\"Saad Irfan Khan ,&nbsp;Hussain Dawood ,&nbsp;M.A. Khan ,&nbsp;Ghassan F. Issa ,&nbsp;Amir Hussain ,&nbsp;Mrim M. Alnfiai ,&nbsp;Khan Muhammad Adnan\",\"doi\":\"10.1016/j.chb.2024.108435\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Understanding human activities in daily life is of utmost importance, especially in the context of personalized and adaptive ubiquitous learning. Although existing HAR systems perform well-identifying activities based on their inter-spatial and temporal relationships, they lack in identifying the importance of accurately detecting postural transitions that not only enhance the activity recognition rate and reduced the error rate but also provides added motivation to explore and develop hybrid models. It's in this context we propose an ensemble approach of 1D-CNN and LSTM for the task of postural transition recognition, facilitated by wireless computing and wearable sensors. The proliferation of achieving ubiquitous learning will ultimately lead to the creation of adaptive devices enabled by various data analysis and relation learning techniques. Our approach is one of the methods that can be incorporated to enable seamless learning and acquire correlations with adaptive learning techniques. The experimental results on testing datasets including newly produced HAPT (Human Activities and Postural Transitions) show better classification accuracy than existing state-of-the-art HAR approaches (97.84% for transitional activities and 99.04% for dynamic human activities) indicating the capability of the model in ubiquitous learning scenarios and personalized and adaptive human learning environments.</p></div>\",\"PeriodicalId\":48471,\"journal\":{\"name\":\"Computers in Human Behavior\",\"volume\":\"162 \",\"pages\":\"Article 108435\"},\"PeriodicalIF\":9.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0747563224003030/pdfft?md5=8aaa469f57822eaae80ceea614b5c0e9&pid=1-s2.0-S0747563224003030-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers in Human Behavior\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0747563224003030\",\"RegionNum\":1,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHOLOGY, EXPERIMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers in Human Behavior","FirstCategoryId":"102","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0747563224003030","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0

摘要

了解人类在日常生活中的活动至关重要,尤其是在个性化和适应性泛在学习的背景下。虽然现有的 HAR 系统能根据活动的空间和时间关系很好地识别活动,但它们缺乏识别准确检测姿势转换的重要性,而这种检测不仅能提高活动识别率和降低错误率,还能为探索和开发混合模型提供更多动力。正是在这种背景下,我们提出了一种 1D-CNN 和 LSTM 的集合方法,用于在无线计算和可穿戴传感器的帮助下识别姿势转换任务。实现泛在学习的普及最终将导致利用各种数据分析和关系学习技术创建自适应设备。我们的方法是实现无缝学习和获取自适应学习技术相关性的方法之一。在包括新制作的 HAPT(人类活动和姿势转换)在内的测试数据集上的实验结果表明,分类准确率高于现有的最先进的 HAR 方法(过渡活动为 97.84%,动态人类活动为 99.04%),这表明该模型在泛在学习场景和个性化自适应人类学习环境中的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Transition-aware human activity recognition using an ensemble deep learning framework

Understanding human activities in daily life is of utmost importance, especially in the context of personalized and adaptive ubiquitous learning. Although existing HAR systems perform well-identifying activities based on their inter-spatial and temporal relationships, they lack in identifying the importance of accurately detecting postural transitions that not only enhance the activity recognition rate and reduced the error rate but also provides added motivation to explore and develop hybrid models. It's in this context we propose an ensemble approach of 1D-CNN and LSTM for the task of postural transition recognition, facilitated by wireless computing and wearable sensors. The proliferation of achieving ubiquitous learning will ultimately lead to the creation of adaptive devices enabled by various data analysis and relation learning techniques. Our approach is one of the methods that can be incorporated to enable seamless learning and acquire correlations with adaptive learning techniques. The experimental results on testing datasets including newly produced HAPT (Human Activities and Postural Transitions) show better classification accuracy than existing state-of-the-art HAR approaches (97.84% for transitional activities and 99.04% for dynamic human activities) indicating the capability of the model in ubiquitous learning scenarios and personalized and adaptive human learning environments.

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
CiteScore
19.10
自引率
4.00%
发文量
381
审稿时长
40 days
期刊介绍: Computers in Human Behavior is a scholarly journal that explores the psychological aspects of computer use. It covers original theoretical works, research reports, literature reviews, and software and book reviews. The journal examines both the use of computers in psychology, psychiatry, and related fields, and the psychological impact of computer use on individuals, groups, and society. Articles discuss topics such as professional practice, training, research, human development, learning, cognition, personality, and social interactions. It focuses on human interactions with computers, considering the computer as a medium through which human behaviors are shaped and expressed. Professionals interested in the psychological aspects of computer use will find this journal valuable, even with limited knowledge of computers.
期刊最新文献
What makes an app authentic? Determining antecedents of perceived authenticity in an AI-powered service app The effects of self-explanation on game-based learning: Evidence from eye-tracking analyses Avatars at risk: Exploring public response to sexual violence in immersive digital spaces Perception of non-binary social media users towards authentic non-binary social media influencers Editorial Board
×
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