Distributed Agent-Based Collaborative Learning in Cross-Individual Wearable Sensor-Based Human Activity Recognition

被引:0
作者
Esmaeili, Ahmad [1 ]
Ghorrati, Zahra [1 ]
Matson, Eric T. [1 ]
机构
[1] Purdue Univ, Comp & Informat Technol, W Lafayette, IN 47907 USA
来源
2023 SEVENTH IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING, IRC 2023 | 2023年
关键词
Human Activity Recognition; Collaborative Learning; Multi-agent Systems; Wearable Sensors;
D O I
10.1109/IRC59093.2023.00068
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
The rapid growth of wearable sensor technologies holds substantial promise for the field of personalized and context-aware Human Activity Recognition. Given the inherently decentralized nature of data sources within this domain, the utilization of multi-agent systems with their inherent decentralization capabilities presents an opportunity to facilitate the development of scalable, adaptable, and privacy-conscious methodologies. This paper introduces a collaborative distributed learning approach rooted in multi-agent principles, wherein individual users of sensor-equipped devices function as agents within a distributed network, collectively contributing to the comprehensive process of learning and classifying human activities. In this proposed methodology, not only is the privacy of activity monitoring data upheld for each individual, eliminating the need for an external server to oversee the learning process, but the system also exhibits the potential to surmount the limitations of conventional centralized models and adapt to the unique attributes of each user. The proposed approach has been empirically tested on two publicly accessible human activity recognition datasets, specifically PAMAP2 and HARTH, across varying settings. The provided empirical results conclusively highlight the efficacy of inter-individual collaborative learning when contrasted with centralized configurations, both in terms of local and global generalization.
引用
收藏
页码:381 / 388
页数:8
相关论文
共 25 条
[1]   An agent-based signal processing in-node environment for real-time human activity monitoring based on wireless body sensor networks [J].
Aiello, F. ;
Bellifemine, F. L. ;
Fortino, G. ;
Galzarano, S. ;
Gravina, R. .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2011, 24 (07) :1147-1161
[2]  
Bettini C, 2021, Arxiv, DOI arXiv:2104.08094
[3]   Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges, and Opportunities [J].
Chen, Kaixuan ;
Zhang, Dalin ;
Yao, Lina ;
Guo, Bin ;
Yu, Zhiwen ;
Liu, Yunhao .
ACM COMPUTING SURVEYS, 2021, 54 (04)
[4]   ProtoHAR: Prototype Guided Personalized Federated Learning for Human Activity Recognition [J].
Cheng, Dongzhou ;
Zhang, Lei ;
Bu, Can ;
Wang, Xing ;
Wu, Hao ;
Song, Aiguo .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (08) :3900-3911
[5]   A Data Analytics Schema for Activity Recognition in Smart Home Environments [J].
Fortino, Giancarlo ;
Giordano, Andrea ;
Guerrieri, Antonio ;
Spezzano, Giandomenico ;
Vinci, Andrea .
UBIQUITOUS COMPUTING AND AMBIENT INTELLIGENCE: SENSING, PROCESSING, AND USING ENVIRONMENTAL INFORMATION, 2015, 9454 :91-102
[6]   ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition [J].
Jain, Yash ;
Tang, Chi Ian ;
Min, Chulhong ;
Kawsar, Fahim ;
Mathur, Akhil .
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT, 2022, 6 (01)
[7]   DCR: A new distributed model for human activity recognition in smart homes [J].
Jarraya, Amina ;
Bouzeghoub, Amel ;
Borgi, Amel ;
Arour, Khedija .
EXPERT SYSTEMS WITH APPLICATIONS, 2020, 140 (140)
[8]  
Kingma D. P., 2014, arXiv
[9]   Human Action Recognition and Prediction: A Survey [J].
Kong, Yu ;
Fu, Yun .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (05) :1366-1401
[10]   Multi-agent Transformer Networks for Multimodal Human Activity Recognition [J].
Li, Jingcheng ;
Yao, Lina ;
Li, Binghao ;
Wang, Xianzhi ;
Sammut, Claude .
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, :1135-1145