Bootstrapping Human Activity Recognition Systems for Smart Homes from Scratch

被引:17
作者
Hiremath, Shruthi K. [1 ,2 ]
Nishimura, Yasutaka [3 ]
Chernova, Sonia [1 ]
Plotz, Thomas [1 ,4 ]
机构
[1] Georgia Inst Technol, Sch Interact Comp, Atlanta, GA 30332 USA
[2] Georgia Inst Technol, E1566B CODA 15th Floor, Atlanta, GA 30308 USA
[3] KDDI Res Inc, Fujimino, Japan
[4] E1564B CODA 15th Floor, Atlanta, GA 30308 USA
来源
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT | 2022年 / 6卷 / 03期
关键词
smart-home; human activity recognition; pattern recognition;
D O I
10.1145/3550294
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Smart Homes have come a long way: From research laboratories in the early days, through (almost) neglect, to their recent revival in real-world environments enabled through the existence of commodity devices and robust, standardized software frameworks. With such availability, human activity recognition (HAR) in smart homes has become attractive for many real-world applications, especially in the domain of Ambient Assisted Living. Yet, getting started with an activity recognition system in specific smart homes, which are highly specialized spaces inhabited by individuals with idiosyncratic behaviors and habits, is a non-trivial endeavor. We present an approach for bootstrapping HAR systems for individual smart homes from scratch. At the beginning of the life cycle of a smart home, our system passively observes activities and derives rich representations for sensor data-action units-which are then aggregated into activity models through motif learning with minimal supervision. The resulting HAR system is then capable of recognizing relevant, most frequent activities in a smart home. We demonstrate the effectiveness of our bootstrapping procedure through experimental evaluations on CASAS datasets that show the practical value of our approach.
引用
收藏
页数:27
相关论文
共 50 条
[41]   Human Activity Recognition in Smart Home With Deep Learning Approach [J].
Mehr, Homay Danaei ;
Polat, Huseyin .
2019 7TH INTERNATIONAL ISTANBUL SMART GRIDS AND CITIES CONGRESS AND FAIR (ICSG ISTANBUL 2019), 2019, :149-153
[42]   Combining emerging patterns with random forest for complex activity recognition in smart homes [J].
Malazi, Hadi Tabatabaee ;
Davari, Mohammad .
APPLIED INTELLIGENCE, 2018, 48 (02) :315-330
[43]   Internet of Things (IoT) Based Activity Recognition Strategies in Smart Homes: A Review [J].
Babangida, Lawal ;
Perumal, Thinagaran ;
Mustapha, Norwati ;
Yaakob, Razali .
IEEE SENSORS JOURNAL, 2022, 22 (09) :8327-8336
[44]   Latent feature learning for activity recognition using simple sensors in smart homes [J].
Guilin Chen ;
Aiguo Wang ;
Shenghui Zhao ;
Li Liu ;
Chih-Yung Chang .
Multimedia Tools and Applications, 2018, 77 :15201-15219
[45]   Latent feature learning for activity recognition using simple sensors in smart homes [J].
Chen, Guilin ;
Wang, Aiguo ;
Zhao, Shenghui ;
Liu, Li ;
Chang, Chih-Yung .
MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (12) :15201-15219
[46]   Enhanced Online Segmentation and Performance Evaluation Method for Real-Time Activity Recognition in Smart Homes [J].
Ramadan, Abbas ;
Said, Farida ;
De lamotte, Florent Frizon .
2024 IEEE EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL AND HEALTH INFORMATICS, BHI, 2024,
[47]   A Graph-Attention-Based Method for Single-Resident Daily Activity Recognition in Smart Homes [J].
Ye, Jiancong ;
Jiang, Hongjie ;
Zhong, Junpei .
SENSORS, 2023, 23 (03)
[48]   Combining emerging patterns with random forest for complex activity recognition in smart homes [J].
Hadi Tabatabaee Malazi ;
Mohammad Davari .
Applied Intelligence, 2018, 48 :315-330
[49]   Human Activity Recognition in Smart Home using Deep Learning Models [J].
Diallo, Abdoulaye ;
Diallo, Cherif .
2021 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE (CSCI 2021), 2021, :1511-1515
[50]   A Novel Human Activity Recognition and Prediction in Smart Home Based on Interaction [J].
Du, Yegang ;
Lim, Yuto ;
Tan, Yasuo .
SENSORS, 2019, 19 (20)