Posture tracking using a machine learning algorithm for a home AAL environment
- The number of home office workers sitting for many hours is increasing. The sensor chair is tracking users’ sitting behavior which the help of pressure sensors and tries to avoid wrong postures which may cause diseases. The system provides live monitoring of the pressure distribution via web interface, as well as sitting posture prediction in real time. Posture analysis is realized through machine learning algorithm using a decision tree classifier that is compared to a random forest. Data acquisition and aggregation for the learning process happens with a mobile app adding users biometrical data and the taken sitting posture as label. The sensor chair is able to differentiate between an arched back, a neutral posture or a laid back position taken on the chair. The classifier achieves an accuracy of 97.4% on our test set and is comparable to the performance of the random forest with 98.9%.
| Author: | Maksim Sandybekov, Clemens Grabow, Maksym GaidukORCiD, Ralf SeepoldORCiDGND |
|---|---|
| URL: | https://doi.org/10.1007/978-981-13-8303-8_31 |
| ISBN: | 978-981-13-8302-1 |
| ISBN: | 978-981-13-8303-8 |
| Parent Title (English): | Intelligent Decision Technologies 2019, Proceedings of the 11th KES International Conference on Intelligent Decision Technologies (KES-IDT 2019) - Volume 2 ; (Smart Innovation, Systems and Technologies ; 143) |
| Publisher: | Springer |
| Place of publication: | Singapore |
| Document Type: | Article |
| Language: | English |
| Year of Publication: | 2019 |
| Release Date: | 2019/07/11 |
| Tag: | Posture tracking; AAL; IoT |
| Edition: | First online: 2 June 2019 |
| First Page: | 337 |
| Last Page: | 347 |
| Institutes: | Fakultät Informatik |
| DDC functional group: | 000 Allgemeines, Informatik, Informationswissenschaft |
| 600 Technik, Medizin, angewandte Wissenschaften | |
| Open Access?: | Nein |
| Licence (German): |  Urheberrechtlich geschützt |
