Open AccessRandom forest-based physical activities recognition by using wearable sensors
Author(s) -
Junjie Zhang,
CAI SHENGHAO,
Jie Xu,
Hua Yuan
Publication year - 2022
Publication title -
industria textilă
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.281
H-Index - 14
ISSN - 1222-5347
DOI - 10.35530/it.073.01.20215
Subject(s) - random forest , accelerometer , gyroscope , classifier (uml) , computer science , wearable computer , artificial intelligence , activity recognition , machine learning , wearable technology , pattern recognition (psychology) , sitting , engineering , medicine , pathology , embedded system , aerospace engineering , operating system
Physical activity recognition (PAR) is a topic worthy of attention. In order to improve the practicality of wearable sensorsfor recognition, in this study, we propose an approach to create a classifier of PAR based on the collected data. At first,we discuss how features extracted from the accelerometer and gyroscope contribute to distinguish different activities,including walking, walking upstairs, walking downstairs, sitting, standing, laying, and also provide an analytical methodemployed for this purpose. Then, a supervised machine learning method, random forest algorithm, is adopted to createa classifier to recognize physical activities based on the extracted features. Lastly, the performances of the constructedclassifier are evaluated and compared with other methods. The performance evaluation shows the classifier trained byrandom forest algorithm are better than other algorithms, and its overall recognition rate reaches 93.75%. In addition,our approach also has strong potential for applications in smart textiles.