Indexed by:
Abstract:
The activity management of the elderly is of great significance to their physical health. However, the traditional manual monitoring method requires a lot of manpower and material resources. Therefore, in this work, we predicted the activity status of elderly people living alone based on the data collected by wearable devices. The data used were collected by battery-free wearable sensors of 14 healthy elderly people aged 66 to 86 provided by Shinomoto Torres. Firstly, we analyzed the effectiveness of features based on Spearman. In order to capture different activity states, we designed a decision tree based on entropy to distinguish behaviors with different speed states. Compared with other advanced models, the decision tree has the best performance in K-fold, with an accuracy rate of 98.98%.
Keyword:
Reprint Author's Address:
Email:
Source :
2022 INTERNATIONAL CONFERENCE ON BIG DATA, INFORMATION AND COMPUTER NETWORK (BDICN 2022)
Year: 2022
Page: 382-386
Cited Count:
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 2
Affiliated Colleges: