Research on ensemble learning algorithm for fall detection

Jinghua Wang; Yadong Liu; Xingshu Qiao; Xiaoliang Liu; Xin Zhao

doi:10.1117/12.3029267

6 May 2024 Research on ensemble learning algorithm for fall detection

Jinghua Wang, Yadong Liu, Xingshu Qiao, Xiaoliang Liu, Xin Zhao

Proceedings Volume 13107, Fourth International Conference on Sensors and Information Technology (ICSI 2024); 131073Q (2024) https://doi.org/10.1117/12.3029267
Event: Fourth International Conference on Sensors and Information Technology (ICSI 2024), 2024, Xiamen, China

Abstract

This research aims to address the issue of fall detection in the elderly using a wearable device-based fall detection system. Data is collected through acceleration sensors and barometric pressure sensors. After applying certain algorithms to the dataset, it was found that a single machine learning algorithm had poor generalization ability for fall detection. To improve classification accuracy, attempts were made to use ensemble learning algorithms for training and validation of the fall detection dataset. By employing Bagging and GBDT ensemble learning algorithms, the generalization ability of the model was successfully enhanced. On the validation set after 0.2 cross-validation, our model achieved an average accuracy of 99.28%, significantly improving the model's high performance and strong generalization ability.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jinghua Wang, Yadong Liu, Xingshu Qiao, Xiaoliang Liu, and Xin Zhao "Research on ensemble learning algorithm for fall detection", Proc. SPIE 13107, Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073Q (6 May 2024); https://doi.org/10.1117/12.3029267

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available