Efficient Fall Detection Method Using Time-of-Flight Sensors and Decision Tree Model
Cheng-Yi Huang, Yuan-Hao Ho, Yu-Chi Hsiung, Peng-Ting Chen, Pi‐Shan Sung, Chih‐Lung Lin · 2023
This work presents a shoe-mounted Time-of-Flight (ToF) sensors system for fall detection, utilizing only two ToF sensors. These ToF sensors measure the distance between the sensors and the ground, which can be used for fall detection. The range data captured by the sensors are discretized by the quantile-based method and classified by the decision tree model. The proposed system employs a fall detection algorithm, resulting in low computing complexity, which makes the system suitable for implementation in low-power wearable devices. Experiment result shows that the decision tree model with proposed quantile-based discretization method, achieves an accuracy of 99.08% in distinguishing activities of daily living (ADLs) and falls among different person.