Fall Detection using Biometric Information Based on Multi-Horizon Forecasting
Inkyung Kim, Daehee Kim, Sunyoung Kwon, Sheayun Lee, Jaekoo Lee · 2022 26th International Conference on Pattern Recognition (ICPR) · 2022
With the steady growth of the aging population, there has been increasing interest in the health of elderly people. In particular, a physical fall can be fatal for the elderly or result in complications that cause more serious physical and mental damage than the cause of the falls. For this reason, it is important to accurately predict the occurrence of abnormal behavior in advance. Although existing methods can be used to analyze general behavioral characteristics, personalized and customized behavioral prediction remains challenging. In this paper, we propose a customized pre-prediction method using sensor wearers’ biometric information as well as behavioral data reflecting the wearers’ unique behavioral characteristics. The technique is based on a temporal fusion transformers method [1] that can be effectively applied to multi-horizon forecasting. A performance evaluation was made to compare the effects of including and excluding biometric information to quantitatively evaluate the enhancement achieved by extending the prediction model. The use of additional biometric information enabled superior performance with 0.9702, 0.9702, 0.9702, 0.9883 in F-1 score, precision, recall respectively, which is all evaluation indicators. The code for the experiments can be found at the following GitHub address: https://github.com/IKKIM00/Fall_Detection_using_multihorizon_forecasting.