Review of Fall Detection Techniques: A Data Availability Perspective

TL;DR

This paper reviews fall detection techniques focusing on data availability challenges, proposing a taxonomy based on training data availability, and discusses future research directions in the field.

Contribution

It introduces a novel taxonomy for fall detection methods based on data availability, independent of sensor types, and reviews related literature within this framework.

Findings

Treating falls as abnormal activities is a promising research direction.

Data scarcity significantly impacts fall detection model performance.

Open research problems include data collection and transfer learning for falls.

Abstract

A fall is an abnormal activity that occurs rarely; however, missing to identify falls can have serious health and safety implications on an individual. Due to the rarity of occurrence of falls, there may be insufficient or no training data available for them. Therefore, standard supervised machine learning methods may not be directly applied to handle this problem. In this paper, we present a taxonomy for the study of fall detection from the perspective of availability of fall data. The proposed taxonomy is independent of the type of sensors used and specific feature extraction/selection methods. The taxonomy identifies different categories of classification methods for the study of fall detection based on the availability of their data during training the classifiers. Then, we present a comprehensive literature review within those categories and identify the approach of treating a fall as an abnormal activity to be a plausible research direction. We conclude our paper by discussing several open research problems in the field and pointers for future research.