Optimal threshold selection for threshold-based fall detection algorithms with multiple features

As people get older, their bodies go through multiple changes that make them more fragile and susceptible to falls. The population of elderly people living alone is increasing worldwide, and this imposes a risk that a potential fall may happen without receiving prompt attention of a healthcare provider or caregiver. To solve this problem, various solutions for automatic fall detection have been proposed that recognise when a person falls and send alarms to someone that could provide quick help. One group of automatic fall detectors use wearable sensors attached to a person's body to measure body accelerations and then to distinguish falls from normal activities of daily living (ADLs) with some of the threshold or machine learning based algorithms. In threshold-based algorithms, features are calculated from measured accelerations and they are evaluated with a set of rules to check whether a fall has happened. The choice of fixed thresholds is thereby important for the overall efficiency of the algorithm. In our previous works in the field of fall detection, we have analysed methods for the determination of appropriate threshold levels for algorithms based on one acceleration-based feature. In this paper, we present a method for setting optimal thresholds in algorithms that use multiple acceleration-derived features. We demonstrate the efficiency of algorithms with thresholds set according to the newly presented method when tested on our dataset of accelerations measured during simulated falls and ADLs.