Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoders

A fall is an abnormal activity that occurs rarely, so it is hard to collect real data for falls. It is, therefore, difficult to use supervised learning methods to automatically detect falls. Another challenge in using machine learning methods to automatically detect falls is the choice of engineered features. In this paper, we propose to use an ensemble of autoencoders to extract features from different channels of wearable sensor data trained only on normal activities. We show that the traditional approach of choosing a threshold as the maximum of the reconstruction error on the training normal data is not the right way to identify unseen falls. We propose two methods for automatic tightening of reconstruction error from only the normal activities for better identification of unseen falls. We present our results on two activity recognition datasets and show the efficacy of our proposed method against traditional autoencoder models and two standard one-class classification methods. Keywords: detection 1. Introduction fall detection, one-class classification, autoencoders, anomaly Falls are a major cause of both fatal and nonfatal injury and a hindrance in living independently. Each year an estimated 424, 000 individuals die from falls globally and 37.3 million falls require medical attention [23]. Experiencing a fall may lead to a fear of falling [6], which in turn can result in lack of mobility, less productivity and reduced quality of life. There exist several commercial wearable devices to detect falls [24]; most of them use accelerometers to capture motion information. They normally come with an alarm button to manually contact a caregiver if the fall is not detected by the device.