Detecting Falls with X-Factor Hidden Markov Models

TL;DR

This paper introduces X-Factor Hidden Markov Models (XHMMs) for fall detection using wearable sensors, effectively identifying falls without requiring fall-specific training data by modeling unseen falls through inflated observation covariances.

Contribution

The paper proposes novel XHMM approaches that model unseen falls with inflated covariances and a cross-validation method to estimate these covariances using only normal activity data.

Findings

High fall detection rates achieved without fall training data

Traditional thresholding methods are ineffective for unseen fall detection

Supervised classifiers perform poorly with limited fall data

Abstract

Identification of falls while performing normal activities of daily living (ADL) is important to ensure personal safety and well-being. However, falling is a short term activity that occurs infrequently. This poses a challenge to traditional classification algorithms, because there may be very little training data for falls (or none at all). This paper proposes an approach for the identification of falls using a wearable device in the absence of training data for falls but with plentiful data for normal ADL. We propose three `X-Factor' Hidden Markov Model (XHMMs) approaches. The XHMMs model unseen falls using "inflated" output covariances (observation models). To estimate the inflated covariances, we propose a novel cross validation method to remove "outliers" from the normal ADL that serve as proxies for the unseen falls and allow learning the XHMMs using only normal activities. We tested the proposed XHMM approaches on two activity recognition datasets and show high detection rates for falls in the absence of fall-specific training data. We show that the traditional method of choosing a threshold based on maximum of negative of log-likelihood to identify unseen falls is ill-posed for this problem. We also show that supervised classification methods perform poorly when very limited fall data are available during the training phase.