A Smartphone-Based Gait Data Collection System for the Prediction of Falls in Elderly Adults

Abstract

Falls prevention efforts for older adults have become increasingly important and are now a significant research effort. As part of the prevention effort, analysis of gait has become increasingly important. Data is typically collected in a laboratory setting using 3-D motion capture, which can be time consuming, invasive and requires expensive and specialized equipment as well as trained operators. Inertial sensors, which are smaller and more cost effective, have been shown to be useful in falls research. Smartphones now contain Micro Electro-Mechanical (MEM) Inertial Measurement Units (IMUs), which make them a compelling platform for gait data acquisition. This paper reports the development of an iOS app for collecting accelerometer data and an offline machine learning system to classify a subject, based on this data, as faller or non-faller based on their history of falls. The system uses the accelerometer data captured on the smartphone, extracts discriminating features, and then classifies the subject based on the feature vector. Through simulation, our preliminary and limited study suggests this system has an accuracy as high as 85%. Such a system could be used to monitor an at-risk person's gait in order to predict an increased risk of falling.