Fall-detection through vertical velocity thresholding using a tri-axial accelerometer characterized using an optical motion-capture system

Abstract

Falls in the elderly population are a major problem for today's society. The immediate automatic detection of such events would help reduce the associated consequences of falls. This paper describes the development of an accurate, accelerometer-based fall detection system to distinguish between Activities of Daily Living (ADL) and falls. It has previously been shown that falls can be distinguished from normal ADL through vertical velocity thresholding using an optical motion capture system. In this study however accurate vertical velocity profiles of the trunk were generated by simple signal processing of the signals from a tri-axial accelerometer (TA). By recording simulated falls onto crash mats and ADL performed by 5 young healthy subjects, using both a single chest mounted TA and using an optical motion capture system, the accuracy of the vertical velocity profiles was assessed. Data analysis was performed using MATLAB to determine the peak velocities recorded and RMS error during four different fall and six ADL types. Results show high correlations and low percentage errors between the vertical velocity profiles generated by the TA to those recorded using the optical motion capture system. In addition, through thresholding of the vertical velocity profiles generated using the TA at -1.3m/s, falls can be distinguished from normal ADL with 100% sensitivity and specificity.

Evaluation of waist-mounted tri-axial accelerometer based fall-detection algorithms during scripted and continuous unscripted activities

“…POSTURE is measured using the dot-product method or the vertical z-axis; both use the same temporal and postural thresholds. VELOCITY is measured using the vertical velocity estimate, which is produced using the method outlined by Bourke et al (2008a). Here a ''day'' refers to the number of waking hours.…”

“…A vertical velocity estimate, V ve , is obtained through numerical integration of the RSS signal with the magnitude of static acceleration (gravity) subtracted (Bourke et al, 2008a).…”

REDLE: A Platform in the Cloud for Elderly Fall Detection and Push Response Tracking

“…A fall is detected when the measured vertical velocity v 0 is lower than −0.7 m/s, following an empirical analysis on activities of daily living (ADLs) data by Bourke and colleagues [15,19].…”

Development of a fall detection algorithm based on a tri-axial accelerometer

“…Do-Un Jeong et al (2007) used SVM and DSVM (differential signal vector magnitude) to distinguish activities and analyzed acceleration of three axes to judge stationary posture [2]. Alan K. Bourke et al (2010) evaluated a variety of existing and novel fall detection algorithms, showing that using an algorithm employing Velocity [3,4] + Impact + Posture can achieve a low false-positive rate with a sensitivity of 94.6%and a specificity of 100% [5,8].…”