Normalization and Extraction of Interpretable Metrics from Raw Accelerometry Data

• Activity Number: 194
• Type: Contributed
• Date/Time: Monday, August 5, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Jiawei Bai*+ and Bing He and Thomas A. Glass and Ciprian M. Crainiceanu
• Companies: Johns Hopkins University and Johns Hopkins University and Johns Hopkins University and The Johns Hopkins University
• Keywords: Activity Intensity ; Movelets ; Movement ; Signal Processing ; Time Active ; Accelerometer

Abstract

We introduce a set of metrics for human activity based on high density acceleration recordings from a hip worn tri-axial accelerometer. Data were collected from 34 older subjects who wore the devices for up to seven days during their daily living activities. We propose simple metrics that are based on two concepts: 1) time active, a measure of the length of time when the subject activity is distinguishable from rest; and 2) activity intensity, a measure of relative amplitude of activity relative to rest. All measurements are normalized (have the same interpretation across subjects and days), easy to explain and implement, and reproducible across platforms and software implementations. This is a non-trivial task in an observational study where raw acceleration can be dramatically affected by the location of the device, angle with respect to body, body geometry, subject-specific size and direction of energy produced, time, battery voltage, and other unpredictable, but often occurring, events. The results of a small study of the association between our activity metrics and health outcomes shows promising initial results.