JSM 2011 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Abstract Details

Activity Number: 122
Type: Contributed
Date/Time: Monday, August 1, 2011 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract - #302204
Title: Accelerometer-Based Prediction of Activity for Epidemiological Research
Author(s): Jiawei Bai*+ and Ciprian Crainiceanu and Brian Caffo and Thomas A. Glass
Companies: The Johns Hopkins University and The Johns Hopkins University and The Johns Hopkins University and The Johns Hopkins University
Address: 615 N. Wolfe Street, Baltimore, MD, 21205,
Keywords: Signal Processing ; Accelerometer ; Acceleration ; Activity Prediction
Abstract:

We introduce statistical methods to quantify and classify daily activity using accelerometers. The methods are complimentary to the current standard based on the Activities of Daily Living (ADL) questionnaire, which suffers fundamental problems, such as memory and selection bias. In particular, we introduce models to predict several types of activity based accelerometers attached to the subject's waist. We show that simple means and standard deviations of acceleration at each second can be effectively used to distinguish between active and sedentary periods. Analysis of spectrum of the acceleration is used to locate walking time periods. Validation is provided to quantify the model accuracy of prediction.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2011 program




2011 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.