Measuring physical activity in obese populations using accelerometry

Gerrard-Longworth, SP

Abstract

The thesis is concerned with objectively measuring human physical activity through
accelerometry, and compares the effectiveness of algorithms between obese and non-obese
groups. The thesis comprises three studies:
Classification of Aerobic and Gym-based Exercises from Accelerometer Output. This study
investigated whether accurate classification could be achieved from hip- or ankle-mounted
accelerometers for a programme of aerobic exercises and free-living activities. It also
examined whether accuracy was affected by obesity, and whether a single classifier could be
applied across BMI groups. The study achieved high classification accuracies (85% for hip
and 94% for ankle) for both obese and normal BMI groups using the same approach across
groups.
Walking Speed Estimation Using Accelerometry. This study aimed to develop a speed
estimation model that was applicable across BMI groups, and which utilised a hip-mounted
accelerometer. To achieve this, multiple accelerometer signal features were evaluated for use
in a linear speed estimation model, and performance was compared between obese and
normal BMI groups. The speed estimation algorithm achieved overall RMSE of 0.08ms-1
for
a mixed BMI group, which is comparable with previous research using homogeneous groups.
Prediction of Energy Expenditure from Accelerometer Output. This study aimed to identify
physiological and anthropometric parameters for use in an improved energy expenditure
estimation model. Model performance was tested on a mixed BMI group. The energy
expenditure prediction model incorporating subject attributes showed around 20%
improvement over the standard model.
This research found that current approaches to activity classification using accelerometry are
equally applicable to obese groups and normal BMI groups. Walking speed prediction was
shown to be possible from a hip-mounted accelerometer for both obese and normal BMI
groups. Energy expenditure estimation is improved by including subject-specific parameters
in the prediction model. Accelerometry is, therefore, a suitable tool for measuring different
aspects of physical activity for obese and mixed BMI groups.

Citation

Gerrard-Longworth, S. (in press). Measuring physical activity in obese populations using accelerometry. (Thesis). University of Salford

• Thesis Type: Thesis
• Acceptance Date: May 1, 2015
• Deposit Date: Jul 27, 2015
• Publicly Available Date: Jul 27, 2015
• Additional Information: Projects : SSHOES: European Community's Seventh Framework Programme (FP7/2007-2013) under SSHOES project
• Award Date: May 1, 2015