Unsupervised detection and analysis of changes in everyday physical activity data

Gina Sprint; Diane J Cook; Maureen Schmitter-Edgecombe

doi:10.1016/j.jbi.2016.07.020

Back

Unsupervised detection and analysis of changes in everyday physical activity data

Journal article

Open access

Peer reviewed

Unsupervised detection and analysis of changes in everyday physical activity data

Gina Sprint, Diane J Cook and Maureen Schmitter-Edgecombe

Journal of biomedical informatics, Vol.63, pp.54-65

10/2016

DOI: https://doi.org/10.1016/j.jbi.2016.07.020

Handle:

https://hdl.handle.net/2376/103867

PMID: 27471222

Files and links (1)

url

https://doi.org/10.1016/j.jbi.2016.07.020View

Published (Version of record) Open

Abstract

Data mining

Change point detection

Physical activity monitoring

Wearable sensors

Unsupervised learning

[Display omitted] •A framework for detecting and analyzing changes in physical activity time series data.•A method to evaluate if the detected changes are representative of a significant lifestyle modification.•Evaluation based on synthetic data and real-world Fitbit data collected from older adults. Sensor-based time series data can be utilized to monitor changes in human behavior as a person makes a significant lifestyle change, such as progress toward a fitness goal. Recently, wearable sensors have increased in popularity as people aspire to be more conscientious of their physical health. Automatically detecting and tracking behavior changes from wearable sensor-collected physical activity data can provide a valuable monitoring and motivating tool. In this paper, we formalize the problem of unsupervised physical activity change detection and address the problem with our Physical Activity Change Detection (PACD) approach. PACD is a framework that detects changes between time periods, determines significance of the detected changes, and analyzes the nature of the changes. We compare the abilities of three change detection algorithms from the literature and one proposed algorithm to capture different types of changes as part of PACD. We illustrate and evaluate PACD on synthetic data and using Fitbit data collected from older adults who participated in a health intervention study. Results indicate PACD detects several changes in both datasets. The proposed change algorithms and analysis methods are useful data mining techniques for unsupervised, window-based change detection with potential to track users’ physical activity and motivate progress toward their health goals.

Metrics

6 Record Views

See more details

Details

Title: Unsupervised detection and analysis of changes in everyday physical activity data
Creators: Gina Sprint - School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, United States
Diane J Cook - School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, United States
Maureen Schmitter-Edgecombe - Department of Psychology, Washington State University, Pullman, WA, United States
Publication Details: Journal of biomedical informatics, Vol.63, pp.54-65
Academic Unit: Psychology, Department of; Electrical Engineering and Computer Science, School of
Publisher: Elsevier Inc
Identifiers: 99900546878801842
Language: English
Resource Type: Journal article