Designing a Robust Activity Recognition Framework for Health and Exergaming Using Wearable Sensors

• Published in: IEEE journal of biomedical and health informatics Vol. 18; no. 5; pp. 1636 - 1646
• Main Authors: Alshurafa, Nabil, Wenyao Xu, Liu, Jason J., Ming-Chun Huang, Mortazavi, Bobak, Roberts, Christian K., Sarrafzadeh, Majid
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-09-2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accelerometers; Accelerometry - instrumentation; Adult; Algorithms; Approximation algorithms; Approximation methods; Classification; Cluster Analysis; clustering; Clustering algorithms; energy expenditure (EE); Exercise Therapy - instrumentation; exergaming; Feature extraction; Human Activities - classification; Humans; intensity-varying activity; Legged locomotion; mixture models; Monitoring, Ambulatory - instrumentation; Monitoring, Ambulatory - methods; stochastic approximation model; Stochastic Processes; Video Games; Young Adult
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2013.2287504

Detecting human activity independent of intensity is essential in many applications, primarily in calculating metabolic equivalent rates and extracting human context awareness. Many classifiers that train on an activity at a subset of intensity levels fail to recognize the same activity at other intensity levels. This demonstrates weakness in the underlying classification method. Training a classifier for an activity at every intensity level is also not practical. In this paper, we tackle a novel intensity-independent activity recognition problem where the class labels exhibit large variability, the data are of high dimensionality, and clustering algorithms are necessary. We propose a new robust stochastic approximation framework for enhanced classification of such data. Experiments are reported using two clustering techniques, K-Means and Gaussian Mixture Models. The stochastic approximation algorithm consistently outperforms other well-known classification schemes which validate the use of our proposed clustered data representation. We verify the motivation of our framework in two applications that benefit from intensity-independent activity recognition. The first application shows how our framework can be used to enhance energy expenditure calculations. The second application is a novel exergaming environment aimed at using games to reward physical activity performed throughout the day, to encourage a healthy lifestyle.