Improving activity classification for health applications on mobile devices using active and semi-supervised learning

• Published in: 2010 4th International Conference on Pervasive Computing Technologies for Healthcare pp. 1 - 7
• Main Authors: Longstaff, Brent, Reddy, Sasank, Estrin, Deborah
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2010
• Subjects: Biomedical monitoring; Cardiac disease; Cardiovascular diseases; Machine learning algorithms; Mobile handsets; Patient monitoring; Semisupervised learning; Smart phones; Training data; User interfaces
• ISSN: 2153-1633
• DOI: 10.4108/ICST.PERVASIVEHEALTH2010.8851

Mobile phones' increasing ubiquity has created many opportunities for personal context sensing. Personal activity is an important part of a user's context, and automatically recognizing it is vital for health and fitness monitoring applications. Recording a stream of activity data enables monitoring patients with chronic conditions affecting ambulation and motion, as well as those undergoing rehabilitation treatments. Modern mobile phones are powerful enough to perform activity classification in real time, but they typically use a static classifier that is trained in advance or require the user to manually add training data after the application is on his/her device. This paper investigates ways of automatically augmenting activity classifiers after they are deployed in an application. It compares active learning and three different semi-supervised learning methods, self-learning, En-Co-Training, and democratic co-learning, to determine which show promise for this purpose. The results show that active learning, En-Co-Training, and democratic co-learning perform well when the initial classifier's accuracy is low (75-80%). When the initial accuracy is already high (90%), these methods are no longer effective, but they do not hurt the accuracy either. Overall, active learning gave the highest improvement, but democratic co-learning was almost as good and does not require user interaction. Thus, democratic co-learning would be the best choice for most applications, since it would significantly increase the accuracy for initial classifiers that performed poorly.