TitleA statistical estimation framework for energy expenditure of physical activities from a wrist-worn accelerometer.
Publication TypeJournal Article
Year of Publication2016
AuthorsLohit, S, Toledo, MJ, Buman, MP, Turaga, P
JournalAnnu Int Conf IEEE Eng Med Biol Soc
Date Published2016 Aug
KeywordsAccelerometry, Adolescent, Adult, Algorithms, Energy Metabolism, Exercise, Female, Humans, Male, Middle Aged, Models, Statistical, Monitoring, Ambulatory, Motor Activity, Probability, Reference Values, Regression Analysis, Support Vector Machine, Wrist, Young Adult

Energy expenditure (EE) estimation from accelerometer-based wearable sensors is important to generate accurate assessment of physical activity (PA) in individuals. Approaches hitherto have mainly focused on using accelerometer data and features extracted from these data to learn a regression model to predict EE directly. In this paper, we propose a novel framework for EE estimation based on statistical estimation theory. Given a test sequence of accelerometer data, the probability distribution on the PA classes is estimated by a classifier and these predictions are used to estimate EE. Experimental evaluation, performed on a large dataset of 152 subjects and 12 activity classes, demonstrates that EE can be estimated accurately using our framework.

Alternate JournalAnnu Int Conf IEEE Eng Med Biol Soc
PubMed ID28268862