Accurate energy expenditure estimation using smartphone sensors

Abstract

Accurate and online Energy Expenditure Estimation (EEE) utilizing small wearable sensors is a difficult task with most existing schemes. In this work, we focus on accurate EEE for tracking ambulatory activities of a common smartphone user. We used existing smartphone sensors (accelerometer and barometer sensor), sampled at low frequency, to accurately detect EEE. Using Artificial Neural Networks, a machine learning technique, a generic regression model for EEE is built that yields upto 83% correlation with actual Energy Expenditure (EE). Using barometer data, in addition to accelerometry is found to significantly improve EEE performance (upto 10%). We compare our results against state-of-the-art Calorimetry Equations (CE) and consumer electronics devices (Fitbit and Nike+ Fuel Band).