Energy Expenditure Estimation using Smartphone Body Sensors

Abstract

Energy Expenditure Estimation (EEE) is an important step in tracking personal activity and preventing chronic diseases such as obesity, diabetes and cardiovascular diseases. Accurate and online EEE utilizing small wearable sensors is a difficult task, primarily because most existing schemes work offline or using heuristics. In this work, we focus on accurate EEE for tracking ambulatory activities (walking, standing, climbing upstairs or downstairs) 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, we build a generic regression model for EEE that yields upto 89% correlation with actual Energy Expenditure (EE). Using barometer data, in addition to accelerometry is found to significantly improve EEE performance (upto 15%). We compare our results against stateof-the-art Calorimetry Equations (CE) and consumer electronics devices (Fitbit and Nike+ Fuel Band). We were able to demonstrate the superior accuracy achieved by our algorithm. The results were calibrated against COSMED K4b2 calorimeter readings. Categories and Subject Descriptors J.3 [Computer Applications]: Life & medical sciences-Health General Terms Experimentation, Algorithms.

Accuracy of Pedometry on a Head-mounted Display

“…However, with the phone carried in the back pocket, the likelihood of undercounting steps increases, due to extra oscillations caused by the relaxation of the gluteus maximus during the walking cycle. A related study found smartphones to be more accurate for energy expenditure prediction than wearable accelerometers [13]. Smartphones feature barometers which can be appropriated to distinguish between walking up or down stairs which generate different amounts of energy expenditure.…”

“…Wearables typically support eyes-and hands-free interaction, which allows them to be used in active contexts, such as walking or running. Pedometry, i.e, step counting, is used in various mobility related applications, such as physical activity tracking [13] or infrastructure-free indoor navigation [8]. Pedometry can be achieved with wearable accelerometers, e.g., Fitbit [2], or using inertial sensors that have become ubiquitous in smartphones [6] and HMDs.…”

The editable self

“…For example, [6] attempts to work on data compression on mobile devices to improve battery life. Similarly, the work of [7] explored more accurate Energy Expenditure Estimates (EEE) of small wearable sensors. The limitations of personal fitness devices has been noted by [8], who state that "sensor measures are subject to various limitations like resolution errors, calibration variability, response time" and "precision depending on working conditions".…”

GreenMonitor: Extending battery life for continuous heart rate monitoring in smartwatches

“…Misra and Lim [16] used an asynchronous querying technique to save 70% energy. Pande et al [18] proposed the use of smartphone sensors at reduced frequency for detecting Energy Expenditure Estimation. On the other hand the work by Wang et al [25] offload data processing to the cloud for better energy management.…”