Energy Expenditure Estimation with Smartphone Body Sensors. Pande, A, Zeng, Y, Das, A, Mohapatra, P, Miyamoto, S, Seto, E, Henricson, E., & Han, J. In 8th International Conference on Body Area Networks (Bodynets) 2013, pages -, 2013. abstract bibtex Energy Expenditure Estimation is an important step in tracking personal activity and preventing chronic diseases such as obesity, diabetes and cardio-vascular diseases. Accurate and online EEE utilizing small wearable sensors is a difficult task with most existing schemes working 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.We used Artificial Neural Networks, a MachineLearning technique to 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 10%). We compare our results against state-of-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.
@inproceedings{ bodynets13,
title = {Energy Expenditure Estimation with Smartphone Body Sensors},
author = {A Pande and Y Zeng and A Das and P Mohapatra and S Miyamoto and E Seto and E.K. Henricson and J.J. Han},
booktitle = {8th International Conference on Body Area Networks (Bodynets) 2013},
pages = {-},
year = {2013},
keywords = {MobileHealthcare,MachineLearning},
abstract = {Energy Expenditure Estimation is an important step in tracking
personal activity and preventing chronic diseases such as
obesity, diabetes and cardio-vascular diseases. Accurate and
online EEE utilizing small wearable sensors is a difficult task
with most existing schemes working 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.We used
Artificial Neural Networks, a MachineLearning technique to
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 10%). We compare
our results against state-of-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.}
}
Downloads: 0
{"_id":{"_str":"53d68d6ef414ae191e00074e"},"__v":2,"authorIDs":["5457f0e12abc8e9f370008e9","54b03381b8c035d64c0006ae"],"author_short":["Pande, A","Zeng, Y","Das, A","Mohapatra, P","Miyamoto, S","Seto, E","Henricson, E.","Han, J."],"bibbaseid":"pande-zeng-das-mohapatra-miyamoto-seto-henricson-han-energyexpenditureestimationwithsmartphonebodysensors-2013","bibdata":{"abstract":"Energy Expenditure Estimation is an important step in tracking personal activity and preventing chronic diseases such as obesity, diabetes and cardio-vascular diseases. Accurate and online EEE utilizing small wearable sensors is a difficult task with most existing schemes working 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.We used Artificial Neural Networks, a MachineLearning technique to 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 10%). We compare our results against state-of-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.","author":["Pande, A","Zeng, Y","Das, A","Mohapatra, P","Miyamoto, S","Seto, E","Henricson, E.K.","Han, J.J."],"author_short":["Pande, A","Zeng, Y","Das, A","Mohapatra, P","Miyamoto, S","Seto, E","Henricson, E.","Han, J."],"bibtex":"@inproceedings{ bodynets13,\n title = {Energy Expenditure Estimation with Smartphone Body Sensors},\n author = {A Pande and Y Zeng and A Das and P Mohapatra and S Miyamoto and E Seto and E.K. Henricson and J.J. Han},\n booktitle = {8th International Conference on Body Area Networks (Bodynets) 2013},\n pages = {-},\n year = {2013},\n keywords = {MobileHealthcare,MachineLearning},\n abstract = {Energy Expenditure Estimation is an important step in tracking\r\npersonal activity and preventing chronic diseases such as\r\nobesity, diabetes and cardio-vascular diseases. Accurate and\r\nonline EEE utilizing small wearable sensors is a difficult task\r\nwith most existing schemes working offline or using heuristics.\r\nIn this work, we focus on accurate EEE for tracking ambulatory\r\nactivities (walking, standing, climbing upstairs or\r\ndownstairs) of a common smartphone user. We used existing\r\nsmartphone sensors (accelerometer and barometer sensor),\r\nsampled at low frequency, to accurately detect EEE.We used\r\nArtificial Neural Networks, a MachineLearning technique to\r\nbuild a generic regression model for EEE that yields upto\r\n89%correlation with actual Energy Expenditure (EE). Using\r\nbarometer data, in addition to accelerometry is found to significantly\r\nimprove EEE performance (upto 10%). We compare\r\nour results against state-of-the-art Calorimetry Equations\r\n(CE) and consumer electronics devices (Fitbit and Nike+\r\nFuel Band). We were able to demonstrate the superior accuracy\r\nachieved by our algorithm. The results were calibrated\r\nagainst COSMED K4b2 calorimeter readings.}\n}","bibtype":"inproceedings","booktitle":"8th International Conference on Body Area Networks (Bodynets) 2013","id":"bodynets13","key":"bodynets13","keywords":"MobileHealthcare,MachineLearning","pages":"-","title":"Energy Expenditure Estimation with Smartphone Body Sensors","type":"inproceedings","year":"2013","bibbaseid":"pande-zeng-das-mohapatra-miyamoto-seto-henricson-han-energyexpenditureestimationwithsmartphonebodysensors-2013","role":"author","urls":{},"keyword":["MobileHealthcare","MachineLearning"],"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"http://www.cs.ucdavis.edu/~amit/pamit2.bib","creationDate":"2014-07-28T17:50:38.868Z","downloads":0,"keywords":["wh","ml","mobile healthcare","machine learning","mobilehealthcare","machinelearning"],"search_terms":["energy","expenditure","estimation","smartphone","body","sensors","pande","zeng","das","mohapatra","miyamoto","seto","henricson","han"],"title":"Energy Expenditure Estimation with Smartphone Body Sensors","year":2013,"dataSources":["eaD4cvM8ipWoG4mZN"]}