Estimating Energy Expenditure With Multiple Models Using Different Wearable Sensors

• Published in: IEEE journal of biomedical and health informatics Vol. 20; no. 4; pp. 1081 - 1087
• Main Authors: Cvetkovic, Bozidara, Milic, Radoje, Lustrek, Mitja
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accelerometers; Adult; Bicycling - physiology; Competition; Consumption; Data models; Energy Metabolism - physiology; Energy use; Estimation; Expenditures; Female; Heart rate; Humans; Legged locomotion; Machine Learning; Male; Models, Biological; Monitoring, Ambulatory - instrumentation; Monitoring, Ambulatory - methods; Motor Activity - physiology; pervasive computing; Regression; sensor fusion; Sensors; Sporting goods; State of the art; Temperature sensors; Walking - physiology; wearable sensors; Young Adult
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2015.2432911

This paper presents an approach to designing a method for the estimation of human energy expenditure (EE). The approach first evaluates different sensors and their combinations. After that, multiple regression models are trained utilizing data from different sensors. The EE estimation method designed in this way was evaluated on a dataset containing a wide range of activities. It was compared against three competing state-of-the-art approaches, including the BodyMedia Fit armband, the leading consumer EE estimation device. The results show that the proposed method outperforms the competition by up to 10.2 percentage points.