VO<inf>2</inf> estimation using 6-axis motion sensor with sports activity classification

Abstract

In this paper, we focus on oxygen consumption (VO2) estimation using 6-axis motion sensor (3-axis accelerometer and 3-axis gyroscope) for people playing sports with diverse intensities. The VO2 estimated with a small motion sensor can be used to calculate the energy expenditure, however, its accuracy depends on the intensities of various types of activities. In order to achieve high accuracy over a wide range of intensities, we employ an estimation framework that first classifies activities with a simple machine-learning based classification algorithm. We prepare different coefficients of linear regression model for different types of activities, which are determined with training data obtained by experiments. The best-suited model is used for each type of activity when VO2 is estimated. The accuracy of the employed framework depends on the trade-off between the degradation due to classification errors and improvement brought by applying separate, optimum model to VO2 estimation. Taking this trade-off into account, we evaluate the accuracy of the employed estimation framework by using a set of experimental data consisting of VO2 and motion data of people with a wide range of intensities of exercises, which were measured by a VO2 meter and motion sensor, respectively. Our numerical results show that the employed framework can improve the estimation accuracy in comparison to a reference method that uses a common regression model for all types of activities.

A development framework for decision support systems in high-performance sport

“…In sport, DSS have been used for purposes such as scheduling optimization (S. Robertson & Joyce, 2018;S. J. Robertson & Joyce, 2015), sport-modality classification (Hogarth, Payton, Van de Vliet, Connick, & Burkett, 2018), skill/movement evaluation and classification (Clermont, Osis, Phinyomark, & Ferber, 2017;Kovalchik & Reid, 2018;Novatchkov & Baca, 2013;Pernek, Kurillo, Stiglic, & Bajcsy, 2015;Richter, King, Falvey, & Franklyn-Miller, 2018;Rindal, Seeberg, Tjonnas, Haugnes, & Sandbakk, 2017;Whiteside, Cant, Connolly, & Reid, 2017;Woods, Veale, Fransen, Robertson, & Collier, 2018;Wundersitz et al, 2015), assessing decision-making and motor control (Maselli et al, 2017), talent identification and team selection (M. Lai, Meo, Schifanella, & Sulis, 2018;B Ofoghi, Zeleznikow, Macmahon, & Dwyer, 2013;Taha, Musa, Abdul Majeed, Alim, & Abdullah, 2018;Woods et al, 2018;Xie, Xu, Nie, & Nie, 2017), biomechanical analysis (Bertani, Cappello, Benedetti, Simoncini, & Catani, 1999;Ertelt, Solomonovs, & Gronwald, 2018;Kianifar, Lee, Raina, & Kulic, 2016;Kipp, Giordanelli, & Geiser, 2018;Richter et al, 2018), assessing injury risk (Carey et al, 2018;Li, Huang, Wang, Yu, & Ao, 2016;Lopez-Valenciano et al, 2018;Rossi et al, 2018;Ruddy et al, 2018;Thornton, Delaney, Duthie, & Dascombe, 2017) & Robertson, 2017;Jaspers et al, 2018;Nagata et al, 2016), or assessing fatigue…”

A Survey on Energy Expenditure Estimation Using Wearable Devices

“…State-of-the-art of AR is out of the scope of this paper, but it is more advanced than EEE because there are several open datasets [31,73,138], competitions [15,54], tutorials [26] and surveys [74,127]. Different approaches have been developed and accuracy is normally in the range [80][81][82][83][84][85][86][87][88][89][90][91][92][93][94][95]% when the number of activities to recognize is less than 15 [127] depending also on the modality and number of sensors.…”

Recent Advances in AI based Automated Personalized Nutrition System: Future Need of Healthcare

“…Validation results shows reduction in errors by 8% in only visual and 18% in only accelerometer conditions. Energy consumption in the body is directly proportional to the oxygen consumption hence T. Nagata et al [30] proposed oxygen consumption estimation with the support of 6-axis motion sensor which is the combination of 3-axis accelerometer and 3-axis gyroscope and validated results of this method with machine learning algorithm. Comparative analysis of all the reviewed articles are shown in table-3.…”