Predicting lying, sitting and walking at different intensities using smartphone accelerometers at three different wear locations: hands, pant pockets, backpack

Seyed Javad Khataeipour; Javad Rahimipour Anaraki; Arastoo Bozorgi; Machel Rayner; Fabien A Basset; Daniel Fuller

doi:10.1136/bmjsem-2021-001242

Predicting lying, sitting and walking at different intensities using smartphone accelerometers at three different wear locations: hands, pant pockets, backpack

BMJ Open Sport Exerc Med. 2022 May 9;8(2):e001242. doi: 10.1136/bmjsem-2021-001242. eCollection 2022.

Authors

Seyed Javad Khataeipour¹, Javad Rahimipour Anaraki², Arastoo Bozorgi¹, Machel Rayner³, Fabien A Basset³, Daniel Fuller^{1

3}

Affiliations

¹ Department of Computer Science, Faculty of Science, Memorial University of Newfoundland, St. John's, Newfoundland, Canada.
² Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada.
³ School of Human Kinetics and Recreation, Memorial University of Newfoundland, St. John's, Newfoundland, Canada.

Abstract

Objective: This study uses machine learning (ML) to develop methods for estimating activity type/intensity using smartphones, to evaluate the accuracy of these models for classifying activity, and to evaluate differences in accuracy between three different wear locations.

Method: Forty-eight participants were recruited to complete a series of activities while carrying Samsung phones in three different locations: backpack, right hand and right pocket. They were asked to sit, lie down, walk and run three Metabolic Equivalent Task (METs), five METs and at seven METs. Raw accelerometer data were collected. We used the R, activity counts package, to calculate activity counts and generated new features based on the raw accelerometer data. We evaluated and compared several ML algorithms; Random Forest (RF), Support Vector Machine, Naïve Bayes, Decision Tree, Linear Discriminant Analysis and k-Nearest Neighbours using the caret package (V.6.0-86). Using the combination of the raw accelerometer data and the computed features leads to high model accuracy.

Results: Using raw accelerometer data, RF models achieved an accuracy of 92.90% for the right pocket location, 89% for the right hand location and 90.8% for the backpack location. Using activity counts, RF models achieved an accuracy of 51.4% for the right pocket location, 48.5% for the right hand location and 52.1% for the backpack location.

Conclusion: Our results suggest that using smartphones to measure physical activity is accurate for estimating activity type/intensity and ML methods, such as RF with feature engineering techniques can accurately classify physical activity intensity levels in laboratory settings.

Keywords: Keywords.