Khataeipour Seyed Javad, Anaraki Javad Rahimipour, Bozorgi Arastoo, Rayner Machel, A Basset Fabien, Fuller Daniel
Department of Computer Science, Faculty of Science, Memorial University of Newfoundland, St. John's, Newfoundland, Canada.
Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada.
BMJ Open Sport Exerc Med. 2022 May 9;8(2):e001242. doi: 10.1136/bmjsem-2021-001242. eCollection 2022.
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.
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.
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.
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.
本研究使用机器学习（ML）开发利用智能手机估计活动类型/强度的方法，评估这些模型对活动进行分类的准确性，并评估三个不同佩戴位置之间准确性的差异。
招募了48名参与者，让他们在三个不同位置携带三星手机完成一系列活动：背包、右手和右口袋。要求他们以三种代谢当量任务（METs）、五种METs和七种METs的强度进行坐、躺、走和跑。收集原始加速度计数据。我们使用R语言的活动计数包来计算活动计数，并根据原始加速度计数据生成新特征。我们评估并比较了几种ML算法；使用caret包（V.6.0 - 86）的随机森林（RF）、支持向量机、朴素贝叶斯、决策树、线性判别分析和k近邻算法。将原始加速度计数据和计算出的特征相结合可提高模型准确性。
使用原始加速度计数据时，RF模型在右口袋位置的准确率为92.90%，右手位置为89%，背包位置为90.8%。使用活动计数时，RF模型在右口袋位置的准确率为51.4%，右手位置为48.5%，背包位置为52.1%。
我们的结果表明，使用智能手机测量身体活动对于估计活动类型/强度是准确的，并且ML方法，如结合特征工程技术的RF，可以在实验室环境中准确地对身体活动强度水平进行分类。
