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

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.

Predicting lying, sitting, walking and running using Apple Watch and Fitbit data.

OBJECTIVES: This study's objective was to examine whether commercial wearable devices could accurately predict lying, sitting and varying intensities of walking and running. METHODS: We recruited a convenience sample of 49 participants (23 men and 26 women) to wear three devices, an Apple Watch Series 2, a Fitbit Charge HR2 and iPhone 6S. Participants completed a 65 min protocol consisting of 40 min of total treadmill time and 25 min of sitting or lying time. The study's outcome variables were six movement types: lying, sitting, walking self-paced and walking/running at 3 metabolic equivalents of task (METs), 5 METs and 7 METs. All analyses were conducted at the minute level with heart rate, steps, distance and calories from Apple Watch and Fitbit. These included three different machine learning models: support vector machines, Random Forest and Rotation forest. RESULTS: Our dataset included 3656 and 2608 min of Apple Watch and Fitbit data, respectively. Rotation Forest models had the highest classification accuracies for Apple Watch at 82.6%, and Random Forest models had the highest accuracy for Fitbit at 90.8%. Classification accuracies for Apple Watch data ranged from 72.6% for sitting to 89.0% for 7 METs. For Fitbit, accuracies varied between 86.2% for sitting to 92.6% for 7 METs. CONCLUSION: This preliminary study demonstrated that data from commercial wearable devices could predict movement types with reasonable accuracy. More research is needed, but these methods are a proof of concept for movement type classification at the population level using commercial wearable device data.

Push-Ups vs. Bench Press Differences in Repetitions and Muscle Activation between Sexes.

Push-ups are an ubiquitous resistance training exercise. While exhibiting a relatively similar upper body motion to the bench press, there are substantial differences in repetitions when employing similar relative loads. The objective was to examine sex-related differences in repetitions and muscle activation associated with push-ups and bench press exercises. Twenty resistance-trained participants (10 men [22 ± 6.1 years] and 10 [24 ± 5.7 years] women) performed maximum push-up and bench press repetitions with loads relative to the body mass during a push-up. Electromyographic (EMG) electrodes were positioned on the middle and anterior deltoids, triceps and biceps brachii, and pectoralis major muscles and their relative (normalized to a maximum voluntary contraction) activity was compared between the two exercises performed to task failure. Both females (3.5 ± 3.9 vs.15.5 ± 8.0 repetitions; p = 0.0008) and males (12.0 ± 6.3 vs. 25.6 ± 5.2 repetitions; p < 0.0001) performed 77.4% and 53.1% less bench press than push-up repetitions respectively. Males significantly exceeded females with both push-ups (p = 0.01) and bench press (p = 0.004) repetitions. Significant linear regression equations were found for females (r2 = 0.55; p = 0.03), and males (r2 = 0.66; p < 0.0001) indicating that bench press repetitions increased 0.36 and 0.97 for each push-up repetition for females and males respectively. Triceps (p = 0.002) and biceps brachii (p = 0.03) EMG mean amplitude was significantly lower during the push-up concentric phase, while the anterior deltoid (p = 0.03) exhibited less activity during the bench press eccentric phase. The sex disparity in repetitions during these exercises indicates that a push-up provides a greater challenge for women than men and regression equations may be helpful for both sexes when formulating training programs.