ExerSense: Physical Exercise Recognition and Counting Algorithm from Wearables Robust to Positioning

Abstract

Wearable devices are currently popular for fitness tracking. However, these general usage devices only can track limited and prespecified exercises. In our previous work, we introduced ExerSense that segments, classifies, and counts multiple physical exercises in real-time based on a correlation method. It also can track user-specified exercises collected only one motion in advance. This paper is the extension of that work. We collected acceleration data for five types of regular exercises by four different wearable devices. To find the best accurate device and its position for multiple exercise recognition, we conducted 50 times random validations. Our result shows the robustness of ExerSense, working well with various devices. Among the four general usage devices, the chest-mounted sensor is the best for our target exercises, and the upper-arm-mounted smartphone is a close second. The wrist-mounted smartwatch is third, and the worst one is the ear-mounted sensor.

A Sensor-Based mHealth Platform for Remote Monitoring and Intervention of Frailty Patients at Home

“…On the other hand, in order to promote physical activity in the elderly, systems that allow supervised control of the correct execution of maintenance exercises are of great interest. In this way, patients are motivated to maintain their own health and well-being [ 45 ]. For this purpose, a control of the number of repetitions of the exercises is required, commonly applied in pedometers and systems that count the number of steps.…”

Transformers for Workout Video Segmentation

“…Most of the works are systematically related to the use of worn sensors [6,7,8], such as smartwatches or smart-bands. These devices are quite limited as they are not able to analyze the execution of complex movements, where several body parts are used.…”

Viewpoint-Invariant Exercise Repetition Counting

“…UI-PRMD dataset UI-PRMD dataset [35] is composed of ten motions commonly used in rehabilitation, including (1) deep squat, (2) hurdle step, (3) inline lunge, (4) side lunge, (5) sit to stand, (6) standing active straight leg raise, (7) standing shoulder abduction, (8) standing shoulder extension, ( 9) standing shoulder internal-external rotation, and (10) standing shoulder scaption. Ten healthy subjects repeated each exercise 10 times.…”

“…Providing repetition counting feedback is common feedback in the HEP. Previous works [6,7,8,9] focused on HEP systems also implemented several feedback, such as repetition counting. Users can be more engaged in the exercise and training program given the counting feedback.…”