Health monitoring and user profiling for sports activities : evaluating heart rate measurements and activity recognition
Year: 2018
Type: article
Abstract: Wearables are often equipped with an accelerometer and heart rate sensor.However, the accuracy of the generated heart rate measurements is still unclear.This paper evaluates heart rate measurements during various physical activities performed by test users and compares three types of wearable devices: the specialized sports device with chest strap, the fitness tracker, and the smart watch.Consistent heart rate measurements are obtained with all wearables during activities that require no or very little wrist movements, such as sitting in a chair, cycling, walking, or even squat exercises.In contrast, wearables worn around the wrist (smart watches and fitness trackers) and sport devices worn around the chest measure significantly different heart rates during activities that require a lot of movement of the wrist, such as dumbbell biceps curl and push up exercises.These movements of the user's wrist were measured using the accelerometer of the wearable, and allow the detection of repetitions of a physical activity with a typical movement pattern, such as a dumbbell biceps curl.Based on accelerometer and heart rate data, a user profile is created for a rule-based filter to generate personal recommendations for physical activities.A mobile app demonstrates that heart rate measurements and activity recognition can be used to assist and guide users during workouts.
Authors: Toon De Pessemier, Enias Cailliau, Luc Martens
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3160811629