Machine Learning on Prediction of Relative Physical Activity Intensity Using Medical Radar Sensor and 3D Accelerometer

Abstract

Background: One of the most critical topics in sports safety today is the reduction in injury risks through controlled fatigue using non-invasive athlete monitoring. Due to the risk of injuries, it is prohibited to use accelerometer-based smart trackers, activity measurement bracelets, and smart watches for recording health parameters during performance sports activities. This study analyzes the synergy feasibility of medical radar sensors and tri-axial acceleration sensor data to predict physical activity key performance indexes in performance sports by using machine learning (ML). The novelty of this method is that it uses a 24 GHz Doppler radar sensor to detect vital signs such as the heartbeat and breathing without touching the person and to predict the intensity of physical activity, combined with the acceleration data from 3D accelerometers. Methods: This study is based on the data collected from professional athletes and freely available datasets created for research purposes. A combination of sensor data management was used: a medical radar sensor with no-contact remote sensing to measure the heart rate (HR) and 3D acceleration to measure the velocity of the activity. Various advanced ML methods and models were employed on the top of sensors to analyze the vital parameters and predict the health activity key performance indexes. three-axial acceleration, heart rate data, age, as well as activity level variances. Results: The ML models recognized the physical activity intensity and estimated the energy expenditure on a realistic level. Leave-one-out (LOO) cross-validation (CV), as well as out-of-sample testing (OST) methods, have been used to evaluate the level of accuracy in activity intensity prediction. The energy expenditure prediction with three-axial accelerometer sensors by using linear regression provided 97–99% accuracy on selected sports (cycling, running, and soccer). The ML-based RPE results using medical radar sensors on a time-series heart rate (HR) dataset varied between 90 and 96% accuracy. The expected level of accuracy was examined with different models. The average accuracy for all the models (RPE and METs) and setups was higher than 90%. Conclusions: The ML models that classify the rating of the perceived exertion and the metabolic equivalent of tasks perform consistently.

AI-Assisted Fatigue and Stamina Control for Performance Sports on IMU-Generated Multivariate Times Series Datasets

“…The modeling and AI experiments were run on the following configurations: Mac Studio (Apple M1 Ultra, 64 GB Memory) and MacBook Pro (Apple M1 Max, 64 GB of memory) on the Google Colab Pro platform [ 5 ].…”

“…Such a comprehensive analysis is crucial, as it can inform tailored training regimens that optimize performance while mitigating the risk of injury. In sports safety, the synchronization of physiological events is crucial for injury prevention [ 5 ]. For instance, the concurrent analysis of joint stress, muscle activation, and impact forces can help in identifying patterns that precede common injuries.…”

Mediating Effect of Sports Safety Awareness between Sports Activity Habits and the Intention to Complete Safety Education among Korean Adolescents

“…(5) drinking water during the designated break time; (6) wearing appropriate clothing and safety gear for the sport; (7) reporting pain and injuries to the coach; (8) checking environmental factors, such as weather disasters and signs before exercising; (9) being aware of first aid methods, such as cardiopulmonary resuscitation (CPR); and (10) engaging in cool-down exercises. Second, the sports safety awareness variable comprised eight items: (1) awareness of how to prevent sports accidents; (2) awareness of how to cope with sports accidents; (3) awareness of CPR; (4) awareness of wound disinfection and use of bandages; (5) awareness of coping with musculoskeletal damage; (6) awareness of coping with accidents caused by diseases; (7) awareness of coping with physical damage caused by shock; and (8) awareness of coping with temperature change accidents.…”

“…(2) checking the surrounding facilities for defects and safety before exercise; (3) performing the appropriate exercise after determining the exercise level beforehand; (4) drinking an adequate intake of water before exercise; (5) wearing appropriate clothing and safety gear for the sport; (6) reporting pain and injuries to the coach; (7) checking environmental factors such as weather disasters and signs before exercising; (8) engaging in cool-down exercises; (9) being aware of how to prevent sports safety accidents; (10) being aware of how to cope with safety accidents in sports; (11) being aware of CPR; (12) being aware of coping with musculoskeletal damage; (13) understanding the necessity of sports safety education; (14) intending to complete safety education; and (15) intending to enroll in a sports safety program.…”

“…Several studies on sports safety have focused on accidents that occur during sporting events [ 8 , 9 ]. Some scholars have reported on the need for more studies on the prevention of accidents, rather than injuries, in sports [ 4 , 10 , 11 , 12 ]. Other researchers have focused on methods for preventing injuries in various sports, while some have looked at the development of sports safety education programs [ 11 , 13 , 14 ] and the use of digital devices to improve sports safety [ 15 , 16 ].…”