Athlete’s physiological parameter monitoring system based on K-means and MTLS-SVM algorithm

Abstract

In the non-medical model physiological parameter monitoring system, learning the monitoring parameters can improve the diagnostic and prediction accuracy. Aiming at the problems of insufficient information mining and low prediction accuracy in multi-task time series, the supervised and semi-supervised learning methods in machine learning are combined to predict the physiological status of remote health monitoring objects. This method uses the K-means algorithm to cluster the same type of data and use the Multitasking Least Squares Support Vector Machine (MTLS-SVM) to train historical data for trend prediction. In order to evaluate the effectiveness of the method, the MTLS-SVM method is compared with the K-means and MTLS-SVM methods. It can be seen from the experimental results that the body temperature data measured by the GY-MCU90615 is close to that of the digital thermometer. Moreover, the body temperature speed collected by the GY-MCU90615 can reach the millisecond level, which can well meet the needs of the system. The research shows that the method has higher prediction accuracy and has a breakthrough significance for the monitoring of athletes’ physiological parameters.