Hamstring and quadriceps muscles are essential for the performance of athletes in various sport branches. Hamstring muscles control running activities and stabilize the knee during turns or tackles, while quadriceps muscles play an important role in jumping and kicking. Although hamstring and quadriceps muscle strength in athletes can be accurately measured using isokinetic dynamometry, practical difficulties, such as the requirement of nonportable and costly equipment as well as a long period of measurement time, motivate the researcher to predict hamstring and quadriceps muscle strength using promising machine-learning methods. The purpose of this study is to build prediction models for estimating the hamstring and quadriceps muscle strength of college-aged athletes using a support vector machine (SVM). The data set included 75 athletes selected from the College of Physical Education and Sport, Gazi University, Turkey. The predictor variables of sex, age, height, weight, body mass index, and sport branch were utilized to build the hamstring and quadriceps muscle strength prediction models for various types of training methods. The generalization error of the prediction models was calculated by carrying out 10-fold cross-validation, and the prediction errors were evaluated using several performance metrics. For comparison purposes, prediction models based on a radial basis function neural network (RBFNN) and single decision tree (SDT) were also developed. The results reveal that the SVM-based hamstring and quadriceps strength prediction models significantly outperform the RBFNN-based and SDT-based models and can be safely utilized to produce predictions regarding new data with acceptable accuracy.

No abstract

Quadriceps refers to a group of four muscles on the front of the thigh. Adequate quadriceps strength is essential for athletic performance. Quadriceps strength in athletes can be reliably assessed using isokinetic dynamometry. Also, some studies in literature showed the possibility of predicting the quadriceps strength of athletes using machine learning methods within acceptable error rates. The purpose of this study is to investigate the effect of sport branch on quadriceps strength prediction using Support Vector Machine (SVM). The dataset included 70 athletes selected from the College of Physical Education and Sport at Gazi University. The optimal values of SVM parameters have been found by using grid search. The predictor variables gender, age, height, weight and sport branch have been utilized to build sixteen different quadriceps strength prediction models. By carrying out 10-fold cross-validation, the performance of the prediction models has been evaluated by calculating the root mean square errors (RMSE's) and multiple correlation coefficients (R's). The results show that the RMSE's of the prediction models change from 23.31 to 47.78 Nm. The model including the predictor variables gender, height, weight and sport branch yields the lowest RMSE and highest R. One can conclude that sport branch has a profound effect for predicting the quadriceps strength of athletes.