Talent classification of motoric parameters with support vector machine
Journal Title: Uluslararası Spor Egzersiz ve Antrenman Bilimi dergisi - Year 2018, Vol 4, Issue 3
Abstract
Aim: In recent years, the methods of analysis of data science have started to be used frequently in talent selection in sports and the evaluation of athletes. Based on the motor and physical measurements of the future athletes, determining which sports branch they are prone to is important in terms of training and resource planning. Within the scope of this study, it was aimed to propose a classification system to determine which sports branches the participants are suitable for, based on motor and physical measurements. Material and Methods: Measurements of height, arm span, body weight, 20-meter sprint test, vertical jump height, 1 kg medicine ball throw, back strength, hand grip strength, flexibility test and standing long jump values [mk1] were recorded with the contribution of 1240 participants who are 9 years old. Afterwards, grouping procedures were carried out with classification methods based on Support Vector Machines (SVM). Radial based functions are used as kernel functions of SVM. The results of evaluations made by consulting expert opinion beforehand were accepted as actual values, compared with the classification results and the performances of the classifiers were calculated. Within the scope of this study, participants were classified into four as rapidity branch (E), strength branch (F), height branch (G) and other group (H). Results: The accuracy values of classification of support vector machines were found ranging from 96% to 100% in each class, and 98% in average. Minimum value of sensitivity was found to be 93% while it was 99% in maximum. On the other hand, precision varied between 92% and 100%. Conclusion: In the light of the information provided, successful classification of the test dataset using the model that is formed by the training dataset, points out a possible high classification accuracy of big test datasets even in the use of a small dataset in the training phase.
Authors and Affiliations
HANİFE KANAT USTA, NACİ USTA, ADİL DENİZ DURU, HASAN BİROL ÇOTUK
Keywords
Related Articles
- EP ID EP400106
- DOI 10.18826/useeabd.454938
- Views 139
- Downloads 0
The attitudes of classroom teacher candidates towards physical education lesson
Aim: It is aimed to determine the attitudes of the 2nd, 3rd, and 4th grade classroom teacher candidates towards the physical education lesson according to various variables. Material and Methods: For the current stud...
Psychological effects of Cardio Bosu exercise on sedentary women
Aim: It was aimed to investigate the effect of Cardio Bosu exercises on the psychological states of sedentary women. Material and Methods: A total of 30 voluntary women with the age range of 25-45 years participated in...
An analysis of home advantage in Iranian football super league
Aim: The purpose of this study was to investigate home advantage in Iranian Football Super League. Methods: The information regarding wins, losses, goals for, goals against, yellow cards, red cards and gained points in m...
The comparison of social skill levels of team sports athletes and individual sport athletes
Aim: The study is to compare the level of social skills scores of undergraduate students at Mersin University School of Physical Education and Sports according to sport types, gender and class levels. Material and Metho...
Talent classification of motoric parameters with support vector machine
Aim: In recent years, the methods of analysis of data science have started to be used frequently in talent selection in sports and the evaluation of athletes. Based on the motor and physical measurements of the future at...