Identification of sport talents using a web-oriented expert system with a fuzzy module

  • Authors:

  • Vladan Papić;Nenad Rogulj;Vladimir Pleština

  • Affiliations:

  • Department of Polytechnics, Faculty of Natural Sciences and Mathematics, University of Split, Teslina 12, 21000 Split, Croatia;Faculty of Kinesiology, University of Split, Teslina 12, 21000 Split, Croatia;Department of Polytechnics, Faculty of Natural Sciences and Mathematics, University of Split, Teslina 12, 21000 Split, Croatia

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2009

Quantified Score

Hi-index 12.05

Visualization

Abstract

This paper presents a fuzzy expert system for scouting and evaluation of young sport talents. Based on the knowledge of several human sport experts, various motoric skills tests, morphologic characteristics measurements and functional tests are quantized according to their importance for a chosen set of sports. Obtained values are entered into the knowledge database along with the grades of the measured results for each test. Fuzzy logic is implemented in order to make the system more flexible and robust. The whole system is web-oriented, i.e. developed ASP.NET application is available to the internet users with a proper login and password. The developed expert system gives acceptability prediction and proposal of the most suitable sports for the person being tested. The output results of the system were evaluated by 4 experts, using real data collected during several years. Comparison is done between the sport proposed by our expert system and the actual outcome of the person's sports career. Also, the comparison of the expert system output and the human expert suggestions were done. All tests showed high reliability and accuracy of the developed system. Strengths, possibilities and future plans of the Sport Talent expert system are also discussed.