Data mining is a process of finding anomalies, patterns and correlations within large data sets to predict outcomes. Neural networks are a method for data mining and are popular biologically-inspired intelligent methodologies, whose classification, prediction, and pattern recognition capabilities have been utilized successfully in many areas. They can be applied to diverse discipline fields as exercise and sport science to assist researchers find patterns that may identify differences between sports groups, genders and different ability levels in different sports. He research aim was to apply neural network methods defined as multilayer perceptron (MLP) and radial basis function (RBF) were applied to a large data base from the 2010 7th Pan Pacific Masters Games to evaluate what items and factors can differentiate participant motivation between male and female masters athletes and the accuracy of these methods. Results indicated both neural network approaches produced similar solutions using the same data set, however as the methods are self-learning they can derive different solutions when implemented consecutively. The methods were more effective in classifying female athletes correctly and associated with factors of completion and affiliation factors. The classification of male athletes based on MLP and RBF were not as effective. Opportunities exist in exercise and sports science for these data mining methods to be applied extensively, especially in the area of talent identification modelling.
|Title of host publication||Proceedings 8th International Conference on Computer Science Education|
|Subtitle of host publication||Innovation and Technology (CSEIT 2017)|
|Number of pages||7|
|Publication status||Published - 2017|
Heazlewood, T., & Walsh, J. (2017). Data Mining: Applications of Neural Network Analysis in Exercise and Sport Science. In Proceedings 8th International Conference on Computer Science Education: Innovation and Technology (CSEIT 2017) (pp. 77-83) https://doi.org/10.5176/2251-2195_CSEIT17.42