Association Rules Based Data Mining on Test Data of Physical Health Standard

With the development of modern electronic and computer technologies, sports training and competition became more and more technical. A great deal of data were recorded, including training data of athletes, test data of students in sports course, and test data of Physical Health Standard (PHS). However, usage of these records is limited to basic statistics analysis and only from some aspects of sport sciences. Important patterns of these datasets themselves and relationships among the data may still retain hidden. Data mining is a useful technique for finding unknown patterns among data, but it was seldom applied in sports field. In this paper, data mining attempt on test data of PHE is introduced, using Microsoft Association Rules algorithm and SQL Server 2005. In the experiment, the grades of vital capacity, grip strength, standing long jump and step test of a student are used for input attributes, and total score of the student is used for prediction attribute. As the results, we have a lot of useful rules and find that the grade of standing long jump is the most important influence factor on total score of a student.