Research On Efficient Association Rule Mining Algorithm For Student Physical Quality Evaluation Index

Association rule mining is one of the most commonly used method for large data analysis,it can find out from huge data set of the implicit connection between each set,but processing large data gathering spend too much time,and execution efficiency of the algorithm directly affect the mining result is good or bad,which requires efficient association rules mining algorithm processing and research.The evaluation and prediction of physical fitness are precisely related to the important information hidden behind the data.In order to extract valuable information effectively,efficiency is often ignored.To solve above problems,based on the students’ physical quality evaluation as the research object,has carried out for evaluation index of efficient association rules mining algorithm research,build the efficiency of the two kinds of effective optimization model,based on to ensure the accuracy of the mining results,optimize the efficiency of association rule mining,so as to realize the fast correlation between the physical health indicators,To find out the key indexes that affect the physical quality in time,and then realize the efficient evaluation of physical quality,and provide a new research perspective for physical education teaching and physical quality evaluation.The specific research contents are as follows:（1）Aiming at the problem of rapid association classification of physical indicators,an optimization model of Apriori association rules based on transaction compression and hash technology was proposed.In this paper,firstly,body mass index data,according to the characteristics of college students the cervix data is limited and the characteristics of the same length,its after data cleaning,data reduction,data conversion and other preprocessing transformation for Boolean data applicable to the Apriori algorithm,and then from the aspects of transaction compression,hash technology jointly improve Apriori association rules mining model of operation efficiency,Finally,strong association rules between indicators are screened based on the framework of "support-confidence degree".Through experiments,it is verified that the optimization model of association rules proposed in this paper can obtain effective association information between physical indexes and improve the operation efficiency significantly.（2）Aiming at the problem of efficient evaluation of physical quality,an evaluation efficiency optimization model based on improved FP-growth algorithm is proposed.Firstly,physical fitness index data and physical fitness level data were selected and transformed into the form suitable for FP-growth algorithm by pre-processing operation.Then,the mapping from project name to bucket address was completed by using the hash function set,so as to shorten the counting time of statistical item set support degree and improve the operation efficiency of FP-growth evaluation model.Finally,considering that there may be a large number of redundant rules in the mining results,the promotion degree parameter is added in the traditional "supportconfidence" framework,and the effective strong association rules based on the promotion degree are formulated to improve the accuracy of the rule base.Experimental results show that compared with THE FP-growth algorithm,the improved algorithm can guarantee the mining accuracy and reduce the time complexity,and the validity of the association rule optimization model based on the improved Apriori algorithm is verified.