Association Rules Based Feature Selection for the Interpretation of Well Log Data

The original purpose of association rules mining aims at the analysis of customer's purchasing behavior. Practically, the customers can be classified into different classes, and each class may show different purchasing behavior which corresponds to the different association rules. Therefore, the association rules corresponding to the specified customers may be considered as features for classification. In this paper, a new idea is proposed that the association rules is adopted to select features for classification and to interpret well logging data. The Apriori algorithm is introduced to mining association rules from preprocessed data. A frequent 8-term set is acquired, and two strong association rules are constructed from the set, the test data is used to validate the association rule, and 78.6% coincidence shows the effect of the approach.