The Reduction And Visualization Techniques For Association Rules Of K-anonymous Data

The Internet has been an indispensable part of our life since the rapid development of the Internet.As a consequence,there is a lot of related information remaining in the Internet.These related information could contain some personal information that is sensitive to users,which the users want to keep private.The users are more and more concerned about the leaking of these sensitive data.K-anonymity privacy model has been developed for many years,which provides a good solution for preserving the private data.Thus,the k-anonymous data will be spreading across the whole Internet.The k-anonymous data is an uncertain data that generalized from the certain data according to the generalization-tree.The results for mining association rules from k-anonymous data are different from the general association rules,whose antecedents and the consequents are generalized values as well.Querying on these association rules could be time-consuming because of the computing from the generalized values to the certain values.Meanwhile,with the growing number of association rules,it becomes more and more difficult for users to explore interesting rules due to its nature complexity.Studies base on human perception and intuition show that graphical representation could be a better illustration of how to handle data by using the capabilities of the human visual system to seek information.The 3D matrix-based approach visualization system of association rules called 3DMVS was implemented in present study.The main visual representation employed the extended matrix-based approach with rule-to-items mapping to general transaction data set,which could be a good solution to visualizing the association rules with multiple antecedents.Taking the importance of antecedents in certain association rules of k-anonymous data,a novel method merging rules and assigning weight is proposed to generate new rules to reduce the dimension of the association rules of k-anonymous data,which will help users to find more important items in the new rule.Moreover,several interactions such as sorting and filtering for support and confidence,zoom and rotation for the visual representation,facilitate decision makers to explore the rules of k-anonymous data they are interested in various aspects.Finally,various evaluation techniques and function testing method has been employed to assess the system.As a contribution,the 3D matrix-based approach visualization system not only provide a solution for cluttering,but also display all the features of the association rules clearly.