Frequent Neighboring Class Set Mining Based on Neighboring Index

Since these present frequent neighboring class set mining algorithms have some repeated computing when gaining support, which also have some redundancy candidate when mining frequent neighboring class set, this paper proposes an algorithm of mining frequent neighboring class set based on neighboring index, which is suitable for mining frequent neighboring class set including more spatial objects in large database. The algorithm uses the neighboring index method to create database of neighboring class set, and then uses neighboring class value declining method to generate frequent candidate neighboring class set, namely, algorithm uses decreasing sequence to generate frequent candidate neighboring class set. The mining efficiency of algorithm is indeed improved through neighboring class value declining method, since not only the method of generating candidate is very simple, but also the method of computing support is very fast and direct. The result of experiment indicates that the algorithm is faster and more efficient than present algorithms when mining frequent neighboring class set contain more spatial objects in large spatial data.