An Algorithm of Complementation Mining Frequent Neighboring Class Set

This paper addresses character that present frequent neighboring class set mining algorithms is inefficient to extract long frequent neighboring class set, and proposes an algorithm of complementation mining frequent neighboring class set. This algorithm is suitable for mining any frequent neighboring class set in large spatial data through using top-down search and complementation mining strategy, and it builds digital database of neighboring class set via neighboring class weight sets. The algorithm generates candidate frequent neighboring class set via top-down and complementation search strategy, namely, it gains candidate frequent item set not only by computing k-subset of (k+1)-non frequent neighboring class set but also by computing their complementary sets. The mining algorithm computes support of candidate frequent neighboring class set by digit logical "and" operation. The algorithm improves mining efficiency through these methods. The result of experiment indicates that the algorithm is faster and more efficient than present algorithms when mining frequent neighboring class set in large spatial data.