Semantic-based pruning of redundant and uninteresting frequent geographic patterns

In geographic association rule mining many patterns are either redundant or contain well known geographic domain associations explicitly represented in knowledge resources such as geographic database schemas and geo-ontologies. Existing spatial association rule mining algorithms are Apriori-like, and therefore generate a large amount of redundant patterns. For non-spatial data, the closed frequent pattern mining technique has been introduced to remove redundant patterns. This approach, however, does not warrant the elimination of both redundant and well known geographic dependences when mining geographic databases. This paper presents a novel method for pruning both redundant and well known geographic dependences, by pushing semantics into the pattern mining task. Experiments with real geographic databases have demonstrated a significant reduction of the total amount of patterns and the efficiency of the method.