Context Based Positive and Negative Spatio-Temporal Association Rule Mining

Pre Prospection data mining model for hydrocarbon development guides to the need of developing a model for prospection activity for which the data of surface indicators collected through remote sensing and microbial sources can be used. This chapter proposes a new approach to mine context based positive and negative spatial association rules. Researchers are using Apriori algorithm on spatial databases which doesn’t utilize the strengths of positive and negative association rules hence ignoring discovery of very interesting and useful associations present in the data. In dense spatial databases, the number of negative association rules is much higher as compared to the positive rules which need exploitation. Positive and negative association rule discovery and then pruning uninteresting rules consumes lots of resources without much improvement in the overall accuracy in the knowledge discovery process. Overall analysis of spatial association rule mining concludes the absence of some unseen factors. The associations among different objects and lattices are strongly dependent upon the context where context is the state of entity, environment or action. We have proposed an approach of spatial association rule mining in which contextual situation is considered while generating positive and negative frequent item sets. An extended algorithm based on Apriori approach is developed and compared with existing spatial association rule algorithms. The numerical evaluation shows that proposed algorithm is efficient in generating specific, reliable and robust information than the traditional algorithms.