The application of association rule mining to remotely sensed data
Jianning Dong, William Perrizo, Qin Ding, Jingkai Zhou · 2000
The explosive growth in data and database has generated an urgent need for new techniques and tools that can intelligently and automatically transform the processed data into useful information and knowledge. Data mining is such a technique. In this paper, we consider the mining of association rules from remotely sensed data and its application in precision. Based on the characteristics of the remotely sensed data and the problem itself, we present a bit oriented formal model and discuss the issues of partitioning quantitative attributes into equal, unequal and discontinuous partitions. We propose two new pruning techniques and compare the performances with a base algorithm. An improvement in performance is shown when using these pruning techniques.