14-08-2012, 04:31 PM
Pattern Discovery
A pattern is interesting , useful and hidden statistic like the mean, median or standard deviation of dataset or it can be a rule such that “the person who buys computer also buys UPS ” and much more. Data mining is the process of discovering potentially these hidden patterns, thus data mining encompasses a set of techniques to generate hypotheses, followed by their validation and verification via standard statistical tools. The promise of data mining is its ability to rapidly and automatically searches for local and potentially high utility patterns using
computer algorithms Spatial data mining can be categorized based on the kinds of rules to be discovered in spatial databases. A spatial characteristics rule is a general description of a set of spatial related data, for example the description of general forest pattern in a set of geographic regions is a spatial characteristics rule. A
spatial discriminant rule is that which gives general description of the contrasting feature of a class of spatial related data from other class.