Comparative Analysis for Mining Fuzzified Dataset Using Association Rule Mining Approach

The constantly-growing size of geospatial databases makes access to relevant knowledge complex. When managing a lot of information, image analysts face difficulties in precisely survey data and to express needle-size knowledge from piles of image databases. In such cases, human review of all images in the databases is not viable, and there is a critical need to create novel computational strategies for data discovery that can help image experts in basic leadership. The difficulty of articulating information from visual patterns and the increasing number of image data created every day are challenges in the automated learning of geospatial intelligence. Human inspection and annotation, especially, are subjective and impractical in this context. In this paper, we have considered two types of dataset weather and forest fire information. This dataset needs to be fuzzifying. Fuzzification is use to check the uncertainty of data that generates the rules. There are some kinds of association rule mining methods. ARM is utilized to detect & study the relationship among regimes discovered in time series data from past years. The comparative analysis represents the comparison graph on given parameters like the number of rules generated & execution time.