Publication

Abstract : The amount of available electronic data is in exponential growth and it needs new technical tools that can be intelligently and automatically extract the implicit, hidden patterns and knowledge from the data. Scaling up high dimensional data without information loss is essentially needed in the current scenario. Soft computing techniques have developed many methods for handling high dimensional data. Out of these several methods the concepts of Rough sets have been analyzed in this paper since Rough set finds the pattern only hidden in the data and it does not require additional information. Rough set handles the data through equivalence and similarity relation. It identifies equivalence and similarity relation between the data. This paper exhibits the reduction of big data through Rough discernibility matrix and the results are examined for real data.