Data mining the PIMA dataset using rough set theory with a special emphasis on rule reduction

摘要: This paper describes how rough set theory can be utilized as a tool for analyzing relatively complex decision tables like the Pima Indian Diabetes Database (PIDD). We Rosetta, public domain implementation of sets on PIDD in order to determine we could generate predictive rule with highest accuracy and fewest number rules. Having reduced is advantageous it provides focus salient attributes makes application clinical practice more efficient (and likely). In this paper, report use genetic algorithm based approach classification diabetes achieved success rate test 83%. favors highly compared other reported results, which ranged from 65% 75%. addition, were able achieve less than 100 The high low support data mining biological databases.