Rough-Set-Theory-Based Classification with Optimized k-Means Discretization

The discretization of continuous attributes in a dataset is an essential step before the Rough-Set-Theory (RST)-based classification process applied. There are many methods for discretization, but not them have linked RST instruments from beginning process. objective this research to propose method improve accuracy and reliability RST-based classifier model by involving at In proposed method, k-means-based optimized with genetic algorithm (GA) was introduced. Four datasets taken UCI were selected test performance method. evaluation technique performed comparing it other methods, i.e., equal-frequency entropy-based. comparison among these measured number bins rules generated its accuracy, precision, recall. A Friedman continued post hoc analysis also applied measure significance difference performance. experimental results indicate that, general, significantly better than compared methods.