Improve data classification performance in diagnosing diabetes using the Binary Exchange Market Algorithm

Abstract Today's lifestyle has led to a significant increase in referrals medical centers diagnose various diseases. To this end, over the past few years, researchers have turned new diagnostic methods, including data mining and artificial intelligence, intending facilitate detection process reliability. The high volume of available can be considered one main problems using these methods. optimal selection essential influential features reduces maximum dimension for better diagnosis with more reliability results. In paper, approach uses Binary Exchange Market Algorithm (BEMA) identify practical diabetes dataset determine best algorithm binary function (type sigmoid function) improve performance EMA is presented. For validation efficiency proposed BEMA algorithm, several SVM, KNN, NB classification models been used train test final model. results obtained from evaluations show that BEMA-SVM combined method than previous methods accuracy offer an effect equivalent 98.502%. Also, provide method, use combination classes which outside scope study.