Dental Disease Detection Using Hybrid Fuzzy Logic and Evolution Strategies

Abstract

Dental disease detection is needed because majority of Indonesian have ever experienced dental disease. There are three areas affected by dental disease: South Sulawesi, West Sulawesi, and South Kalimantan according to Basic Health Research 2013. Obtaining accurate detection is difficult because it requires expert observations and interviews in order to improve their perception. Accurate dental disease detection is required by dentists as a tool to make it easier to improve patient interaction and time effeciency. Good and accurate detection requires an approach to obtain a model capable of processing observation data. This research proposes a method as solution utilizing hybrid approach employed both fuzzy logic and evolution algorithm. Evolution Strategies is used for optimization that get results better accuracy than simply using FIS Tsukamoto. Optimization focuses on the function of the degree of membership. This can be utilized to categorize the following dental disease. Variance: pulpitis, gingivitis, periodontitis and advacend periodontitis using formula Root Mean Square Error (RMSE) obtain with RMSE 0.82.