Combination Multilayer Fuzzy Inference System with K-means for Classification of Dental Diseases

This study was conducted to solve the problem of classifying dental diseases such as pulpitis, gingivitis, periodontitis and advanced periodontitis. The method in this study uses a combination of algorithms with a multilayer system where in the first layer a fuzzy inference will be carried out whether a patient is suffering from pulpitis. Early symptoms of pulpitis are characterized by pain with varying levels. Meanwhile, in the second layer a fuzzy inference process will also be carried out to identify other types of dental diseases, but in this second layer the centroid value calculation process is carried out using the K-means algorithm for all input variables. Then the inference process will run to determine the type of disease suffered by the patient following the fuzzy set of other types of diseases. This study is expected to contribute to helping the initial screening process for dental diseases so that it is easier for dentists to carry out further examinations. The results of this study have been proven to be able to help doctors in conducting initial screening to determine dental disease. In this study, the multilayer system is intended to differentiate the results of dental disease classification because pulpitis does not have a relationship between input variables and other types of dental disease. Meanwhile, the use of the fuzzy inference system method in this study showed good results because the FIS method can map the level of pain suffered by a patient with mild, moderate and severe levels into a numeric value that can be classified where the level of pain is a feeling that cannot be calculated, by using the fuzzy method, the linguistic value can be defined into a conclusion. Grouping input values by finding the means value in the second layer and combined with the fuzzy method has been proven to provide good results for determining the type of dental disease.