Performance Analysis of ANN and Naive Bayes Classification Algorithm for Data Classification

Abstract

Classification is an important data mining technique with a wide range of applications to classify the various types of data existing in almost all areas of our lives. The purpose of this discovery study can be used to estimate the potential of having breast cancer by taking advantage of anthropometric data and collected routine blood analysis parameters. The study was performed using data from patients who were admitted to the clinic with the suspicion of breast cancer. The values of Age (years), BMI (kg/m2), Glucose (mg/dL), Insulin (µU/mL), HOMA, Leptin (ng/mL), Adiponectin (µg/mL), Resistin (ng/mL), MCP-1(pg/dL) were used. In our study, classification algorithms were applied to the data and they were asked to estimate the disease diagnosis. The classification performance of Artificial neural networks and Naive Bayes classifiers which were applied to data with 9 inputs and one output were calculated and theperformance results were compared. This article sheds light on the performance evaluation based on correct and incorrect data classification examples using ANN and Naive Bayes classification algorithm. When we look at the performances obtained, it is predicted that using the anthropometric data and the collected routine blood analysis parameters, the potential for diagnosing breast cancer is high using these data.