Risk classification is a major technical challenge in medical diagnosis and chronic illness management. Various computational techniques have been developed for risk classification in recent years. This paper presents an approach combining support vector machines (SVM) and fuzzy modelling (SVM-Fuzzy). The goal is to evaluate the proposed design for better accuracy in risk classification and to investigate training the machine learning algorithm using sample real world data. A goal is also to determine efficiency in classification by optimizing selection of right sized datasets through experiments. Diagnosis of diabetes mellitus (Type 2 diabetes) is the motivating problem for risk classification. Fuzzy reasoning is used to classify the level of risks from data. SVM is used to design the fuzzy rules. Pima diabetes dataset is used to train the SVM and for testing the fuzzy system. The experiments from the model show promising results.
|Number of pages||6|
|Journal||International Journal of Computer Science and Information Technologies|
|Publication status||Published - 2015|