A Novel Method of Hybrid Extreme Learning Machine for Diabetes Mellitus Diagnosis

Objectives: To design a classifier for the detection of Diabetes Mellitus with optimal cost and precise performance. Method and Analysis: The diagnosis and interpretation of the diabetes data is must because major problem occurs due to this data maintenance. Several researches are made with machine learning but still needs improvements. In this paper a new method is evaluated as hybrid Extreme Learning Machine (HELM) with African Buffalo Optimization (ABO). Findings: ELM is used to select the input data because of fast learning speed. Optimization technique is used for searching and classifying the good diabetic data. The ABO is a population based algorithm in which individual buffalos work together to identify the diabetics data by updating fitness value for best output solution. The proposed HELM technique is successfully implemented for diagnosing diabetes disease. By using this machine learning algorithm, the classification accuracy is achieved for classifying the diabetes patients by using much of the data set for training and few data sets for testing. In order to improve the quality as well as accuracy there is a need for algorithm. The combination of ELM-ABO classifier is applied in training dataset taken from PRIMA Indian dataset for classification and the experimental results are compared with SVM and other ELM classifiers applied on the same database. Improvement: It is observed that the HELM method obtained high accuracy in classification with less execution time along with performance evaluation of parameters such as recall, precision and F-Measure.