EFASFMM: A Unique Approach for Early Prediction of Type II Diabetics using Fire Fly and Semi-supervised Min-Max Algorithm

Abstract

Non-insulin-reliant, one of the most serious illnesses is diabetes mellitus, often known as type 2 diabetes, and it affects a large number of people. Between 2 and 5 million individuals worldwide die from diabetes each year. If diabetes is identified sooner, it can be managed, and catastrophic dangers including nephropathy, heart stroke, and other conditions linked to it can be avoided. Therefore, early diabetes diagnosis aids in preserving excellent health. Machine learning (ML), which has recently made strides, is now being used in a number of medical health-related fields. The innovative, nature-inspired Firefly algorithm has been shown to be effective at solving a range of numerical optimization issues. While using alliterations, the traditional firefly method employed a fixed step size models for semi-supervised learning (SSL). The firefly is effective for solving classification issues involving both a sizable number of unlabelled data and a limited number of samples with labels. The fuzzy min-max (FMM) family of neural networks in this regard provide the capability of online learning for tackling both supervised and unsupervised situations. Using a special mix of the two proposed algorithms, one of which is utilised for optimization and the other for making early predictions of type 2 diabetes. The findings for the training and testing phases for the parameter’s accuracy, precision, sensitivity, specificity, and F-score are reported as 97.96%, 97.82%, 98.10%, 97.82%, and 97.95% which, when compared to current state-of-the-art methods, are finer