Fuzzy Optimized Gravitational Search Algorithm for Disease Prediction

Abstract

In this article, fuzzy logic and gravitational search algorithms have been amalgamated and explored for feature selection in the automated prediction of diseases. The gravitational search algorithm has been used for search optimization while fuzzy logic had been used for its parameter tuning. Feature selection has been considered as a dual objective problem in the article, i.e. selecting minimum number of features without compromising the accuracy of classification, which is performed using K-Nearest Neighbour classifier. The improved algorithm has been tested with various publicly available medical datasets to analyse its effectiveness. The results indicate that the approach not only reduces the feature set by an average of 67.66% but also increases the accuracy by an average of 12%. Further, the results have also been compared with the prior work wherein the feature selection has been done using other evolutionary techniques. It is observed that the proposed approach is able to generate better results in most of the cases.