An Optimal Feature Selection with Neural Network-Based Classification Model for Dengue Fever Prediction

A vast range of neural network applications has been reported in recent research. This model can make various predictions using this model, and this research has taken dengue disease prediction. Uncertain Neural Network (UNN) is introduced to efficiently classify the dengue disease dataset. Research can be conducted in a wide range of fields to resolve the issue of missing and uncertain data. Also, real-time data sets contain a lot of missing attributes or values. Researchers use real-time data because it is approximately measured. Researchers thus pay more attention to disease prediction. The problem can be solved by putting into action the dengue prediction system that has been developed. The primary goal of this study is to create a reliable classification model based on feature selection for predicting dengue fever. This research work is applied for feature model creation and relative analysis to improve dengue virus prediction correctness in three stages: Collecting dengue virus datasets from the UCI Machine Learning library was the first step; secondly, a Genetic Algorithm (GA) is used for feature selection, the UNN model is used to create a classification model; As part of the final stage, Accuracy (A), Specificity (Sp), and Sensitivity (Se) can be calculated for justifying the result. A simulation of the proposed method is conducted using the WEKA tool. Therefore, the proposed classification procedure was the most effective model for predicting and detecting dengue fever.