Identification of Vector Borne Disease Spread Using Big Data Analysis

Abstract

Diseases transmitted by vectors are becoming an increasingly serious problem in India. The prevention and control of these vector-borne diseases continues to be a struggle for the government, even though they have developed into a burden for society. Every year, a sizeable proportion of the population in India is struck down with this illness. The primary objective of this research is to create a prediction model for vector-borne diseases by making use of several machine learning methodologies. Research into diseases transmitted by vectors encompasses a wide variety of illnesses and is therefore an expansive field. Dengue fever, on the other hand, is the only condition that will be examined in detail within the scope of this study because it has been one of the most common in recent times. The purpose of this research is to offer a prediction model that is capable of diagnosing dengue fever in its early stages from an Indian point of view and also classifying the phases of dengue fever cases that have been clinically proven. The model that has been proposed contains a total of five modules, which are referred to as Data Transformation, Data Pre-processing, Feature scaling & Normalization, Split dataset, and Model Building and Prediction module respectively. The process of transforming the data has been completed in the first module. The processes of data preprocessing, feature scaling, and normalization of the dataset were carried out in the second module. The data pre-processing and normalization process has been completed in the third module of the project. The prediction model has been constructed with the assistance of Gaussian Naive Byes classification in the fourth module of the training program. At the end of the investigation, a prediction model for vector-borne disease that can identify dengue disease at each stage of dengue was proposed as part of the study. The suggested model was put through its paces with five different machine learning methods, namely Decision Tree, Logistic Regression, Support Vector Machine (SVM), Random Forest Classifier, and Gaussian Naive Bayes Classifier. All of these techniques were used to test and validate the model. After going through the testing and validation process, the suggested model had an accuracy rate of 97.5 percent on average. However, the Gaussian Naive Bayes classifier has achieved an accuracy of 97.5% while maintaining a 0% mean square error.