Exploratory Data Analysis of Vector Borne Diseases using Random Forest, Gradient Boosting, AdaBoost, and XGBoost Pre-Trained Models

• Published in: 2023 IEEE Fifth International Conference on Advances in Electronics, Computers and Communications (ICAECC) pp. 1 - 5
• Main Authors: Gill, Kanwarpartap Singh, Anand, Vatsala, Gupta, Rupesh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07.09.2023
• Subjects: AdaBoost; Biological system modeling; Boosting; Classification; CNN; Confusion matrix; Data analysis; Deep Learning; Gradient Boosting; Model Training; Predictive models; Random Forest; Resource management; Surveillance; Vector- Borne Disease; Vectors
• ISSN: 2642-6595
• DOI: 10.1109/ICAECC59324.2023.10560225

Before creating predictive models, exploratory data analysis (EDA) is a crucial stage in comprehending and visualising the properties of the data. EDA aids in the discovery of trends, connections, and possible predictors in the setting of vector-borne illnesses that may have an impact on their occurrence. The primary goal of research is to gather and evaluate information on the prevalence and spread of vector-borne illnesses. This entails keeping an eye on illness patterns, spotting high-risk locations, and comprehending how diseases spread. Resource allocation and public health actions are guided by surveillance data. It is crucial for this research to provide a comprehensive framework for doing EDA and putting machine learning models into practise in order to forecast the accuracy of pre-trained Random Forest, Gradient Boosting, and AdaBoost models. Depending on the properties of the dataset and the particular specifications of the vector-borne illness study that is considered, the individual implementation details and methodologies change.