Dengue fever anticipation: insights from advanced ml and deep learning models

Abstract

Recently, there has been a significant increase in the prevalence of physical illnesses, including dengue disease, drawing considerable attention due to its impact on a large population. The severity of the illness can be better understood by analyzing differences between normal and affected diagnostic reports. With numerous studies focused on understanding dengue disease, there are promising opportunities for advancing diagnostic techniques. In this study, I used the utilization of algorithmic models for early identification and raising awareness of potential threats. My straightforward approach is suitable for predicting simple cases of dengue disease illness in real-world scenarios. I have collected the dataset from Jamalpur Sadar Hospital. I employed various classifiers, including Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Convolution Neural Network (CNN), Long Short-Term Memory Network (LSTM), Bi-Directional Long Short-Term Memory Network (BLSTM), Random Forest (RF), Logistic Regression (LR), Gradient Boosting (GB), K-Nearest Classifier (KNN), Adaboost Classifier (ABC), Decision Tree (DT), Support Vector Machine (SVM), Quadratic Discriminant Analysis (QDA), Ridge Classifier (RC), Passive Aggressive (PA), Gaussian Naïve Bayes (GNB) and ensemble techniques. Notable results were achieved, with the Ridge Classifier (RC) standing out as the most accurate, achieving an impressive accuracy rate of 96%. I implemented hyperparameter tuning to optimize the performance of each classifier. Through an experimental investigation and a review of recent findings, I confirmed that the bagging classifier Ridge Classifier (RC) performed exceptionally well, accurately predicting dengue disease with an accuracy rate of 96%.