Abstract :

This Paper Presents An AI-based Method For Finding Dengue Early Utilizing “complete Blood Count (CBC)” Data. We Use “different Feature Selection Methods, Such As Pearson Correlation”, “Recursive Feature Elimination (RFE) With Random Forest, SelectKBest, Chi-square (Chi2), And ExtraTree, To Find The Most Important Features”. There Are Many ML And DL Algorithms Used, Such As Logistic Regression, “support Vector Machine (SVM), Naive Bayes, Random Forest, AdaBoost, XGBoost, Multi-Layer Perceptron (MLP), LightGBM, And Ensemble Methods Like A Stacking Classifier (XGB + LR + MLP With LightGBM) And Voting Classifier (Boosted Decision Tree + ExtraTree). DL Architectures Including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Bidirectional Long Short-term Memory (Bi-LSTM), Feedforward Neural Networks (FNN), Transformer, And Hybrid Models Like CNN + LSTM Are Used”. Ensemble Approaches Improve The Resilience And Accuracy Of Predictions By Combining Them From Different Models. “The Voting Classifier, For Example, Gets 98% Accuracy And An F1 Score. Using Hybrid Models, Especially CNN + LSTM, Makes The System Work Even Better”. The Method Is Meant To Let Users Interact With It And Check It Through A Flask-based UI With Authentication. This Makes It Easy To Use And Safe While Keeping The Predicted Accuracy High. “Index Terms - Complete Blood Count, Dengue Prediction, Explainable AI, Feature Selection, Machine Learning, Ensemble Learning, Transformer Model”.

Published:

11-7-2025

Issue:

Vol. 25 No. 7 (2025)

Page Nos:

251-261

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite