Reinforcement Learning based Efficient Zika Virus Prediction Model: A Logistic Model Tree

Zika Virus is a Mosquito-born disease, Which is Propagating rapidly entire the world. As of now 89 countries and territories were evidence of Zika Virus($\mathbf{Z V}$) infection and still there is no specific treatment for Zika, it is primarily transmitted by the Aedes aegypti mosquito, as well as from mother to fetus, through sexual transmission, and in rare cases, via blood transfusion. Fetal loss, preterm birth, stillbirth, guillainbarre syndrome, neuropathy and myelitis are major health complications associated with $\mathbf{Z V}$, particularly affecting pregnant women and newborns. The proposed system utilizes a Logistic Model Trees(LMT) Machine Learning algorithm to predict Zikainfected individuals at an early stage more effectively by analyzing symptoms. LMT was chosen for its effectiveness in managing large, complex symptom datasets and accurately classifying the data. The algorithm separates the data into training and testing sets, where the model being constructed by optimizing the training data and the performance evaluated using testing data. The trained model simulated using Waikato Environment for Knowledge Analysis(WEKA) tool for the data of Zika virus infection condition. The proposed algorithm achieves the high accuracy of 99.8% which is more effective when compared to other existing models.