Dengue infection is caused by the mosquito Aedes aegypti. According to WHO, 50 to 100 million dengue infections will occur every year. Data-miming techniques will extract information from the raw data. Dengue symptoms are fever, severe headache, body pain, vomiting, diarrhoea, cough, pain in the abdomen, etc. The research work is carried out on real data and the patient data is collected from the Department of General Medicine, PESIMSR, Kuppam, Andrapradesh. Dataset consists of 18 attributes and one target value. Research work has been done on a binary classification to classify dengue positive (DF) and dengue negative (NDF) cases using different ML techniques. The proposed work demonstrates that ensemble techniques of bagging, boosting, and stacking give better results than other models. The Extreme Gradient Boost (XGB), Random Forest by majority voting, and stacking with different meta-classifiers are the ensemble techniques used for binary classification. The dataset is divided into 80% training and 20 % testing dataset. Performance parameters used for the analysis are accuracy, precision, recall, and f1 score, and compared the proposed model with other ML models.
The dengue infection is caused by the mosquito Aedes aegypti. According to WHO, 50 to 100 million dengue infections will occur every year. Data-miming techniques will extract information from the raw data. Dengue symptoms are fever, severe headache, body pain, vomiting, diarrhea, cough, pain in abdomen etc. The research work is carried out on real data and the patient data is collected from the Department of General Medicine, PESIMSR, Kuppam, Andrapradesh. Dataset consists of 18 attributes and one target value. Research work has been done on binary classification to classify dengue positive (DF) and dengue negative (NDF) cases using different ML techniques. The proposed work demonstrates that ensemble techniques bagging, boosting and stacking gives better results than other models. The Extreme Gradient Boost (XGB), Random Forest by majority voting and stacking with different meta classifiers are the ensemble techniques used for the binary classification. The dataset is divided into 80% training and 20 % testing dataset. Performance parameters used for the analysis are accuracy, precision, recall, and f1 score, and compared the proposed model with other ML models. The experimental results shows that the accuracy of extended boost, random forest and stacking is 98%, 99%, 99% for training dataset and 97%, 94%,98%testing dataset respectively. The extended metrics ROC, Precision -Recall curve and AUC better analysis