Improved prediction of dengue outbreak using combinatorial feature selector and classifier based on entropy weighted score based optimal ranking

Informatics in Medicine Unlocked

M.S. Mohamed Mallick¹  S. Appavu alias Balamurugan²  G. Chinthana³ 

[1] Corresponding author.;Department of Computer Science, Central University of Tamilnadu, Thiruvarur, India;Research Scholar, Information and Communication Engineering, Anna University, India;

关键词: Dengue disease prediction;    Machine learning;    Feature selection;    Classification;    Healthcare;   

DOI  :  

来源: DOAJ

【 摘 要 】

The main objective of this work is to enhance the classification performance and to improve the accuracy of prediction for health care management systems. The proposed novel feature selection algorithm named Entropy Weighted Score based Optimal Ranking Algorithm (EWSORA) is shown to be an efficient and helpful algorithm for medical data analysis and prediction. The optimal feature subset selected by the proposed algorithm to easily identify the attributes (features) is responsible for the main cause of the disease. Under this analysis, the Dengue Dataset is framed by collecting the medical laboratory test reports of many patients as real-time samples from the various health centers of the Thanjavur zone of Tamilnadu. The observation is made on a real-time dataset with the proposed method, and the results obtained outperform the results of existing methods.

【 授权许可】

Unknown