Title :
A Critical Study of Selected Classification Algorithms for Dengue Fever and Dengue Hemorrhagic Fever
Author :
Farooqi, Wajeeha ; Ali, Shady
Author_Institution :
Comput. Sci. & IT Dept., Univ. of Lahore, Lahore, Pakistan
Abstract :
Dengue fever is viral infection caused by dengue virus which is transmitted in human body by bite of female Eddie mosquito. There are 50 million people suffer from it globally every year. Pakistan has been victim of this rapidly growing disease from last few years. The world health organization identified two main types of dengue fever. This paper appraises the selected classification algorithms for the classification of dengue fever (DF) and dengue haemraghic fever (DHF) datasets. Naïve Bayes classifier, Decision Tree, K-nearest neighbor algorithm, multilayered perception algorithm and Support vector machines are considered here for classification of dengue fever. These algorithms are measured based on five criteria: Accuracy, Precision, Sensitivity, Specificity and false negative rate.
Keywords :
Bayes methods; decision trees; diseases; medical diagnostic computing; microorganisms; multilayer perceptrons; pattern classification; support vector machines; K-nearest neighbor algorithm; Pakistan; accuracy; classification algorithm; decision tree; dengue fever; dengue hemorrhagic fever; dengue virus; disease; false negative rate; female Eddie mosquito; human body; multilayered perception algorithm; naïve Bayes classifier; precision; sensitivity; specificity; support vector machine; viral infection; Accuracy; Classification algorithms; Decision trees; Hospitals; Pain; Sensitivity; Support vector machines; Dataminingmining; dengue fever; supervised machine learning;
Conference_Titel :
Frontiers of Information Technology (FIT), 2013 11th International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4799-2293-2
DOI :
10.1109/FIT.2013.33