Abstract
In present time, large numbers of machine learning approaches have been applied for analysis of medical data. These approaches have also been proved its importance through accurate and earlier diagnosis of diseases. The motive of this work is to develop a diagnostic model for earlier detection and diagnosis of dengue disease. Dengue fever is a fatal and life threatening disease spreads through female mosquito’s, called Aedes aegypti. The symptoms of this fever are similar to other fibers such as viral flu, Chikungunya, Zika fever, etc. But in this fever, human life can threaten due to severe depletion of platelets. So, earlier detection of dengue disease can protect several human lives and also take curative action before it becomes an infectious disease. Hence, in this work, an effort is made to develop a PSO-ANN based diagnostic model for earlier detection of dengue fever. In the proposed model, PSO technique is applied to optimize the weight and bias parameters of ANN method. Further, PSO optimized ANN approach is used to detect dengue affected patients. The effectiveness of the proposed model is evaluated using accuracy, sensitivity, specificity, error rate and AUC parameters. The results of the proposed model are compared with some other approaches like ANN, DT, NB, and PSO. It is seen that the proposed diagnostic model is an efficient and effective model for more accurate and earlier detection of dengue fever.
Keywords —Classification, Neural Network, Decision Tree, Naive Bayes, CART, PSO