PREDICTION OF DENGUE OUTBREAKS IN PERSPECT OF BANGLADESH USING ARTIFICIAL INTELLIGENCE
No Thumbnail Available
Date
2021-03-20
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Dengue Fever is a disease that has grown worldwide in the last few years. The
information about the patients can be maintained with clinical documents. By keeping
huge volume of clinical documents we can easily predict the occurrence of dengue
disease in the patients. Dengue is considered to be one of the vital diseases which are
spreading in more than 110 countries. It is a vector borne disease caused by the
mosquitoes of female Aedes Albopictus and Aedes Aegypti which are well suited
human environment. With nearly 45,000 cases reported all over Bangladesh in the last
year. Dengue fever has become a major health hazard in Bangladesh over the past few
years. Several studies show that which variable is related to the disease, however, as far
as we know there is no effective study in Bangladesh that reveals this relation. This
research shows the accuracy of different algorithms of Artificial Neural Network
(ANN) to predict Dengue outbreaks. Firstly, data is collected from different hospitals,
and then data is normalized. Data is analyzed to see the infection rate of different
parameters. Then data is splitted for training and testing and finally find the best
accuracy for different Multi-layer perceptron algorithms such as Scaled Conjugate
Gradient (SCG), Levenberg–Marquardt (LM) based on back propagation algorithm and
Learning Vector Quantization (LVQ). In this work, an analysis of the influence of
variables is performed and shows the efficiency of the neural networks is used to predict
the number of disease cases. Accuracy of SCG, LM and LVQ algorithm is 87.1%, 95%
and 90.3% with MSE 0.137, 0.0241 and 0.0967 respectively. And decision tree
algorithm gives 98.92% in training stage but 90% accuracy gives in validation and
testing. LM outperforms with minimum MSE than other algorithm. Thus, this work
finds an efficient prediction model for dengue cases for districts of Bangladesh.