Detection of Dengue Disease Empowered with Fused Machine Learning

Elmitwally, Nouh (2022) Detection of Dengue Disease Empowered with Fused Machine Learning. ICCR 2022 IEEE proceedings. (In Press)

[img] Text
paper_8515.pdf - Accepted Version
Restricted to Repository staff only

Download (948kB)

Abstract

Dengue fever is a life-threatening illness that affects both industrialized and poor nations, including Pakistan. It is necessary to forecast the illness at an early stage to avoid it. Machine Learning (ML) methods outperform other computer approaches in terms of illness prediction. The model utilized in this study to predict dengue fever is fused with machine learning. Artificial Neural Networks (ANN) and Support Vector Machine (SVM) provide the foundation of the conceptual framework. The datasets employed in these models have been collected from a government hospital in Lahore, Pakistan for diagnosing dengue fever (positive or negative). 70% of the statistics in the dataset are training data, whereas 30% are testing data. This fused model's membership functions explain whether a dengue diagnostic is positive or negative, which controls the model's output. A cloud storage system saves the fused model based on patients' real-time information for future use. The proposed model has a 96.19 % accuracy rate, which is much greater than earlier research.

Item Type: Article
Dates:
DateEvent
6 October 2022Accepted
Uncontrolled Keywords: Dengue Fever (DF), Dengue Hemorrhagic Fever (DHF), Dengue Prediction, Prediction Fused Dengue Model (PFDM)
Subjects: CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions: Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology
Depositing User: Nouh Elmitwally
Date Deposited: 22 Nov 2022 11:42
Last Modified: 22 Nov 2022 11:42
URI: https://www.open-access.bcu.ac.uk/id/eprint/13754

Actions (login required)

View Item View Item

Research

In this section...