Diagnosis classification of dengue fever based on Neural Networks and Genetic algorithms

• Published in: Journal of physics. Conference series Vol. 1175; no. 1; pp. 12065 - 12070
• Main Authors: Adias Sabara, Martselani, Somantri, Oman, Nurcahyo, Heru, Kurnia Achmadi, Nanang, Latifah, Ulfatul, Harsono
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.03.2019
• Subjects: Classification; Dengue fever; Diagnosis; Genetic algorithms; Machine learning; Mathematical models; Momentum; Neural networks; Optimization; Optimization techniques; Parameters
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1175/1/012065

To classify the diagnosis of dengue fever is not easy, an accurate accuracy is needed for doctors and health workers in making a decision related to the diagnosis of dengue fever. In the classification of diagnosis of dengue fever, the Neural Network is used as the model applied. To implement the Neural Network there are several parameters that we must determine such as learning rate and momentum, the problem is the absence of standard guidelines in determining the parameters to be used in this method whom the experimental method is used. For this reason, a method that can solve the problem is needed, with the parameters obtained can be optimized. The solution that can be applied with applying the Genetic Algorithm (GA) on the Neural Network, in order to optimize the learning rate parameter value and momentum. The results obtained are apparently the application of optimization techniques with Genetic Algorithms which can make it easier to find parameter values optimally and can increase the accuracy value in the Neural Network algorithm, thus the model obtained can be used for doctors and health workers in determining the classification of dengue fever diagnosis.