Multilayer Perceptron Based Mobile Application for Diagnosing Typhoid Fever

Abstract

Typhoid fever is a significant infectious disease that poses a threat to public health, particularly in areas with inadequate sanitation and limited access to clean water. Prompt and accurate diagnosis of typhoid fever is crucial for effective treatment and prevention of complications. In this study, we propose a typhoid fever diagnosis system based on a Multilayer Perceptron Neural Network. The Multilayer Perceptron Neural Network was trained using a typhoid fever dataset obtained from Adetoyin Hospital, Ado-Ekiti, Nigeria. The dataset was pre-processed to normalize the input features, and split into training and testing sets. The multilayer perceptron architecture was optimized through the selection of appropriate activation functions, the number of hidden layers, and the number of neurons in each layer. Experimental results demonstrate the effectiveness of the proposed typhoid fever diagnosis mobile application. The system achieves a high accuracy rate in classifying patients, thereby providing reliable and efficient diagnosis tool for typhoid fever. The system will be of great benefit in the health sector.