Open    Access



Comparison of Different Types of Artificial Neural Networks for Diagnosing Thyroid Disease



Author(s)

Rehab Abdulmunem Ali Alshireef

Full-Text PDF XML     374 Views

DOI:10.17265/2328-2150/2023.03.001

Thyroid disease is one of major causes of severe medical problems for human beings. Therefore, proper diagnosis of thyroid disease is considered as an important issue to determine treatment for patients. In this paper, three methods of using neural network to achieve high precision are compared. The first one is using a multilayer feed forward architecture of artificial neural network (ANN) is adopted in the proposed design, and the back propagation is selected as learning algorithm to accomplish the training process, with 3 inputs, 5 nodes of hidden layer and 8 output but only one is active with accuracy 99.2%. Second one will be a Multi-layer Perceptron (MLP) ANN using back propagation learning algorithm to classify Thyroid disease. It consists of an input layer with 5 neurons, a hidden layer with 6 neurons and an output layer with just 1 neuron with accuracy 98.6%. Third one a multilayer feed forward network with Genetic Algorithm the input layer with 5 neurons equal to the number of the dataset features, 1 hidden layer which its neurons will be determined by the GA and it’s 4 gene, and the output layer with only 1 neuron, the overall accuracy is 100% for training and in range between 96% and 98% for testing.

Artificial Neural Network, Thyroids disease.

Alshireef, R. A. A. 2023. "Comparison of Different Types of Artificial Neural Networks for Diagnosing Thyroid Disease." Journal of Pharmacy and Pharmacology 11 (3): 45-55.