IDENTIFICATION OF ERYTHEMATO-SQUAMOUS SKIN DISEASES USING EXTREME LEARNING MACHINE AND ARTIFICIAL NEURAL NETWORK

In this work, a new identification model, based on extreme learning machine (ELM), to better identify Erythemato ? Squamous skin diseases have been proposed and implemented and the results compared to that of the classical artificial neural network (ANN). ELMs provide solutions to single- and multi- hidden layer feed-forward neural networks. ELMs can achieve high learning speed, good generalization performance, and ease of implementation. Experimental results indicated that ELM outperformed the classical ANN in all fronts both for the training and testing cases. The effect of varying size of training and testing set on the performance of classifiers were also investigated in this study. The proposed classifier demonstrated to be a viable tool in this germane field of medical diagnosis as indicated by its high accuracy and consistency of result.