Prediction of Skin Disease using Decision Tree and Artificial Neural Network (ANN)

Apply

Prediction of Skin Disease using Decision Tree and Artificial Neural Network (ANN)

Journal Title: Annals. Computer Science Series - Year 2018, Vol 16, Issue 1

Abstract

Skin diseases are common diseases that exist between the children and adults in the society. The issue of finding and proffering a better skin disease predictive model in the health care system has been identified to be major problem. Thus, this study provides a comparative evaluation on two data mining classification techniques; Decision Tree and Multi-layer Neural Network apply for the prediction of skin diseases. All experimental analysis were carried out in WEKA data mining tool environment. Each individual classifier was put through training and testing using the N-fold cross validation technique (N value was set to 10). The two classifiers are Decision Tree and Neural Network family respectively. The predictive model obtained from the J48 and Multi-layer Perceptron (MLP) was measured and evaluated accordingly with the use of basic parameters such as accuracy, kappa statistics, TP Rate, FP Rate, Precision, Recall, ROC area. Multi-layer neural network presented accuracy of 96.9945 % while J48 gave an accuracy of 93.9891%.

Authors and Affiliations

Tinuke Omolewa Oladele, Dorcas Romoke Olarinoye, Samuel Segun Adebisi

Keywords

EP ID EP540173
DOI -
Views 107
Downloads 0