Symmetry Based Feature Selection with Multi layer Perceptron for the prediction of Chronic Disease

Abstract

Huge amount of Healthcare data are produced every day from the various health care sectors. The accumulated data can be effectively analyzed to identify people's risk from chronic diseases. The process of predicting the presence or absence of the disease and also to diagnosing the various disease using the historical medical data is known as Health Care Analytics. Health care analytics will improve patient care and also the harness practice of medical practitioner. The feature selection is considered as a core aspect of the machine learning which hugely contribute towards the performance of the machine learning model. In this paper symmetry based feature subset selection is proposed to select the optimal features from the Health care data which contribute towards the prediction outcome. The Multilayer perceptron algorithm(MLP) used as a classifier which will predict the outcome by using the features which are selected from the Symmetry-based feature subset selection technique. The chronic disease dataset Diabetes, Cancer, Breast Cancer, and HeartDisease data set accumulated from UCI repository is used to conduct the experiment. The experimental results demonstrate that the proposed hybrid combination of feature selection technique and the multilayer perceptron outperforms in accuracy compare to the existing approaches.

Thai Water Buffalo Disease Analysis with the Application of Feature Selection Technique and Multi-Layer Perceptron Neural Network

“…So, the developed model can be applied to the development of an analysis system for water buffalo diseases. The results of this study conform to the research conducted in [15], in which the SMOTE+MLP method was applied for data classification and a high level of effectiveness was reached with an accuracy of 90%, and also are in accordance with [16], in applied feature selection techniques were which alongside the MLP for data classification and gained a higher level of effectiveness.…”

“…The experiment results showed that the application of SMOTE+MLP provided a data classification accuracy of 96%, which was higher than the one gained from the application of SMOTE+RBF. Authors in [16] applied feature selection along with MLP to predict chronic diseases. The research findings showed that applying these two methods provided higher effectiveness in terms of chronic disease prediction than the application of Support Vector Machine (SVM) and Decision Tree.…”