Medical Data Classification Using Correlation Based Feature Selection and Multilayer Perceptron Model
Published: 2017
Author(s) Name: Amit Yerpude, Sanjeev Sharma |
Author(s) Affiliation: Assist. Prof., Dept. of Comp. Science & Engg., Rungta College of Engg. & Tech., Chhattisgarh, India.
Locked
Subscribed
Available for All
Abstract
The classification accuracy in medical diagnosis is critically very important. It is highly reliant on the quality of data and the features use for this purpose. Identifying a good set of features from the set of collected feature is very challenging nowadays because of the available size of data. This challenge can be addressed by applying feature selection method. We create a model for classification based on correlation based feature selection technique and multi layer perceptron model. We select nine different medical dataset and test the performance of the proposed model on it. The experimental results show that the classification accuracy is improved by upto 28%, and the execution time reduces upto 30% to 97% subjected to the different datasets.
Keywords: Classification, Feature selection, Medical dataset, Multilayer perceptron.
View PDF