Classification techniques based on Artificial immune system algorithms for Heart disease using Principal Component Analysis

Abstract

The modern era is a period of machine learning, which helps in finding new facts for future predictions. Classification is a machine learning tool that helps in the discovery of knowledge in Big data and has various potential applications. Researchers nowadays are more inclined to the techniques which are inspired by nature. The artificial immune system (AIS) is such a method that is originated by the qualities of the humanoid immune system. In this paper, artificial immune stimulated classifiers as supervised learning methods are used for classifying Heart disease datasets. The performance of the classifiers strongly depends on the datasets used for learning. Here it is observed that, when the principal component analysis is performed on the standard dataset, then classifiers' accuracy and other facts show improvement in performance, which leads to a fall in errors.