Data Reduction and Regression Using Principal Component Analysis in Qualitative Spatial Reasoning and Health Informatics

Abstract

The central idea of principal component analysis (PCA) is to reduce the dimensionality of a dataset consisting of a large number of interrelated variables, while retaining as much as possible of the variation present in the dataset. In this paper, we use PCA based algorithms in two diverse genres, qualitative spatial reasoning (QSR) to achieve lossless data reduction and health informatics to achieve data reduction along with improved regression analysis respectively. In an adaptive hybrid approach, we have employed PCA to traditional regression algorithms to improve their performance and representation. This yields prediction models that have both a better fit and reduced number of attributes than those produced by using standard logistic regression alone. We present examples using both synthetic data and real health datasets from UCI Repository.