Mutual Information-Based Unsupervised Feature Transformation for Heterogeneous Feature Subset Selection

TL;DR

This paper introduces an unsupervised mutual information-based feature transformation method that converts non-numerical features into numerical form, enhancing the effectiveness of feature selection algorithms on heterogeneous data.

Contribution

It proposes a novel, unbiased unsupervised feature transformation technique that improves mutual information-based feature selection for heterogeneous datasets.

Findings

UFT improves classification accuracy over traditional methods.

UFT is MI-based and independent of class labels.

UFT enhances the performance of existing FS algorithms.

Abstract

Conventional mutual information (MI) based feature selection (FS) methods are unable to handle heterogeneous feature subset selection properly because of data format differences or estimation methods of MI between feature subset and class label. A way to solve this problem is feature transformation (FT). In this study, a novel unsupervised feature transformation (UFT) which can transform non-numerical features into numerical features is developed and tested. The UFT process is MI-based and independent of class label. MI-based FS algorithms, such as Parzen window feature selector (PWFS), minimum redundancy maximum relevance feature selection (mRMR), and normalized MI feature selection (NMIFS), can all adopt UFT for pre-processing of non-numerical features. Unlike traditional FT methods, the proposed UFT is unbiased while PWFS is utilized to its full advantage. Simulations and analyses of large-scale datasets showed that feature subset selected by the integrated method, UFT-PWFS, outperformed other FT-FS integrated methods in classification accuracy.