Feature interaction maximisation

Bennasar, Mohamed, Setchi, Rossitza ORCID: https://orcid.org/0000-0002-7207-6544 and Hicks, Yulia Alexandrovna ORCID: https://orcid.org/0000-0002-7179-4587 2013. Feature interaction maximisation. Pattern Recognition Letters 34 (14) , pp. 1630-1635. 10.1016/j.patrec.2013.04.002

Full text not available from this repository.

Abstract

Feature selection plays an important role in classification algorithms. It is particularly useful in dimensionality reduction for selecting features with high discriminative power. This paper introduces a new feature-selection method called Feature Interaction Maximisation (FIM), which employs three-way interaction information as a measure of feature redundancy. It uses a forward greedy search to select features which have maximum interaction information with the features already selected, and which provide maximum relevance. The experiments conducted to verify the performance of the proposed method use three datasets from the UCI repository. The method is compared with four other well-known feature-selection methods: Information Gain (IG), Minimum Redundancy Maximum Relevance (mRMR), Double Input Symmetrical Relevance (DISR), and Interaction Gain Based Feature Selection (IGFS). The average classification accuracy of two classifiers, Naïve Bayes and K-nearest neighbour, is used to assess the performance of the new feature-selection method. The results show that FIM outperforms the other methods.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Uncontrolled Keywords:	Feature selection; Interaction information; Mutual information; Subset feature selection; Classification; Dimensionality reduction
Publisher:	Elsevier
ISSN:	0167-8655
Last Modified:	06 Jul 2023 10:18
URI:	https://orca.cardiff.ac.uk/id/eprint/46887

Citation Data

Cited 22 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item