Welcome to the InfoSci Platform
Reference Hub5
A Cosine-Similarity Mutual-Information Approach for Feature Selection on High Dimensional Datasets

A Cosine-Similarity Mutual-Information Approach for Feature Selection on High Dimensional Datasets

Vimal Kumar Dubey, Amit Kumar Saxena
Copyright: © 2017 |Volume: 10 |Issue: 1 |Pages: 14
ISSN: 1938-7857|EISSN: 1938-7865|EISBN13: 9781522511878|DOI: 10.4018/JITR.2017010102
Cite Article Cite Article

MLA

Dubey, Vimal Kumar, and Amit Kumar Saxena. "A Cosine-Similarity Mutual-Information Approach for Feature Selection on High Dimensional Datasets." JITR vol.10, no.1 2017: pp.15-28. http://doi.org/10.4018/JITR.2017010102

APA

Dubey, V. K. & Saxena, A. K. (2017). A Cosine-Similarity Mutual-Information Approach for Feature Selection on High Dimensional Datasets. Journal of Information Technology Research (JITR), 10(1), 15-28. http://doi.org/10.4018/JITR.2017010102

Chicago

Dubey, Vimal Kumar, and Amit Kumar Saxena. "A Cosine-Similarity Mutual-Information Approach for Feature Selection on High Dimensional Datasets," Journal of Information Technology Research (JITR) 10, no.1: 15-28. http://doi.org/10.4018/JITR.2017010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

A novel hybrid method based on Cosine Similarity and Mutual Information is presented to find out relevant feature subset. Initially, the supervised Cosine Similarity of each feature is calculated with respect to the class vector and then features are grouped based on the obtained cosine similarity values. From each group the best mutual informative feature is selected. The selected features subset is tested using the three classifiers namely Naïve Bayes (NB), K-Nearest Neighbor and Classification and Regression trees (CART) for getting classification accuracy. The proposed method is applied to various high dimensional datasets. Obtained results showed that the proposed method is capable of eliminating the redundant and irrelevant features.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.