A Copula Statistic for Measuring Nonlinear Dependence with Application to Feature Selection in Machine Learning
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 7
Abstract
Feature selection in machine learning aims to find out the best subset of variables from the input that reduces the computation requirement and improves the predictor performance. In this paper, a new index based on empirical copulas, termed the Copula Statistic (CoS) to assess the strength of statistical dependence and for testing statistical independence is introduced. It is shown that this test exhibits higher statistical power than other indices. Finally, the CoS is applied to feature selection in machine learning problems, which allow a demonstration of the good performance of the CoS.
Authors and Affiliations
Mohsen Ben Hassine, Lamine Mili, Kiran Karra
Keywords
Related Articles
- EP ID EP260212
- DOI 10.14569/IJACSA.2017.080720
- Views 124
- Downloads 0
Stemmer Impact on Quranic Mobile Information Retrieval Performance
Stemming algorithms are employed in information retrieval (IR) to reduce verity variants of the same word with several endings to a standard stem. Stemmers can also help IR systems by unifying vocabulary, reducing term v...
Self-Protection against Insider Threats in DBMS through Policies Implementation
In today’s world, information security of an organization has become a major challenge as well as a critical business issue. Managing and mitigating these internal or external security related issues, organizations hire...
Creating and Protecting Password: A User Intention
Students Academic Information System (SAIS) is an application that provides academic information for the students. The security policy applied by our university requires the students to renew their SAIS password based on...
Research on Chinese University Students’ Media Images
At present, university students, as the "after 90" and a new generation of young intellectuals, are being paid generally attentions by mass media. Nevertheless, university students’ public images are on a decline as they...
Iterative Removing Salt and Pepper Noise based on Neighbourhood Information
Denoising images is a classical problem in low-level computer vision. In this paper, we propose an algorithm which can remove iteratively salt and pepper noise based on neighbourhood while preserving details. First, we c...