Monthly Mathematical Colloquium (MMC) 2, 2019
Monthly Mathematical Colloquium (MMC) is one of the platforms where the mathematics lecturers and postgraduates could share their research and it runs bimonthly. In addition, this colloquium improves the collaboration and networking among the lecturers and postgraduates. The MMC help the postgraduates to improve their skills in presenting their research and their self-confident before they defend their proposal or thesis.
Date: 20 February 2019 (Wednesday)
Time: 09:00 – 10:00
Venue: Mathematics Support Center (MSC), Campus Gambang, UMP
Presenters: Ts. Dr. Azlyna Senawi
Title: A New Maximum Relevance-Minimum Multicollinearity (MRmMC) Method for Feature Selection and Ranking
Azlyna Senawi, Hua-Liang Wei, Stephen A. Billings
A substantial amount of datasets stored for various applications are often high dimensional with redundant and irrelevant features. Processing and analyzing data under such circumstances is time consuming and makes it difficult to obtain efficient predictive models. There is a strong need to carry out analyses for high dimensional data in some lower dimensions, and one approach to achieve this is through feature selection. This paper presents anew relevancy-redundancy approach, called the maximum relevance–minimum multicollinearity(MRmMC) method, for feature selection and ranking, which can overcome some shortcomings of existing criteria. In the proposed method, relevant features are measured by correlation characteristics based on conditional variance while redundancy elimination is achieved according to multiple correlation assessment using an orthogonal projection scheme. A series of experiments were conducted on eight datasets from the UCI Machine Learning Repositoryand results show that the proposed method performed reasonably well for feature subset selection.