The new issues for classification problems

Md Mahmudul Hasan, University of Texas at El Paso

Abstract

The data involved with science and engineering getting bigger everyday. To study and organize a big amount of data is difficult without classification. In machine learning, classification is the problem of identifying a given data from a set of categories. There are several classification technique people using to classify a given data. In our work we present a sparse representation technique to perform classification. The popularity of this technique motivates us to use on our collected samples. To find a sparse representation, we used an ℓ1-minimization algorithm which is a convex relaxation algorithm proven very efficient by researchers. The purpose of our work lies in presenting the new methodology in a simple manner to the community for easy understanding. We have applied two types of dataset to present the performance of the proposed method. One dataset involves with a small number of features and another involves with a large number of features. For a small number of features, we used classic Fisher Iris dataset incorporated in Matlab environment and for the large number of features, we used gene expression dataset. The results from the numerical experimentation provides the efficiency of the presented method. Studying and organizing a large amount of data is costly and time consuming. Our future work aims in compressing the size of the data using model order reduction to reduce the time and cost. At the same time we are also interested to improve the performance of the proposed method.

Subject Area

Mathematics|Computer science

Recommended Citation

Hasan, Md Mahmudul, "The new issues for classification problems" (2016). ETD Collection for University of Texas, El Paso. AAI10151258.
https://scholarworks.utep.edu/dissertations/AAI10151258

Share

COinS