A novel multi-class imbalance method based on the SVDD

Dong Cui; Qiang Zhang; Zhimin Miao

doi:10.1117/12.832374

30 October 2009 A novel multi-class imbalance method based on the SVDD

Dong Cui, Qiang Zhang, Zhimin Miao

Proceedings Volume 7498, MIPPR 2009: Remote Sensing and GIS Data Processing and Other Applications; 749856 (2009) https://doi.org/10.1117/12.832374
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

In the application of machine learning, there is data imbalance problem generally. In view of multi-class imbalance particularities, in this paper a new method named Multi-SVDD is proposed. And it is presented aimed to solving the problem of multi-class imbalance based on the existing Support Vector Data Description (SVDD), which is used to solve multi-class learning questions and the solution method for two-class imbalance problem. It was verified on the UCI data set, and compared with multi-class classification method proposed. The experiment has indicated that the Multi-SVDD algorithm is efficient when it is used to solve the multi-class imbalanced classification problems.

Citation Download Citation

Dong Cui, Qiang Zhang, and Zhimin Miao "A novel multi-class imbalance method based on the SVDD", Proc. SPIE 7498, MIPPR 2009: Remote Sensing and GIS Data Processing and Other Applications, 749856 (30 October 2009); https://doi.org/10.1117/12.832374

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available