Hadamard Kernel SVM with applications for breast cancer outcome predictions.

Journal: BMC systems biology
Published Date: Dec 21, 2017

Abstract

BACKGROUND: Breast cancer is one of the leading causes of deaths for women. It is of great necessity to develop effective methods for breast cancer detection and diagnosis. Recent studies have focused on gene-based signatures for outcome predictions. Kernel SVM for its discriminative power in dealing with small sample pattern recognition problems has attracted a lot attention. But how to select or construct an appropriate kernel for a specified problem still needs further investigation.

Authors

  • Hao Jiang
    Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences , 555 Zuchongzhi Road, Shanghai 201203, China.
  • Wai-Ki Ching
    Department of Mathematics, The University of Hong Kong, Pokfulam Road, Hong Kong, Hong Kong.
  • Wai-Shun Cheung
    Department of Mathematics, The University of Hong Kong, Pokfulam Road, Hong Kong, Hong Kong.
  • Wenpin Hou
    Department of Mathematics, The University of Hong Kong, Pokfulam Road, Hong Kong, Hong Kong.
  • Hong Yin
    Department of Mathematics, School of Information, Renmin University of China, No.59 Zhong Guan Cun Avenue, Hai Dian District, Beijing, 100872, China. yinxiaohong82@hotmail.com.

Keywords

External Resources

Popular Topics
Recent Journals