The Community for Technology Leaders
Green Image
Issue No. 06 - November/December (2011 vol. 8)
ISSN: 1545-5963
pp: 1671-1677
Bing-Yu Sun , Chinese Academy of Sciences, Hefei
Zhi-Hua Zhu , Sun Yat-sen University, Guangzhou
Jiuyong Li , University of South Australia, Adelaide
Bin Linghu , Chinese Academy of Sciences, Hefei
Prognostic prediction is important in medical domain, because it can be used to select an appropriate treatment for a patient by predicting the patient's clinical outcomes. For high-dimensional data, a normal prognostic method undergoes two steps: feature selection and prognosis analysis. Recently, the L_1\hbox{-}L_2-norm Support Vector Machine (L_1\hbox{-}L_2 SVM) has been developed as an effective classification technique and shown good classification performance with automatic feature selection. In this paper, we extend L_1\hbox{-}L_2 SVM for regression analysis with automatic feature selection. We further improve the L_1\hbox{-}L_2 SVM for prognostic prediction by utilizing the information of censored data as constraints. We design an efficient solution to the new optimization problem. The proposed method is compared with other seven prognostic prediction methods on three real-world data sets. The experimental results show that the proposed method performs consistently better than the medium performance. It is more efficient than other algorithms with the similar performance.
Prognostic prediction, support vector machine, censored data, feature selection.

J. Li, B. Sun, B. Linghu and Z. Zhu, "Combined Feature Selection and Cancer Prognosis Using Support Vector Machine Regression," in IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 8, no. , pp. 1671-1677, 2010.
91 ms
(Ver 3.3 (11022016))