Abstract The kernel distance measure is proposed as a new type of class separability. The distance of samples between two classes is measured in the kernel space and used to evaluate the separability of subsets. Using the sequential forward selection algorithm as the search strategy, tests are carried out on both synthetic and real datasets. Experimental results demonstrate that the proposed method outperforms the traditional non-kernel class separability. Moreover, the proposed method is superior or close to the kernel scatter matrix measures proposed by Wang and its running time is an order of magnitude faster. When applied to the pancreatic EUS image classification, the proposed method receives a good result.
[1] Wang Lei. Feature Selection with Kernel Class Separability. IEEE Trans on Pattern Analysis and Machine Intelligence, 2008, 30(9): 1534-1546 [2] Liu Huan, Yu Lei. Toward Integrating Feature Selection Algorithms for Classification and Clustering. IEEE Trans on Knowledge and Data Engineering, 2005, 17(4): 491-502 [3] Webb A R. Statistical Pattern Recognition. 2nd Edition. New York, USA: John Wiley Sons, 2002 [4] Cai Zheyuan, Yu Jianguo, Zhang Minmin, et al. Texture Feature Extraction and Classification of Pancreatic Endoscopic Ultrasonography Images. Shanghai Journal of Biomedical Engineering, 2008, 29(3): 141-145 (in Chinese) (蔡哲元,余建国,张敏敏,等.胰腺内镜超声图像纹理特征提取与分类研究.生物医学工程学进展, 2008, 29(3): 141-145) [5] Narendra P M, Fukunaga K. A Branch and Bound Algorithm for Feature Subset Selection. IEEE Trans on Computers, 1977, 26(9): 917-922 [6] Liu H, Motoda H. Feature Selection for Knowledge Discovery and Data Mining. Boston, USA: Kluwer Academic, 1998 [7] Busetti F. Simulated Annealing Overview[EB/OL]. [2009-05-03]. http://www.geocities.com/francorbusetti/saweb.pdf [8] Muller K R, Mika S, Ratsch G, et al. An Introduction to Kernel-Based Learning Algorithms. IEEE Trans on Neural Networks, 2001, 12(2): 181-201 [9] Weston J, Mukherjee S, Chapelle O, et al. Feature Selection for SVMs // Proc of the Annual Conference on Neural Information Processing Systems. Denver, USA, 2000: 668-674
2010, Vol. 23 
