A novel approach to stellar recognition by combining EKF and RBF net

CASIA OpenIR > 09年以前成果

	A novel approach to stellar recognition by combining EKF and RBF net
	Bai, L ; Guo, P ; Yin, FL ; Wang, J; Guo, CG
发表期刊	ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1
	2004
卷号	3173 页码:1002-1007
文章类型	Article
摘要	A new approach to stellar recognition is proposed. It uses extended Kalman filter as a feature selector and pre-classifier for stellar spectra data, while radial basis function neural networks is adopted for classification. Experiments with real-world data set show that the performance of the proposed technique is quite well, and the correct classification rate can reach as high as 93%. It is shown that the result using EKF is better than that using principle component analysis data dimension reduction technique.
WOS标题词	Science & Technology ; Technology
收录类别	ISTP ; SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号	WOS:000223492600165
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/9035
专题	09年以前成果
作者单位	1.Beijing Normal Univ, Dept Comp Sci, Beijing 100875, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Bai, L,Guo, P,Yin, FL,et al. A novel approach to stellar recognition by combining EKF and RBF net[J]. ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1,2004,3173:1002-1007.
APA	Bai, L,Guo, P,Yin, FL,Wang, J,&Guo, CG.(2004).A novel approach to stellar recognition by combining EKF and RBF net.ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1,3173,1002-1007.
MLA	Bai, L,et al."A novel approach to stellar recognition by combining EKF and RBF net".ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1 3173(2004):1002-1007.