光谱学与光谱分析 |
|
|
|
|
|
A Novel Spectrum Feature Extraction Method |
LI Xiang-ru1, FENG Chun-ming2, WANG Yong-jun1, LU Yu1 |
1. School of Mathematical Sciences, South China Normal University, Guangzhou 510631, China 2. Dongchang College, Liaocheng University, Liaocheng 252000, China |
|
|
Abstract The present focuses on the celestial spectra feature extraction problem, which is a key procedure in automatic spectra classification. By extracting features, the authors can reduce redundancy, alleviate noise influence, and improve accuracy and efficiency in spectra classification. The authors introduced a novel feature analysis framework STP (space transformation and partition), which focuses on four essential components in feature extraction: decompose and reorganize spectrum components, reorganize, alleviate noise influence and eliminate redundancy. Based on STP, we can analyze most of the available feature extraction methods, for example, the unsupervised methods principal component analysis (PCA), wavelet transform, the supervised methods support vector machine (SVM), relevance vector machine (RVM), linear discriminant analysis (LDA), etc. We introduced a novel feature analysis framework and proposed a novel feature extraction method. The outstanding characteristics of the proposed method are its simplicity and efficiency. Researches show that it is sufficient to extract features by the proposed method in some cases, and it is not necessary to use the sophisticated methods, which is usually more complex in computation. The proposed method is evaluated in classifying Galaxy and QSO spectra, which is disturbed by red shift and is representative in automatic spectra classification research. The results are practical and helpful to gain novel insight into the traditional feature extraction methods and design more efficient spectrum classification method.
|
Received: 2011-01-03
Accepted: 2011-04-10
|
|
Corresponding Authors:
LI Xiang-ru
E-mail: xiangru.li@gmail.com
|
|
[1] ZHAO Mei-fang, WU Chao, LUO A-li, et al(赵梅芳, 吴 潮, 罗阿理). Acta Astronomica Sinica(天文学报), 2007, 48(1): 1. [2] LI Xiang-ru, HU Zhan-yi, ZHAO Yong-heng, et al(李乡儒, 胡占义, 赵永恒, 等). Spectroscopy and Spectral Analysis (光谱学与光谱分析),2009, 29(6): 1702. [3] Li X, Lu Y, Wang Y. International Conference on Information Science and Technology, 2011. 712. [4] Gaspar G, Valerie L. Astronomy and Astrophysics, 1998, 332: 459. [5] LIU Rong, DUAN Fu-qing, LIU San-yang, et al(刘 蓉, 段福庆,刘三阳,等). Acta Electronica Sinica(电子学报), 2005,33(11): 2059. [6] ZHANG Huai-fu,ZHAO Rui-zhen,LUO A-li(张怀福, 赵瑞珍, 罗阿理). Journal of Beijing Jiaotong University(北京交通大学学报), 2008, 32(2): 30. [7] Li X, Hu Z, Wu Fuchao. Pattern Recognition, 2007, 40(6): 1756. [8] DUAN Fu-qing, ZHOU Ming-quan, ZHANG Jia-cai(段福庆, 周明全, 张家才). Journal of Jilin University (Engineering and Technology Edition)(吉林大学学报·工学版), 2007, 37(3): 634. [9] LIU Rong, DUAN Fu-qing, LIU San-yang, et al(刘 蓉, 段福庆, 刘三阳, 等). Journal of Ecttonics&Information Teehnology(电子与信息学报), 2006, 28(2): 312. [10] Li X, Hu Z. International Journal of Computer Vision, 2010, 89(1): 1. [11] Li X R, Li X M, Li H, et al. Acta Automatica Sinica, 2009, 35(1): 17. [12] Abazajian K N, Adelman-McCarthy J K, Agüeros M A, et al. The Astrophysical Journal Supplement, 2009, 182(2): 543. [13] LI Xiang-ru, HU Zhan-yi, ZHAO Yong-heng, et al(李乡儒, 胡占义, 赵永恒, 等). Acta Astronomica Sinica(天文学报), 2007, 48(3): 280. |
[1] |
MA Yang, ZHANG Ji-fu, CAI Jiang-hui, YANG Hai-feng, ZHAO Xu-jun*. Parallel Extraction and Analysis of Abnormal Features of QSO Spectra Based on Sparse Subspace[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(04): 1086-1091. |
[2] |
LI Xin-xing1, LIANG Bu-wen1, BAI Xue-bing1, LI Na2*. Research Progress of Spectroscopy in the Detection of Soil Moisture Content[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(12): 3705-3710. |
[3] |
CEN Yi1, ZHANG Lin-shan1,2, SUN Xue-jian1*, ZHANG Li-fu1, LIN Hong-lei1, ZHAO Heng-qian3, WANG Xue-rui4. Spectral Analysis of Main Mineral Pigments in Thangka[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(04): 1136-1142. |
[4] |
ZHAO Heng-qian1, ZHAO Xue-sheng1*, CEN Yi2, YANG Hang2 . Research on the Impact of Absorption Feature Extraction on Spectral Difference Between Similar Minerals [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(03): 869-874. |
[5] |
SHI Zhi-xin1, 2, 3, Georges Comte2, 4, LUO A-li2*, TU Liang-ping5, ZHAO Yong-heng2, WU Fu-chao1 . The Backgroud Sky Subtraction Around [OIII] Line in LAMOST QSO Spectra [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(11): 3132-3135. |
[6] |
GAI Ying-ying1,2,FAN Wen-jie1*,XU Xi-ru1,YAN Bin-yan1,WANG Huan-jiong3,4,LIU Yuan1 . Flower Species Identification and Coverage Estimation Based on Hyperspectral Remote Sensing Data in Hulunbeier Grassland [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2011, 31(10): 2778-2783. |
[7] |
LI Xiang-ru1, LU Yu1, ZHOU Jian-ming2, WANG Yong-jun1 . Galaxy/Quasar Classification Based on Nearest Neighbor Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2011, 31(09): 2582-2585. |
[8] |
LI Xiang-ru1, 2, 5,HU Zhan-yi1,ZHAO Yong-heng3,LI Xiao-ming4 . RVM Supervised Feature Extraction and Seyfert Spectra Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(06): 1702-1706. |
[9] |
LI Xiang-ru1,HU Zhan-yi1*,ZHAO Yong-heng2. Supervised Feature Extraction Based on FDA and Galaxy Spectra Classification [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2007, 27(09): 1898-1901. |
[10] |
LI Xiang-ru1,2,LIU Zhong-tian1,2,HU Zhan-yi1*,WU Fu-chao1,ZHAO Yong-heng2 . Celestial Spectrum Flux Standardization for Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2007, 27(07): 1448-1451. |
[11] |
LIU Rong1,LIU San-yang1,ZHAO Rui-zhen2 . An Auto-Extraction Method of Spectral Line for Normal Galaxy Spectra [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2006, 26(03): 583-586. |
[12] |
ZHAO Mei-fang1, LUO A-li2, WU Fu-chao1, HU Zhan-yi1 . Automated Recognition of Quasars Based on Adaptive Radial Basis Function Neural Networks[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2006, 26(02): 377-381. |
[13] |
XU Xin1,2, WU Fu-chao1, HU Zhan-yi1, LUO A-li2 . A Novel Method for the Determination of Redshifts of Normal Galaxies by Non-Linear Dimensionality Reduction [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2006, 26(01): 182-186. |
[14] |
LIU Rong1, DUAN Fu-qing2*, LUO A-li3. A Method for Redshift Determination of Quasars Based on Cross Correlation[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2005, 25(07): 1155-1157. |
[15] |
XU Xin1,2,LUO A-li2,WU Fu-chao1,ZHAO Yong-heng2 . Using Neural Networks Based Template Matching Method to Obtain Redshifts of Normal Galaxies[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2005, 25(06): 996-1001. |
|
|
|
|