Identifying the Characteristics of FTIR Spectra of Herba Epimedii Icariin via Wavelet Analysis and RBF Neural Network
CHEUNG Yiu-ming1, ZHOU Qun2, GUO Bao-lin3, SUN Su-qin2*
1. Department of Computer Science, Hong Kong Baptist University, Hong Kong, China 2. Key Laboratory of Bioorganic Phosphorus Chemistry and Chemical Biology (Ministry of Education), Department of Chemistry, Tsinghua University, Beijing 100084, China 3. Institute of Medicinal Plant Development, Chinese Academy of Medical Science and Peking Union of Medical College, Beijing 100094, China
Abstract：In the present paper, the authors extracted active components of herba epimedii and their important features using Fourier transform infrared spectroscopy (FTIR), correlation coefficient comparison, and multilevel wavelet analysis. The extracted features were then used to classify herba epimedii via radial basis function (RBF) neural network. There were altogether 250 samples of the medicine with various different types, including epimedium brevicornu Maxim., E.sagittatum (Sieb. et Zucc.) Maxim, E. pubescens Maxim., E. koreanum Nakai and E wushanense T.S.Ying. An important component of herba epimedii, herba epimedii icariin, has a special peak at 1 259 cm-1 on the FTIR spectra obtained from the methanol extraction, which is consistent with the result obtained by traditional HPLC qualitative analysis. Therefore, this special peak can be used to determine if herba epimedii contains herba epimedii icariin. Furthermore, large variations in the spectrum caused by low content of icariin, weak absorption peaks and noise were successfully removed by applying correlation coefficient comparison and multilevel wavelet analysis, which significantly increased the quality of classification of RBF neural network. This paper creates a framework of fast identification of herba epimedii icariin in raw herba epimedii by FTIR spectra via wavelet analysis and RBF neural network.
[1] The Pharmacopoeia Committee of the People’s Republic of China(国家药典委员会编). Chinese Pharmacopoeia(中华人民共和国药典). Vol Ⅰ. Beijing: Chemical Industrial Publishing House(北京: 化学工业出版社), 2005. 229. [2] XU Guo-jun, XU Luo-shan, WANG Zheng-tao(徐国钧，徐珞珊，王峥涛). Species Systematization and Quality Evaluation of Commonly Used Chinese Traditional Drugs(常用中药材品种整理和质量研究). Fuzhou：Fujian Science & Technology Publishing House(福州：福建科学技术出版社)，1994. 745. [3] GUO Bao-lin, XIAO Pei-gen(郭宝林，肖培根). China Journal of Chinese Materia Medica(中国中药杂志), 2003，28(4)：303. [4] SUN Su-qin, ZHANG Xuan, QIN Zhu, et al(孙素琴，张宣，秦竹, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 1999, 19(4): 542. [5] SUN Su-qin, DU De-guo, LEUNG Hi-wun, et al(孙素琴，杜德国，梁曦云, 等). Chinese Journal of Analytical Chemistry(分析化学), 2001, 29(3): 309. [6] PENG Yong, SUN Su-qin, ZHAO Zhong-zhen, et al(彭勇，孙素琴，赵中振，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2004, 24(6): 679. [7] SUN Su-qin, ZHOU Qun, QIN Zhu(孙素琴，周群，秦竹). Atlas of Two-Dimensional Correlation Infrared Spectroscopy for Traditional Chinese Medicine Identification(中药二维相关红外光谱鉴定图集). Beijing: Chemical Industry Press(北京：化学工业出版社), 2003. [8] LI Y M, SUN S Q, ZHOU Q. Vibrational Spectroscopy, 2004, 36(2): 227. [9] Soldati F, Tanaka O. Planta Medica. 1984, 51(4): 351 [10] ZHAN Da-qi, SUN Su-qin. Lecture Notes in Computer Science, 2005, 3645: 356. [11] ZHAN Da-qi, SUN Su-qin, CHEUNG Yin-ming. Lecture Notes in Artificial Intelligence, 2005, 3801: 965. [12] ZHAN Da-qi，CHEUNG Yin-ming, SUN Su-qin(詹达琦，张晓明，孙素琴). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(8): 1497. [13] Daubechies I. Ten Lectures on Wavelets. CBMS Conf. Series in Appl. Math., vol. 61, SIAM, Philadelphia, 1992.
