Analysis of Infrared Spectroscopy of Ginsengs by Support Vector Machine and Wavelet Transform
JIN Xiang-jun1,ZHANG Yong2, 3,XIE Yun-fei1,CONG Qian2,ZHAO Bing1*
1. State Key Laboratory for Supramolecular Structure and Material, Ministry of Education, Jilin University, Changchun 130012, China 2. Key Laboratory for Terrain-Machine Bionics Engineering, Ministry of Education, Jilin University, Changchun 130022, China 3. Jilin Teacher’s Institute of Engineering and Technology, Changchun 130052, China
Abstract：In the present study, 40 samples of ginsengs (20 samples from Jian and 20 samples from Fushun) were surveyed by Fourier transform infrared (IR) spectroscopy. Meanwhile, in order to eliminate the spectral differences from the baseline drifts, the original ginseng spectra were processed using first derivative method. To avoid enhancing the noise resulting from the derivative the spectra were smoothed. This smoothing was done by using the Savitzky-Golay algorithm, a moving window averaging method. Artificial neural network (ANN), support vector machine (SVM) as the new pattern recognition technology, and wavelet transform (WT) were applied. Firstly, the spectrum variables of infrared spectroscopy were compressed through the WT technology before the models were established, in order to reduce the time in establishing models. Then, the identification models of cultivation area of ginsengs were studied comparatively by the use of ANN and SVM methods. The corresponding important parameters of models were also discussed in detail, including the parameters of wavelet compressing and training parameters of ANN and SVM models. The simulation experiment indicated that the ANN model can carry on the distinction among 40 samples of ginsengs from Jilin, and the accuracy rate of identification was 92.5%. The radial basis function (RBF) SVM classifiers and the polynomial SVM classifiers were studied comparatively in this experiment. The best experimental results were obtained using RBF SVM classifier with σ=0.6, and the accuracy rate of identification was 97.5%. Finally, compared with ANN approach, SVM algorithm showed its excellent generalization for identification results while the number of samples was smaller. The overall results show that IR spectroscopy combined with SVM and WT technology can be efficiently utilized for rapid and simple identification of the cultivation area of ginsengs, and thus provides the certain technology support and the foundation for further researching ginseng and other IR applications.
金向军1,张勇2,3,谢云飞1,丛茜2,赵冰1* . 基于支持向量机及小波变换的人参红外光谱分析[J]. 光谱学与光谱分析, 2009, 29(03): 656-660.
JIN Xiang-jun1,ZHANG Yong2, 3,XIE Yun-fei1,CONG Qian2,ZHAO Bing1*. Analysis of Infrared Spectroscopy of Ginsengs by Support Vector Machine and Wavelet Transform. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(03): 656-660.
[1] HE Yong, LI Xiao-li, DENG Xun-fei. Journal of Food Engineering, 2007, 79: 1238. [2] PANG Tao-tao, YAO Jian-bin, DU Li-ming(庞涛涛, 姚建斌, 杜黎明). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(7): 1336. [3] TANG Yan-feng, ZHANG Zhuo-yong, FAN Guo-qiang, et al(汤彦丰, 张卓勇, 范国强, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2005, 25(5): 715. [4] LI Xiao-yu, ZHANG Xin-feng, SHEN Lan-sun(李晓宇, 张新峰, 沈兰荪). Measurement & Control Technology(测控技术), 2006, 25 (5): 7. [5] Feisi Technical Product Research and Development Center(飞思科技产品研发中心编). The Theory of Wavelet Transform and Its Realizations in MATLAB 7(小波分析理论与MATLAB 7实现). Beijing: Publishing House of Electronics Industry(北京：电子工业出版社), 2005. 114. [6] TIAN Gao-you, YUAN Hong-fu, LIU Hui-ying, et al(田高友, 袁洪福, 刘慧颖, 等). Journal of Instrumental Analysis(分析测试学报)，2005, 24(1): 17. [7] LIU Ming-yang, MENG Yu, LI Jun-feng, et al. Chinese Chemical Letters, 2006, 17: 1209. [8] LU Yong-jun, QU Yan-ling, CAO Zhi-qiang, et al(卢永军, 曲艳玲, 曹志强, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26(8): 1457. [9] YE Zheng-liang, YU Ke, CHENG Yi-yu(叶正良, 虞 科, 程翼宇). Chemical Journal of Chinese Universities(高等学校化学学报), 2007, 28(3): 441. [10] FAN Lu, WANG Mei-mei, YANG Hong-wei, et al(范 璐, 王美美, 杨红卫, 等). Chinese Journal of Analytical Chemistry(分析化学), 2007, 35: 390. [11] LIU Yan, LIU Shun-hang, WANG Jun-quan, et al(刘 岩, 刘顺航, 王俊全, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(6): 1093. [12] LI Yan-kun, SHAO Xue-guang, CAI Wen-sheng(李艳坤, 邵学广, 蔡文生). Chemical Journal of Chinese Universities(高等学校化学学报), 2007, 28(2): 246. [13] LI Ying-ming, SUN Su-qin, ZHOU Qun, et al. Vibrational Spectroscopy, 2004, 34: 227. [14] LI Xiao-li, HE Yong, QIU Zheng-jun(李晓丽, 何 勇, 裘正军). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(2): 279. [15] SHAO Yong-ni, HE Yong, WANG Yan-yan. European Food Research and Technology, 2007, 224: 591. [16] ZHAO Jie-wen, CHEN Quan-sheng，HUANG Xing-yi，et al. Journal of Pharmaceutical and Biomedical Analysis，2006, 41: 1198. [17] LI Ning, WANG Yan, XU Ke-xin. Optics Express, 2006, 14(17): 7630. [18] Alessandra B, et al. Analytica Chimica Acta, 2006, 579: 25. [19] Lü Jian-feng, DAI Lian-kui(吕剑峰, 戴连奎). Chinese Journal of Analytical Chemistry(分析化学), 2007, 35(3): 340.
