Study on the Early Detection of Sclerotinia of Brassica Napus Based on Combinational-Stimulated Bands
LIU Fei1, FENG Lei1, LOU Bing-gan2*, SUN Guang-ming1, WANG Lian-ping3, HE Yong1
1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310029, China 2. Institute of Biotechnology, Zhejiang University, Hangzhou 310029, China 3. Institute of Plant Protection and Micrology，Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, China
Abstract：The combinational-stimulated bands were used to develop linear and nonlinear calibrations for the early detection of sclerotinia of oilseed rape (Brassica napus L.). Eighty healthy and 100 Sclerotinia leaf samples were scanned, and different preprocessing methods combined with successive projections algorithm (SPA) were applied to develop partial least squares (PLS) discriminant models, multiple linear regression (MLR) and least squares-support vector machine (LS-SVM) models. The results indicated that the optimal full-spectrum PLS model was achieved by direct orthogonal signal correction (DOSC), then De-trending and Raw spectra with correct recognition ratio of 100%, 95.7% and 95.7%, respectively. When using combinational-stimulated bands, the optimal linear models were SPA-MLR (DOSC) and SPA-PLS (DOSC) with correct recognition ratio of 100%. All SPA-LS-SVM models using DOSC, De-trending and Raw spectra achieved perfect results with recognition of 100%. The overall results demonstrated that it was feasible to use combinational-stimulated bands for the early detection of Sclerotinia of oilseed rape, and DOSC-SPA was a powerful way for informative wavelength selection. This method supplied a new approach to the early detection and portable monitoring instrument of sclerotinia.
Key words：Visible/near infrared spectroscopy;Sclerotinia of oilseed rape;Direct orthogonal signal correction;Successive projections algorithm;Least squares-support vector machine
刘 飞1，冯 雷1，楼兵干2*，孙光明1，王连平3，何 勇1 . 基于组合模拟波段的油菜菌核病早期诊断方法研究 [J]. 光谱学与光谱分析, 2010, 30(07): 1934-1938.
LIU Fei1, FENG Lei1, LOU Bing-gan2*, SUN Guang-ming1, WANG Lian-ping3, HE Yong1 . Study on the Early Detection of Sclerotinia of Brassica Napus Based on Combinational-Stimulated Bands . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(07): 1934-1938.
[1] ZHANG Guo-ping, ZHOU Wei-jun(张国平, 周伟军). Cultivation of Crops(作物栽培学). Hangzhou: Zhejiang University Press(杭州: 浙江大学出版社), 2001. [2] YAN Yan-lu, ZHAO Long-lian, HAN Dong-hai, et al(严衍禄, 赵龙莲, 韩东海, 等). The Foundation and Application of Near Infrared Spectroscopy Analysis(近红外光谱分析基础与应用). Beijing: China Light Industry Press(北京: 中国轻工业出版社), 2005. [3] Liu F, He Y, Sun G M. Journal of Agricultural and Food Chemistry, 2009, 57: 4520. [4] QIU Zheng-jun, SONG Hai-yan, HE Yong, et al(裘正军, 宋海燕, 何 勇, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2007, 23(7): 150. [5] Müller K, Bttcher U, Meyer-Schatz F, et al. Biosystems Engineering, 2008, 101: 172. [6] ZHANG Xiao-dong, MAO Han-ping(张晓东, 毛罕平). Transactions of the Chinese Society for Agricultural Machinary(农业机械学报), 2009, 40(2): 164. [7] LIU Fei, ZHANG Fan, FANG Hui, et al(刘 飞, 张 帆, 方 慧, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2009, 29(11): 3079. [8] Liu F, Zhang F, Jin Z L, et al. Analytica Chimica Acta, 2008, 629: 56. [9] LIU Fei, FANG Hui, ZHANG Fan, et al(刘 飞, 方 慧, 张 帆, 等). Chinese Journal of Analytical Chemistry(分析化学), 2009, 37(1): 67. [10] CHU Xiao-li, YUAN Hong-fu, LU Wan-zhen (褚小立，袁洪福，陆婉珍). Progress in Chemistry(化学进展), 2004, 16(4): 528. [11] Westerhuis J A, De Jong S, Smilde A K. Chemometrics and Intelligent Laboratory Systems, 2001, 56: 13. [12] Naes T, Mevik B H. Journal of Chemometrics, 2001, 15: 413. [13] Cen H Y, He Y, Huang M. Journal of Agricultural and Food Chemistry, 2006, 54: 7437. [14] Vapnik V N. The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995. [15] Suykens J A K, Vanderwalle J. Neural Processing Letters, 1999, 9: 293. [16] Liu F, He Y, Wang L. Analytica Chimica Acta, 2008, 610: 196.
