Study on Disease Level Classification of Rice Panicle Blast Based on Visible and Near Infrared Spectroscopy
WU Di1, CAO Fang1, ZHANG Hao2, SUN Guang-ming1, FENG Lei1*, HE Yong1*
1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310029, China 2. Digital Agricultural Research Centre, Zhejiang Academy of Agricultural Sciences,Hangzhou 310021, China
Abstract：Visible and near infrared (Vis-NIR) spectroscopy was used to fast and non-destructively classify the disease levels of rice panicle blast. Reflectance spectra between 325 and 1 075 nm were measured. Kennard-Stone algorithm was operated to separate samples into calibration and prediction sets. Different spectral pretreatment methods, including standard normal variate (SNV) and multiplicative scatter correction (MSC), were used for the spectral pretreatment before further spectral analysis. A hybrid wavelength variable selection method which is combined with uninformative variable elimination (UVE) and successive projections algorithm (SPA) was operated to select effective wavelength variables from original spectra, SNV pretreated spectra and MSC pretreated spectra, respectively. UVE was firstly operated to remove uninformative wavelength variables from the full-spectrum. Then SPA selected the effective wavelength variables with less colinearity after UVE. Least square-support vector machine (LS-SVM) was used as the calibration method for the spectral analysis in this study. The selected effective wavelengths were set as input variables of LS-SVM model. The LS-SVM model established based on SNV-UVE-SPA obtained the best results. Only six effective wavelengths (459, 546, 569, 590, 775 and 981 nm) were selected from the full-spectrum which has 600 wavelength variables by UVE-SPA, and their LS-SVM model’s performance was further improved. For SNV-UVE-SPA-LS-SVM model, coefficient of determination for prediction set (R2p), root mean square error for prediction (RMSEP) and residual predictive deviation (RPD) were 0.979, 0.507 and 6.580, respectively. The overall results indicate that Vis-NIR spectroscopy is a feasible way to classify disease levels of rice panicle blast fast and non-destructively. UVE-SPA is an efficient variable selection method for the spectral analysis, and their selected effective wavelengths can represent the useful information of the full-spectrum and have higher signal/noise ratio and less colinearity.
Key words：Visible and near infrared (Vis-NIR) spectroscopy;Rice panicle blast;Uninformative variable elimination (UVE);Successive projections algorithm (SPA);Variable selection
吴 迪1，曹 芳1，张 浩2，孙光明1，冯 雷1*，何 勇1* . 基于可见-近红外光谱技术的水稻穗颈瘟染病程度分级方法研究[J]. 光谱学与光谱分析, 2009, 29(12): 3295-3299.
WU Di1, CAO Fang1, ZHANG Hao2, SUN Guang-ming1, FENG Lei1*, HE Yong1* . Study on Disease Level Classification of Rice Panicle Blast Based on Visible and Near Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(12): 3295-3299.
[1] SUN Guo-chang, SHEN Zong-tan(孙国昌, 申宗坦). Chinese Journal of Rice Science(中国水稻科学), 1992, 6(1): 39. [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] WU Di，FENG Lei，ZHANG Chuan-qing, et al(吴 迪，冯 雷，张传清, 等). J. Infrared Millim. Waves(红外与毫米波学报), 2007, 26(4): 269. [4] Dawson T P, Curran P J, North P. Remote Sensing of Environment, 1999, 67(2): 147. [5] Macho S, Iusa R, Callao M P, et al. Anal. Chim. Acta, 2001, 445(2): 213. [6] Centner V，Massart D L. Anal. Chem., 1996, 36: 8851. [7] Araújo M C U，Saldanha T C B，Galvo R K H，et al. Chemom. Intell. Lab. Syst., 2001, 57: 65. [8] Galvo R K H，Araújo M C U，Fragoso W D，et al. Chemom. Intell. Lab. Syst., 2008, 92: 83. [9] CHEN Bin, MENG Xiang-long, WANG Hao(陈 斌，孟祥龙，王 豪). Journal of Instrumental Analysis(分析测试学报), 2007, 26(1): 66. [10] Wu D, He Y, Feng S, et al. Journal of Food Engineering, 2008, 84: 124. [11] Chauchard F, Cogdill R, Roussel S, et al. Chemom. Intell. Lab. Syst., 2004, 71: 141.
