1. College of Engineering, China Agricultural University, Beijing 100083, China 2. College of Science, China Agricultural University, Beijing 100083, China 3. Quality & Safety Assessment Research Unit, USDA-ARS, Athens, GA 30605, USA
摘要: 黄曲霉毒素是广泛存在于玉米中且具有剧毒的一种代谢产物,以美国农业部农业研究署(USDA-ARS) Toxicology and Mycotoxin Research Unit提供的2010年先锋玉米为研究对象,验证了高光谱成像技术对玉米中黄曲霉毒素检测的可行性。以甲醇为溶剂制备四种不同浓度的黄曲霉毒素溶液,并将其逐一滴在等量的4组共120粒玉米颗粒表面,以未处理的30粒洁净玉米作为一组对照样本,将大小、形状相似的150个样品随机分为训练集103个,验证集47个;对获取的400~1 000 nm波段范围内的高光谱图像,先进行标准正态变量变换(standard normal variate transformation, SNV)预处理,然后引入基于Fisher判别最小误判率的方法选择最优波长,并以所选波长作为Fisher判别分析法的输入建立判别模型,对玉米颗粒表面不同浓度的黄曲霉毒素进行识别,最后对模型判别正确率进行了验证。结果表明,选取四个最优波长(812.42, 873.00, 900.36和965.00 nm)时Fisher判别分析模型对训练集与验证集的准确率分别为87.4%和80.9%。该方法为含黄曲霉毒素玉米颗粒便携式检测仪器的开发,以及对田间霉变玉米自然代谢产生毒素的检测奠定了技术基础。
关键词:最优波长;Fisher判别分析法;玉米颗粒;黄曲霉毒素;近红外高光谱图像
Abstract:Aflatoxin is a toxic metabolite widely existing in corn. In the present paper, the feasibility of detecting aflatoxin on corn kernel surface by hyperspectral imaging technology was verified. The corn called pioneer with the same shape is provided by Toxicology and Mycotoxin Research Unit. With methanol configuration, four different concentrations of aflatoxin solutions were prepared and dripped on every 30 corn kernels. Also other clean 30 kernels without aflatoxin dripped were prepared to be the control samples. Among the 150 kernel samples, 103 training samples and 47 validation samples were prepared randomly. Firstly, hyperspectral image in the range of 400 to 1 000 nm was collected .For eliminating the deviations in original spectrum, standard normal variate transformation (SNV) was adopted as pretreatment method. And then several optimum wavelengths were selected by the principle of minimum misdiagnosis rate. After that the selected optimum wavelengths were taken as the input of the Fisher discrimination analysis to discriminate the different concentrations of aflatoxin on the corn. Finally, the discrimination model based on four optimum wavelengths (812.42, 873.00, 900.36 and 965.00 nm) was built and the accuracy of the model was tested. Results indicate that the classification accuracy of calibration and validation set was 87.4% and 80.9% respectively. This method provides basis for designing the corresponding portable instrument and distinguishing aflatoxin produced by naturally metabolism in corn.
[1] Ni X Z, Wilson J P, Buntin G D, et al. Toxins, 2011, 3: 920. [2] LI Rui-fang, HAN Bei-zhong, CHEN Jing-yu, et al(李瑞芳,韩北忠,陈晶瑜,等). Joumal of the Chinese Cereals and Oils Association(中国粮油学报), 2008, 23(3): 144. [3] Widstrom N W. Advances in Agronomy, 1996, 56: 219. [4] ZHANG Min, ZHANG Yu-hao, MA Liang(张 敏, 张宇昊, 马 良). Chinese Journal of Analytical Chemistry(分析化学),2011, 39(12): 1907. [5] XIE Gang, WANG Song-xue, ZHANG Yan(谢 刚,王松雪,张 艳). Chinese Journal of Analytical Chemistry(分析化学),2013, 41(2): 223. [6] Ono E Y, Silva M, Ribeiro R M, et al. Brazilian Archives of Biology and Technology, 2010, 53(3): 687. [7] Stroka J, Anklam E. Trends in Analytical Chemistry, 2002, 21(2): 90. [8] Williams P J, Geladi P, Britz T J, et al. Journal of Cereal Science, 2012, 55(3): 272. [9] Singh C B, Jayas D S, Paliwal J, et al. Cereal Chemistry, 2009, 86(3): 256. [10] ZHU Qi-bing, FENG Zhao-li, HUANG Min, et al(朱启兵, 冯朝丽, 黄 敏,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2012, 28(23): 271. [11] Polder G, van der Heijden G W A M, Waalwijk C, et al. Seed Science and Technology, 2005, 33(3): 655. [12] Cogdill R P, Hurburgh C R, Rippke G R, et al. Transactions of the ASAE, 2004, 47(1): 311. [13] ZHANG Yu-hao, YANG Lin, MA Liang, et al(张宇昊,杨 琳,马 良,等). Journal of the Chinese and Oils Associations(中国粮油学报), 2011, 26(6): 123. [14] ZHOU Jian, CHENG Hao, YE Yang, et al(周 健,成 浩,叶 阳,等). Acta Optica Sinica(光学学报), 2009, 29(4): 1117. [15] LIU Nian-ping, WANG Hong-tu, YUAN Zhi-gang, et al(刘年平,王宏图,袁志刚,等). Rock and Soil Mechanics(岩石力学),2012,33(2):554. [16] WANG Rong-hui, ZONG Ruo-wen, WANG Zheng-zhou, et al(王荣辉,宗若雯,王正洲,等). Joural of University of Science and Technology of China(中国科学技术大学学报), 2006,36(12): 1331. [17] CHU Xiao-li(褚小立). Molecular Spectroscopy Analytical Technology Combined with Chemometrics and its Applications(化学计量学方法与分子光谱分析技术). Beijing: Chemical Industry Press(北京: 化学工业出版社), 2011. 47. [18] Yao H B, Hruska Z, Kincaid R, et al. Sensing and Instrumentation for Food Quality and Safety,2008, 2(3): 215.