文献类型： 外文期刊

作者： Liu, C. ¹ ; Liu, W. ² ; Lu, X. ³ ; Chen, W. ¹ ; Chen, F. ⁴ ; Yang, J. ³ ; Zheng, L. ¹ ;

作者机构： 1.Hefei Univ Technol, Sch Biotechnol & Food Engn, Hefei 230009, Peoples R China

2.Hefei Univ, Intelligent Control & Compute Vis Lab, Hefei 230601, Peoples R China

3.Anhui Acad Agr Sci, Rice Res Inst, Hefei 230031, Peoples R China

4.Clemson Univ, Dept Food Nutr & Packaging Sci, Clemson, SC 29634 USA

5.Hefei Univ Technol, Sch Med Engn, Hefei 230009, Peoples R China

期刊名称：JOURNAL OF AGRICULTURAL SCIENCE （ 影响因子：1.476； 五年影响因子：1.891 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： Soybean is an important oil- and protein-producing crop and over the last few decades soybean genetic transformation has made rapid strides. The probability of occurrence of transgene flow should be assessed, although the discrimination of conventional and transgenic soybean seeds and their hybrid descendants is difficult in fields. The feasibility of non-destructive discrimination of conventional and glyphosate-resistant soybean seeds and their hybrid descendants was examined by a multispectral imaging system combined with chemometric methods. Principal component analysis (PCA), partial least squares discriminant analysis (PLSDA), least squares-support vector machines (LS-SVM) and back propagation neural network (BPNN) methods were applied to classify soybean seeds. The current results demonstrated that clear differences among conventional and glyphosate-resistant soybean seeds and their hybrid descendants could be easily visualized and an excellent classification (98% with BPNN model) could be achieved. It was concluded that multispectral imaging together with chemometric methods would be a promising technique to identify transgenic soybean seeds with high efficiency.