当前位置: X-MOL 学术Food Control › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Standardisation of near infrared hyperspectral imaging for quantification and classification of DON contaminated wheat samples
Food Control ( IF 6 ) Pub Date : 2020-05-01 , DOI: 10.1016/j.foodcont.2019.107074
Antoni Femenias , Ferran Gatius , Antonio J. Ramos , Vicente Sanchis , Sonia Marín

Abstract Near infrared hyperspectral imaging (HSI-NIR) is considered a promising technique able to replace time-consuming, costly and destructive classic methods to predict and classify deoxynivalenol (DON) contaminated wheat kernels or samples by its concentration and level of contamination, respectively. The main objective of the present study was to standardise the HSI-NIR image acquisition method in naturally contaminated whole wheat kernels to obtain a high accuracy method to quantify and classify samples according to DON levels. To confirm the results, wheat samples were analysed by high performance liquid chromatography as the reference method to determine their DON levels. Hyperspectral images for single kernels and whole samples were obtained and spectral data were processed by multivariate analysis software. The initial work revealed that HSI-NIR was able to overcome kernel orientation, position and pixel selection. The subsequent developed Partial Least Squares (PLS) prediction achieved a RMSEP (Root Mean Square Error of Prediction) of 405 μg/kg and 1174 μg/kg for a cross-validated model and an independent set validated model, respectively. Moreover, the classification accuracy obtained by Linear Discriminant Analysis (LDA) was 62.7% for two categories depending on the EU maximum level (1250 μg/kg). Despite of the results are not accurate enough for DON quantification and sample classification, they can be considered a starting point for further improved protocols for DON management.

中文翻译:

用于 DON 污染小麦样品量化和分类的近红外高光谱成像标准化

摘要 近红外高光谱成像 (HSI-NIR) 被认为是一种很有前景的技术,能够取代耗时、昂贵和破坏性的经典方法,分别根据其浓度和污染水平对脱氧雪腐镰刀菌烯醇 (DON) 污染的小麦籽粒或样品进行预测和分类。本研究的主要目的是标准化天然污染全麦籽粒的 HSI-NIR 图像采集方法,以获得根据 DON 水平对样品进行定量和分类的高精度方法。为确认结果,以高效液相色谱法分析小麦样品作为测定其 DON 水平的参考方法。获得单个内核和整个样品的高光谱图像,并通过多变量分析软件处理光谱数据。最初的工作表明 HSI-NIR 能够克服内核方向、位置和像素选择。随后开发的偏最小二乘法 (PLS) 预测分别为交叉验证模型和独立集验证模型实现了 405 μg/kg 和 1174 μg/kg 的 RMSEP(预测均方根误差)。此外,根据欧盟最高水平(1250 μg/kg),通过线性判别分析 (LDA) 获得的分类准确度为两个类别的 62.7%。尽管结果对于 DON 量化和样本分类不够准确,但它们可以被视为进一步改进 DON 管理协议的起点。随后开发的偏最小二乘法 (PLS) 预测分别为交叉验证模型和独立集验证模型实现了 405 μg/kg 和 1174 μg/kg 的 RMSEP(预测均方根误差)。此外,根据欧盟最高水平(1250 μg/kg),通过线性判别分析 (LDA) 获得的分类准确度为两个类别的 62.7%。尽管结果对于 DON 量化和样本分类不够准确,但它们可以被视为进一步改进 DON 管理协议的起点。随后开发的偏最小二乘法 (PLS) 预测分别为交叉验证模型和独立集验证模型实现了 405 μg/kg 和 1174 μg/kg 的 RMSEP(预测均方根误差)。此外,根据欧盟最高水平(1250 μg/kg),通过线性判别分析 (LDA) 获得的分类准确度为两个类别的 62.7%。尽管结果对于 DON 量化和样本分类不够准确,但它们可以被视为进一步改进 DON 管理协议的起点。根据欧盟最高水平(1250 μg/kg),两个类别为 7%。尽管结果对于 DON 量化和样本分类不够准确,但它们可以被视为进一步改进 DON 管理协议的起点。根据欧盟最高水平(1250 μg/kg),两个类别为 7%。尽管结果对于 DON 量化和样本分类不够准确,但它们可以被视为进一步改进 DON 管理协议的起点。
更新日期:2020-05-01
down
wechat
bug