Videometer多光譜成像系統(tǒng)發(fā)表小麥鐮刀菌監(jiān)測上的應(yīng)用

近期，科學(xué)家利用VideometerLab多光譜成像系統(tǒng)發(fā)表了題為Monitoring the growth of Fusarium graminearum in wheat kernels using multispectral imaging with chemometric methods的文章。多光譜成像技術(shù)是功能強(qiáng)大的圖譜合一技術(shù)，在植物病理學(xué)研究領(lǐng)域有著巨大的應(yīng)用前景。

詳細(xì)應(yīng)用介紹見以下鏈接http://www.bjbiopute.cn/Wenzhang/detail/id/1043.html

利用化學(xué)計(jì)量學(xué)多光譜成像技術(shù)監(jiān)測小麥籽粒中禾谷鐮刀菌的生長

摘要 

小麥?zhǔn)菫槿祟愄峁┠芰亢蜖I養(yǎng)的重要農(nóng)業(yè)經(jīng)濟(jì)作物。然而，小麥籽粒容易受到禾谷鐮刀菌的污染，對人類健康有害。本研究開發(fā)了一種利用多光譜成像技術(shù)快速無損檢測小麥籽粒中禾谷鐮刀菌污染程度和數(shù)量的方法�；�于遺傳算法（GA）和主成分分析（PCA）數(shù)據(jù)預(yù)處理方法，結(jié)合偏最小二乘（PLS）、支持向量機(jī)（SVM）和反向傳播神經(jīng)網(wǎng)絡(luò)（BPNN）化學(xué)計(jì)量學(xué)方法，建立了禾谷鐮刀菌識別和定量測定模型。GA-BPNN方法在不同污染期的小麥籽粒污染程度識別中獲得了最佳結(jié)果，準(zhǔn)確率高達(dá)100%。不同方法的結(jié)果比較表明，GA-SVM對禾谷鐮刀菌數(shù)量的預(yù)測效果最好，校正集和預(yù)測集的相關(guān)系數(shù)（R）分別為0.9663和0.9292，校準(zhǔn)集和預(yù)測集的均方根誤差（RMSE）分別為0.5992和0.6725 CFU g−1。可以得出結(jié)論，多光譜成像和化學(xué)計(jì)量學(xué)方法的結(jié)合在實(shí)際應(yīng)用中對谷物真菌的快速無損檢測具有潛在的實(shí)用價(jià)值。

Monitoring the growth of Fusarium graminearum in wheat kernels using multispectral imaging with chemometric methods

Abstract

Wheat is an important agricultural economic crop providing energy and nutrition for human beings. However, wheat kernels are easily contaminated with Fusarium graminearum that is harmful to human health. In this study, a rapid and nondestructive detection method has been developed to identify the degree of contamination and determine the count of Fusarium graminearum in wheat kernels using multispectral imaging technology. Based on genetic algorithm (GA) and principal component analysis (PCA) data preprocessing methods combined with partial least squares (PLS), support vector machine (SVM) and back propagation neural network (BPNN) chemometric methods, identification and quantitative determination models were established. The best result was obtained by GA-BPNN with an accuracy of up to 100% in the identification of the degree of contamination in wheat kernels at different contamination periods. Comparison of the results from different methods revealed that the best prediction of the count of Fusarium graminearum was obtained by GA-SVM with the correlation coefficient (R) in the calibration set and prediction set being 0.9663 and 0.9292, while the root mean square error (RMSE) in the calibration set and prediction set was 0.5992 and 0.6725 CFU g−1, respectively. It can be concluded that the combination of multispectral imaging and chemometric methods was potentially useful for rapid and nondestructive detection of cereal fungi in