摘要
[目的/意义]可见-近红外光谱可对小麦霉变情况快速无损检测,但是高分辨率光谱仪价格高、体积大,不利于在农业环境中推广,因此通过对低分辨率光谱数据进行优化处理,以期接近高分辨率光谱仪分辨霉变小麦的效果。[方法]使用可见-近红外农产品检测仪(型号VNIAPD,分辨率1.6 nm)和复享光纤光谱仪(型号SIN02040,分辨率0.19 nm)采集100份小麦样本的新鲜状态以及不同霉变状态的光谱数据。首先对SINO2040光谱进行裁剪,让其和VNIAPD波长保持一致,均为640~1 050 nm;然后对其使用标准差标准化(Standard Deviation Normalization,SDN)、标准正态变换(Standard Normal Variation,SNV)、均值中心化(Mean Centrality,MC)、一阶导数(First-order Derivatives,1ST)、Savitzky-Golay平滑(Savitzky-Golay Smoothing,SG)、多元散射校正(Multiple Scattering Correction,MSC)等多种预处理方法处理并使用离群点检测算法(Local Outlier Factor,LOF)筛选出离群点并剔除;其次使用连续投影算法(Sequential Projection Algorithm,SPA)和最小绝对收缩和选择算法(Least Absolute Shrinkage and Selection Operator,LASSO)对预处理后的光谱进行特征波长提取;最后分别采用K近邻算法(K-Nearest Neighbor,KNN)、支持向量机(Support Vector Machine,SVM)、随机森林(Random Forests,RF)和朴素贝叶斯(Na?ve-Bayes)、后向传播神经网络(Back Propagation Neural Network,BPNN)、深度神经网络(Deep Neural Networks,DNN)6种算法对特征波长光谱进行建模分析,从而分辨霉变小麦以及区分霉变程度。[结果和讨论]BPNN、DNN两种神经网络模型的测试集准确率均可达到100%,但是建模时间长,模型内存大;而KNN、SVM、RF和Na?ve-Bayes浅层模型的测试集准确率为93.18%~100%,建模速度快、模型内存小。本研究光谱仪VNIAPD在光学参数(光学分辨率1.6 nm)低于SINO2040的光学参数(光学分辨率0.19 nm)且成本更低的情况下,检测准确率到达同一水平。[结论]本研究通过对比光谱数据的不同预处理方法从而找出了对应算法的最佳数据优化选择,使低分辨率光谱仪VNIAPD检测霉变小麦性能可以追平高分辨率光谱仪SINO2040,为基于可见-近红外光谱的小麦霉变低成本无损检测提供了新选择。
[Objective]Traditional methods for detecting mold are time-consuming,labor-intensive,and vulnerable to environmental influences,highlighting the need for a swift,precise,and dependable detection approach.Researchers have utilized visible-near infrared(NIR)spectroscopy for the non-destructive,rapid assessment of wheat moisture content,crude protein content,concealed pests,starch con‐tent,dry matter,weight,hardness,origin,and other attributes.However,most of these studies rely on research-grade Visible-NIR spec‐trometers typically found in laboratories.While these spectrometers offer superior detection accuracy and stability,their bulky size,lack of portability,and high cost hinder their widespread use and adoption across various agricultural product distribution channels.[Methods]A low-resolution Visible-NIR spectrometer(VNIAPD,with a resolution of 1.6 nm)was utilized to gather wheat data.The aim was to enhance the accuracy of moldy wheat detection by identifying suitable spectral data preprocessing methods using corre‐sponding algorithms.A high-resolution Visible-NIR spectrometer(SINO2040,with a resolution of 0.19 nm)served as a control to vali‐date the instrument and method's effectiveness.The Zhoumai(No.22)wheat variety was adopted,with a total of 100 samples pre‐pared.The spectra of fresh wheat were scanned and then placed in a constant temperature chamber at 35°C to replicate the appropri‐ate conditions for mold growth,thereby accelerating the reproduction of naturally occurring mold in the wheat.The degree of mold was categorized based on the cultivation time in the constant temperature chamber,with wheat classified as mildly,moderately,or se‐verely moldy after 3,6,and 9 days of cultivation,respectively.A total of 400 wheat spectral data points were collected,including 100 samples each of fresh wheat,wheat cultured for 3 days,wheat cultured for 6 days,and wheat cultured for 9 days.Preprocessing meth‐ods such as standard deviation normalization(SDN),standard normal variation(SNV),mean centrality(MC),first-order derivatives(1ST),Savitzky-Golay smoothing(SG),and multiple scattering correction(MSC)were applied to the spectral data.Outliers were iden‐tified and eliminated using the local outlier factor(LOF)method.Following this,the sequential projection algorithm(SPA)and Least absolute shrinkage and selection operator(LASSO)were used to extract characteristic wavelengths from the preprocessed spectra.Subsequently,six algorithms,including k-nearest neighbors(KNN),support vector machines(SVM),random forests(RF),Naïve Bayes,back propagation neural networks(BPNN),and deep neural networks(DNN),were employed to model and analyze the feature wavelength spectra,differentiating moldy wheat and classifying the degree of mold.Evaluation criteria encompassed accuracy,model‐ing time,and model size to aid in selecting the most suitable model for specific application scenarios.[Results and discussions]Regarding accuracy,even when utilizing the computationally slower and more memory-demanding neural net‐work models BPNN and DNN,both the VNIAPD and SINO2040 achieved a perfect 100%accuracy in the binary classification task of distinguishing between fresh and moldy wheat.They also maintained a faultless 100%accuracy in the ternary classification task that differentiates three varying levels of mold growth.Adopting faster and more memory-efficient shallow models such as KNN,SVM,RF,and Naïve-Bayes,the VNIAPD yielded a top test set accuracy of 97.72%when combined with RF for binary classification.Con‐versely,SINO2040 achieved 100%accuracy using Naïve-Bayes.In the ternary classification scenario,the VNIAPD hit the mark at 100%accuracy with both KNN and RF,while SINO2040 demonstrated 97.72%accuracy with KNN and SVM.Regarding modeling speed,the shallow machine learning algorithms,including KNN,SVM,RF,and Naïve-Bayes,exhibited quicker training times,with Naïve-Bayes being the swiftest at just 3 ms.In contrast,the neural network algorithms BPNN and DNN required more time for train‐ing,taking 3293 and 18614 ms,respectively.Regarding memory footprint,BPNN had the largest model size,occupying 4028 kb,whereas SVM was the most memory-efficient,with a size of only 4 kb.Overall,the VNIAPD matched the SINO2040 in detection ac‐curacy despite having lower optical parameters:A slightly lesser optical resolution of 1.6 nm compared to the SINO2040's 0.19 nm-and a lower cost,highlighting its efficiency and cost-effectiveness in the given context.[Conclusions]In this study,by comparing different preprocessing methods for spectral data,the optimal data optimization choices for corresponding algorithms were identified.As a result,the low-resolution spectrometer VNIAPD was able to achieve performance on par with the high-resolution spectrometer SINO2040 in detecting moldy wheat,providing a new option for low-cost,non-destructive detection of wheat mold and the degree of moldiness based on Visible-NIR spectroscopy.
作者
贾文珅
吕浩林
张上
秦英栋
周巍
JIA Wenshen;LYU Haoin;ZHANG Shang;QIN Yingdong;ZHOU Wei(College of Computer and Information Technology,China Three Gorges University,Yichang 443002,China;Institute of Quality Standards and Testing Technology,Beijing Academy of Agricultural and Forestry Sciences,Beijing 100097,China;Food Inspection and Research Institute,Hebei Food Safety Key Laboratory,Shijiazhuang 050000,China)
出处
《智慧农业（中英文）》
CSCD
2024年第1期89-100,共12页
Smart Agriculture
基金
河北省重点研发计划(21375501D)
北京市农林科学院科技创新能力建设专项(KJCX20230438)
国家自然科学基金(31801634)。
关键词
可见-近红外光谱
小麦霉变
机器学习
无损检测
食品安全
神经网络
Visible-NIR spectroscopy
wheat mold
machine learning
nondestructive detection
food safety
neural networks
作者简介
贾文珅,研究方向为农产品安全快检方法。E-mail:jiawenshen@163.com;通信作者:张上,博士,副教授,研究方向为计算机应用。E-mail:3011408157@qq.com。
