Detection of heavy metal lead in lettuce leaves based on fluorescence hyperspectral technology combined with deep learning algorithm.
Detection of heavy metal lead in lettuce leaves based on fluorescence hyperspectral technology combined with deep learning algorithm.
复制标题
DOI：
10.1016/j.saa.2021.120460
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Xin Zhou;Jun Sun;Yan Tian;Kunshan Yao;Min Xu
中科院分区：
文献类型：
--
作者：
Xin Zhou;Jun Sun;Yan Tian;Kunshan Yao;Min Xu
研究了荧光高光谱成像技术用于生菜叶片铅含量检测的可行性。进一步提出了基于蒙特卡罗优化的小波变换层叠自编码器（WT-MC-SAE）对荧光光谱数据进行降维和深度特征提取。选取2800个生菜叶片样品的荧光高光谱图像，以整片生菜叶片作为感兴趣区域（ROI）提取荧光光谱。采用标准归一化变量（SNV）、一阶导数（1st Der）、二阶导数（2ndDer）、三阶导数（3rd Der）和四阶导数（4th Der）五种不同的预处理算法对原始ROI光谱数据进行预处理。采用小波变换层叠自编码器（WT-SAE）和WT-MC-SAE对数据进行降维，并采用支持向量机回归（SVR）进行建模分析。其中，第4阶Der光谱数据对生菜叶片中Pb含量的检测最有用，其Rc 2为0.9802，RMSEC为0.02321 mg/kg，Rp 2为0.9467，RMSEP为0.04017 mg/kg，RPD为3.273，模型尺度为0.067 ~ 1.400 mg/kg在第五级小波分解下，输入层、隐含层和输出层的节点数分别为407-314-286-121-76。进一步研究表明，WT-MC-SAE实现了荧光光谱的深度特征提取，对利用荧光高光谱成像实现生菜叶片中铅的定量检测具有重要意义。
The feasibility analysis of fluorescence hyperspectral imaging technology was studied for the detection of lead content in lettuce leaves. Further, Monte Carlo optimized wavelet transform stacked auto-encoders (WT-MC-SAE) was proposed for dimensionality reduction and depth feature extraction of fluorescence spectral data. The fluorescence hyperspectral images of 2800 lettuce leaf samples were selected and the whole lettuce leaf was used as the region of interest (ROI) to extract the fluorescence spectrum. Five different pre-processing algorithms were used to pre-process the original ROI spectral data including standard normalized variable (SNV), first derivative (1st Der), second derivative (2ndDer), third derivative (3rd Der) and fourth derivative (4th Der). Moreover, wavelet transform stacked auto-encoders (WT-SAE) and WT-MC-SAE were used for data dimensionality reduction, and support vector machine regression (SVR) was used for modeling analysis. Among them, 4th Der tends to be the most useful fluorescence spectral data for Pb content detection at 0.067 ∼ 1.400 mg/kg in lettuce leaves, withRc2of 0.9802, RMSEC of 0.02321 mg/kg,Rp2of 0.9467, RMSEP of 0.04017 mg/kg and RPD of 3.273, and model scale (the number of nodes in the input layer, hidden layer and output layer) was 407-314-286-121-76 under the fifth level of wavelet decomposition. Further studies showed that WT-MC-SAE realizes the depth feature extraction of the fluorescence spectrum, and it is of great significance to use fluorescence hyperspectral imaging to realize the quantitative detection of lead in lettuce leaves.