Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy. 2025 May 10:340:126387. doi: 10.1016/j.saa.2025.126387

Detection of composite heavy metal content in rape leaf using feature clustering and hyperspectral imaging technology

基于特征聚类和高光谱成像技术的油菜叶片复合重金属快速检测方法研究翻译改进

Jun Sun¹, Bo Li², Yang Liu², Zhaoqi Wu², Lei Shi², Xin Zhou³, Pengcheng Wu², Kunshan Yao⁴

作者单位 +展开

作者单位

¹ School of Electrical and Information Engineering of Jiangsu University, Zhenjiang 212013, China. Electronic address: sun2000jun@sina.com.

² School of Electrical and Information Engineering of Jiangsu University, Zhenjiang 212013, China.

³ School of Electrical and Information Engineering of Jiangsu University, Zhenjiang 212013, China; Key Laboratory for Theory and Technology of Intelligent Agricultural Machinery and Equipment of Jiangsu University, Zhenjiang 212013, China; Jiangsu Province and Education Ministry Co-Sponsored Synergistic Innovation Center of Modern Agricultural Equipment, Zhenjiang 212013, China.

⁴ School of Electrical and Information Engineering, Changzhou Institute of Technology, Changzhou, Jiangsu 213032, China.

DOI: 10.1016/j.saa.2025.126387 PMID: 40373553

摘要中英对照阅读

Exploring composite heavy metal content in rape is significant for crop growth and human health. The focus of this paper was to assess the viability of detection of composite heavy metal content in rape leaf utilizing hyperspectral imaging technology (HSI). Furthermore, a hybrid feature selection based on feature clustering and symmetric uncertainty (HFCSU) was proposed for spectral data to reduce dimensionality. Firstly, hyperspectral images of rape leaf stressed by different composite heavy metal concentrations were collected. Then, the spectral data in the wavelength range of 480-1000 nm was extracted. Subsequently, the spectral data was preprocessed utilizing Savitzky-Golay (SG) smoothing, standard normalized variable (SNV) and its combination (SG-SNV). Competitive adaptive reweighted sampling (CARS), random frog (RF), genetic algorithm-partial least squares (GA-PLS) and HFCSU were utilized for feature selection. Ultimately, the support vector machine regression (SVR) was utilized to build predictive models of Cd and Pb content. The results demonstrated that the SVR model using HFCSU provided the optimal prediction performance, the R_P², RMSEP and RPD for prediction of Cd content were 0.9392, 0.1494 mg·kg^-1 and 3.915, respectively, and the R_P², RMSEP and RPD for prediction of Pb content were 0.9442, 0.1806 mg·kg^-1 and 4.702, respectively. The results indicated that HFCSU can effectively mine features relevant to heavy metals, and HFCSU combined with HSI has a greater potential in the determination of composite heavy metal content in rape leaves.

Keywords: Composite heavy metal; Feature clustering; Hyperspectral imaging technique; Rape leaf; Support vector machine regression.

Keywords：composite heavy metal content; feature clustering

探索油菜中复合重金属含量对于作物生长和人类健康具有重要意义。本文的重点是利用高光谱成像技术（HSI）检测受不同浓度复合重金属胁迫的油菜叶片中的复合重金属含量。此外，提出了一种基于特征聚类和对称不确定性（HFCSU）的混合特征选择方法，以减少光谱数据的维度。首先，收集了受不同浓度复合重金属胁迫的油菜叶片的高光谱图像。然后，在480-1000 nm波长范围内提取光谱数据。接着，利用Savitzky-Golay（SG）平滑、标准归一化变量（SNV）及其组合（SG-SNV）对光谱数据进行预处理。随后使用竞争自适应重加权采样（CARS）、随机蛙（RF）、遗传算法-偏最小二乘法（GA-PLS）和HFCSU进行特征选择。最终，利用支持向量机回归（SVR）建立Cd和Pb含量的预测模型。结果表明，使用HFCSU构建的SVR模型提供了最佳的预测性能，对于Cd含量预测的RP^2、RMSEP和RPD分别为0.9392、0.1494 mg·kg^-1 和 3.915；对于Pb含量预测的RP^2、RMSEP和RPD分别为0.9442、0.1806 mg·kg^-1 和 4.702。结果表明，HFCSU能够有效挖掘与重金属相关的特征，并且结合HSI技术在油菜叶片复合重金属含量测定方面具有更大的潜力。

关键词：复合重金属；特征聚类；高光谱成像技术；油菜叶片；支持向量机回归。

关键词：复合重金属含量; 特征聚类; 高光谱成像技术

翻译效果不满意？用Ai改进或寻求AI助手帮助，对摘要进行重点提炼

相关内容

全文链接

官方链接

PMC全文

引文链接

复制

已复制！

格式：

Detection of composite heavy metal content in rape leaf using feature clustering and hyperspectral imaging technology

基于特征聚类和高光谱成像技术的油菜叶片复合重金属快速检测方法研究翻译改进

Feature clustering for robust frequency-domain classification of EEG activity

基于特征聚类的EEG信号频域稳健分类方法

Testing for a difference in means of a single feature after clustering

聚类后的单个特征的均值差异检验

iView: a feature clustering framework for suggesting informative views in volume visualization

基于体积可视化的信息视图建议的特征聚类框架

Feature clustering of intracranial pressure time series for alarm function estimation in traumatic brain injury

颅内压时序特征聚类在创伤性脑损伤中的报警功能估计方法研究

Testing for a difference in means of a single feature after clustering

检验聚类后单个特征的平均差异

Feature selection for genomic data sets through feature clustering

基因数据集的特征选择及其聚类分析

RAMClust: a novel feature clustering method enables spectral-matching-based annotation for metabolomics data

RAMClust：一种新的特征聚类方法可实现实基于光谱匹配的代谢组学数据注释

Simultaneous classification and feature clustering using discriminant vector quantization with applications to microarray data analysis

基于判别向量分量的分类和特征聚类方法及其在微阵列数据分析中的应用

Gait episode identification based on wavelet feature clustering of spectrogram images

基于频谱图像小波特征聚类的步态分期方法

Detection of composite heavy metal content in rape leaf using feature clustering and hyperspectral imaging technology

基于特征聚类和高光谱成像技术的油菜叶片复合重金属快速检测方法研究 翻译改进

Feature clustering for robust frequency-domain classification of EEG activity

基于特征聚类的EEG信号频域稳健分类方法

Testing for a difference in means of a single feature after clustering

聚类后的单个特征的均值差异检验

iView: a feature clustering framework for suggesting informative views in volume visualization

基于体积可视化的信息视图建议的特征聚类框架

Feature clustering of intracranial pressure time series for alarm function estimation in traumatic brain injury

颅内压时序特征聚类在创伤性脑损伤中的报警功能估计方法研究

Testing for a difference in means of a single feature after clustering

检验聚类后单个特征的平均差异

Feature selection for genomic data sets through feature clustering

基因数据集的特征选择及其聚类分析

RAMClust: a novel feature clustering method enables spectral-matching-based annotation for metabolomics data

RAMClust：一种新的特征聚类方法可实现实基于光谱匹配的代谢组学数据注释

Simultaneous classification and feature clustering using discriminant vector quantization with applications to microarray data analysis

基于判别向量分量的分类和特征聚类方法及其在微阵列数据分析中的应用

Gait episode identification based on wavelet feature clustering of spectrogram images

基于频谱图像小波特征聚类的步态分期方法

基于特征聚类和高光谱成像技术的油菜叶片复合重金属快速检测方法研究翻译改进