生物学杂志

生物学杂志 ›› 2024, Vol. 41 ›› Issue (6): 104-.doi: 10.3969/j.issn.2095-1736.2024.06.104

• 技术方法 • 上一篇    下一篇

基于高光谱技术的重金属污染蛤仔快速无损鉴别

刘忠艳1, 杨俊杰1, 乔沐溪2, 刘　瑶3   

  1. 1. 岭南师范学院 计算机与智能教育学院， 湛江 524048； 2. 中央财经大学 统计与数学学院，
    北京 102206； 3. 岭南师范学院 电子与电气工程学院， 湛江 524048
  • 出版日期:2024-12-18 发布日期:2024-12-16
  • 通讯作者: 刘瑶，博士，副教授，研究方向为光谱分析与模式识别，E-mail:liuyao0904@163.com
  • 作者简介:刘忠艳，博士，副教授，研究方向为光谱检测与模式识别，E-mail:912968544@qq.com
  • 基金资助:
    国家自然科学基金青年科学基金项目（62005109）； 湛江市科技发展专项资金竞争性分配项目：湛江市特色水果农药残留高光谱快速无损检测机理与方法研究（2023A21802）； 广东省哲学社会科学规划学科共建项目（GD22XJY32）； 广东省教育科学规划课题（2018JKZ022）； 广东省哲学社会科学规划学科共建项目（GD23XJY71）

Rapid non-destructive identification of heavy metal contaminated clams based on hyperspectral technology#br#

LIU Zhongyan1, YANG Junjie1, QIAO Muxi2, LIU Yao3#br#   

  1. 1. School of Computer Science and Intelligence Education, Lingnan Normal University, Zhanjiang 524048, China;
    2. School of Statistics and Mathematics, Central University of Finance and Economics, Beijing 102206, China;
    3. School of Electronic and Electrical Engineering, Lingnan Normal University, Zhanjiang 524048, China
  • Online:2024-12-18 Published:2024-12-16

PDF (PC)

12

摘要： 为探索重金属污染蛤仔鉴别新方法，采用高光谱仪对正常和重金属污染的蛤仔采集450~900 nm范围内的反射光谱，利用多元散射校正（MSC）方法消除光谱中的干扰因素，采用主成分分析（PCA）、线性判别分析（LDA）、局部线性嵌入（LLE）、独立成分分析（ICA）、多维缩放（MDS）和等度量映射（ISOMAP）等6种方法对数据降维，运用KNN、LogitBoost、SVM和GradientBoosting等4种分类器，对800个重金属\[镉（Cd）、铜（Cu）、铅（Pb）和锌（Zn）\]污染和正常的蛤仔进行分类，结果显示，4种分类器都对LDA降维后的光谱鉴别性能较好，而且LogitBoost分类器对LDA降维后的光谱平均准确率达到99.40%、F测度为97.99%，优于其他分类器。又在样本类别数量不均衡下，分别对每种重金属污染和正常的蛤仔进行分类，进一步验证MSC-LDA-LogitBoost鉴别模型具有更好的稳健性。证实用高光谱技术结合机器学习方法鉴别重金属污染蛤仔是可行的。

关键词: 高光谱成像, 重金属污染鉴别, 蛤仔, LogitBoost分类器, 光谱降维

Abstract: To explore a new method for identifying heavy metal contaminated clams, a hyperspectral spectrometer was used to collect reflectance spectra in the range of 450－900 nm of normal and heavy metal contaminated clams. The Multiple Scatter Correction(MSC) method was employed to eliminate interference factors in the spectra. Six methods, including Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Local Linear Embedding (LLE), Independent Component Analysis (ICA), Multidimensional Scaling (MDS), and Isometric Mapping (ISOMAP), were used to reduce the dimensionality of the data. Four classifiers, namely K-Nearest Neighbors (KNN), LogitBoost, Support Vector Machine (SVM), and GradientBoosting, were applied to classify 800 contaminated clams with heavy metals(cadmium (Cd), copper (Cu), lead (Pb) and zinc (Zn)) and normal clams. The results showed that all four classifiers performed well on the spectra reduced by LDA, with the LogitBoost classifier achieving an averageAccuracyof 99.40% and anF-measureof 97.99%, outperforming the other classifers. Furthermore, under imbalanced sample class sizes, classifying each type of heavy metal contaminated and normal clams separately further confirmed the robustness of the MSC-LDA-LogitBoost identification model. This study confirmed the feasibility of using hyperspectral technology combined with machine learning method to identify heavy metal contaminated clams.

Key words: 高光谱成像, 重金属污染鉴别, 蛤仔, LogitBoost分类器, 光谱降维

中图分类号: