陈孝敬温州大学基于近红外光谱的重金属污染泥蚶的快速检测.pdfVIP

基于近红外光谱的重金属污染泥蚶的快速检测 刘科 林冬秀 陈孝敬* （温州大学物理与电子信息工程学院温州 325035） 摘要 本文提出了利用近红外光谱技术对重金属污染泥蚶的快速检测。通常，泥蚶所富集的重金属离子 不具有近红外活性，在近红外光谱中几乎没有特征峰。然而，重金属污染会通过诱导使贝类相关分子结构 和成分发生变化，从而产生与重金属有关的相当微弱的光谱信息。本文的实验方案设计分为两种：对照泥 蚶和单一重金属(Cd、Cu、Pb 或Zn)污染泥蚶的分类（设计I ）；所有样本包括对照泥蚶和4 种重金属污染 泥蚶的分类（设计II ）。本文采用了两种不同的识别算法，即最小二乘支持向量机(LS-SVM)和随机森林(RF)， 对设计I 和设计II 分别建立分类模型并进行预测。预测结果显示：对设计I ，LS-SVM 和RF 的平均预测正 确率分别为100%和95%；对设计II ，LS-SVM 和RF 的平均预测正确率分别为96%和92%。本文的研究结果 表明，利用近红外光谱技术快速检测重金属污染泥蚶具有可行性,可以为泥蚶重金属污染提供一种快速检测 方法。 关键词重金属；近红外光谱；水产品；重金属污染；泥蚶；最小二乘支持向量机；随机森林 Rapid detection of heavy metal-contaminated Tegillarca granosa using near infrared spectroscopy KeLiuDongxiu LinXiaojing Chen* (College of Physics and Electronic Engineering Information, Wenzhou University, Wenzhou 325035) AbstractThis study proposedthe rapid detection of heavy metal contamination in Tegillarca granosa by using near infrared spectroscopy.Generally, there is no specific characteristic peak of heavy metals in the near infrared range as heavy metals generally do not any show NIR activity.Nevertheless, these are some changes in the structure and concentration of relevant biological moleculesinduced by heavy metal contamination produce remarkably weak spectral information on heavy metals. In this paper, the experimental design was divided into two: classify Tegillarca granosa samples that were uncontaminated (control) and contaminated by a certain 1 heavy metal (Cd, Cu, Pb, or Zn) (Design I);classify all sample varieties, including the samples that were uncontaminated and contaminated by the four heavy metals (Design II). Two recognitionalgorithms, namely, the leastsquares support vector machines (LS-SVM) and random forest (RF)were used to construct classification models