| 基于近红外光谱技术的小白菜农药残留鉴别分析 |
| 投稿时间：2020-07-15 修订日期：2020-07-24 点此下载全文 |
| 引用本文：李敏.基于近红外光谱技术的小白菜农药残留鉴别分析[J].红外,2020,41(10):41~48 |
| 摘要点击次数: 66 |
| 全文下载次数: 55 |
|
| 基金项目:四川省教育厅自然科学重点(18ZA0231) |
|
| 中文摘要:针对市场销售蔬菜存在农药残留的问题，提出了一种高效无损的小白菜农药残留定性分类鉴别方法。以3组小白菜叶片和农药氯氟氰菊酯为研究对象，对其中的2组小白菜分别喷洒2种不同浓度的农药（农药与水的配比分别为1:500和1:20），构成不含农药、含轻度农残和含重度农残三类样本。分别采集了这三类样本的近红外光谱，然后对该数据进行小波软阈值预处理和主成份分析降维，并对其进行Fisher判决和K近邻分类鉴别。实验结果表明，该方法对小白菜无农药残留和含轻度农药残留两类样本的正确鉴别率为95%，对含轻度农残和含重度农残的两类样本的正确鉴别率为90%。因此本文方法对小白菜农残定性分类鉴别有效，为蔬菜农残定性分类鉴别提供了一种新思路。 |
| 中文关键词:近红外光谱 农药残留鉴别 K-近邻分类(KNN) |
| |
| Identification and Analysis of Pesticide Residues in Chinese Cabbage based on Near Infrared Spectroscopy Technology |
|
|
| Abstract:In order to solve the problem of pesticide residues in vegetables sold in the market, an efficient and nondestructive method for the qualitative classification and identification of pesticide residues in Chinese cabbage was proposed. Three groups of Chinese cabbage leaves and cyhalothrin were used as the research objects. Two groups of Chinese cabbage were sprayed with two different concentrations of pesticides (the ratio of pesticide to water was 1:500 and 1:20 respectively), and three types of samples were formed, which contained no pesticides, mild pesticide residues and severe pesticide residues. The three kinds of samples were collected by near infrared spectroscopy, and the spectral data were preprocessed by wavelet soft threshold, then the dimension was reduced by principal component analysis, and then Fisher decision and k-nearest neighbor classification were performed. The results showed that the correct identification rate of the two kinds of samples without pesticide residues and with mild pesticide residues was 95%, and that of the samples with mild and severe pesticide residues was 90%. The experimental results show that this method is effective for the qualitative classification and identification of pesticide residues in Chinese cabbage. |
| keywords:Near Iinfrared Spectroscopy Identification of Pesticide Residues K-Nearest Neighbor Classification (KNN) |
| 查看全文 HTML 查看/发表评论 下载PDF阅读器 |