柑桔黄龙病近红外光谱无损检测

为探讨快速无损检测柑桔黄龙病的可行性,应用近红外光谱技术结合机器学习方法进行研究。在4000-9000cm-1光谱范围内,采集黄龙病、缺素和健康3类叶片样本的近红外光谱。采用一阶导数、平滑和多元散色校正组合的光谱预处理方法,消除光谱的基线漂移和散射效应。分别对偏最小二乘判别模型（PLS-DA）的主成分因子数和最小二乘支持向量机（LS-SVM）的输入变量数量、核函数类型及其参数进行了优化,建立了PLS-DA和LS-SVM模型。采用预测集样本,评价模型的预测能力,经比较,采用11个主成分得分向量为输入、线性核函数和惩罚因子为2.25的LS-SVM模型预测效果最佳,模型误判率为0。结果表明采用近红外...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 32; no. 14; pp. 202 - 208
Main Author 刘燕德 肖怀春 邓清 张智诚 孙旭东 肖禹松
Format Journal Article
LanguageChinese
Published 华东交通大学机电工程学院,南昌,330013 2016
Subjects
光谱分析
支持向量机
机器学习
柑桔
模型
近红外光谱技术
黄龙病
支持向量机
models
citrus greening
模型
machine learning
柑桔
citrus
近红外光谱技术
spectrum analysis
机器学习
黄龙病
光谱分析
near infrared spectroscopy
least square support vector machine
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2016.14.027

Cover

More Information
Summary:为探讨快速无损检测柑桔黄龙病的可行性,应用近红外光谱技术结合机器学习方法进行研究。在4000-9000cm-1光谱范围内,采集黄龙病、缺素和健康3类叶片样本的近红外光谱。采用一阶导数、平滑和多元散色校正组合的光谱预处理方法,消除光谱的基线漂移和散射效应。分别对偏最小二乘判别模型（PLS-DA）的主成分因子数和最小二乘支持向量机（LS-SVM）的输入变量数量、核函数类型及其参数进行了优化,建立了PLS-DA和LS-SVM模型。采用预测集样本,评价模型的预测能力,经比较,采用11个主成分得分向量为输入、线性核函数和惩罚因子为2.25的LS-SVM模型预测效果最佳,模型误判率为0。结果表明采用近红外光谱技术结合最小二乘支持向量机进行柑桔黄龙病无损检测是可行的。
Bibliography:Liu Yande, Xiao Huaichun, Deng Qing, Zhang Zhicheng, Sun Xudong, Xiao Yusong （College of MechanicaI and Electrical Engineering, East China Jiaotong University, Nanchang 330013, China）
11-2047/S
The feasibility was explored for identifying health, nutrient deficiency and citrus greening leaves based on near infrared（NIR） spectroscopy combined with machine learning methods. 232 samples were divided into the calibration and prediction sets for calibrating the models and accessing their performance according to the proportion of 3：1. The calibration set included citrus greening samples of 54, nutrient deficiency samples of 64 and healthy samples of 54. The prediction set included citrus greening samples of 21, nutrient deficiency samples of 17 and healthy samples of 22. The spectra of health, nutrient deficiency and citrus greening leaves were recorded in the wavelength range of 4 000-9 000 cm-1. After compared the representative spectra of health, nutrient deficiency and citrus greening, it was found that two sign
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2016.14.027