文章摘要
孟庆龙,尚静,黄人帅,杨欣,张艳.基于主成分回归的猕猴桃可溶性固形物无损检测[J].包装工程,2021,42(3):19-24.
MENG Qing-long,SHANG Jing,HUANG Ren-shuai,YANG Xin,ZHANG Yan.Nondestructive Detection for Soluble Solids Content of Kiwifruits Based on Principal Component Regression[J].Packaging Engineering,2021,42(3):19-24.
基于主成分回归的猕猴桃可溶性固形物无损检测
Nondestructive Detection for Soluble Solids Content of Kiwifruits Based on Principal Component Regression
投稿时间:2020-05-04  
DOI:10.19554/j.cnki.1001-3563.2021.03.003
中文关键词: 紫外/可见光谱  猕猴桃  可溶性固形物  主成分回归  无损检测
英文关键词: UV/Visible spectroscopy  kiwifruits  soluble solids content  principal component regression  nondestructive detection
基金项目:国家自然科学基金(61505036);贵州省基础研究计划(科学技术基金)(黔科合基础[2020]1Y270);贵州省普通高等学校工程研究中心资助项目(黔教合KY字[2016]017);贵阳学院科研资金(GYU-KY-[2021]);大学生创新创业训练计划(S202010976001)
作者单位
孟庆龙 贵阳学院贵阳 550005 
尚静 贵阳学院贵阳 550005 
黄人帅 贵阳学院贵阳 550005 
杨欣 贵阳学院贵阳 550005 
张艳 贵阳学院贵阳 550005 
摘要点击次数:
全文下载次数:
中文摘要:
      目的 为实现猕猴桃可溶性固形物含量的快速无损检测。方法 实验采用反射式光谱采集系统获取不同成熟期“贵长”猕猴桃的反射光谱。比较3种光谱预处理方法(标准正态变换、多元散射校正以及二阶导数)对回归预测模型的影响;采用主成分分析对预处理后的光谱数据进行降维,并基于提取的特征变量,建立猕猴桃可溶性固形物含量的回归预测模型。结果 采用主成分分析,从1024个全光谱波段中提取了前16个主成分作为特征变量;基于特征变量建立的回归预测模型具有较好的预测性能,其预测集决定系数R2P=0.88,剩余预测偏差为2.94。结论 基于紫外/可见光谱结合主成分回归可以很好地预测猕猴桃可溶性固形物含量。
英文摘要:
      The work aims to conduct rapid nondestructive detection on soluble solids content of kiwifruits. Reflecting spectra acquisition system was used to collect reflectance spectra of Guichang kiwifruits in different maturity stages. The influences of standard normal variation, multi-scatter calibration and second derivative on the regression prediction model were compared. And the principal component analysis was used to reduce data dimension from preprocessing reflectance spectra. And a regression model was established based on selected characteristic variables for predicting soluble solids content of kiwifruits. The results showed that the first 16 principal components were selected as the characteristic variables by principal component analysis from 1024 full wavelengths. The regression model based on selected characteristic variables had a relatively good prediction ability (R2P=0.88, RPD=2.94). Therefore, it can accurately predict SSC of kiwifruits based on UV/Visible spectroscopy and principal component regression.
查看全文   查看/发表评论  下载PDF阅读器
关闭

关于我们 | 联系我们 | 投诉建议 | 隐私保护 | 用户协议

您是第21103813位访问者    渝ICP备15012534号-2

版权所有:《包装工程》编辑部 2014 All Rights Reserved

邮编:400039 电话:023-68795652 Email: designartj@126.com

    

渝公网安备 50010702501716号