计算机与数字工程2019，Vol.47Issue(2)：275-280,6.DOI:10.3969/j.issn.1672-9722.2019.02.004
基于回归CNN的烟叶近红外光谱模型研究
Study on Near Infrared Spectroscopy Model of Tobacco Leaves Based on Regression CNN
宗倩倩 1丁香乾 1韩凤 2宫会丽 1张磊1
作者信息
- 1. 中国海洋大学信息科学与工程学院 青岛 266100
- 2. 山东烟草研究院有限公司信息技术研究中心 济南 250001
- 折叠
摘要
Abstract
In order to extract the deep critical features of near-infrared spectroscopy to a greater extent,a novel prediction method,namely,regression-based convolutional neural network(CNNR),which removes the pooling layer and substitute the re?gression layer for the linear softmax classification layer at the top of the general CNN's structure,has been proposed to develop the quantitative model for the tobacco constituents. In order to verify the effectiveness of the CNNR algorithm,the models for total sug?ar,total nicotine and chlorine in tobacco are built for which correlation coefficient R are 0.9318,0.941,0.933,respectively and RMSECV of cross validation were 0.7052,0.0710,0.0971,respectively. The results indicate that the extracted features have a strong ability to interpret the spectral data and have better prediction performance and comprehensive expression ability of tobacco chemical components.关键词
烟叶化学成分/回归卷积神经网络/近红外光谱/定量模型/拓扑结构Key words
tobacco chemical components/convolutional neural network/near infrared spectrum/quantitative model/topol⁃ogy structure分类
信息技术与安全科学引用本文复制引用
宗倩倩,丁香乾,韩凤,宫会丽,张磊..基于回归CNN的烟叶近红外光谱模型研究[J].计算机与数字工程,2019,47(2):275-280,6.
