首页 > 论文 > 光谱学与光谱分析 > 38卷 > 12期(pp:3724-3728)

基于卷积神经网络的烟叶近红外光谱分类建模方法研究

The Study of Classification Modeling Method for Near Infrared Spectroscopy of Tobacco Leaves Based on Convolution Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

卷积神经网络(CNN)在图像分类识别领域应用广泛, 但其在近红外光谱分类中的研究还未见报道, 对基于CNN的近红外光谱分类建模方法进行了研究。 针对近红外光谱数据的特点, 提出了一种改进的卷积神经网络建模方法, 对CNN经典模型LeNet-5所做改进: ①将方形矩阵卷积核改为适用于一维近红外光谱的向量卷积核; ②简化网络结构, 将LeNet-5结构中C5, F6及输出层改为单层感知机。 同时, 采用隔点采样的方法对近红外光谱降维, 加快收敛速度; 并对卷积核尺寸对建模结果的影响进行了研究。 以我国东北、 黄淮、 西南三大烤烟产区的600个中部烟叶样本的近红外光谱为实验对象, 建立烟叶产区分类NIR-CNN模型。 该模型对训练集和测试集的判别准确率为98.2%和95%。 实验结果表明, 应用卷积神经网络可对近红外光谱数据准确、 可靠地判别分类; 烟叶产区NIR-CNN建模方法可为卷烟企业烟叶原料科学合理利用提供指导, 为维护卷烟产品的质量稳定有重要意义; 基于卷积神经网络的近红外光谱判别方法也可推广到其他农产品的分类应用中。

Abstract

Convolutional neural network (CNN) was widely used in image classification and recognition but its application in near infrared spectroscopy has not been reported. Therefore, the near-infrared spectroscopy classification modeling method based on CNN was studied in this paper. Taking into account the characteristics of near-infrared spectral data, an improved CNN modeling method was presented in this paper, which improves the CNN classical model Lenet-5: ①The square matrix convolution kernel was transformed into a vector convolution kernel for one-dimensional near-infrared spectroscopy. ②The C5, F6 and output layers of the lenet-5 structure were changed to single-layer sensing machines in order to simplify the network structure. At the same time, the method of sampling points was used to reduce the dimensionality of near infrared spectrum and speed up the convergence rate. The influence of convolution kernel size on modeling results was also studied in this paper. NIR-CNN model was established by the near-infrared spectroscopy of 600 central tobacco samples from northeast, Huanghuai and southwest China. The accuracy of the model was 98.2% and 95% for the training set and test set. The experimental results showed that the application of CNN could accurately and reliably identify the near infrared spectrum data. This method provided guidance for the scientific and rational utilization of raw materials of tobacco enterprises, and it was important to maintain the quality stability of cigarette products. The method of near infrared spectroscopy based on CNN could also be applied in the classification of other agricultural products.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:O657.3

DOI:10.3964/j.issn.1000-0593(2018)12-3724-05

基金项目:国家重点研发计划子课题(2016YFD0700304)资助

收稿日期:2017-07-31

修改稿日期:2017-11-03

网络出版日期:--

作者单位    点击查看

鲁梦瑶:中国农业大学信息与电气工程学院, 北京 100083中国农业大学, 教育部现代精细农业系统集成研究重点实验, 北京 100083
杨 凯:上海烟草集团有限责任公司, 上海 200082
宋鹏飞:云南中烟技术中心, 云南 昆明 650202
束茹欣:上海烟草集团有限责任公司, 上海 200082
王萝萍:云南中烟技术中心, 云南 昆明 650202
刘 慧:中国农业大学信息与电气工程学院, 北京 100083中国农业大学, 教育部现代精细农业系统集成研究重点实验, 北京 100083
李军会:中国农业大学信息与电气工程学院, 北京 100083中国农业大学, 教育部现代精细农业系统集成研究重点实验, 北京 100083
赵龙莲:中国农业大学信息与电气工程学院, 北京 100083中国农业大学, 教育部现代精细农业系统集成研究重点实验, 北京 100083
张晔晖:中国农业大学信息与电气工程学院, 北京 100083中国农业大学, 教育部现代精细农业系统集成研究重点实验, 北京 100083

联系人作者:鲁梦瑶(498408325@qq.com)

备注:鲁梦瑶, 女, 1993年生, 中国农业大学信息与电气工程学院硕士研究生

【1】QIAO Xue-yi, WANG Bing, WU Dian-xin, et al(乔学义, 王 兵, 吴殿信, 等). Tobacco Science & Technology(烟草科技), 2016, 49(9): 70.

【2】YIN Qi-sheng, ZHANG Yan-ling, XUE Chao-qun, et al(尹启生, 张艳玲, 薛超群, 等). Acta Tabacaria Sinica(中国烟草学报), 2009, 15(4): 33.

【3】PENG Xin-hui, YI Jian-hua, ZHOU Qing-ming(彭新辉, 易建华, 周清明). Chinese Tobacco Science(中国烟草科学), 2009, 30(1): 68.

【4】SHU Ru-xin, SUN Ping, YANG Kai, et al(束茹欣, 孙 平, 杨 凯, 等). Tobacco Science & Technology(烟草科技), 2011, (11): 50.

【5】ZHANG Ying, HE Li-yuan(章 英, 贺立源). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2011, 27(4): 350.

【6】TANG Guo, TIAN Kuang-da, LI Zu-hong(唐 果, 田旷达, 李祖红, 等). Tobacco Science & Technology(烟草科技), 2013, (4): 60.

【7】Lecun Y, Kavukcuoglu K, Farabet C. IEEE International Symposium on Circuits & Systems, 2010, 14 (5): 253.

【8】Ji S, Xu W, Yang M, et al. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35(1): 221.

【9】Su B, Lu S. Pattern Recognition, 2007, 63: 397.

【10】Sarikaya R, Hinton G E, Deoras A. IEEE/ACM Transactions on Audio Speech & Language Processing, 2014, 23(4): 778.

【11】Mohamed A R, Dahl G E, Hinton G. IEEE Transactions on Audio Speech & Language Processing, 2012, 20(1): 14.

【12】Abdel-Hamid O, Mohamed A R, Jiang H, et al. IEEE International Conference on Acoustics, 2012, 22(10): 77.

【13】Lecun Y, Bottou L, Bengio Y, et al. Proceedingsof the IEEE, 1998, 86(11): 2278.

引用该论文

LU Meng-yao,YANG Kai,SONG Peng-fei,SHU Ru-xin,WANG Luo-ping,YANG Yu-qing,LIU Hui,LI Jun-hui,ZHAO Long-lian,ZHANG Ye-hui. The Study of Classification Modeling Method for Near Infrared Spectroscopy of Tobacco Leaves Based on Convolution Neural Network[J]. Spectroscopy and Spectral Analysis, 2018, 38(12): 3724-3728

鲁梦瑶,杨 凯,宋鹏飞,束茹欣,王萝萍,刘 慧,李军会,赵龙莲,张晔晖. 基于卷积神经网络的烟叶近红外光谱分类建模方法研究[J]. 光谱学与光谱分析, 2018, 38(12): 3724-3728

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF