Zhang Lei, Ding Xiangqian, Hou Ruichun
College of Information Science and Engineering, Ocean University of China, Qingdao 266100, China.
J Anal Methods Chem. 2020 Feb 12;2020:9652470. doi: 10.1155/2020/9652470. eCollection 2020.
The origin of tobacco is the most important factor in determining the style characteristics and intrinsic quality of tobacco. There are many applications for the identification of tobacco origin by near-infrared spectroscopy. In order to improve the accuracy of the tobacco origin classification, a near-infrared spectrum (NIRS) identification method based on multimodal convolutional neural networks (CNN) was proposed, taking advantage of the strong feature extraction ability of the CNN. Firstly, the one-dimensional convolutional neural network (1-D CNN) is used to extract and combine the pattern features of one-dimensional NIRS data, and then the extracted features are used for classification. Secondly, the one-dimensional NIRS data are converted into two-dimensional spectral images, and the structure features are extracted from two-dimensional spectral images by the two-dimensional convolutional neural network (2-D CNN) method. The classification is performed by the combination of global and local training features. Finally, the influences of different network structure parameters on model identification performance are studied, and the optimal CNN models are selected and compared. The multimodal NIR-CNN identification models of tobacco origin were established by using NIRS of 5,200 tobacco samples from 10 major tobacco producing provinces in China and 3 foreign countries. The classification accuracy of 1-D CNN and 2-D CNN models was 93.15% and 93.05%, respectively, which was better than the traditional PLS-DA method. The experimental results show that the application of 1-D CNN and 2-D CNN can accurately and reliably distinguish the NIRS data, and it can be developed into a new rapid identification method of tobacco origin, which has an important promotion value.
烟草的产地是决定烟草风格特征和内在品质的最重要因素。近红外光谱技术在烟草产地鉴别方面有诸多应用。为提高烟草产地分类的准确性，利用卷积神经网络（CNN）强大的特征提取能力，提出了一种基于多模态卷积神经网络的近红外光谱（NIRS）鉴别方法。首先，使用一维卷积神经网络（1-D CNN）提取并合并一维近红外光谱数据的模式特征，然后将提取的特征用于分类。其次，将一维近红外光谱数据转换为二维光谱图像，通过二维卷积神经网络（2-D CNN）方法从二维光谱图像中提取结构特征。通过全局和局部训练特征相结合进行分类。最后，研究了不同网络结构参数对模型鉴别性能的影响，选择并比较了最优的卷积神经网络模型。利用来自中国10个主要产烟省份和3个外国的5200个烟草样品的近红外光谱建立了烟草产地的多模态近红外-卷积神经网络鉴别模型。一维卷积神经网络（1-D CNN）和二维卷积神经网络（2-D CNN）模型的分类准确率分别为93.15%和93.05%，优于传统的偏最小二乘判别分析（PLS-DA）方法。实验结果表明，一维卷积神经网络（1-D CNN）和二维卷积神经网络（2-D CNN）的应用能够准确可靠地区分近红外光谱数据，可发展成为一种新的烟草产地快速鉴别方法，具有重要的推广价值。
