当前位置: X-MOL 学术J. Near Infrared Spectrosc. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Application of neural networks for classifying softwood species using near infrared spectroscopy
Journal of Near Infrared Spectroscopy ( IF 1.6 ) Pub Date : 2020-07-09 , DOI: 10.1177/0967033520939320
Sang-Yun Yang 1, 2 , Ohkyung Kwon 3 , Yonggun Park 1, 2 , Hyunwoo Chung 1 , Hyunbin Kim 1 , Se-Yeong Park 4 , In-Gyu Choi 1, 2, 5 , Hwanmyeong Yeo 1, 2
Affiliation  

Lumber species identification is an important issue for the wood industry. In this study, three types of neural networks (artificial neural network (ANN), deep neural network (DNN), and convolutional neural network (CNN)) were employed for classifying softwood lumber species using NIR spectroscopy. The results show that CNN, which is based on deep learning, was more stable than the other neural networks. In particular, the stability of the training process was remarkably improved in CNN models. During the training procedure, the validation accuracy of the CNN model was 99.3% for the raw spectra, 99.9% for the standard normal variate (SNV) spectra and 100.0% for the Savitzky-Golay second derivative spectra. Interestingly, there was little difference in the validation accuracies among the CNN models depending on mathematical preprocessing. The results showed that CNN is sufficiently adequate to classify the softwood lumber species.

中文翻译:

神经网络在近红外光谱法分类针叶材中的应用

木材品种鉴定是木材工业的一个重要问题。在这项研究中,三种类型的神经网络(人工神经网络 (ANN)、深度神经网络 (DNN) 和卷积神经网络 (CNN))用于使用 NIR 光谱对针叶材树种进行分类。结果表明,基于深度学习的 CNN 比其他神经网络更稳定。特别是训练过程的稳定性在 CNN 模型中得到了显着提高。在训练过程中,CNN 模型的原始光谱验证精度为 99.3%,标准正态变量 (SNV) 光谱为 99.9%,Savitzky-Golay 二阶导数光谱为 100.0%。有趣的是,根据数学预处理的不同,CNN 模型之间的验证精度几乎没有差异。
更新日期:2020-07-09
down
wechat
bug