摘要
卷积神经网络(CNN)近年来已经广泛应用在各种化学计量学任务中。然而,通过CNN从光谱中学习长程相关性仍然是一个挑战,为了避免过拟合,很多之前的工作中使用的CNN架构都很浅。本文提出了一种并行空洞卷积网络(ACPnet)的方法来学习定量光谱的长程相关性,该方法将具有不同空洞率的并行卷积分支组合在一起,以寻找近程和长程相关性的最佳平衡。并在片剂(拉曼光谱)、土壤(近红外光谱)和葡萄酒(核磁共振光谱)3个数据集上验证了该方法的通用性。结果表明,与偏最小二乘回归(PLS)、最小二乘支持向量机(LS-SVM)、常规CNN和级联模式空洞卷积网络(ACCnet)相比,ACPnet在3个数据集的回归精度都达到了最佳。此外,将ACPnet提取的特征输入到不同的回归器中进行分析,来评估该结构作为有监督特征提取器的性能。特征提取-回归模型的预测结果表明,ACPnet在3个数据集上提取的特征信息都要优于常规CNN。
The convolutional neural network(CNN)has been widely used in various chemometric tasks in the past few years.However,learning longrange correlations from spectra using the CNN remains challenging,because most CNN architectures utilized in previous studies are quite shallow to avoid overfitting.In this paper,we present an atrous convolutional network(ACPnet)for learning longrange spectral correlation in quantitative spectrometric analysis.Paralleled convolution branches with different atrous rates are assembled to determine the best tradeoff between shortrange and longrange information.Three data sets,viz.tablets(Raman),soil(NIR),and wines(NMR),are evaluated to demonstrate the versatility of the proposed network.The overall results indicate that the ACPnet achieves better regression accuracies for all three data sets than those of partial least squares regression(PLS),least square support vector machine(LSSVM),a regular CNN,and an atrous CNN in a cascaded pattern(ACCnet).Furthermore,the features extracted by the ACPnet are fed into different regressors to evaluate the proposed network as a supervised feature extractor.The results of the extraction–regression model show that ACPnet gives better featureextraction performance than that of a conventional CNN on the three data sets.
作者
陈国喜
刘忆森
周松斌
赵路路
Chen Guoxi;Liu Yisen*;Zhou Songbin;Zhao Lulu(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,Yunnan,China;Institute of Intelligent Manufacturing,Guangdong Academy of Sciences,Guangzhou 510070,Guangdong,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2023年第9期430-438,共9页
Laser & Optoelectronics Progress
基金
国家青年科学基金(61803107)
广东省自然科学基金(2020A1515010768)
梅州市科技计划(2021B0203001)。
关键词
光谱学
空洞卷积神经网络
定量光谱分析
短程和长程相关性
spectroscopy
atrous convolutional neural network
quantitative spectrometric analysis
shortrange and longrange correlation
