摘要
近红外光谱(NIRS)技术因其快速、无损和高效的特点,广泛应用于石油、纺织、食品、制药等领域。然而传统的分析方法在处理变量多、冗余大的光谱数据时,往往存在特征提取困难和建模精度不高等问题。因此提出一种适用于近红外光谱且无需变量筛选的一维波长注意力卷积神经网络(WA-1DCNN)定量建模方法,该建模方法结构简单、通用性强、准确率高。该研究引入波长注意力机制,通过赋予不同波长数据不同的权重,增强模型对重要波长特征的捕捉能力,从而提高定量分析的准确性和鲁棒性。为了验证所提出方法的可行性,采用了公开的4种近红外光谱数据集,将所提出的算法与加入波长筛选偏最小二乘法(PLS)、支持向量回归(SVR)、极限学习机(ELM)三种传统建模方法和一维卷积神经网络(1DCNN)建模方法进行了对比,并通过模型性能指标均方根误差(RMSE)和决定系数(R^(2))对模型性能评估。结果表明没有使用波长筛选算法的WA-1DCNN建模方法性能指标均优于加入波长筛选算法的传统建模方法和1DCNN建模方法。其中在655药片数据集中测试集决定系数为0.9563,相比于1DCNN和加入波长筛选的PLS、SVR、ELM提升了4.34%、12.56%、18.42%、11.59%;在310药片数据集中测试集决定系数为0.9574,相比于1DCNN和加入波长筛选的PLS、SVR、ELM、1DCNN提升了2.72%、8.28%、7.27%、1.17%;在玉米水分和蛋白质数据集中测试集决定系数分别为0.9803和0.9685,相比于1DCNN和加入波长筛选的PLS、SVR、ELM提升了6.24%、1.48%、1.75%、6.08%和5.81%、1.85%、1.58%、2.96%;在小麦蛋白质数据集中测试集决定系数为0.9600,相比于DCNN和加入波长筛选的PLS、SVR、ELM提升了8.67%、5.79%、7.94%、0.56%。为了验证WA-1DCNN模型结构的最佳性,在4种近红外光谱数据集上进行了改变WA-1DCNN模型结构的消融实验。研究结果表明:基于波长注意力卷积神经网络是一种结构简单、通用性强、准确率高的光谱定量分析方法,该方法对于近红外光谱定量分析具有促进作用。
Near-infrared spectroscopy(NIRS)technology is widely used in petroleum,textiles,food,pharmaceuticals,etc.,due to its fast,non-destructive,and efficient characteristics.However,there are problems with traditional analysis methods,such as difficulty in feature extraction,low modeling accuracy when dealing with spectral data with many variables,and high redundancy.Therefore,this paper proposes a quantitative modeling method of one-dimensional wavelength attention convolutional neural network(WA-1DCNN)suitable for near-infrared spectroscopy without variable screening.The modeling method has a simple structure,strong versatility,and high accuracy.This study introduces the wavelength attention mechanism,which enhances the model's ability to capture important wavelength features by giving different weights to different wavelength data,thereby improving the accuracy and robustness of quantitative analysis.Four publicly available near-infrared spectral datasets were used in this paper to verify the feasibility of the proposed method.The proposed algorithm was compared with three traditional modeling methods that added wavelength screening,namely partial least squares(PLS),support vector regression(SVR),extreme learning machine(ELM),and one-dimensional convolutional neural network(1DCNN)modeling method.The model performance indicators root evaluated the model performance mean square error(RMSE)and coefficient of determination(R^(2)).The results show that the performance indicators of the WA-1DCNN modeling method without the wavelength screening algorithm are better than those of the traditional modeling method and the 1DCNN modeling method with the wavelength screening algorithm.The R^(2) of the test set in the 655 tablets dataset is 0.9563,which is 4.34%,12.56%,18.42%,and 11.59%higher than that of 1DCNN and PLS,SVR,and ELM with wavelength screening;the R^(2) of the test set in the 310 tablets dataset is 0.9574,which is 2.72%,8.28%,7.27%,and 1.17%higher than that of 1DCNN and PLS,SVR,ELM,and 1DCNN with wavelength screening;The R^(2) of the test set were 0.9803 and 0.9685,respectively,which were 6.24%,1.48%,1.75%,6.08%and 5.81%,1.85%,1.58%,2.96%higher than those of 1DCNN and PLS,SVR,and ELM with wavelength screening;in the wheat protein dataset,the R^(2) of the test set was 0.9600,which was 8.67%,5.79%,7.94%,and 0.56%higher than those of 1DCNN and PLS,SVR,and ELM with wavelength screening.To verify the optimality of the WA-1DCNN model structure in this paper,ablation experiments were conducted on four near-infrared spectral datasets to change the WA-1DCNN model structure.The results show that the wavelength-attention convolutional neural network is a spectral quantitative analysis method with strong versatility,high generalization ability and simple structure,which can promote the quantitative analysis of near-infrared spectra.
作者
陈蓓
蒋思远
郑恩让
CHEN Bei;JIANG Si-yuan;ZHENG En-rang(School of Electrical and Control Engineering,Shaanxi University of Science&Technology,Xi'an 710021,China)
出处
《光谱学与光谱分析》
北大核心
2025年第6期1598-1604,共7页
Spectroscopy and Spectral Analysis
基金
国家自然科学基金项目(62203285)资助。
关键词
近红外光谱
定量分析
波长注意力机制
一维卷积神经网络
Near-infrared spectroscopy
Quantitative analysis
Wavelength attention mechanism
One-dimensional convolutional neural network
