基于波段注意力卷积网络的近红外奶粉皮革水解蛋白掺假检测

doi:10.3964/j.issn.1000-0593(2022)12-3811-06

摘要
参考文献
相关文章 (15)

全文: PDF (3155 KB)
输出: BibTeX | EndNote (RIS)

摘要：近年来，深度学习技术在近红外光谱、拉曼光谱、荧光光谱等的光谱学数据建模上取得一系列突破。由于深度学习方法对于样本数量的需求高，而在分析化学领域获得大量有标签样本较为困难，因此过拟合问题一直是深度神经网络在化学计量学中应用时研究者高度关注的问题。该工作提出基于波段注意力卷积网络(WA-CNN)的近红外数据建模方法，并应用于婴儿配方奶粉皮革水解蛋白(HLP)掺假定量分析。WA-CNN在传统卷积网络的基础上加入波段注意力模块，该模块采用卷积操作自训练波段注意力权值，并以乘法加权形式对有效波段进行激活，从而有效缓解深度神经网络在近红外数据建模中的波段信息冗余问题，达到抑制过拟合，提升预测精度的目的。研究中共测试100个皮革水解蛋白掺假婴儿配方奶粉样本的近红外光谱数据，其中皮革水解蛋白的掺假比例范围是0%～20%。采用60%的样本训练，剩余40%样本测试，随机采样10次，通过测试集均方根误差(RMSEP)、决定系数(R²)以及相对分析误差(RPD)的均值来进行模型评价。并建立偏最小二乘回归(PLS)、支持向量机回归(SVR)和常规的一维卷积神经网络(CNN)三种传统模型用于对比。与上述对比方法相比，WA-CNN取得最优的模型预测结果，最终获得了RMSEP=1.32%±0.12%，R²=0.96±0.01，RPD=4.92±0.41的掺假定量预测结果。此外，实验结果还表明，相比于传统CNN，WA-CNN在训练过程中对于训练集及测试集损失函数都具有更快更稳定的收敛速度。在20%～80%的不同训练样本数量情况下，WA-CNN相比于三种对比方法均取得最优的模型预测结果。

关键词：波段注意力；近红外光谱；奶粉掺假

Abstract：In recent years, deep learning has made a series of breakthroughs in processing near-infrared spectroscopy, Raman spectroscopy, fluorescence spectroscopy and other spectroscopy data. However, due to the high demand for deep learning methods for the size of the training set, and it is difficult to obtain a large number of labeled samples in the field of analytical chemistry, the overfitting issue has always been highly-concerned by researchers in the application of deep neural network in chemometrics. In response to this problem, this paper proposed a near-infrared spectra modeling method based on the wavelength attention-convolutional neural networks (WA-CNN) and applied it to the quantitative analysis of hydrolyzed leather protein (HPL) adulteration in infant formula. WA-CNN adds a wavelength attention module based on the traditional convolutional network. This module uses convolution operation to learn the attention weights and activates the effective bands in the form of multiplication, thereby effectively alleviating the redundancy and over-fitting problem in NIR modeling based on deep learning. A total of 100 HLP adulterated infant formula samples were tested, and the adulteration ratio was in the range of 0% to 20%. Random sampling was performed 10 times for modeling, in which 60% of the samples were used for training, while the remaining 40% of samples were adopted for testing. The model was evaluated by the mean of root mean square error (RMSEP), coefficient of determination (R²) and relative analysis error (RPD). Three traditional models, namely partial least squares regression (PLS), support vector machine regression (SVR) and conventional one-dimensional convolutional neural network (CNN), were also established for comparison. Compared with the above comparison methods, WA-CNN achieved the best model prediction results and obtained RMSEP=1.32%±0.12%, R²=0.96±0.01, RPD=4.92±0.41. In addition, the results also show that the WA-CNN has a faster and more stable convergence process than the traditional CNN for both the training set and the test set during the training process. Moreover, in the case of different training sample sizes (ranging from 20% to 80%), WA-CNN also achieves the best accuracies among all the examined models.

Key words：Wavelength attention; Near-infrared spectroscopy; Adulteration in infant formula

收稿日期: 2021-07-26 修订日期: 2022-04-12

中图分类号:

O657.33

基金资助: 国家自然科学基金青年科学基金项目(61803107), 广东省自然科学基金项目(2020A1515010768), 中国博士后科学基金项目(2020M672553)资助

通讯作者: 周松斌 E-mail: sb.zhou@giim.ac.cn

作者简介: 陈国喜，1997年生，昆明理工大学信息工程与自动化学院硕士研究生 e-mail: yonhang@163.com

引用本文:

陈国喜，周松斌，陈颀，刘忆森，赵路路，韩威. 基于波段注意力卷积网络的近红外奶粉皮革水解蛋白掺假检测[J]. 光谱学与光谱分析, 2022, 42(12): 3811-3816.
CHEN Guo-xi, ZHOU Song-bin, CHEN Qi, LIU Yi-sen, ZHAO Lu-lu, HAN Wei. Detection of Hydrolyzed Leather Protein Adulteration in Infant Formula Based on Wavelength Attention Convolutional Network and Near-Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(12): 3811-3816.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2022)12-3811-06 或 https://www.gpxygpfx.com/CN/Y2022/V42/I12/3811