MIV波长优选改善VIS/NIR光谱TVB-N模型性能研究

doi:10.3964/j.issn.1000-0593(2020)05-1413-07

摘要
参考文献
相关文章 (15)

全文: PDF (4125 KB)
输出: BibTeX | EndNote (RIS)

摘要：挥发性盐基氮(TVB-N)是衡量肉品新鲜的重要理化指标，利用可见/近红外(VIS/NIR)光谱对TVB-N含量进行定量检测具有重要意义。预测模型是VIS/NIR光谱检测TVB-N含量性能的关键要素，使其兼顾准确性与稳健性可有效改善TVB-N的定量分析结果。以猪肉为例，采集51组不同新鲜度样本的VIS/NIR光谱数据，去除低信噪比区间200～450和900～1 000 nm，选取有效波段450～900 nm的光谱数据用于建模。随后利用主成分分析(PCA)对光谱信息降维，构建一个反向传播神经网络(BPNN)模型。在此基础上，提出用平均影响值(MIV)方法从有效波段中优选与肉质TVB-N含量强相关的特征波长，最终基于221个优选波长，构建一个MIV-PCA-BPNN预测模型。实验表明，初步构建的PCA-BPNN非线性预测模型, 校正相关系数(R_C)和校正均方根误差(RMSEC)分别为0.96和1.47 mg/100 g，预测相关系数(R_P)和预测均方根误差(RMSEP)分别为0.93和1.74 mg/100 g，模型稳健性指标为1.18，优于经典的线性预测模型主成分分析回归和偏最小二乘回归，证明TVB-N具有较强的非线性效应。最终构建的MIV-PCA-BPNN预测模型的R_C和RMSEC分别为0.98和1.21 mg/100 g，R_P和RMSEP分别为0.96和1.12 mg/100 g，模型稳健性指标为1.08，在所构建的预测模型中，RMSEC和RMSEP最小，R_C和R_P最大，模型的准确性和稳健性最佳。另外，MIV方法筛选出的特征波长集中在7个波峰附近，皆分布于肉品中化学成分的吸收区内，且与TVB-N中的含氢基团的特征吸收峰表现出高度一致性，为利用MIV方法筛选波长变量提供了理论依据。研究结果显示，MIV波长优选可有效改善预测模型的性能，为利用神经网络剔除无关波长变量提供了新思路，所构建的MIV-PCA-BPNN预测模型满足了肉质中TVB-N定量分析的需求。

关键词：VIS/NIR光谱检测；反向传播神经网络；波长优选；挥发性盐基氮

Abstract：Volatile Basic Nitrogen (TVB-N) is an important physicochemical property for the detection of meat freshness. Using visible/near-infrared (VIS/NIR) spectroscopy to analyze TVB-N content is of great importance quantitatively-. The prediction model is the key factor for detection TVB-N content in visible or near infrared spectroscopy. Thus, an accurate and robust prediction model can improve the quantitative analysis results of TVB-N. Firstly, we collected 51 representative pork samples with different freshness, and determine the effective band from 450 to 900 nm after removing low signal-to-noise ratio band from 200 to 450 nm and from 900 to 1 000 nm. Then we use principal component analysis (PCA) to reduce spectral data in order to construct a back propagation neural network (BPNN) model. On this basis, we use the mean impact value (MIV) method to select characteristic wavelengths which strongly related to the content of Total Volatile Basic Nitrogen (TVB-N) in edible meat, and finally construct a MIV-PCA-BPNN prediction model based on 221 selected wavelengths. Experimental results show that the related coefficient of calibration (R_C), the related coefficient of prediction (R_P), the root means square error of calibration (RMSEC), the root mean square error of prediction (RMSEP) and the robustness index of the PCA-BPNN model are 0.96, 0.93, 1.47 mg/100 g, 1.74 mg/100 g and 1.18, respectively. The PCA-BPNN nonlinear prediction model is better than the classical linear prediction model principal component regression and partial least squares regression prediction model, which proves that TVB-N has strong nonlinear effects. The R_C, R_P, RMSEC, RMSEP and the robustness index of the MIV-PCA-BPNN model are 0.98, 0.96, 1.12 mg/100 g, 1.21 mg/100 g and 1.08, respectively, it is RMSEC and RMSEP are the smallest, while R_C, R_P are the largest. Therefore, MIV-PCA-BPNN is the most accurate and robust model in all constructed prediction model. In addition, the characteristic wavelengths selected by the MIV method are concentrated near 7 peaks, which are distributed in the absorption regions of chemical composition in meat. The characteristic wavelengths are consistent with the absorption peaks of H Contained Groups in TVB-N, which provides a theoretical basis for selecting wavelengths by the MIV method. It is found that the MIV wavelength selection is effective to improve the performance of the prediction model, which offers new thought for using the neural network to eliminate irrelevant wavelength variables. The MIV-PCA-BPNN prediction model could be used for the quantitative analysis of TVB-N in meat.

Key words：Visible/near-infrared spectroscopy; Back propagation neural network (BPNN); Wavelength selection; Total volatile basic nitrogen (TVB-N)

收稿日期: 2019-04-17 修订日期: 2019-08-28

中图分类号:

O433.4

基金资助: 湖北省自然科学基金科技支撑计划项目（2015BCE048），国家科技支撑计划课题（2015BAD29B01），湖北省自然科学基金重点项目(2014CFA051)，中央高校基本科研业务费专项资金自科培育项目（CZP17026）资助

通讯作者: 杨春勇 E-mail: cyyang@mail.scuec.edu.cn

作者简介: 陈亦凡，1999年生，中南民族大学电子信息工程学院本科生 e-mail: anguoc@gmail.com

引用本文:

陈亦凡，李芸婧，彭苗苗，杨春勇，侯金，陈少平. MIV波长优选改善VIS/NIR光谱TVB-N模型性能研究[J]. 光谱学与光谱分析, 2020, 40(05): 1413-1419.
CHEN Yi-fan, LI Yun-jing, PENG Miao-miao, YANG Chun-yong, HOU Jin, CHEN Shao-ping. Improvements of VIS-NIR Spectroscopy Model in the Prediction of TVB-N Using MIV Wavelength Selection. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(05): 1413-1419.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2020)05-1413-07 或 https://www.gpxygpfx.com/CN/Y2020/V40/I05/1413

[1] Qiao L, Tang X, Dong J. Food Chemistry, 2017, 237: 1179.
[2] Qu F, Ren D, He Y, et al. Meat Science, 2018, 146: 59.
[3] Fan Y, Liao Y, Cheng F. International Journal of Food Properties, 2018, 21(1): 1180.
[4] SONG Xiang-zhong，TANG Guo，ZHANG Lu-da, et al(宋相中，唐果，张录达, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(4): 1048.
[5] Alamprese C, Casale M, Sinelli N, et al. LWT—Food Science and Technology, 2013, 53(1): 225.
[6] CAI Jian-rong，WAN Xin-min，CHEN Quan-sheng(蔡健荣，万新民，陈全胜). Acta Optica Sinica(光学学报), 2009, (10): 2808.
[7] Huang L, Zhao J, Chen Q, et al. Food Chemistry, 2014, 145: 228.
[8] Li H D, Liang Y Z, Long X X, et al. Chemometrics & Intelligent Laboratory Systems, 2013, 122(5): 23.
[9] YANG Mei-hua，ZHAO Xiao-min，FANG Qian, et al(杨梅花，赵小敏，方倩, 等). Scientia Agricultura Sinica(中国农业科学), 2014，(12): 2374.
[10] Dombi G W, Nandi P, Saxe J M, et al. Journal of Trauma and Acute Care Surgery, 1995, 39(5): 915.
[11] Tan X, Ji Z, Zhang Y. Technology & Health Care, 2018, 26(6): 1.
[12] Zhang Z, Yang J. International Journal of Oil, Gas and Coal Technology, 2016, 11(3): 279.
[13] Fan H, Xuan J, Du X, et al. RSC Advances, 2018, 8(69): 39602.
[14] WEI Wen-song，PENG Yan-kun，ZHENG Xiao-chun, et al(魏文松，彭彦昆，郑晓春, 等). Acta Optica Sinica(光学学报), 2017, 37(11): 382.
[15] YAN Yan-lu, CHEN Bin, ZHU Da-zhou, et al(严衍禄, 陈斌，朱大洲，等). Near Infrared Spectroscopy—Principles, Technologies and Applications(近红外光谱分析的原理、技术与应用). Beijing: China Light Industry Press(北京: 中国轻工业出版社), 2013. 123.
[16] Wu J, Peng Y, Li Y, et al. Journal of Food Engineering, 2012, 109(2): 267.
[17] Cheng J, Sun D, Qu J, et al. Journal of Food Engineering, 2016, 182: 9.
[18] ZOU Hao，TIAN Han-you，LIU Fei, et al(邹昊，田寒友，刘飞, 等). Food Science(食品科学), 2016, 37(22): 180.