基于迭代保留信息变量和连续投影的近红外光谱波长选择方法

引用本文: 程介虹, 陈争光. 基于迭代保留信息变量和连续投影的近红外光谱波长选择方法[J]. 分析化学, 2021, 49(8): 1402-1409. doi: 10.19756/j.issn.0253-3820.201307 shu

Citation: CHENG Jie-Hong, CHEN Zheng-Guang. Wavelength Selection Method for Near Infrared Spectroscopy Based on Iteratively Retains Informative Variables and Successive Projections Algorithm[J]. Chinese Journal of Analytical Chemistry, 2021, 49(8): 1402-1409. doi: 10.19756/j.issn.0253-3820.201307 shu

基于迭代保留信息变量和连续投影的近红外光谱波长选择方法

程介虹 ,
陈争光 ^,

黑龙江八一农垦大学电气与信息学院, 大庆 163319

通讯作者: 陈争光,E-mail:ruzee@sina.com

基金项目:
国家重点研发计划项目（No.2016YFD0701300）、黑龙江省农垦总局重点科研计划项目（No.HKKYZD190804）和黑龙江省省属高校基本科研业务费项目（No.ZRCPY201913）资助。

摘要: 连续投影算法（SPA）作为一种波长选择算法，用于近红外光谱的定量分析中以简化模型复杂度，提高模型预测精度。由SPA算法的原理可知，SPA算法只能保证相邻两次投影所选择的两个波长之间具有较低的冗余性，但不保证所选变量一定是有效变量，即SPA筛选出的变量子集中可能包含一些无信息变量甚至是干扰变量。所以通过迭代保留信息变量（IRIV）提取有效变量（即强、弱信息变量），再基于有效变量进行SPA波长选择，以解决SPA所选变量可能含有无信息和干扰变量的问题，提高模型预测精度。将改进的IRIV-SPA算法应用于两组公开的近红外光谱数据，进行特征波长选择后，建立MLR模型，并与全谱的PLSR模型以及一些常用的高性能的波长选择方法（SPA、IRIV、随机蛙跳（RF）算法）进行对比，以验证改进的IRIV-SPA算法的有效性。结果表明，在两组公开的测试数据集下，改进的IRIV-SPA-MLR模型的预测精度最优，相较于其它算法极大地提高了预测精度，简化了模型的复杂度。研究结果表明，改进的IRIV-SPA可实现高效降维，是一种有效的特征波长选择算法。

关键词:

English

Wavelength Selection Method for Near Infrared Spectroscopy Based on Iteratively Retains Informative Variables and Successive Projections Algorithm

CHENG Jie-Hong ,
CHEN Zheng-Guang ^,

College of Electrical and Information, Heilongjiang Bayi Agricultural University, Daqing 163319, China

Corresponding author: CHEN Zheng-Guang, ruzee@sina.com

Received Date: 25 May 2020
Revised Date: 18 January 2021
Fund Project:
Supported by the National Key R&D Program of China (No.2016YFD0701300), the key Scientific Research Program of Heilongjiang Agricultural Reclamation Bureau (No.HKKYZD190804), and the Scientific Research Projects of Basic Scientific Research Funds in Heilongjiang Provincial Colleges and Universities (No.ZRCPY201913).

Abstract: As a wavelength selection algorithm, successive projection algorithm (SPA) is used in the quantitative analysis of near infrared spectroscopy to simplify the model complexity and improve the prediction accuracy. According to the principle of SPA algorithm, SPA method can only ensure that there is low redundancy between the two wavelengths selected by two adjacent projections, but it does not guarantee that the selected variables must be effective variables, that is to say, the subset of variables screened by SPA may contain some uninformation variables or even interfering variables. We extract effective variables (i.e. strong and weak information variables) by iteratively retains informative variables (IRIV), and then select wavelength by SPA based on effective variables, so as to solve the problem that the selected variables by SPA may contain uninformation and interfering variables, and improve the prediction accuracy of the model. The improved IRIV-SPA is applied to processing of two groups of public NIR spectral data. After the wavelengths are selected, the MLR model is established and compared with the FULL-PLSR model and some other commonly used high-performance wavelength selection methods (SPA, IRIV, RF) to prove the effectiveness of the improved IRIV-SPA algorithm. The results show that the improved IRIV-SPA-MLR model has the best prediction accuracy under two opening test datasets, which greatly improves the prediction accuracy and simplifies the complexity of the model compared with other algorithms. The improved IRIV-SPA can achieve efficient dimensionality reduction and is an effective wavelength selection algorithm.

Key words:

Near-infrared spectroscopy
/ Wavelength selection
/ Multivariate calibration
/ Successive projection algorithm
/ Iteratively retains informative variables

1. [1]
  MEHMOOD T, LILAND K H, SNIPEN L, SAEBO S S. Chemom. Intell. Lab. Syst., 2012, 118: 62-69.MEHMOOD T, LILAND K H, SNIPEN L, SAEBO S S. Chemom. Intell. Lab. Syst., 2012, 118: 62-69.
2. [2]
  YUN Y H, LI H D, DENG B C, CAO D S. TrAC-Trends Anal. Chem., 2019, 113: 102-115.YUN Y H, LI H D, DENG B C, CAO D S. TrAC-Trends Anal. Chem., 2019, 113: 102-115.
3. [3]
  ZOU X B, ZHAO J W, POVEY M J W, HOLMES M, MAO H P. Anal. Chim. Acta, 2010, 667(1-2): 14-32.ZOU X B, ZHAO J W, POVEY M J W, HOLMES M, MAO H P. Anal. Chim. Acta, 2010, 667(1-2): 14-32.
4. [4]
  ARAUJO M C U, SALDANHA T C B, GALVÄO R K H, YONEYAMA T, CHAME H C, VISANI V. Chemom. Intell. Lab. Syst., 2001, 57(2): 65-73.ARAUJO M C U, SALDANHA T C B, GALVÄO R K H, YONEYAMA T, CHAME H C, VISANI V. Chemom. Intell. Lab. Syst., 2001, 57(2): 65-73.
5. [5]
  HAO Yong, SUN Xu-Dong, WANG Hao. J. Jiangsu Univ. (Nat. Sci. Ed.), 2013, 34(1): 49-53. 郝勇, 孙旭东, 王豪. 江苏大学学报(自然科学版), 2013, 34(1): 49-53.
6. [6]
  XU Zhi-Bin, WU Nan, LI Cui, CHEN Fan. Coal Tech., 2015, 34(2): 280-282. 徐志彬, 吴楠, 李翠, 陈凡. 煤炭技术, 2015, 34(2): 280-282.
7. [7]
  CHEN Hua-Zhou, GU Jie, CHEN Wei-Hao, MO Li-Na, QIAO Han-Li. Spectrosc. Spectral Anal., 2018, 38(S1): 118-119. 陈华舟, 辜洁, 陈伟豪, 莫丽娜, 乔涵丽. 光谱学与光谱分析, 2018, 38(S1): 118-119.
8. [8]
  TANG R, CHEN X, LI C. Appl. Spectrosc., 2018, 72(5): 740-749.TANG R, CHEN X, LI C. Appl. Spectrosc., 2018, 72(5): 740-749.
9. [9]
  DE ALMEIDA V E, GOMES A D, FERNANDES D D D, GOICOECHEA H C, GALVAO R K H, ARAUJO M C U. Talanta, 2018, 181: 38-43.DE ALMEIDA V E, GOMES A D, FERNANDES D D D, GOICOECHEA H C, GALVAO R K H, ARAUJO M C U. Talanta, 2018, 181: 38-43.
10. [10]
  YUAN Ying, WANG Wei, CHU Xuan, XI Ming-Jie. Spectrosc. Spectral Anal., 2016, 36(1): 226-230. 袁莹, 王伟, 褚璇, 喜明杰. 光谱学与光谱分析, 2016, 36(1): 226-230.
11. [11]
  SONG Xiang-Zhong, TANG Guo, ZHANG Lu-Da, XIONG Yan-Mei, MIN Shun-Geng. Spectrosc. Spectral Anal., 2017, 37(4): 1048-1052. 宋相中, 唐果, 张录达, 熊艳梅, 闵顺耕. 光谱学与光谱分析, 2017, 37(4): 1048-1052.
12. [12]
  YUN Y H, WANG W T, TAN M L, LIANG Y Z, LI H D, CAO D S, LU H M, XU Q S. Anal. Chim. Acta, 2014, 807: 36-43.YUN Y H, WANG W T, TAN M L, LIANG Y Z, LI H D, CAO D S, LU H M, XU Q S. Anal. Chim. Acta, 2014, 807: 36-43.
13. [13]
  LI H D, XU Q S, LIANG Y Z. Anal. Chim. Acta, 2012, 740: 20-26.LI H D, XU Q S, LIANG Y Z. Anal. Chim. Acta, 2012, 740: 20-26.
14. [14]
  [dataset] U.S. Army, Near Infrared Spectra of Diesel Fuels, Soutwest Research Institute (SWRI), Eigenvector Research Inconrporated.[dataset] U.S. Army, Near Infrared Spectra of Diesel Fuels, Soutwest Research Institute (SWRI), Eigenvector Research Inconrporated.
15. [15]
  [dataset] Havstrom, Soil Samples Measured by NIR, Long Term Field Experiment in Abisko, Quality & Technology.[dataset] Havstrom, Soil Samples Measured by NIR, Long Term Field Experiment in Abisko, Quality & Technology.
16. [16]
  CHENG Jie-Hong, CHEN Zheng-Guang, ZHANG Qing-Hua. J. Agric. Sci. Tech. China, 2020, 22(1): 162-170. 程介虹, 陈争光, 张庆华. 中国农业科技导报, 2020, 22(1): 162-170.
17. [17]
  SOARES S F C, GOMES A, FILHO A R G, ARAUJO M C U, GALVAO R K H. TrAC-Trends Anal. Chem., 2013, 42: 84-98.SOARES S F C, GOMES A, FILHO A R G, ARAUJO M C U, GALVAO R K H. TrAC-Trends Anal. Chem., 2013, 42: 84-98.
18. [18]
  ZHANG Hang, LIU Guo-Hai, JIANG Hui, MEI Cong-Li, HUANG Yong-Hong. Las. Optoelect. Prog., 2017, 54(2): 314-320. 张航, 刘国海, 江辉, 梅从立, 黄永红. 激光与光电子学进展, 2017, 54(2): 314-320.
19. [19]
  YU Lei, ZHANG Tao, ZHU Ya-Xing, ZHOU Yong, XIA Tian, NIE Yan. Trans. Chin. Soc. Agric. Eng., 2018, 34(16): 148-154. 于雷, 章涛, 朱亚星, 周勇, 夏天, 聂艳. 农业工程学报, 2018, 34(16): 148-154.
20. [20]
  GAO Sheng, WANG Qiao-Hua. Chin. J. Lumin., 2019, 40(12): 1574-1584. 高升, 王巧华. 发光学报, 2019, 40(12): 1574-1584.
21. [21]
  XIE Yue, LI Fei-Yue, FAN Xing-Jun, HU Shui-Jin, XIAO Xin, WANG Jian-Fei. Chin. J. Anal. Chem., 2018, 46(4): 609-615. 谢越, 李飞跃, 范行军, 胡水金, 肖新, 汪建飞. 分析化学, 2018, 46(4): 609-615.

扫一扫看文章

计量

PDF下载量: 18
文章访问数: 1086
HTML全文浏览量: 171

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于迭代保留信息变量和连续投影的近红外光谱波长选择方法

通讯作者: 陈争光,E-mail:ruzee@sina.com

English

Wavelength Selection Method for Near Infrared Spectroscopy Based on Iteratively Retains Informative Variables and Successive Projections Algorithm

Corresponding author: CHEN Zheng-Guang, ruzee@sina.com

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

基于迭代保留信息变量和连续投影的近红外光谱波长选择方法

通讯作者: 陈争光,E-mail:ruzee@sina.com

English

Wavelength Selection Method for Near Infrared Spectroscopy Based on Iteratively Retains Informative Variables and Successive Projections Algorithm

Corresponding author: CHEN Zheng-Guang, ruzee@sina.com

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs