English
往期目录
新闻公告
More
化学进展 2017, Vol. 29 Issue (8): 902-910 DOI: 10.7536/PC170416 前一篇   

• 综述 •

近红外光谱模型转移新算法

张进1, 蔡文生1, 邵学广1,2,3,4,5*   

  1. 1. 南开大学化学学院 分析科学研究中心 天津 300071;
    2. 天津市生物传感与分子识别重点实验室 天津 300071;
    3. 药物化学生物学国家重点实验室 天津 300071;
    4. 天津化学化工协同创新中心 天津 300071;
    5. 喀什大学化学与环境科学学院 喀什 844000
  • 收稿日期:2017-04-13 修回日期:2017-06-28 出版日期:2017-08-15 发布日期:2017-07-24
  • 通讯作者: 邵学广,E-mail:xshao@nankai.edu.cn E-mail:xshao@nankai.edu.cn
  • 基金资助:
    国家自然科学基金项目（No.21475068）资助
下载PDF ( 2041 ) 引用
导出 被引次数 ( 1 | 8 )

New Algorithms for Calibration Transfer in Near Infrared Spectroscopy

Jin Zhang1, Wensheng Cai1, Xueguang Shao1,2,3,4,5*   

  1. 1. Research Center for Analytical Sciences, College of Chemistry, Nankai University, Tianjin 300071, China;
    2. Tianjin Key Laboratory of Biosensing and Molecular Recognition, Tianjin 300071, China;
    3. State Key Laboratory of Medicinal Chemical Biology, Tianjin 300071, China;
    4. Collaborative Innovation Center of Chemical Science and Engineering (Tianjin), Tianjin 300071, China;
    5. College of Chemistry and Environmental Science, Kashgar University, Kashgar 844000, China
  • Received:2017-04-13 Revised:2017-06-28 Online:2017-08-15 Published:2017-07-24
  • Supported by:
    The work was supported by the National Natural Science Foundation of China (No. 21475068).
模型转移是解决分析仪器或分析方法通用性的关键技术。近红外光谱受测量仪器或测量条件的影响较大，模型转移对近红外光谱技术的实际应用尤为重要。本文综述了近年来近红外光谱分析中被广泛应用和新提出的模型转移算法，从计算原理角度梳理了有标样和无标样算法的联系和区别。有标样算法重点介绍了基于多元校正、因子分析、人工神经网络、多任务学习的模型转移方法，无标样算法重点介绍了基于光谱校正、模型参数校正和稳健建模的模型转移方法。从算法的角度分析了各种模型转移方法的特点和转移效果，并展望了模型转移算法的进一步发展。在综述的众多方法中分段直接标准化及其变体仍是模型转移的黄金标准，但是，基于因子分析的算法正变得受欢迎且基于神经网络和多任务学习的方法近年来也吸引了越来越多的注意。但是，在实际应用中，获得标准样品以在主机和子机上测得其光谱比较困难甚至是不可能的，无标样模型转移则更加实用。此外，随着仪器小型化、成像及超光谱成像的发展，模型转移在未来会变得愈加必不可少。
关键词： 近红外光谱, 化学计量学, 模型转移, 多任务学习, 光谱空间转换
Calibration transfer is a key technique to ensure the consistency of instruments or analytical methods. Near infrared spectra is strongly influenced by the status of instrument or the environment of measurement. Therefore, calibration transfer is essential for practical applications of near infrared spectroscopy. This paper provides an overview of the state-of-the-art pertaining to calibration transfer methods, including those with and without standard samples, and the focus is on the methods based on multivariate calibration, factor analysis, neural network and multi-task learning for algorithms with standard samples and on the methods based on spectral correction, model coefficient correction and robust multivariate calibration for algorithms without standard samples. The formulation and efficiency of different calibration transfer methods are analyzed from the viewpoint of the algorithms. Among the summarized methods, piecewise direct standardization (PDS) and its variants are still the gold standard for calibration transfer, but algorithms based on factor analysis is becoming popular and those based on neural network and multi-task learning has gradually attracted more attention in recent years. In practical applications, however, it is difficult or even impossible to obtain the standard samples for measuring their spectra on both master and slave instruments, calibration transfer without standard samples is more practical. Furthermore, with the development of the instrumentation in miniaturization, imaging and hyper-spectral imaging, calibration transfer will be more and more essential in the future.Contents
1 Introduction
2 Algorithms with standard samples
2.1 Multivariate calibration transfer
2.2 Factor analysis methods
2.3 Neural network
2.4 Multi-task learning
2.5 Others
3 Algorithms without standard samples
3.1 Spectral correction methods
3.2 Model coefficient correction methods
3.3 Robust multivariate calibration
4 Conclusion
Key words: near infrared spectroscopy, chemometrics, calibration transfer, multi-task learning, spectral space transformation

中图分类号: 

()
[1] Huang H B, Yu H Y, Xu H R, Ying Y B. J. Food Eng., 2008, 87(3):303.
[2] Huppert T J, Diamond S G, Franceschini M A, Boas D A. Appl. Opt., 2009, 48(10):D280.
[3] Prieto N, Roehe R, Lavín P, Batten G, Andrés S. Meat Science, 2009, 83(2):175.
[4] 刘言(Liu Y), 蔡文生(Cai W S), 邵学广(Shao X G). 科学通报(Chinese Science Bulletin), 2015, 60(08):704.
[5] 刘言(Liu Y), 蔡文生(Cai W S), 邵学广(Shao X G). 科学通报(Chinese Science Bulletin), 2015, 60(08):694.
[6] Wang Y D, Kowalski B R. Anal. Chem., 1993, 65(9):1301.
[7] Barboza F D, Poppi R J. Anal. Bioanal. Chem., 2003, 377(4):695.
[8] Liu X, Huang C J, Han L J. Energy & Fuels, 2015, 29(10):6450.
[9] Pereira L S A, Carneiro M F, Botelho B G, Sena M M. Talanta, 2016, 147:351.
[10] Leion H, Folestad S, Josefson M, Sparen A. J. Pharm. Biomed. Anal., 2005, 37(1):47.
[11] Fearn T. J. Near Infrared Spectrosc., 2001, 9(4):229.
[12] Liu Y, Cai W S, Shao X G. Anal. Chim. Acta, 2014, 836:18.
[13] Yu B F, Ji H B, Kang Y. Spectrosc. Lett., 2016, 49(1):23.
[14] Bouveresse E, Hartmann C, Massart D L, Last I R, Prebble K A. Anal. Chem., 1996, 68(6):982.
[15] 褚小立(Chu X L), 袁洪福(Yuan H F), 陆婉珍(Lu W Z). 光谱学与光谱分析(Spectroscopy and Spectral Analysis), 2001, 21(06):881.
[16] Osborne B G, Fearn T. Int. J. Food Sci. Technol., 1983, 18(4):453.
[17] Shenk J S, Westerhaus M O. US 4866644, 1989.
[18] Wang Y D, Veltkamp D J, Kowalski B R. Anal. Chem., 1991, 63(23):2750.
[19] Ma C X, Shao X G. J. Chem. Inf. Model., 2004, 44(3):907.
[20] Blank T B, Sum S T, Brown S D, Monfre S L. Anal. Chem., 1996, 68(17):2987.
[21] Sj blom J, Svensson O, Josefson M, Kullberg H, Wold S. Chemom. Intell. Lab. Syst., 1998, 44(1/2):229.
[22] Feudale R N, Woody N A, Tan H W, Myles A J, Brown S D, Ferré J. Chemom. Intell. Lab. Syst., 2002, 64(2):181.
[23] Forina M, Drava G, Armanino C, Boggia R, Lanteri S, Leardi R, Corti P, Conti P, Giangiacomo R, Galliena C, Bigoni R, Quartari I, Serra C, Ferri D, Leoni O, Lazzeri L. Chemom. Intell. Lab. Syst., 1995, 27(2):189.
[24] 张学博(Zhang X B), 冯艳春(Feng Y C), 胡昌勤(Hu C Q). 药物分析杂志(Chinese Journal of Pharmaceutical Analysis), 2009, 29(08):1390.
[25] Tan H W, Brown S D. J. Chemom., 2001, 15(8):647.
[26] 田高友(Tian G Y), 袁洪福(Yuan H F), 刘慧颖(Liu H Y), 陆婉珍(Lu W Z). 光谱学与光谱分析(Spectroscopy and Spectral Analysis), 2003, 23(6):1111.
[27] Yoon J G, Lee B W, Han C H. Chemom. Intell. Lab. Syst., 2002, 64(1):1.
[28] 田高友(Tian G Y), 褚小立(Chu X L), 袁洪福(Yuan H F), 陆婉珍(Lu W Z). 分析化学(Chinese Journal of Analytical Chemistry), 2006, 34(07):927.
[29] 王菊香(Wang J X), 李华(Li H), 邢志娜(Xing Z N), 郭恒光(Guo H G). 分析化学(Chinese Journal of Analytical Chemistry), 2011, 39(06):846.
[30] Wang J X, Qu J, Li H, Han X, Xu G. Pet. Sci. Technol., 2012, 30(19):1975.
[31] Liang C, Yuan H F, Zhao Z, Song C F, Wang J J. Chemom. Intell. Lab. Syst., 2016, 153:51.
[32] 王艳斌(Wang Y B), 袁洪福(Yuan H F), 陆婉珍(Lu W Z). 光谱学与光谱分析(Spectroscopy and Spectral Analysis), 2005, 25(03):398.
[33] Du W, Chen Z P, Zhong L J, Wang S X, Yu R Q, Nordon A, Littlejohn D, Holden M. Anal. Chim. Acta, 2011, 690(1):64.
[34] Fan W, Liang Y Z, Yuan D L, Wang J J. Anal. Chim. Acta, 2008, 623(1):22.
[35] Zheng K Y, Zhang X, Iqbal J, Fan W, Wu T, Du Y P, Liang Y Z. J. Chemom., 2014, 28(10):773.
[36] Cai D, He X F, Han J W. IEEE 11th International Conference on Computer Vision. IEEE, 2007. 1.
[37] Yan S, Xu D, Zhang B, Zhang H J, Yang Q, Lin S. IEEE Trans. Pattern Anal.Machine Intelligence, 2007, 29(1):40.
[38] Peng J T, Peng S L, Jiang A, Tan J. Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy, 2011, 78(4):1315.
[39] Wu H L, Shibukawa M, Oguma K. J. Chemom., 1998, 12(1):1.
[40] 吴海龙(Wu H L), 俞汝勤(Yu R Q). 化学通报(Chinese Science Bulletin), 2011, 74(9):771.
[41] Despagne F, Walczak B, Massart D L. Appl. Spectrosc., 1998, 52(5):732.
[42] Duponchel L, Ruckenbusch C, Huvenne J, Legrand P. J. Near Infrared Spectrosc., 1999, 7(3):155.
[43] Huang G B, Zhu Q Y, Siew C K. Neurocomputing, 2006, 70(1/3):489.
[44] Chen W R, Bin J, Lu H M, Zhang Z M, Liang Y Z. Analyst, 2016, 141(6):1973.
[45] Pan S J, Yang Q. IEEE Trans. Knowl. Data Eng., 2010, 22(10):1345.
[46] Evgeniou T, Pontil M. Regularized Multi-Task Learning. Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Seattle:ACM, 2004. 109.
[47] Yan K, Zhang D. Sens. Actuators, B:Chem., 2016, 225:288.
[48] Yu B F, Ji H B. Anal. Methods, 2015, 7(6):2714.
[49] 杨辉华(Yang H H), 张晓凤(Zhang X F), 樊永显(Fan Y X), 谢谱模(Xie P M), 褚小立(Chu X L). 分析化学(Chinese Journal of Analytical Chemistry), 2014, 42(09):1229.
[50] 王家俊(Wang J J), 者为(Zhe W), 刘言(Liu Y), 蔡文生(Cai W S), 邵学广(Shao X G). 中国烟草学报(Acta Tabacaria Sinica), 2014, 20(06):1.
[51] Wang J J, Li Z F, Wang Y, Liu Y, Cai W S, Shao X G. Spectrosc. Lett., 2016, 48(5):348.
[52] 彭黔荣(Peng Q R), 张进(Zhang J), 刘娜(Liu N), 胡芸(Hu Y), 刘剑(Liu J), 姬厚伟(Ji H W), 王芳(Wang F). CN 105628645A, 2016.
[53] Kramer K E, Morris R E, Rose-Pehrsson S L. Chemom. Intell. Lab. Syst., 2008, 92(1):33.
[54] Li X Y, Xu Z H, Cai W S, Shao X G. Anal. Chim. Acta, 2015, 880:26.
[55] Amat-Tosello S, Dupuy N, Kister J. Anal. Chim. Acta, 2009, 642(1/2):6.
[56] Roger J M, Chauchard F, Bellon M V. Chemom. Intell. Lab. Syst., 2003, 66(2):191.
[57] Lin Z Z, Xu B, Li Y, Shi X Y, Qiao Y J. J. Chemom., 2013, 27(11):406.
[58] Kalivas J H, Siano G G, Andries E, Goicoechea H C. Appl. Spectrosc., 2009, 63(7):800.
[59] Shahbazikhah P, Kalivas J H. Chemom. Intell. Lab. Syst., 2013, 120:142.
[60] Kunz M R, Kalivas J H, Andries E. Anal. Chem., 2010, 82(9):3642.
[61] Kunz M R, She Y Y. J. Chemom., 2013, 27(9):233.
[62] Li X Y, Cai W S, Shao X G. J. Near Infrared Spectrosc., 2015, 23(5):285.
[63] Liu Y, Cai W S, Shao X G. Spectrochim Acta A, 2016, 169:197.
[64] Geladi P, Macdougall D, Martens H. Appl. Spectrosc., 1985, 39(3):491.
[65] Wold S, Antti H, Lindgren F, Öhman J. Chemom. Intell. Lab. Syst., 1998, 44(1/2):175.
[66] Martens H, Høy M, Wise B M, Bro R, Brockhoff P B. J. Chemom., 2003, 17(3):153.
[67] Malli B, Birlutiu A, Natschläger T. Chemom. Intell. Lab. Syst., 2017, 161:49.
[68] 张晓羽(Zhang X Y), 李庆波(Li Q B), 张广军(Zhang G J). 光谱学与光谱分析(Spectroscopy and Spectral Analysis), 2014, 34(05):1429.
[69] Martins M N, Galvao R K H, Pimentel M F. J. Braz. Chem. Soc., 2010, 21(1):127.
[70] Greensill C V, Wolfs P J, Spiegelman C H, Walsh K B. Appl. Spectrosc., 2001, 55(5):647.
[71] Greensill C V, Walsh K. J. Near Infrared Spectrosc., 2002, 10(1):27.
[72] Alamar M C, Bobelyn E, Lammertyn J, Nicolaï B M, Moltó E. Postharvest Biol. Technol., 2007, 45(1):38.
[73] Hayes C J, Walsh K B, Greensill C V. J. Near Infrared Spectrosc., 2016, 24(1):59.
[1] 樊梦丽, 赵越, 刘言, 蔡文生, 邵学广. 近红外光谱水光谱组学[J]. 化学进展, 2015, 27(2/3): 242-250.
[2] 江艳,武培怡. 大豆蛋白的中红外和近红外光谱研究*[J]. 化学进展, 2009, 21(04): 705-714.
[3] 江艳,武培怡. 近红外光谱在蛋白质和含酰胺基团聚合物研究中的应用*[J]. 化学进展, 2008, 20(12): 2021-2033.
[4] 褚小立,袁洪福,陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用[J]. 化学进展, 2004, 16(04): 528-.
[5] 张秀琦,刘辉,郑建斌,高鸿. 信号处理技术在重叠化学信号解析中的应用*[J]. 化学进展, 2002, 14(03): 174-.
[6] 毕开顺,徐筱杰,王玺,罗旭. 关于统计学中一个新兴化学分支学科的建立、定义和教育[J]. 化学进展, 1999, 11(02): 173-.
阅读次数
全文


摘要

近红外光谱模型转移新算法