近红外光谱变分推断标定自适应方法研究

doi:10.12068/j.issn.1005-3026.2023.10.002

东北大学学报（自然科学版） ›› 2023, Vol. 44 ›› Issue (10): 1377-1383.DOI: 10.12068/j.issn.1005-3026.2023.10.002

近红外光谱变分推断标定自适应方法研究

赵煜辉，齐天舒，芦鹏程

(东北大学秦皇岛分校计算机与通信工程学院，河北秦皇岛066000)

发布日期:2023-10-27
通讯作者: 赵煜辉
作者简介:赵煜辉(1971-)，男，河北秦皇岛人，东北大学秦皇岛分校教授.
基金资助:
-

Research on Calibration Adaptation Method via Variational Inference for Near-Infrared Spectroscopy

ZHAO Yu-hui， QI Tian-shu， LU Peng-cheng

School of Computer and Communication Engineering， Northeastern University at Qinhuangdao， Qinhuangdao 066000， China.

Published:2023-10-27
Contact: ZHAO Yu-hui
About author:-
Supported by:
-

摘要/Abstract

摘要： 在近红外光谱分析中，已有的标定迁移方法多基于标准样本和无参数归纳模型，普遍存在模型生存周期短、适用范围小等问题.针对此问题，提出了一种参数化对齐源域(主仪器)和目标域(从仪器)特征分布的变分推断标定自适应(variational inference calibration adaptation， VICA)方法.VICA对源域数据进行主成分分析，建立源域特征的变分回归模型.在预测时，VICA首先将目标域数据投影到源域特征子空间中，然后建立源域特征和目标域特征的分布差异函数，通过最小化该函数得到目标域的概率密度模型，实现模型迁移.实验对比表明，VICA比现有的大多数标定迁移方法的标定效果更好.

关键词: 化学计量学；近红外光谱；领域自适应；标定迁移；变分推断

Abstract: In near-infrared spectroscopy analysis， existing calibration transfer methods are mostly based on standard samples and non-parametric induction models， which generally suffer from short model lifespan， limited model applicability. To address this problem， a variational inference calibration adaptation(VICA)method is proposed， which aligns the feature distributions of the source domain(master instrument)and a target domain(slave instrument)by a parametric method. VICA performs principal component analysis on the source domain data and establishes a variational regression model for the source domain features. During prediction， VICA first projects the target domain data into the source domain feature subspace， and then establishes a distribution difference function between the source and target domain features， and obtains the probability density model of the target domain by minimizing this function， achieving model transfer. Experimental comparison results show that VICA performs better in calibration transfer than most existing methods.

Key words: chemometrics; near-infrared spectroscopy; domain adaptation; calibration transfer; variational inference

中图分类号:

O657. 33

赵煜辉，齐天舒，芦鹏程. 近红外光谱变分推断标定自适应方法研究[J]. 东北大学学报（自然科学版）, 2023, 44(10): 1377-1383.

ZHAO Yu-hui， QI Tian-shu， LU Peng-cheng. Research on Calibration Adaptation Method via Variational Inference for Near-Infrared Spectroscopy[J]. Journal of Northeastern University(Natural Science), 2023, 44(10): 1377-1383.

参考文献

[1]Aryal G H，Hunter K W，Huang L.A supramolecular red to near-infrared fluorescent probe for the detection of drugs in urine［J］.Organic & Biomolecular Chemistry，2018，16(40):7425-7429.
[2]Rahimpour A，Noubari H A，Kazemian M.A case-study of NIRS application for infant cerebral hemodynamic monitoring:a report of data analysis for feature extraction and infant classification into healthy and unhealthy［J］.Informatics in Medicine Unlocked，2018，11:44-50.
[3]Workman Jr J J.A review of calibration transfer practices and instrument differences in spectroscopy［J］.Applied Spectroscopy，2018，72(3):340-365.
[4]Weiss K，Khoshgoftaar T M，Wang D D.A survey of transfer learning［J］.Journal of Big Data，2016，3(1):1-40.
[5]Wang Y，Veltkamp D J，Kowalski B R.Multivariate instrument standardization［J］.Analytical Chemistry，1991，63(23):530-533.
[6]Wang Y，Lysaght M J，Kowalski B R.Improvement of multivariate calibration through instrument standardization［J］.Analytical Chemistry，1992，64(5):562-564.
[7]Bouveresse E，Massart D L.Improvement of the piecewise direct standardisation procedure for the transfer of NIR spectra for multivariate calibration［J］.Chemometrics and Intelligent Laboratory Systems，1996，32(2):201-213.
[8]Fan W，Liang Y，Yuan D，et al.Calibration model transfer for near-infrared spectra based on canonical correlation analysis［J］.Analytica Chimica Acta，2008，623(1):22-29.
[9]Kramer K E，Morris R，Rose-Pehrsson S L.Comparison of two multiplicative signal correction strategies for calibration transfer without standards［J］.Chemometrics & Intelligent Laboratory Systems，2008，92(1):33-43.
[10]Malli B，Birlutiu A，Natschlger T.Standard-free calibration transfer-an evaluation of different techniques［J］.Chemometrics & Intelligent Laboratory Systems，2017，161:49-60.
[11]Pan S J，Tsang I W，Kwok J T，et al.Domain adaptation via transfer component analysis［J］.IEEE Transactions on Neural Networks，2011，22(2):199-210.
[12]Fukumizu K，Bach F R，Jordan M I.Dimensionality reduction for supervised learning with reproducing kernel Hilbert spaces［J］.Journal of Machine Learning Research，2004，5:73-99.
[13]Blei D M，Kucukelbir A，McAuliffe J D.Variational inference:a review for statisticians［J］.Journal of the American Statistical Association，2017，112(518):859-877.
[14]Wold S，Esbensen K，Geladi P.Principal component analysis［J］.Chemometrics and Intelligent Laboratory Systems，1987，2(1/2/3):37-52.
[15]Sun B，Feng J，Saenko K.Correlation alignment for unsupervised domain adaptation［M］//Domain Adaptation in Computer Vision Applications.Cham:Springer，2017:153-171.

近红外光谱变分推断标定自适应方法研究

Research on Calibration Adaptation Method via Variational Inference for Near-Infrared Spectroscopy

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价