Independent component analysis as a pretreatment method for parallel factor analysis to eliminate artefacts from multiway data

被引:37
作者
Bouveresse, Delphine Jouan-Rimbaud
Benabid, Hamida
Rutledge, Douglas N.
机构
[1] INRA, UMR 214, INA P G Ingn Anal Qual Aliments, F-75231 Paris 05, France
[2] Univ Mentouri Constantine, INATAA, Fac Sci, Constantine 25000, Algeria
关键词
independent component analysis; 3D-fluorescence; excitation-emission matrix; parallel factor analysis; Rayleigh and Raman scattering;
D O I
10.1016/j.aca.2007.02.061
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Parallel factor analysis (PARAFAC) has successfully been used in many applications for the analysis of excitation-emission fluorescence data. However, some measurement "artefacts", such as Rayleigh or Raman scattering, can pose a problem for the extraction of the PARAFAC components and their interpretation. Replacing the spectral zones corresponding to these signals by missing values in the data is not necessarily a method of choice in the cases where informative signals lie in the same wavelength regions. In this article, independent component analysis (ICA) is used on the unfolded cubic array, and the independent components related to the Rayleigh and Raman scattering are identified and removed prior to the reconstruction of the excitation-emission fluorescence data cube. PARAFAC is then applied on these data reconstructed after selective artefact removal, and satisfactory models can be obtained. This procedure, although particularly useful for 3D fluorescence data, may be applied to other types of data as well. (c) 2007 Elsevier B.V. All rights reserved.
引用
收藏
页码:216 / 224
页数:9
相关论文
共 19 条
[1]  
ANDERSON RN, 2001, NATL VITAL STAT REP, V52, P1
[2]  
[Anonymous], 1999, INDEPENDENT COMPONEN
[3]   A new efficient method for determining the number of components in PARAFAC models [J].
Bro, R ;
Kiers, HAL .
JOURNAL OF CHEMOMETRICS, 2003, 17 (05) :274-286
[4]   PARAFAC. Tutorial and applications [J].
Bro, R .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1997, 38 (02) :149-171
[5]  
BRO R, 1998, THESIS U AMSTERDAM
[6]   High-order contrasts for independent component analysis [J].
Cardoso, JF .
NEURAL COMPUTATION, 1999, 11 (01) :157-192
[7]  
De Lathauwer L, 2000, J CHEMOMETR, V14, P123, DOI 10.1002/1099-128X(200005/06)14:3<123::AID-CEM589>3.0.CO
[8]  
2-1
[9]   Automatically identifying scatter in fluorescence data using robust techniques [J].
Engelen, Sanne ;
Moller, Stina Frosch ;
Hubert, Mia .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2007, 86 (01) :35-51
[10]  
Harwood J., 2000, HDB OLIVE OIL ANAL P, DOI DOI 10.1007/978-1-4757-5371-4