Bayesian analysis of spectral mixture data using Markov Chain Monte Carlo Methods

This paper presents an original method for the analysis of multicomponent spectral data sets. The proposed algorithm is based on Bayesian estimation theory and Markov Chain Monte Carlo (MCMC) methods. Resolving spectral mixture analysis aims at recovering the unknown component spectra and at assessing the concentrations of the underlying species in the mixtures. In addition to non-negativity constraint, further assumptions are generally needed to get a unique resolution. The proposed statistical approach assumes mutually independent spectra and accounts for the non-negativity and the sparsity of both the pure component spectra and the concentration profiles. Gamma distribution priors are used to translate all these information in a probabilistic framework. The estimation is performed using MCMC methods which lead to an unsupervised algorithm, whose performances are assessed in a simulation study with a synthetic data set.

[1]  T. Brown,et al.  A new method for spectral decomposition using a bilinear Bayesian approach. , 1999, Journal of magnetic resonance.

[2]  S. J. Roberts,et al.  Independent Component Analysis: Source Assessment Separation, a Bayesian Approach , 1998 .

[3]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[4]  W. Windig,et al.  Factor Analysis in Chemistry (3rd Edition) , 2002 .

[5]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[6]  Pierre Comon.  Independent component analysis - a new concept? signal processing , 1994 .

[7]  R. Henry,et al.  Extension of self-modeling curve resolution to mixtures of more than three components: Part 2. Finding the complete solution , 1999 .

[8]  Peter Green,et al.  Markov chain Monte Carlo in Practice , 1996 .

[9]  Patrik O. Hoyer,et al.  Non-negative sparse coding , 2002, Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.

[10]  Satoshi Kawata,et al.  Advanced Algorithm for Determining Component Spectra Based on Principal Component Analysis , 1985 .

[11]  Mark D. Plumbley.  Algorithms for nonnegative independent component analysis , 2003, IEEE Trans. Neural Networks.

[12]  Bruce R. Kowalski,et al.  An extension of the multivariate component-resolution method to three components , 1985 .

[13]  David Brie,et al.  Non-negative source separation: range of admissible solutions and conditions for the uniqueness of the solution , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[14]  J. Nuzillard,et al.  Model-free analysis of mixtures by NMR using blind source separation , 1998, Journal of magnetic resonance.

[15]  R. Tauler.  Calculation of maximum and minimum band boundaries of feasible solutions for species profiles obtained by multivariate curve resolution , 2001 .

[16]  Marc Garland,et al.  An improved algorithm for estimating pure component spectra in exploratory chemometric studies based on entropy minimization , 1998 .

[17]  P. Paatero,et al.  Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values† , 1994 .

[18]  H. R. Keller,et al.  Evolving factor analysis , 1991 .

[19]  Jean-Marc Nuzillard,et al.  Application of blind source separation to 1-D and 2-D nuclear magnetic resonance spectroscopy , 1998, IEEE Signal Processing Letters.

[20]  M. Kendall,et al.  Kendall's advanced theory of statistics , 1995 .

[21]  Mark D. Plumbley.  Algorithms for Non-Negative Independent Component Analysis , 2002 .

[22]  D. Brie,et al.  Separation of Non-Negative Mixture of Non-Negative Sources Using a Bayesian Approach and MCMC Sampling , 2006, IEEE Transactions on Signal Processing.

[23]  Romà Tauler,et al.  Chemometrics applied to unravel multicomponent processes and mixtures: Revisiting latest trends in multivariate resolution , 2003 .

[24]  J. W. Miskin,et al.  Ensemble Learning for Blind Source Separation , 2001 .

[25]  Marc Garland,et al.  Pure component spectral reconstruction from mixture data using SVD, global entropy minimization, and simulated annealing. Numerical investigations of admissible objective functions using a synthetic 7‐species data set , 2002, J. Comput. Chem..

[26]  Yi-Zeng Liang,et al.  Principles and methodologies in self-modeling curve resolution , 2004 .

[27]  H. Gampp,et al.  Evolving Factor Analysis , 1987 .

[28]  D. Massart,et al.  Orthogonal projection approach applied to peak purity assessment. , 1996, Analytical chemistry.

[29]  P. Paatero.  Least squares formulation of robust non-negative factor analysis , 1997 .

[30]  Christian P. Robert,et al.  The Bayesian choice , 1994 .

[31]  R. Bro,et al.  A fast non‐negativity‐constrained least squares algorithm , 1997 .

[32]  B. Kowalski,et al.  Multivariate curve resolution applied to spectral data from multiple runs of an industrial process , 1993 .

[33]  Romà Tauler,et al.  Simultaneous analysis of several spectroscopic titrations with self-modelling curve resolution , 1993 .

[34]  P. Sajda,et al.  RECOVERY OF CONSTITUENT SPECTRA IN 3D CHEMICAL SHIFT IMAGING USING NON-NEGATIVE MATRIX FACTORIZATION , 2003 .

[35]  Desire L. Massart,et al.  Resolution of multicomponent overlapped peaks by the orthogonal projection approach, evolving factor analysis and window factor analysis , 1997 .

[36]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

[37]  Daniel B. Rowe,et al.  Multivariate Bayesian Statistics: Models for Source Separation and Signal Unmixing , 2002 .

[38]  N. Sidiropoulos,et al.  Least squares algorithms under unimodality and non‐negativity constraints , 1998 .

[39]  N. Ohta,et al.  Estimating absorption bands of component dyes by means of principal component analysis , 1973 .

[40]  S Kawata,et al.  Constrained nonlinear method for estimating component spectra from multicomponent mixtures. , 1983, Applied optics.

[41]  Edmund R. Malinowski,et al.  Factor Analysis in Chemistry , 1980 .

[42]  Richard M. Everson,et al.  Independent Component Analysis: Principles and Practice , 2001 .

[43]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[44]  E. A. Sylvestre,et al.  Self Modeling Curve Resolution , 1971 .

[45]  Charles L. Lawson,et al.  Solving least squares problems , 1976, Classics in applied mathematics.

[46]  Marcel Maeder,et al.  Evolving factor analysis, a new multivariate technique in chromatography , 1988 .

[47]  C. Lawson,et al.  Solving least squares problems , 1976, Classics in applied mathematics.

[48]  W. Windig,et al.  Interactive self-modeling mixture analysis , 1991 .

[49]  R. Henry,et al.  Extension of self-modeling curve resolution to mixtures of more than three components: Part 1. Finding the basic feasible region , 1990 .

[50]  W. Windig.  Mixture analysis of spectral data by multivariate methods , 1988 .

[51]  Christian P. Robert,et al.  Monte Carlo Statistical Methods , 2005, Springer Texts in Statistics.

[52]  Paul J. Gemperline,et al.  A priori estimates of the elution profiles of the pure components in overlapped liquid chromatography peaks using target factor analysis , 1984, J. Chem. Inf. Comput. Sci..

[53]  Joseph G. Ibrahim,et al.  Monte Carlo Methods in Bayesian Computation , 2000 .

[54]  Ronald C. Henry,et al.  Extension of self-modeling curve resolution to mixtures of more than three components: Part 3. Atmospheric aerosol data simulation studies☆ , 1990 .

[55]  S Kawata,et al.  Estimation of component spectral curves from unknown mixture spectra. , 1984, Applied optics.

[56]  Romà Tauler,et al.  Assessment of new constraints applied to the alternating least squares method , 1997 .

[57]  Kevin H. Knuth.  A Bayesian approach to source separation , 1999 .

[58]  P. Comon.  Independent Component Analysis , 1992 .

[59]  W. Windig,et al.  Interactive self-modeling multivariate analysis , 1990 .