Decomposition of spectra using maximum autocorrelation factors

Rasmus Larsen, Nørgaard Nørgaard (Editor)

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    144 Downloads (Pure)

    Abstract

    This paper addresses the problem of generating a low dimensional representation of the variation present in a set of spectra, e.g. reflection spectra recorded from a series of objects. The resulting low dimensional description may subseque ntly be input through variable selection schemes into classification or regression type analyses. A featured method for low dimensional representation of multivariate datasets is Hotellings principal components transform. We will extend the use of principal components analysis incorporating new information into the algorithm. This new information consists of the fact that given a spectrum we have a natura ln order of the input \$\backslash\$underline{variables}. This is similar to Switzers maximum au tocorrelation factors, where a natural order of \$\backslash\$underline{observations} (pixels) in multispectral images is utilized. However, in order to utilize an ordering of the input \$\backslash\$underline{variables} we need a non-trivial reformulation of the maximum autocorrelation problem in Q-mode. We call the resulting transformation for Q-MAF. The resulting new variables can be interpreted as a frequency ecomposition of the spectra. But contrary to ordinary Fourier decomposition these new variables are located in frequency as well as well wavelength. The proposed algorithm is tested on 100 samples of NIR spectra of wheat.
    Original languageEnglish
    Title of host publication7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark
    Publication date2001
    Publication statusPublished - 2001

    Cite this

    Larsen, R., & Nørgaard, N. (Ed.) (2001). Decomposition of spectra using maximum autocorrelation factors. In 7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark
    Larsen, Rasmus ; Nørgaard, Nørgaard (Editor). / Decomposition of spectra using maximum autocorrelation factors. 7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark. 2001.
    @inproceedings{264bdc4cfe5d4a159047c8196e06f8e2,
    title = "Decomposition of spectra using maximum autocorrelation factors",
    abstract = "This paper addresses the problem of generating a low dimensional representation of the variation present in a set of spectra, e.g. reflection spectra recorded from a series of objects. The resulting low dimensional description may subseque ntly be input through variable selection schemes into classification or regression type analyses. A featured method for low dimensional representation of multivariate datasets is Hotellings principal components transform. We will extend the use of principal components analysis incorporating new information into the algorithm. This new information consists of the fact that given a spectrum we have a natura ln order of the input \$\backslash\$underline{variables}. This is similar to Switzers maximum au tocorrelation factors, where a natural order of \$\backslash\$underline{observations} (pixels) in multispectral images is utilized. However, in order to utilize an ordering of the input \$\backslash\$underline{variables} we need a non-trivial reformulation of the maximum autocorrelation problem in Q-mode. We call the resulting transformation for Q-MAF. The resulting new variables can be interpreted as a frequency ecomposition of the spectra. But contrary to ordinary Fourier decomposition these new variables are located in frequency as well as well wavelength. The proposed algorithm is tested on 100 samples of NIR spectra of wheat.",
    keywords = "chemometrics, shape analysis, maximum autocorrelation factors",
    author = "Rasmus Larsen and N{\o}rgaard N{\o}rgaard",
    year = "2001",
    language = "English",
    booktitle = "7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark",

    }

    Larsen, R & Nørgaard, N (ed.) 2001, Decomposition of spectra using maximum autocorrelation factors. in 7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark.

    Decomposition of spectra using maximum autocorrelation factors. / Larsen, Rasmus; Nørgaard, Nørgaard (Editor).

    7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark. 2001.

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    TY - GEN

    T1 - Decomposition of spectra using maximum autocorrelation factors

    AU - Larsen, Rasmus

    A2 - Nørgaard, Nørgaard

    PY - 2001

    Y1 - 2001

    N2 - This paper addresses the problem of generating a low dimensional representation of the variation present in a set of spectra, e.g. reflection spectra recorded from a series of objects. The resulting low dimensional description may subseque ntly be input through variable selection schemes into classification or regression type analyses. A featured method for low dimensional representation of multivariate datasets is Hotellings principal components transform. We will extend the use of principal components analysis incorporating new information into the algorithm. This new information consists of the fact that given a spectrum we have a natura ln order of the input \$\backslash\$underline{variables}. This is similar to Switzers maximum au tocorrelation factors, where a natural order of \$\backslash\$underline{observations} (pixels) in multispectral images is utilized. However, in order to utilize an ordering of the input \$\backslash\$underline{variables} we need a non-trivial reformulation of the maximum autocorrelation problem in Q-mode. We call the resulting transformation for Q-MAF. The resulting new variables can be interpreted as a frequency ecomposition of the spectra. But contrary to ordinary Fourier decomposition these new variables are located in frequency as well as well wavelength. The proposed algorithm is tested on 100 samples of NIR spectra of wheat.

    AB - This paper addresses the problem of generating a low dimensional representation of the variation present in a set of spectra, e.g. reflection spectra recorded from a series of objects. The resulting low dimensional description may subseque ntly be input through variable selection schemes into classification or regression type analyses. A featured method for low dimensional representation of multivariate datasets is Hotellings principal components transform. We will extend the use of principal components analysis incorporating new information into the algorithm. This new information consists of the fact that given a spectrum we have a natura ln order of the input \$\backslash\$underline{variables}. This is similar to Switzers maximum au tocorrelation factors, where a natural order of \$\backslash\$underline{observations} (pixels) in multispectral images is utilized. However, in order to utilize an ordering of the input \$\backslash\$underline{variables} we need a non-trivial reformulation of the maximum autocorrelation problem in Q-mode. We call the resulting transformation for Q-MAF. The resulting new variables can be interpreted as a frequency ecomposition of the spectra. But contrary to ordinary Fourier decomposition these new variables are located in frequency as well as well wavelength. The proposed algorithm is tested on 100 samples of NIR spectra of wheat.

    KW - chemometrics

    KW - shape analysis

    KW - maximum autocorrelation factors

    M3 - Article in proceedings

    BT - 7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark

    ER -

    Larsen R, Nørgaard N, (ed.). Decomposition of spectra using maximum autocorrelation factors. In 7th Scandinavian Symposium on Chemometrics, 19-23 August, Copenhagen , Denmark. 2001