Die Wavelet-Analyse als chemometrisches Werkzeug

In most cases chemometric methods (PCA, PCR, PLS) are used for data modelling when NIR-spectrometry is applied for analytical purposes. This work is about the application of the wavelet-transform as a tool in chemometrics for analysing NIR-spectra. Beside aspects of data pretreatment, like smoothing of NIR-spectra, and data compression the focus was set on NIR-analysis using wavelet-transformed NIR-spectra. A new method for building multivariate calibration models based on wavelet-coefficients selected by a genetic algorithm is introduced. In addition the results obtained by calibrating wavelet-coefficients using PCR and PLS are descriped. Furthermore the identification of post consumer plastic waste by wavelet-transformed NIR-spectra and an artificial neural network is demonstrated. Two new special types of wavelets which allow analysing finitely extended signals (like spectra) without introducing artifacts near the boundaries were applied


Citation style:
Could not load citation form.


Use and reproduction:
All rights reserved