Application of multidimensional data analysis to chromatography

• Autorzy: Satława T. , Grabska-Chrząstowska J. , Korohoda P.
• Języki publikacji: EN

Abstrakty

EN

This work presents analysis of chromatographic signal used to identify substances in samples. First part consists of chromatography overview and description of three classification methods (neural network with backpropagation, probabilistic neural network with Parzen window and support vector machines). Designed algorithm consists of several stages: signal filtering, peak detection and its approximation with sum of two Gaussian functions. The parameters of that two curves are the features vectors describing the peak of the substance. The last step is classification, for which two types of supervised machine learning were compared, based on the whole signal and on features vectors. Both types were tested for different classificators and their parameters. Verification was based on 55 chromatography signals. The best results for both methods of learning were achieved for probabilistic neural networks. The correct classification rate was 82% for the whole signal and 93% for feature vectors.

Słowa kluczowe

EN

chromatographic signal; backpropagation neural network; support vector machine

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2013
• Tom: Vol. 18, no. 2-3
• Strony: 101--108
• Opis fizyczny: Bibliogr. 19 poz., rys.

Twórcy

autor

Satława T.

• AGH University of Science and Technology, Department of Measurement and Electronics, Krakow, Poland

autor

Grabska-Chrząstowska J.

• AGH University of Science and Technology, Department of Measurement and Electronics, Krakow, Poland

autor

Korohoda P.

• AGH University of Science and Technology, Department of Automatics and Bioengineering, Krakow, Poland

Bibliografia

• [1] N. Crisianini, J.Shewe-Taylor, An introduction to support vector machines and other kernel-based learning methods, Cambridge University Press, 2000
• [2] Dragan A. Cirovic., Feed-forward artificial networks: application to spectroscopy, Trends in analytical chemistry, vol. 3, pp. 148-155, 1997
• [3] E. Dudek-Dyduch, R. Tadeusiewicz, A. Horzyk, Neural network adaptation process effectiveness dependent of constant training data availability, Neurocomputing, vol. 72, no. 13-15, pp. 3138-3149, 2009
• [4] P. Eiler, H. Boelens, Baseline correction with asymmetric least squares smoothing, 2005
• [5] L. Fausett, Fundamentals of Neural Networks: Architectures, Algorithms And Applications, Pearson, 1993
• [6] A. Gidudu, G. Hulley, T. Marwala, Image classifications using SVMs: One-against-One Vs One- Against-All, Proccedings of the 28th Asian Conference on Remote Sensing, 2007
• [7] Ł. Komsta, Comparison of several methods of chromatographic baseline removal with a new approach based on quantile regression, Chromatographia, vol. 73, pp. 721-731, 2011
• [8] G. Madzarov, D. Gjorgjevikj, I. Chorbev, A multi class SVM classifier utilizing binary decision tree, Informatica, vol. 33, pp. 233-241, 2009
• [9] T. Masters, Sieci neuronowe w praktyce. Programowanie w j˛ezyku C++, WNT, 1993
• [10] E. Parzen, On estimation of a probability density function and mode, Annals of mathematical statistics, vol. 33, pp. 1065-1076, 1962
• [11] T. Skov, R. Bro, Solving fundamental problems in chromatographic analysis, Analytical and Bioanalytical Chemistry, vol. 390, pp. 281-285, 2008
• [12] D.F. Specht, Probabilistic neural networks, Neural networks, vol. 3, pp. 109-118, 1990
• [13] M. Szaleniec, R. Tadeusiewicz, M. Witko, How to select an optimal neural model of chemical reactivity?, Neurocomputing, vol. 72, pp. 241-256, 2008
• [14] W. Szczepaniak, Metody instrumentalne w analizie chemicznej, Wydawnictwa naukowe PWN, 2002
• [15] R. Tadeusiewicz, Sieci neuronowe, Akademicka Oficyna Wydawnicza, 1993
• [16] R. Tadeusiewicz, Using Neural Networks for Simplified Discovery of Some Psychological Phenomena, Chapter in book: Rutkowski L. (et al., eds.): Artificial Intelligence and Soft Computing, LNAI 6114, Springer-Verlag, Berlin - Heidelberg - New York, pp. 104-123, 2010
• [17] C.S. Teng, K.C. Cheng, Mass spectral search using the neural network approach., Neural Networks, vol. 6, pp. 3962-3967, 1999
• [18] Uniwersytet Gda´nski, Wydział Chemii: Chromatografia gazowa, http://www.chem.univ.gda.pl/zas/dydaktyka/slady_gc.pdf,online;dost˛ep25.12.2012
• [19] Z. Witkiewicz, Podstawy chromatografii, WNT, Warszawa, 2000