Application of neural network and genetic algorithms in computer aided gastric diagnostic system

• Autorzy: Świerczyński Z. , Zagańczyk A.
• Języki publikacji: EN

Abstrakty

EN

In the paper, computer aided stomach diagnosis problems are presented. The subject of the study is electrical signal generated by human stomach, called the electrogastrographic (EGG) signal. The non-invasively measured signals were subjected to parametrization and then neural network based classification. The parametrization was performed with one of the time series modelling methods, with linear autoregressive models (AR). A special feature of the presented methodology of classification is its hybrid approach. The idea of this specific combination is that a genetic algorithm is used as the evolutionary method of training of the neural network. The structure and parameters of the system (NEUROGEN v.02), used for classification of the parameterized EGG data, are described. The finally obtained effectiveness of the whole system (NEUROGEN v.02 with the parametrization method applied), amounting to 74%, is quite high and according to the authors' analysis, can be improved. A way of improvement of the effectiveness are also outlined in the summary.

Słowa kluczowe

EN

neural networks; genetic algorithm; electrogastrographic signals; gastric electrical activity; parametrization

PL

sieć neuronowa; algorytm genetyczny; sygnał elektrogastrograficzny

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2005
• Tom: Vol. 25, no. 1
• Strony: 49--58
• Opis fizyczny: Bibliogr. 15 poz., rys.

Twórcy

autor

Świerczyński Z.

• Chair of Electronic and Photonic Metrology, Faculty of Electronics, Wrocław University of Technology, ul. B. Prusa 53/55, 50-371 Wrocław, Poland

autor

Zagańczyk A.

• Faculty Division of Computer Systems and Networks, Faculty of Electronic, Wrocław University of Technology, Wrocław, Poland

Bibliografia

• [1] Chen J., McCallum R. W.: Electrogastrography: measurement, analysis and prospective applications, Med. Biol. Eng. & Comput., 1991, 29, 339-350.
• [2] Mintchev M. P., Kingma Y. J., Bowes K. L.: Accuracy of cutaneous recordings of gastric electrical activity, Gastroenterology, 1993, 104, 1273-1280.
• [3] Świerczynski Z. et al.: Akwizycja i analiza sygnałów elektrogastrograficznych, Acta Bio-Optica et Informatica Medica, 1, 1997, 3, 45-50.
• [4] Swierczynski Z.: Parametryzacja sygnałów biomedycznych generowanych przez żołądek człowieka, PhD Thesis, Institute of Telecommunication and Acoustics, Faculty of Electronics, Wrocław University of Technology, Wrocław 2002.
• [5] Box G. E. P., Jenkins G. M.: Analiza szeregów czasowych. Prognozowanie i sterowanie, PWN, Warszawa 1983.
• [6] Kay S. M.: Modern Spectral Estimation: Theory and Application, Engelwood Cliffs, Prentice Hall, New Jersey 1988.
• [7] Muciek A., Swierczynski Z.: Parametric models of biomedical signals, Proc. Third Int. Symposium on Methods and Models in Automation and Robotics, 1996, 2, 683-687.
• [8] Zaganczyk A.: Evolutionary algorithms and neural networks applied to the computer-aided medical diagnosis, Journal of Medical Informatics and Technologies, 2002, 4, SN-21-24.
• [9] Osowski S.: Sieci neuronowe w ujeciu algorytmicznym, WNT, Warszawa 1996.
• [10] Żurada J., Barski M., Jędruch W.: Sztuczne sieci neuronowe. Podstawy teorii i zastosowania, PWN, Warszawa 1996.
• [11] Hertz J., Krogh A., Palmer R.: Wstęp to teorii obliczeń neuronowych, WNT, Warszawa 1995.
• [12] Rutkowska D., Piliński M., Rutkowski L.: Sieci neuronowe, algorytmy genetyczne i systemy rozmyte, PWN, Łódź 1999.
• [13] KwaśnickaH.: Obliczenia ewolucyjne w sztucznej inteligencji, Oficyna Wydawnicza PWr, Wrocław 1999.
• [14] Masters T.: Sieci neuronowe w praktyce, WNT, Warszawa 1996.
• [15] Zaganczyk A.: A neuro-genetic approach to system modelling, Computer Recognition Systems, Oficyna Wydawnicza Politechniki Wrocławskiej, Wrocław 2003, 451-456.