Classification of EGG Signals Combining Neural Networks and Independent Component Analysis

• Hallan Santos UFS
• Carlos A. E. Montesco UFS
• Methanias C. Júnior UFS

Abstract

Identify digestive traits of people through Electrogastrography (EGG) is important because it is usually an economic, non-invasive and less bother than the traditional Endoscopy procedure. This research evaluates the behavior of artificial neural networks learning on the components extracted by Independent Component Analysis (ICA) algorithms. An experiment with statistical analysis whose goal was to present the relationship between the viewing of neutral, negative or positive images and digestive reactions was performed. The results showed that extract only the stomach signal component may reduce the error rate of learning of the neural network compared with experiment.

References

Basili, V., Gianluig, C., Rombach, H. D. (1994).The Goal Question Metric Approach.

Basili, V. R., Selby, R.W., Hutchens, D. H. (1986). Experimentation in software engineering, IEEE Transactions in Software Engineering 12 (7) 733-743.

Corder, G. W., Foreman, D. I. (2009). Nonparametric Statistics for Non-Statisticians: A Step-by-Step Approach.

Comm, P. (1994). Independent component analysis—A new concept? Signal Processing. Vol. 36, pp. 287-314.

Fausset, L. (1994). Fundamentals of neural network: architectures, algorithms and applications, Prentice Hall.

Gopu, H., Neelaveni, R., Porkumara, K. (2009) Analysis of EGG Signals for Digestive System Disorders Using Neural Networks.

Haykin, S. (1999) Neural Networks A Comprehensive Foundation, Second Edition, Pearson Prentice Hall.

Hubka, P., Rosik, V., Zidnak, J., Tysler, M., Hulin, I. (2005) Independent Component Analysis of Electrogastrographic Signals. Measurement Science Review, Volume 5.

Hyvärinen, A. (1999). Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural Networks, Vol10, pp.626-634.

Hyvärinen, A., Karhunen,J., Oja, E. (2001). Independent Component Analysis, Wiley Interscience Publication.

Hyvärinen, A. (1997). A Fast Fixed-Point Algorithm for Independent Component Analysis, Neural Computation.

Komorowski, D., Pietraszek. S. (2009); Preprocessing for Spectral Analysis of Electrogastrogram. WC 2009, IFMBE Proceedings 25/IV.

Kovacs, Z. l. (1996). Redes neurais artificiais: fundamentos e aplicações, um texto básico, Editora Livraria da Física.

Shorack, G. R., Wellner, J. A. (1986). Empirical Processes with Applications to Statistics. Wiley. p. 239.

Todd, M.J. (1976). The computation of fixed points and applications. Springer, Berlin.

Wang, Z., Chen, Z. (1997) Blind EGG Separation Using ICA Neural Networks. 19th International Conference IEEE/EMBS.

Wu, X., Lu, J., Chen, K., Long, Z., Wang, X., Shu, H., Li, K., Liu, Y., Yao, L. (2009) Multiple neural networks supporting a semantic task.

Yu, S., Chou, K. (2006) Combining Independent Component Analysis and Backpropagation Neural Network for ECG Beat Classification. Proceedings of the 28th IEEE EMBS Annual International Conference.