Abstract
Electrogastrogram (EGG) is a noninvasive measurement of gastric myoelectrical activity cutaneously, which is usually covered by strong artifacts. In this paper, the independent component analysis (ICA) with references was applied to separate the gastric signal from noises. The nonlinear uncorrelatedness between the desired component and references was introduced as a constraint. The results show that the proposed method can extract the desired component corresponding to gastric slow waves directly, avoiding the ordering indeterminacy in ICA. Furthermore, the perturbations in EGG can be suppressed effectively. In summary, it can be a useful method for EGG analysis in research and clinical practice.
Similar content being viewed by others
References
Chen J, McCallum RW (1993) Clinical applications of electrogastrography. Am J Gastroenterol 88:1324–1336
Chen J, McCallum RW (1994) Electrogastrography: principles and applications. Raven Press, New York
Chen J, McCallum RW (1991) Electrogastrography: measurement, analysis and prospective applications. Med Biol Eng Comput 29:339–350
Liang J, Cheung JY, Chen JD (1997) Detection and deletion of motion artifacts in electrogastrogram using feature analysis and neural networks. Ann Biomed Eng 25:850–857
Chen J, Vandewalle J, Sansen W, Vantrappen G, Janssens J (1989) Adaptive Method for Cancellation of Respiration Artifact in Electrogastric Measurements. Med Biol Eng Comput 27:57–63
Liang H, Lin Z, McCallum RW (2000) Artifact reduction in electrogastrogram based on the empirical mode decomposition method 3. Med Biol Eng Comput 8:35–41
Wang ZS, Cheung JY, Chen JD (1999) Blind separation of multichannel electrogastrograms using independent component analysis based on a neural network. Med Biol Eng Comput 37:80–86
Liang H (2001) Adaptive independent component analysis of multichannel electrogastrograms. Med Eng Phys 23:91–97
Irimia A, Bradshaw LA (2005) Artifact reduction in magnetogastrography using fast independent component analysis. Physiol Meas 26:1059–1073
Liang H (2005) Extraction of gastric slow waves from electrogastrograms: combining independent component analysis and adaptive signal enhancement. Med Biol Eng Comput 43:245–251
Hyvärinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, New York
Delfosse N, Loubaton P (1995) Adaptive blind separation of independent sources: a deflation approach. Signal Process 45:59–83
Hyvärinen A, Oja E (1997) A fast fixed-point algorithm for independent component analysis. Neural Comput 9:1483–1492
Hyvärinen A (1999) Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans Neural Netw 10:626–634
Bell AJ, Sejnowski TJ (1995) An iinformation-maximization approach to blind separation and blind deconvolution. Neural Comput 7:1129–1159
Comon P(1994) Independent component analysis—a new concept? Signal Process 36:287–314
He Z, Yang L, Liu J, Lu Z, He C, Shi Y (2000) Blind source separation using clustering based multivariate density estimation algorithm. IEEE Trans Signal Process 48:575–579
Lu W, Rajapakse JC (2000) Constrained independent component analysis. In: Advances in neural information processing systems, vol 13. MIT Press, Cambridge, pp 570–576
Lu W, Rajapakse JC (2003) Eliminate indeterminacy in ICA. Neurocomputing 50:271–290
Lu W, Rajapakse JC (2005) Approach and applications of constrained ICA. IEEE Trans Neural Netw 16:203–212
James CJ, Gibson OJ (2003) Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis. IEEE Trans Bio-med Eng 50:1108–1116
Lin Q, Zheng Y, Yin F, Liang H (2004) Speech segregation using constrained ICA. Lect Notes Comput Sci 3173:755–760
Hesse CW, James CJ (2005) The fast ICA algorithm with spatial constraints. IEEE Signal Proc Lett 12:792–795
Jutten C (2000) Source separation: from dusk till dawn. In: Proceedings of the 2nd international workshop on independent component analysis and blind source separation, Helsinki, Finland, pp 15–26
Ham FM, Kostanic I (2001) Principles of neurocomputing for science & engineering. McGraw-Hill, New York
Peng C, Ye DT (2005) Cutaneous electrical stimulation of mid-frequency on acupiont affects the electrogastrogram. In: Proceedings of the 27th annual conference on IEEE-EMBS, pp 4933–4935
Acknowledgements
The authors would like to thank Prof. Z. C. Wu and his colleagues in Acupuncture Institute of China Academy of Traditional Chinese Medicine for their assistance in acquiring the EGG data used in this paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Peng, C., Qian, X. & Ye, D. Electrogastrogram extraction using independent component analysis with references. Neural Comput & Applic 16, 581–587 (2007). https://doi.org/10.1007/s00521-007-0100-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-007-0100-3