Abstract
Nowadays there exist different approaches to cancel out noise effect and baseline drift in biomedical signals. However, none of them can be considered as completely satisfactory. In this work an artificial neural network (ANN) based approach to cancel out baseline drift in electrocardiogram signals is presented. The system is based on a grown ANN allowing to optimize both the hidden layer number of nodes and the coefficient matrixes. These matrixes are optimized following the simultaneous perturbation algorithm, offering much lower computational cost that the traditional back propagation algorithm. The proposed methodology has been compared with traditional baseline reduction methods (FIR, Wavelet-based and Adaptive LMS filtering) making use of cross correlation, signal to interference ratio and signal to noise ratio indexes. Obtained results show that the ANN-based approach performs better, with respect to baseline drift reduction and signal distortion at filter output, than traditional methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Sörnmo L, Laguna P (2005) Bioelectrical Signal Processing in Cardiac an Neuro-logical Applications. Elsevier Academic Press.
Zheng Xiaoyun Wang Zhigang WN, Lan X (1997) Restraining respiratory baseline drift of impedance cardiogram signals using wavelet transform. Journal of Chongquing University Natural science edition 20(5):58-62
Lian Y, HO P (2004) ECG noise reduction using multiplier-free FIR digital filters. Proceedings of 2004 International Conference on Signal Processing 2198-2201
Sörnmo L. (1991) Time-varying filtering for removal of baseline wander in exercise ECGs. Computers in Cardiology 145-148
Laguna P.,J ane R. and Caminal P.(1992) Adaptive filtering of ECG baseline wander. Engineering in Medicine and Biology Society Proceedings of de Annual International Conference of the IEEE 508-509
Chiu CC, Yeh SJ (1997) A tentative approach based on wiener filter for the reduction of respiratory effect in pulse signals. Proc. 19th Int Conf IEEEEMBS 1394-1397
Lisheng Xu DZ, Wang K (2005) Wavelet-based cascaded adaptive filter for removing baseline drift in pulse waveforms. IEEE Trans Biomed Eng 53(11):1973-1975
Nibhanupudi S. Signal Denoising Using Wavelets. Ph.D. thesis, University of Cincinnati, 2003
Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE (2000) PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 101(23):e215-e220
Haykin S (1994) Neural Networks: A Comprehensive Approach. IEEE Computer Society Press. Piscataway, USA
Lehtokangas M(1999) Fast Initialization for Cascade-Correlation Learning. IEEE Trans. on Neural Networks 10(2):410–414
Sanchez G. K. Toscazo, M. Nakano and H. Perez (2001) A growing cell neural network structure with back propagation learning algorithm. Telecommunications and Radio Engineering 56(1):37–45
Hodge V (2001) Hierarchical Growing Cell Structures, Trees GCS. IEEE Trans. on Knowledge and Engineering 13(2):207–218
Schetinin V (2003) A Learning Algorithm for Evolving Cascade Neural Networks. Neural Letters 17(1):21–3
Maeda Y. and R.J.P. De Figueiredo (1997) Learning Rules for Neuro-controller via Simultaneous Perturbation, IEEE Trans. on Neural Networks 8(6):1119–1130
Spall J.C., A Stochastic Approximation Technique for Generating Maximum Likelihood Parameter Estimates, Proc. of The American Control Conference 1987, 1161–1167
Spall J.C., y J.A. Criston (1994) Nonlinear Adaptive Control Using Neural Networks: Estimation with a Smoothed Form of Simultaneous Perturbation Gradient Approximation. Statistical Sinica 4:1–27
Kathivalavakumar I. y P. Thangavel (2003) A New Learning Algorithm Using Simultaneous Perturbation with Weight Initialization. Neural Letters 17(1):55–68
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mateo Sotos, J., Sanchez, C., Mateo, J., Alcaraz, R., Vaya, C., Rieta, J. (2007). Neural Networks Based Approach to remove Baseline drift in Biomedical Signals. In: Jarm, T., Kramar, P., Zupanic, A. (eds) 11th Mediterranean Conference on Medical and Biomedical Engineering and Computing 2007. IFMBE Proceedings, vol 16. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73044-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-73044-6_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73043-9
Online ISBN: 978-3-540-73044-6
eBook Packages: EngineeringEngineering (R0)