NEW FAST TRAINING ALGORITHM SUITABLE FOR HARDWARE KOHONEN NEURAL NETWORKS DESIGNED FOR ANALYSIS OF BIOMEDICAL SIGNALS

Rafał Długosz, Marta Kolasa

2009

Abstract

A new optimized algorithm for the learning process suitable for hardware implemented Winner Takes Most Kohonen Neural Network (KNN) has been proposed in the paper. In networks of this type a neighborhood mechanism is used to improve the convergence properties of the network by decreasing the quantization error. The proposed technique bases on the observation that the quantization error does not decrease monotonically during the learning process but there are some ‘activity’ phases, in which this error decreases very fast and then the ‘stagnation’ phases, in which the error does not decrease. The stagnation phases usually are much longer than the activity phases, which in practice means that the network makes a progress in training only in short periods of the learning process. The proposed technique using a set of linear and nonlinear filters detects the activity phases and controls the neighborhood R in such a way to shorten the stagnation phases. As a result, the learning process may be 16 times faster than in the classic approach, in which the radius R decreases linearly. The intended application of the proposed solution will be in Wireless Body Sensor Networks (WBSN) in classification and analysis of the EMG and the ECG biomedical signals.

References

  1. Osowski, S., Tran Hoai Linh, “ECG beat recognition using fuzzy hybrid neural network”, IEEE Transactions on Biomedical Engineering, Vol.48, Issue 11, Nov. 2001
  2. Wismüller A., Lange O., Dersh R. D., Leinsinger G. L., Hahn K., Pütz B., and Auer D. “Cluster Analysis of Biomedical Image Time-Series”, International Journal of Computer Vision, Vol. 46, No. 2, Feb. 2002
  3. Jehan Zeb Shah, Naomie bt Salim, “A Fuzzy Kohonen SOM Implementation and Clustering of Bio-active Compound Structures for Drug Discovery”, IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology (CIBCB), 28-29 September 2006
  4. M. McInerney, A. Dhawan, Training the self-organizing feature map using hybrids of geneticand Kohonen methods Neural Networks, IEEE World Congress on Computational Intelligence, Vol.2, 27 Jun-2 Jul 1994
  5. Rajesh Ghongade, A. A. Ghatol, “Performance Analysis of Feature Extraction Schemes for Artificial Neural Network Based ECG Classification”, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA), 2007, Vol. 2
  6. T. Kohonen, Self-Organizing Maps, third edition, Springer Berlin, 2001
  7. Mokriš, R. Forgác, “Decreasing the Feature Space Dimension by Kohonen Self-Orgaizing Maps”, 2nd Slovakian - Hungarian Joint Symposium on Applied Machine Intelligence, Herlany, Slovakia 2004
  8. Dlugosz R., Talaska T., Dalecki J., Wojtyna R., “Experimental Kohonen Neural Network Implemented in CMOS 0.18µm Technology”, 15th International Conference Mixed Design of Integrated Circuits and Systems (MIXDES), Poznan, Poland, June 2008
  9. Dlugosz R., Kolasa M., “CMOS, Programmable, Asynchronous Neighborhood Mechanism For WTM Kohonen Neural Network”, 15th International Conference Mixed Design of Integrated Circuits and Systems (MIXDES), Poznan, Poland, June 2008
Download


Paper Citation


in Harvard Style

Długosz R. and Kolasa M. (2009). NEW FAST TRAINING ALGORITHM SUITABLE FOR HARDWARE KOHONEN NEURAL NETWORKS DESIGNED FOR ANALYSIS OF BIOMEDICAL SIGNALS . In Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2009) ISBN 978-989-8111- 64-7, pages 364-367. DOI: 10.5220/0001536703640367


in Bibtex Style

@conference{biodevices09,
author={Rafał Długosz and Marta Kolasa},
title={NEW FAST TRAINING ALGORITHM SUITABLE FOR HARDWARE KOHONEN NEURAL NETWORKS DESIGNED FOR ANALYSIS OF BIOMEDICAL SIGNALS},
booktitle={Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2009)},
year={2009},
pages={364-367},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001536703640367},
isbn={978-989-8111- 64-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2009)
TI - NEW FAST TRAINING ALGORITHM SUITABLE FOR HARDWARE KOHONEN NEURAL NETWORKS DESIGNED FOR ANALYSIS OF BIOMEDICAL SIGNALS
SN - 978-989-8111- 64-7
AU - Długosz R.
AU - Kolasa M.
PY - 2009
SP - 364
EP - 367
DO - 10.5220/0001536703640367