A RECONFIGURABLE ARRAY FOR BLIND SOURCE-SEPARATION ON AN FPGA

Ricardo Escalona, Daniel Herrera, Miguel Figueroa

Abstract

We present a reconfigurable array which performs blind source separation on a range of field-programmable gate array (FPGA) devices. Our array uses independent component analysis (ICA) with the InfoMax algorithm to separate a mixture of signals without an external reference. We describe two configurations of the array, representing distinct points in the design space. Our experimental results show a performance improvement of more than one order of magnitude over an optimized software implementation of the algorithm on a computer, with a power consumption of just 100mW. Our array successfully separates a fetal electrocardiogram (ECG) mixture into the source signals of mother and fetus, enabling medical analysis on the resulting independent components.

References

  1. Anguita, D., Boni, A., and Ridella, S. (2003). A digital architecture for support vector machines: Theory, algorithm, and FPGA implementation. IEEE Transactions on Neural Networks, 14:993-1009.
  2. Bell, A. J. and Sejnowski, T. J. (1997). The 'Independent Components' of Natural Scenes are Edge Filters. Vision Research, 37(23):3327-3338.
  3. Cardoso, J. F. (1997). Infomax and maximum likelihood for blind source separation. IEEE Signal Processing, 4:112-114.
  4. Li, Z. and Lin, Q. (2005). FPGA implementation of Infomax BSS algorithm with fixed-point number representation. Neural Networks and Brain, 2:889-892.
  5. Potter, M., Gadhok, N., and Kinsner, W. (2002). Separation performance of ICA on simulated EEG and ECG signals contaminated by noise. IEEE Canadian Conference on Electrical & Computer Engineering, 2:1099- 1104.
  6. Yang, Y., Huang, X., and Yu, X. (2007). Real-time ECG monitoring system based on FPGA. 33rd Annual Conference of IEE Industrial Electronics Society, pages 2136-2140.
  7. Zeng, Y., Liu, S., and Zhang, J. (2008). Extraction of fetal ECG signal via adaptive noise cancellation approach. The 2nd International Conference on Bioinformatics and Biomedical Engineering, pages 2270-2273.
Download


Paper Citation


in Harvard Style

Escalona R., Herrera D. and Figueroa M. (2009). A RECONFIGURABLE ARRAY FOR BLIND SOURCE-SEPARATION ON AN FPGA . In Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2009) ISBN 978-989-8111- 64-7, pages 262-267. DOI: 10.5220/0001551902620267


in Bibtex Style

@conference{biodevices09,
author={Ricardo Escalona and Daniel Herrera and Miguel Figueroa},
title={A RECONFIGURABLE ARRAY FOR BLIND SOURCE-SEPARATION ON AN FPGA},
booktitle={Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2009)},
year={2009},
pages={262-267},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001551902620267},
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 - A RECONFIGURABLE ARRAY FOR BLIND SOURCE-SEPARATION ON AN FPGA
SN - 978-989-8111- 64-7
AU - Escalona R.
AU - Herrera D.
AU - Figueroa M.
PY - 2009
SP - 262
EP - 267
DO - 10.5220/0001551902620267