DATA REDUCTION OR DATA FUSION IN BISOGINAL PROCESSING?

Martin Golz, David Sommer, Udo Trustschel

Abstract

When subjects are monitored over long time spans and when several biosignals are derived a large amount of data has to be processed. In consequence, the number of features which has to be extracted is mostly very restricted in order to avoid the so-called “curse of high dimensionality”. Donoho (Donoho, 2000) stated that this applies only if algorithms perform local in order to search systematically for general discriminant functions in a high-dimensional space. If they take into account a concept for regularization between locality and globality “blessings of high dimensionality” are to be expected. The aim of the present study is to examine this on a particular real world data set. Different biosignals were recorded during simulated overnight driving in order to detect driver’s microsleep events (MSE). It is investigated if data fusion of different signals reduces dete¬ction errors or if data reduction is beneficial. This was realized for nine electroencephalography, two electro¬oculography, and for six eyetracking signals. Features were extracted of all signals and were processed dur¬ing a training process by computational intelligence methods in order to find a discriminant function which separates MSE and Non-MSE. The true detection error of MSE was estimated based on cross-validation. Results indicate that fusion of all signals and all features is most beneficial. Feature reduction was of limited success and was slightly beneficial if Power Spectral Densities were averaged in many narrow spectral bands. In conclusion, the processing of several biosignals and the fusion of many features by computational intelligence methods has the potential to establish a reference standard (gold standard) for the detection of extreme fatigue and of dangerous microsleep events which is needed for upcoming Fatigue Monitoring Technologies.

References

  1. Donoho, D. (2000). High-Dimensional Data Analysis: The curses and blessing of dimensionality. Ann Conf Amer Math Soc, Los Angeles. (http://www-stat.stanford.edu/donoho/Lectures)
  2. Schleicher, R., N. Galley, S. Briest, L. Galley (2007). Blinks and Saccades as Indicators of Fatigue in Sleepiness Warnings: Looking Tired? Ergonomics, vol. 51, pp. 982-1010.
  3. Summala, H., H. Häkkänen, T. Mikkola, J. Sinkkonen (1999). Task effects on Fatigue Symptoms in Overnight Driving. Ergonomics, vol. 42, pp. 798-806.
  4. Ingre, M., T. Akerstedt, B. Peters, A. Anund, G. Kecklund (2006). Subjective Sleepiness, Simulated Driving Performance and Blink Duration. J Sleep Research, vol. 15, pp. 47-53.
  5. Santamaria, J., K.H. Chiappa (1987). The EEG of Drowsiness in Normal Adults, J Clin Neurophysiol, vol. 4, pp. 327-382.
  6. Maulsby, R.L. et al (1968). The Normative Electroencephalographic Data Reference Library, Final Report, Contract NASA 9-1200, National Aeronautics and Space Administration.
  7. Akerstedt, T., G. Kecklund, A. Knutsson (1991). Manifest Sleepiness and the Spectral Content of the EEG During Shift Work, Sleep, vol. 14, pp. 221-225.
  8. Makeig, S., T. P. Jung (1995). Changes in Alertness are a Principal Component of Variance in the EEG Spectrum, Neuroreport, vol. 7, pp. 213-216.
  9. Makeig, S., T.P. Jung, T. Sejnowski (2000). Awareness During Drowsiness: Dynamics and Electrophysiological Correlates, Can J Exp Psychol, vol. 54, pp. 266-273.
  10. Lal, S., A. Craig (2002). Driver Fatigue: Electroencephalography and Psychological Assessment, Psychophysiology, vol. 39, pp. 313-321.
  11. Wilhelm, B. et al (2001). Daytime Variations in Central Nervous System Activation Measured by a Pupillographic Sleepiness Test, J Sleep Res, vol.10, pp.1-7.
  12. Sommer, D., M. Golz, J. Krajewski (2008). Consecutive Detection of Extreme Central Fatigue. Proc 4th Europ Congr Med & Biomed Engineering (EMBEC-2008), to appear.
  13. Golz, M., D. Sommer, M. Chen, U. Trutschel, D. Mandic (2007). Feature Fusion for the Detection of Microsleep Events. J VLSI Signal Proc Syst, vol. 49, pp. 329-342, 2007.
  14. Sommer, D., M. Golz (2007). Feature Reduction for Microsleep Detection. In IWK'07, 52nd Int. Sci. Koll., Technical Univ. of Ilmenau, Germany, Vol I, 77-82.
Download


Paper Citation


in Harvard Style

Golz M., Sommer D. and Trustschel U. (2009). DATA REDUCTION OR DATA FUSION IN BISOGINAL PROCESSING? . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009) ISBN 978-989-8111-65-4, pages 440-445. DOI: 10.5220/0001782604400445


in Bibtex Style

@conference{biosignals09,
author={Martin Golz and David Sommer and Udo Trustschel},
title={DATA REDUCTION OR DATA FUSION IN BISOGINAL PROCESSING?},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009)},
year={2009},
pages={440-445},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001782604400445},
isbn={978-989-8111-65-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009)
TI - DATA REDUCTION OR DATA FUSION IN BISOGINAL PROCESSING?
SN - 978-989-8111-65-4
AU - Golz M.
AU - Sommer D.
AU - Trustschel U.
PY - 2009
SP - 440
EP - 445
DO - 10.5220/0001782604400445