Microsleep Detection in Electrophysiological Signals

Martin Golz, David Sommer, Danilo Mandic

2005

Abstract

An adaptive biosignal analysis system for the detection of microsleep events is presented. The system was applied to the electroencephalogram and electrooculogram recorded of 23 young volunteers while performing monotonic overnight driving in our real car driving simulation laboratory. Biosignals during clear observable microsleep and non-microsleep events were processed and classified. Besides the commonly applied Periodogram method to estimate power spectral densities we utilized the recently established method of Delay Vector Variance. The obtained feature set was used as input vectors of populations of Learning Vector Quantization networks which were evolved by Genetic Algorithms. The results were compared with results from best performing Support Vector Machines. Fusion of all recorded signals and of both types of features led to empirical test errors down to 11.2 %. It is shown that the proposed methodology is able to detect, but not to predict immediately oncoming events.

References

  1. Polychronopoulos, A., Amditis, A., Bekiaris, E.: Information data flow in AWAKE multisensor driver monitoring system, Proc. IEEE Intell. Vehicles Symp. (2004), 902-906
  2. Hagenmeyer, L., Bekiaris, E., Widlroither, H.: Guidelines for the development of HCIelements for drowsy operators in transportation and process control; Proc. UAHCI 2005, Las Vegas, Nevada, USA (2005)
  3. De Waard, D.: The measurement of drivers' mental workload. PhD thesis, University of Groningen, Traffic Research Centre, The Netherlands. ISBN 90-6807-308-7 (1996)
  4. Devroye, L., Gyorfi, L. & Lugosi, G.: A probabilistic theory of pattern recognition; Springer, New York (1996)
  5. Gautama, T., Van Hulle, M.M., Mandic, D.P.: On the characterization of deterministic / stochastic and linear / nonlinear nature of time series, Technical Report (2004)
  6. Gautama, T., Mandic, D.P., Van Hulle, M.M.: A Novel Method for Determining the Nature of Time Series. IEEE Trans. Biomedical Engineering, 51(5), (2004) 728-736
  7. Heitmann, A. et al.: Technologies for the monitoring and prevention of driver fatigue. Proc. First Int Driving Symp Human Factors in Driver Assessment, Training and Vehicle Design. Aspen CO, Iowa City, IA: University of Iowa (2001) 81-86
  8. Sagberg, F., Jackson, P., Krüger, H-P., Muzet, A., Williams, A.J.: Fatigue, sleepiness and reduced alertness as risk factors in driving, Project Report, Transport RTD (2004)
  9. Sommer, D., Hink, T., Golz, M.: Application of Learning Vector Quantization to detect drivers dozing-off, European Symposium on Intelligent Technologies, Hybrid Systems and their implementation on Smart Adaptive Systems (2002) 119-123 10.Galley, N., Andrés, G., Reitter, C.: "Driver Fatigue as Identified by Saccadic and Blink Indicators" in A. Gale (eds.); "Vision in Vehicles - VII"; Amsterdam: Elsevier (1999) 49- 59
  10. Jung, T.-P. et al.: Estimating alertness from the EEG Power Spectrum. IEEE Transactions on Biomedical Engineering 44 (1997) 60-69
  11. Golz, M. et al.: Application of vector-based neural networks for the recognition of beginning Microsleep episodes with an eyetracking system. In: Kuncheva, L. I. (ed.) Computational Intelligence: Methods & Applications (2001) 130-134
  12. Joachims, T.: Learning to Classify Text Using Support Vector Machines. Kluwer, Boston (2002)
  13. Kohonen, T.: Self-Organizing Maps (third edition). Springer, New York (2001)
Download


Paper Citation


in Harvard Style

Golz M., Sommer D. and Mandic D. (2005). Microsleep Detection in Electrophysiological Signals . In Proceedings of the 1st International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2005) ISBN 972-8865-35-X, pages 102-109. DOI: 10.5220/0001195701020109


in Bibtex Style

@conference{bpc05,
author={Martin Golz and David Sommer and Danilo Mandic},
title={Microsleep Detection in Electrophysiological Signals},
booktitle={Proceedings of the 1st International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2005)},
year={2005},
pages={102-109},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001195701020109},
isbn={972-8865-35-X},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2005)
TI - Microsleep Detection in Electrophysiological Signals
SN - 972-8865-35-X
AU - Golz M.
AU - Sommer D.
AU - Mandic D.
PY - 2005
SP - 102
EP - 109
DO - 10.5220/0001195701020109