![](bg8.png)
If the methods were to be used in real-life appli-
cations, they need to be used in real-time. Therefore,
the methods would have to be adapted. It would for
example be possible to calculate the features in a slid-
ing window, hereby giving a continuous prediction.
The thresholds for eye blink detection, which are now
defined manually, can be fixed during a test drive. To
increase the practical usability, the number of elec-
trodes should be decreased, since it is virtually impos-
sible to equip drivers with a full EEG cap. Finally, to
reduce the computational load, it can be researched if
the method gives good results when only calculating
one or two features, instead of calculating 32 features
and selecting one of them.
REFERENCES
A.A.A. Foundation (2010). Asleep at the wheel: The preva-
lence and impact of drowsy driving.
Abdi, H. and Williams, L. (2010). Principal component
analysis. Wiley Interdisciplinary Review: computa-
tional statistics, (2):433–459.
Borga, M. and Knutsson, H. (2001). A canonical ap-
proach to Blind Source Separation. Report LiU-
IMT-EX-0062 Department of Biomedical Engineer-
ing, Linkping University.
Borghini, G., Astolfi, L., Vecchiato, G., Mattia, D., and Ba-
biloni, F. (2012). Measuring neurphysiological signals
in aircraft pilots and car drivers for the assessment
of mental workload, fatigue and drowsiness. Neuro-
science and Biobehavioral Reviews, pages 45–57.
De Clercq, W., Vergult, A., Vanrumste, B., Van Paesschen,
W., and Van Huffel, S. (2006). Canonical Correla-
tion Analysis Applied to Remove Muscle Artifacts
From the Electroencephalogram. IEEE transactions
on Biomedical Engineering, 53(12):2583–2587.
Fenton, N. and Neil, M. (2012). Correlation coefficient and
p-values: what they are and why you need to be wary
of them. In Risk assessment and Decision Analysis
with Bayesian Networks. CRC Press.
Geetha, G. and Geethalakshmi, S. (2011). Scrutinizing dif-
ferent techniques for artifact removal from EEG sig-
nals. International Journal of Engineering Science
and Technology, (1).
Hargutt, V. and Kruger, H. (2001). Eyelid movements and
their predictive value for fatigue stages. In Interna-
tional Conference on Traffic and Transport Psychol-
ogy.
Homan, R. W., Herman, J., and Purdy, P. (1987). Cere-
bral location of international 10–20 system electrode
placement. Electroencephalography and clinical neu-
rophysiology, 66(4):376–382.
Hu, S. and Zheng, G. (2009). Driver drowsiness detection
with eyelid related parameters by support vector ma-
chine. Expert Systems with Applications, 36(4):7651–
7658.
Kaida, K., Takahasi, M., Akerstedt, T., Nakata, A., Otsuka,
Y., Haratani, T., and Fukasawa, K. (2006). Valida-
tion of the Karolinska sleepiness scale against perfor-
mance and EEG variables. Clinical Neurophysiology,
7(117):1574–1581.
Krishnaveni, V., Jayaraman, S., Aravind, S., Hariharasud-
han, V., and Ramadoss, K. (2006). Automatic Iden-
tification and Removal of Ocular Artifacts from EEG
using Wavelet Transform. Measurement science re-
view, 6(2):45–57.
Picot, A., Charbonnier, S., and Caplier, A. (2011). EOG-
based drowsiness detection: Comparison between
a fuzzy system and two supervised learning classi-
fiers. Preprints of the 18th IFAC World Congress,
18:14283–14288.
Reyner, L. and Horne, J. (1998). Falling asleep whilst driv-
ing: are drivers aware of prior sleepiness? Int J Legal
Med, 3(111):120–123.
Rosenfield, M. (2011). Computer vision syndrome: a re-
view of ocular causes and potential treatments. Oph-
thalmic and Physiological Optics, 31(5):502–515.
Salwani, M. and Jasmy, Y. (2005). Comparison of few
wavelets to filter ocular artifacts in eeg using lifting
wavelet transform. In TENCON 2005 2005 IEEE Re-
gion 10, pages 1–6. IEEE.
Simon, M., Schmidt, E. A., Kincses, W. E., Fritzsche, M.,
Bruns, A., Aufmuth, C., Bogdan, M., Rosenstiel, W.,
and Schrauf, M. (2011). Eeg alpha spindle measures
as indicators of driver fatigue under real traffic condi-
tions. Clinical Neurophysiology, 122(6):1168–1178.
Svensson, U. (2004). Blink behaviour based drowsiness de-
tecion - method development and validation. Master’s
thesis, University of Link
¨
oping.
Vergult, A., De Clercq, W., Palmini, A., Vanrumste, B.,
Dupont, P., Van Huffel, S., and Van Paesschen, W.
(2007). Improving the Interpretation of Ictal Scalp
EEG: BSS-CCA algorithm for muscle artifact re-
moval. Epilepsia, 48(5):950–958.
Verwey, W. B. and Zaidel, D. M. (2000). Predicting drowsi-
ness accidents from personal attributes, eye blinks and
ongoing driving behaviour. Personality and Individual
Differences, 28(1):123–142.
Vuckovic, A., Radivojevic, V., Chen, A. C., and Popovic,
D. (2002). Automatic recognition of alertness and
drowsiness from eeg by an artificial neural network.
Medical Engineering & Physics, 24(5):349–360.
Yue, C. (2011). EOG signals in drowsiness research. Mas-
ter’s thesis, University of Link
¨
oping.
BIOSIGNALS2014-InternationalConferenceonBio-inspiredSystemsandSignalProcessing
212