Conference PaperPDF Available

Microsleep Episodes and Related Crashes During Overnight Driving Simulations

University of Iowa
Iowa Research Online
5-9-2+66)661)2732*)5)2') 5-9-2+66)661)2732*)5)2')
Microsleep Episodes and Related Crashes During
Overnight Driving Simulations
Martin Golz
University of Applied Sciences, Schmalkalden, Germany
David Sommer
University of Applied Sciences, Schmalkalden, Germany
Jarek Krajewski
University of Wuppertal, Wuppertal, Germany
Udo Trutschel
Circadian Technologies, Inc., Stoneham, MA
Dave Edwards
Caterpillar, Inc., Peoria, IL
3003:7,-6%2(%((-7-32%0:35/6%7 ,@4-58-3:%)(8(5-9-2+%66)661)27
?-69)27-6&538+,773<38*35*5))%2(34)2%'')66&<7,)8&0-'30-'<)27)5%73:% )6)%5',20-2)7,%6&))2%'')47)(*35-2'086-32-25-9-2+
66)661)2732*)5)2')&<%2%87,35-=)(%(1-2-675%7353*3:% )6)%5',20-2)35135)-2*351%7-3240)%6)'327%'7 0-&-58-3:%)(8
30=%57-2!311)5%9-(5%.):6/-%5)/"5876',)0#(3%2((:%5(6%9)-'5360))44-63()6%2( )0%7)(5%6,)6
)27)5#2-9)56-7<3*3:% ,@46(3-35+(5-9-2+%66)661)27
PROCEEDINGS of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
Martin Golz1,5, David Sommer1, Jarek Krajewski2, Udo Trutschel3,5, & Dave Edwards4
1 Faculty of Computer Science, University of Applied Sciences Schmalkalden, Germany
2 Work and Organizational Psychology, University of Wuppertal, Germany
3 Circadian Technologies, Inc., Stoneham, Massachusetts, USA
4 Machine Research, Caterpillar, Inc., Peoria, Illinois, USA
5 Institute for System Analysis and Applied Numerics, Tabarz, Germany
Summary: Microsleep (MS) episodes and related crashes were studied in an
overnight driving simulation study. A new definition of MS proposed recently
was applied and the mean number as well as the mean length of MS was calculat-
ed. MS occurred much more frequently than crashes. Within all pre-crash inter-
vals (length 1 minute) the percentage of MS was calculated. Results showed that
there are numerous MS episodes before every crash. The mean length of MS was
between 5 and 9 seconds and did not change significantly during the night. The
mean MS percentage was high within pre-crash intervals (60-80%) and is a pre-
dictor for crashes.
Two important consequences of sleepiness during driving simulations are microsleep (MS) and
crashes. The rate of both events increases if sleepiness as well as monotony is increasing. To
keep monotony on a high level, the simulated traffic complexity should be low, no kind of
communication should be allowed and a non-animating environment should be presented.
Overnight driving in the fully dark lab with sparsely illuminated driving scenes fulfills this
condition. In order to increase sleepiness, the time since sleep and the time on driving task
should be long. In addition, the time of day should be selected such that the driver passes the
circadian trough. The latter factor is very important for drivers having high circadian amplitudes,
such as young drivers.
Unfortunately, the combination of all conditions is sometimes fulfilled on the real road (e.g.
overnight highway driving after an active day and evening). The combination is also important
for studies in the lab in order to get enough examples to drive statistical investigations. In this
paper we present statistical results on MS events and crashes and ask how they are related in
time. How many MS events occur in the average immediately before a crash happened? How
many crashes occur without any MS events beforehand? How is their temporal development
across the night? And how is the inter-individual variation?
The definition of MS comprises a problem. On the one hand several authors have defined MS
strictly by EEG criteria no matter what behavior is observed simultaneously. Then again, MS can
be defined in behavioral terms at the cost of strictness because of many different behavioral signs
with large inter-individual variations. In addition, some of them are vague to assess. Another
difficulty is that sometimes subjects display signs of oculomotoric quiescence or blank stare.
PROCEEDINGS of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
A third way which combines both types of criteria has been proposed by (Sommer, Golz,
Schnupp, Krajewski, Trutschel, Edwards, 2009). In a first step only events with clear behavioral
signs were considered, such as prolonged eyelid closures, slow roving eye movements, head
noddings, slow drifting head movements. All of them are often followed by abrupt reactions. The
occurrence of these behavioral signs led to the class label ‘MS’ for an adaptive biosignal
processing (EEG, EOG) and pattern recognition methodology. EEG/EOG segments
accompanied by behavioral signs of high sleepiness, but still active driving and fulfilling the lane
tracking were labeled as the other class (‘Non-MS’). This way, behavioral criteria and biosignal
criteria were combined by modern, automatically learning computer algorithms (Golz and
Sommer, 2008). It has been demonstrated that the MS detector gained high sensitivity as well as
high specifity to strictly defined behavioral MS. Furthermore, many events were detected in the
EEG/EOG which are similar to behavioral MS, but no strict behavioral signs of MS occurred
simultaneously (Sommer, 2009; Sommer, Golz, Schnupp, Krajewski, Trutschel, Edwards, 2009).
The detected MS events correlated strongly with independent subjective self-ratings of
sleepiness as well as objective measures of driving performance, e.g. standard deviations of
lateral position in lane. In this paper, this combined definition of EEG/EOG-based detection of
MS which are related to evident behavioral events is utilized.
Driving simulations were conducted at the driving simulation lab of the University of Applied
Sciences, Schmalkalden, Germany. The study was designed to investigate driving performance
and subjects’ behaviour under high level of monotony and sleepiness. Monotony was supported
by selecting very low traffic density (no car in lane, 1 car every 3 minutes in the opponent lane;
road configuration: winding two-lane road, undulating landscape). Subjects were instructed to
keep in lane as best as possible and to avoid falling asleep. After returning from MS events
subjects were reminded that if driving performance becomes too bad or signs of behavioral MS
returned too fast, the experiment would be terminated.
Crashes have been defined as intervals where all four wheels were out of lane, no matter if the
car went to the left or to the right. Incidents, such as 1, 2, or 3 wheels out of lane were not
regarded as crashes. When crashes appeared, an extensive soundscape, as well as video scene,
was played to increase the emotional importance of this event, to set a short break in the run of
the driving simulation and to warn the driver by the observers.
Fourteen healthy young volunteers ranging from 18-32 years of age (mean 22.4; SD 4.1) and had
held a driver’s licence for at least 1 year. 1 male and 2 female quitted driving because of
simulator sickness, 1 male quitted because of back pain.
Driving Simulations
Ten subjects (8 male, 2 female) completed all 7 overnight driving runs starting at the top of every
hour (1:00–7:00 AM). Each run had a duration of 40 minutes and was preceded and followed by
vigilance tests and response-to-sleepiness questionnaires. Reports of vigilance tests will be given
PROCEEDINGS of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
elsewhere. Time since sleep was at least 16 hours, checked by actigraphy. Subjects have been
prepared beforehand by at least one hour training on the simulator.
Several biosignals were recorded: EEG (F1, F2, C3, Cz, C4, O1, O2, A1, A2, com.av.ref.), EOG
(vertical, horizontal), ECG, EMG (m. submentalis). In addition, three video recordings (driver’s
head & pose, driver’s eyes, driving scene) were stored. Also several variables of the car (e.g.
time series of steering angle and lateral position of the vehicle) were sampled.
Subjectively experienced sleepiness was rated every 4 minutes during driving following
suggestions of (Åkerstedt et al., 2006). Subject’s response was given orally using the Karolinska
Sleepiness Scale (KSS) (Åkerstedt, 1990). Further experimental details have been published
elsewhere (Golz et al., 2007).
Visual Ratings of MS
Two operators who watched the video streams performed a first judgment of ongoing MS
immediately during the experiments. Typical signs of MS are prolonged eyelid closures, slow
roving eye movements, head noddings, slow drifting head movements, and major driving
incidents. They were often followed by abrupt reactions. Several other signs were observed, but
it has been decided not to solely rely on them. Some examples are bursts of alpha and theta
activity in the EEG, spontaneous pupil contractions and blank stare. In all, we have found 2,290
MS events (per subject: mean number 229 ± 67, range 138–363).
For the detection of MS events on a second by second basis a careful determination of the point
in time where MS is starting will be needed. Therefore, all recorded video material and
biosignals underwent off-line scoring made by an independent and trained rater. He refined and
eventually corrected the results of online ratings.
Visual ratings were only utilized to select examples of MS and Non-MS out of the continuum of
the recordings. This leads to so-called data labeling needed for supervised learning algorithms
like Support-Vector Machines (see below).
Signal Analysis
Segments of EEG/EOG during MS were processed by a multi-stage classification methodology.
Segment length should range between 4 and 12 seconds (Golz et al., 2007). We used 6s and
calculated spectral power densities by the modified periodogram method. Afterwards logarithmic
scaling and summation in narrow spectral bands (width 1 Hz) in the range 0.5 to 23 Hz turned
out to be important to reduce the error rate in the subsequent classification step. Support-Vector
Machines with Gaussian kernel function were applied to these data in order to perform
classification (i.e. to separate signal segments labeled as MS from segments labeled as Non-MS).
After a series of parameter optimizations, an accurate MS detector was constructed. The mean
accuracy of 97.7% has been estimated on evident examples of behavioral MS (Sommer et al.
2009). In a second step, the MS detector has been applied consecutively to all data (not only
PROCEEDINGS of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
evident MS and Non-MS examples) to detect further examples which are similar in the
EEG/EOG characteristics.
With increasing time since sleep the mean number of detected MS events as well as the number
of crashes increased (Figure 1). MS occurred much more frequently than crashes. In the first four
driving runs (1:00–4:00 AM) almost no crash happened. Afterwards, rapidly increasing crash
probabilities were observed. Several subjects were not longer able to perform the driving task.
From the beginning of the night, the mean number of detected MS was high and increased by
factor 3 to the end of the night.
The length of MS is a highly varying quantity, both inter- and intra-individually. Their mean
value ranged between 5 and 9 seconds and increased slightly with time since sleep (Figure 1).
Figure 1. Results of MS detection: The mean number of MS (left; squares), of crashes (left; circles),
and the mean length of MS (right) increase with time of day
(Data were averaged across subjects; the bars represent standard errors)
To answer the question if and how many MS periods occurred preceding crashes, a fixed interval
prior to each crash was analysed. The length was chosen to 60s and it was estimated how much
of the time MS was detected. The resulting quantity is called MS percentage and is 100% if
during all 60s prior to a crash MS was detected. If no MS was detected during 60s prior to a
crash, then a MS percentage of 0% resulted. Both extremes didn’t occur. Since crashes occurred
almost always in the second half of the night, where both number and length of MS were high,
the percentage of MS prior to crashes was relatively high (Figure 2). The mean values varied
between subjects in the range between 55% and 78%. The number of crashes varied highly
between subjects (Figure 2, upper line). One subject performed with less than 10 crashes whereas
other subjects had much more than 100 crashes over the whole night.
Immediately during the seconds from crashes high MS percentages occurred. Short intervals
completely free of MS constituted an exception. Their frequency rapidly decreased with interval
length (Figure 2). Only less than 2% of all crashes happened with no MS during pre-crash
intervals when interval length was greater than 5s. In the present study no crash was found
without MS during 180s long pre-crash intervals.
PROCEEDINGS of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
This pilot study demonstrated the application of a new way to assess MS episodes with high
temporal resolution. Short as well as long MS episodes were detected. The mean length of MS
was between 5 and 9 seconds and was slightly but not significantly dependent on time since
sleep. Results suggest that crashes are signalized by MS episodes, although an accurate
prediction of crashes based on MS was not possible. There were many MS episodes which were
not followed by a crash.
Figure 2. Results of crash analysis: Mean and standard deviations of MS percentage (MSP) during the 1 min
interval preceding every crash; Mean MSP ranges between 55% and 78% (left); The percentage of pre-crash
intervals containing no MS is below 10% and decreases rapidly with increasing length of the interval (right)
(Data were averaged across subjects; the bars represent standard errors)
The quantification of the EEG/EOG suspected to be MS during pre-crash intervals, which we
called MS percentage, is a new measure (Sommer, Golz, Schnupp, Krajewski, Trutschel,
Edwards, 2009). The consecutive application of an MS detection algorithm on the entire
EEG/EOG led to a binary information (MS or Non-MS) with high temporal resolution (100ms).
Averaging across intervals (length 1 min) led to this new variable. It was demonstrated that the
EEG/EOG is highly suspective to MS if analysis was done at least 5s prior to crashes.
Driving performance during MS episodes was also investigated in terms of steering variability,
variation of lateral position in lane, minimum time to lane crossing (Paul, Boyle, Tippin, Rizzo,
2005). It has been shown that there is a remarkable change compared to both intervals pre- and
post-MS (interval length 3s). The mean variation of the lateral position in lane almost doubled
during MS and the mean minimum time to lane crossing was reduced by ca. 40%. Therefore, in
their study a remarkable increase of crashes in succession to MS must be assumed.
Lower effects of MS on driving performance variables were reported recently (Boyle, Tippin,
Paul, Rizzo, 2008). They demonstrated large differences between straight and curved roadway
segments. Non-MS versus MS episodes were characterized by insignificant changes in the mean
speed (< 1%), in the steering entropy (< 3%), and in the standard deviation of the slow wave
EEG activity (+2.2% on straight roadways, +10.4% in curves). Both measures of lane tracking
performance, the standard deviation of position in lane and the minimum time to lane crossing
were sensitive to MS, but depend highly on the roadway type. The first variable increased by
+12.7% and +23.7%, and the second variable increased by +24.2% and decreased by -23.2% on
straight and curved roadway segments, respectively. Crashes were not considered.
PROCEEDINGS of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
Risser, Ware, Freeman (2000) found that MS defined as EEG episodes of increased alpha or
theta activity lasting more than 3s correlated with lane position variability and crash frequency.
Crashes occurred always in later sessions and were relatively rare events, whereas MS episodes
were significantly more frequent, which was also reported by other authors for daytime driving
simulations (Moller, Kayumov, Bulmash, Nhan, Shapiro, 2006). They investigated EEG defined
MS episodes as a consequence of daytime sleepiness in healthy normals. A much lower mean
number of MS episodes was reported ranging between 0.6 and 1.2. Three main reasons may
explain why our result was much higher (ranging between 40 and 140). Firstly, the authors’
definition of MS was completely different. EEG activity lasting 3-30s were scored if alpha, theta
activity, or true sleep EEG dominated. Our MS detector methodology oftentimes found shorter
events. Moreover, EEG with more complex patterns were classified to MS episodes, because
evident behavioral MS also occurred with such EEG characteristics (Golz, Sommer, Chen,
Trutschel, Mandic, 2007). Secondly, our study protocol provided partial sleep deprivation. Time
since sleep was between 17 and 23 hours as against 2 and 8 hours in their daytime experiments.
Thirdly, our driving sessions lasted 10 minuters longer. This is important, because time on task
effects are known to play a role on MS. Subsequent analysis showed that the mean number of
MS episodes reduces by 34.1% if driving simulations would have been reduced from 40 minutes
to 30 minutes and the number of crashes reduces by 43.0%.
Nevertheless, both, the results of (Moller, Kayumov, Bulmash, Nhan, Shapiro, 2006) as well as
the present study demonstrate that the number of MS episodes across a single driving session and
crash risk correlated highly. Future investigations should ask if the incidence of MS episodes and
their temporal evolution are useful as an indicator of upcoming crashes. Visual inspection of our
data suggested that this relation is complex and not easily recognizable. It may be that a
prediction of crashes is not possible. For now it can be stated that in sleep deprivation studies the
crash risk is highly associated with numerous MS suspected EEG/EOG immediately before.
This study was funded by the Federal Ministry of Education and Research within the research
program “Research at University of Applied Sciences together with Enterprises” under the
project 176X08.
Boyle, L.N., Tippin, J., Paul, A., & Rizzo, M. (2008). Driver Performance in the Moments
Surrounding a Microsleep. J Transport Res Part F, 11, 126-136.
Davidson, P.R., Jones, R.D., & Peiris, M.T.R. (2007). EEG-Based Lapse Detection with High
Temporal Resolution, IEEE Trans Biomed Engin, 54(5), 832-839.
Golz, M., Sommer, D., Trutschel, U., Sirois, B., & Edwards, D. (2010). Evaluation of Fatigue
Monitoring Technologies. J Somnology, 14(3), 187-189.
Golz, M., & Sommer, D. (2008). Automatic knowledge extraction: fusion of human expert
ratings and biosignal features for fatigue monitoring applications. In D. Mandic, M. Golz, A.
Kuh, D. Obradovic & Tanaka T. (Eds.) Signal processing techniques for knowledge
extraction and information fusion. New York: Springer.
PROCEEDINGS of the Sixth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
Golz, M., Sommer, D., Chen, M., Trutschel, U., & Mandic, D. (2007). Feature Fusion for the
Detection of Microsleep Events. J VLSI Signal Proc Syst, 49, 329-342.
Moller, H.J., Kayumov, L., Bulmash, E.L., Nhan, J., & Shapiro, C.M. (2006). Simulator per-
formance, microsleep episodes, and subjective sleepiness: normative data using convergent
methodologies to assess driver drowsiness. J Psychosomatic Res, 61, 335-342.
Paul, A., Boyle, L.N., Tippin, J., & Rizzo, M. (2005). Variability of Driving Performance During
Microsleeps, Proc 3rd Int Symp Driver Assessment, Rockport, Maine, 18-24.
Risser, M.R., Ware, J.C., & Freeman, F.G. (2000). Driving Simulation with EEG Monitoring in
Normal and Obstructive Sleep Apnea Patients. Sleep, 23(3), 393–398.
Sommer, D. (2009). Microsleep characterisation utilizing neuroinformatic methods. PhD Thesis
(in German). Ilmenau University of Technology, Ilmenau, Germany.
Sommer, D., Golz, M., Schnupp, T., Krajewski, J., Trutschel, U., & Edwards, D. (2009). A
Measure of Strong Driver Fatigue. Proc 5th Int Symp Driver Assessment, Big Sky, Montana,
... He refined and eventually corrected the online ratings. This resulted in relative precise points in time where MS started; in average 0.8 MS events per minute, in total 2,290 MS events were observed (Golz et al, 2009). MS detection. ...
... After empirical parameter optimizations an MS detector was constructed (accuracy 97.7 ± 2.1 %). Next, the MS detector was applied consecutively to all data to detect EEG/EOG patterns which are similar to MS [8]. AB detection: 1 EEG signal (O1) was divided in overlapping segments (1 s length, 75 % overlap) [3] . ...
Conference Paper
Full-text available
Periodogram and other spectral power estimation methods are established in quantitative EEG analysis. Their outcome in case of drowsy subjects fulfilling a sustained attention task is difficult to interpret. Two novel kind of EEG analysis based on pattern recognition were proposed recently, namely the microsleep (MS) and the alpha burst (AB) pattern recognition. We compare both methods by applying them to the same experimental data and relating their output variables to two independent variables of driver drowsiness. The latter was an objective lane tracking performance variable and the first was a subjective variable of self-experienced sleepiness. Results offer remarkable differences between both EEG analysis methodologies. The expected increase with time since sleep as well as with time on task, which also exhibited in both independent variables, was not identified after applying AB recognition. The EEG immediately before fatigue related crashes contained both patterns. MS patterns were remarkably more frequent before crashes; almost every crash (98.5 %) was preceded by MS patterns, whereas less than 64 % of all crashes had AB patterns within a 10 sec pre-crash interval.
... Microsleeps have traditionally been defined through Electroencephalography (EEG), with intrusions of theta waves anywhere between 3 and 15 s (Liang et al., 2019;Hertig-Godeschalk et al., 2020). EEG defined microsleeps have been linked with driver impairment and crash risk (Boyle et al., 2008;Golz et al., 2011). Microsleep identification through EEG is currently both impractical in driving and limited by the temporal capabilities and signal noise of the technology. ...
Full-text available
Driver distraction and drowsiness remain significant contributors to death and serious injury on our roads and are long standing issues in road safety strategies around the world. With developments in automotive technology, including driver monitoring, there are now more options available for automotive manufactures to mitigate risks associated with driver state. Such developments in Occupant Status Monitoring (OSM) are being incorporated into the European New Car Assessment Programme (Euro NCAP) Safety Assist protocols. The requirements for OSM technologies are discussed along two dimensions: detection difficulty and behavioral complexity. More capable solutions will be able to provide higher levels of system availability, being the proportion of time a system could provide protection to the driver, and will be able to capture a greater proportion of complex real-word driver behavior. The testing approach could initially propose testing using both a dossier of evidence provided by the Original Equipment Manufacturer (OEM) alongside selected use of track testing. More capable systems will not rely only on warning strategies but will also include intervention strategies when a driver is not attentive. The roadmap for future OSM protocol development could consider a range of known and emerging safety risks including driving while intoxicated by alcohol or drugs, cognitive distraction, and the driver engagement requirements for supervision and take-over performance with assisted and automated driving features.
... Apart from dangerously decreasing cognitive and physical performance endangering traffic safety, sleepiness can also result in total loss of consciousness, i.e., microsleep (Craig et al. 2006;Grandjean 1979). Microsleep is a temporary episode of sleep, lasting from a fraction of a second up to a few seconds, where an individual loses awareness followed by a sudden and frightened shift to wakefulness (Durmer and Dinges 2005;Golz et al. 2011;Schleicher et al. 2008;Tirunahari et al. 2003). While clinical definitions of microsleep are based on distinct changes in brain activity, several behavioural markers related to facial expression, head movement and eyelid closure have been successfully used to detect episodes of microsleep events (Skorucak et al. 2020). ...
Full-text available
Fatigued driving is one of the main contributors to road traffic accidents. Poor sleep quality and lack of sleep negatively affect driving performance, and extreme states of fatigue can cause microsleep (i.e. short episodes of sleep with complete loss of awareness). Driver monitoring systems analyze biosignals (e.g. gaze, blinking, heart rate) and vehicle data (e.g. steering wheel movements, lane holding, acceleration) to detect states of fatigue and prevent accidents. We argue that inter-individual differences in personality, sensation seeking behavior, and intelligence could improve microsleep prediction, in addition to sleepiness. We tested 144 male participants in a supervised driving track after 27 hours of sleep deprivation. More than 74% of drivers experienced microsleep, after an average driving time of 51:31min. Overall, prediction models for microsleep vulnerability and driving time before microsleep were significantly improved by conscientiousness, sensation seeking and non-verbal IQ, in addition to situational sleepiness, as individual risk factors. Practitioner summary: This study offers valuable insights for the design of driver monitoring systems. The use of individual risk factors such as conscientiousness, sensation seeking, and non-verbal IQ can increase microsleep prediction. These findings may improve monitoring systems based solely on physiological signals (blinking, heart rate) and vehicle data (steering wheel movements, acceleration, cornering).
... Behavioral changes and performance lapses may not always be accompanied by detectable changes in the EEG and vice versa, and the first MSE may not necessarily lead to a traffic accident. More likely, and independent of their definition, multiple MSEs will often precede an accident [37], which increases the chances of detecting at least one MSE prior to a crash independent of the assessment method. ...
Study objectives The wake-sleep transition zone represents a poorly defined borderland, containing e.g. microsleep episodes (MSEs) which are of potential relevance for diagnosis and may have consequences while driving. Yet, the scoring guidelines of the American Academy of Sleep Medicine (AASM) completely neglect it. We aimed to explore the borderland between wakefulness and sleep by developing the Bern continuous and high-resolution wake-sleep (BERN) criteria for visual scoring, focusing on MSEs visible in the electroencephalogram (EEG), as opposed to purely behaviour- or performance-defined MSEs. Methods Maintenance of Wakefulness Test (MWT) trials of 76 randomly selected patients were retrospectively scored according to both the AASM and the newly developed BERN scoring criteria. The visual scoring was compared with spectral analysis of the EEG. The quantitative EEG analysis enabled a reliable objectification of the visually scored MSEs. For less distinct episodes within the borderland, either ambiguous or no quantitative patterns were found. Results As expected, the latency to the first MSE was significantly shorter in comparison to the sleep latency, defined according to the AASM criteria. In certain cases, a large difference between the two latencies was observed, and a substantial number of MSEs occurred between the first MSE and sleep. Series of MSEs were more frequent in patients with shorter sleep latencies, while isolated MSEs were more frequent in patients who did not reach sleep. Conclusion The BERN criteria extend the AASM criteria and represent a valuable tool for in-depth analysis of the wake-sleep transition zone, particularly important in the MWT.
... After empirical parameter optimizations an MS detector was constructed (accuracy 97.7 ± 2.1 %). Next, the MS detector was applied consecutively to all data to detect EEG/EOG patterns which are similar to MS [8]. AB detection: 1 EEG signal (O1) was divided in overlapping segments (1 s length, 75 % overlap) [3] . ...
Full-text available
Microsleep (MS) and alpha burst (AB) patterns in the EEG of ten young drivers were detected. Their percentage within 1 min intervals was compared with independent variables of drowsiness: 1) lane tracking performance, 2) self-rating of sleepiness. In addition, the occurrence of both patterns immediately before crashes was investigated. Results offer remarkable differences. AB displays no time-since-sleep as well as no time-on-task effect. AB failed in predicting crashes. MS displays both effects and always occurred immediately before crashes.
The article elaborates upon a study of the phenomenon of microsleep in drivers operating means of collective public transport on a regular basis. The microsleep phenomenon has been observed as a rather common one among drivers in general, however, in the case of professional drivers operating public transport lines, this is particularly dangerous. The consequences it may trigger are not limited to traffic accidents, but may even include road traffic disasters. The study addressed in the article was conducted using the eye tracking technique supported by auxiliary testing apparatus, including systems of the authors’ own design and make. The study was conducted in operation of different means of collective transport on public transport lines in Poland. In one case, microsleep was studied in a driver of the EN57 passenger train, while the second case studied was that of a driver of the Solaris Urbino bus. The data retrieved from the measurements were processed using the SMI BeGaze 3.4 software. Results of the studies, subsequently processed in statistical terms, were used to formulate operational conclusions concerning the microsleep phenomenon and to define specific recommendations for drivers of means of collective public transport based on such grounds. The article also touches upon the matter of the values of parameters characterising the phenomena of microsleep and blinking, as previously commented in the literature of the subject.
Conference Paper
The microsleeps (MS) cause many accidents and can have a huge social impact. Automated prediction or early detection of the MS states could help to monitor level of fatigue. An automated MS classifier based on the EOG signal is proposed. There were analysed 28 episodes of MS. We observed slow eye movements without rapid changes during MS episodes. An automated feature extraction and classification using EOG channels showed promising results (sensitivity 93 %, positive predictivity 57 %). To confirm the hypothesis it is crucial to extend the study and to analyse larger amount of MS data.
Previous research on driver drowsiness detection has focused on developing in-car systems that continuously monitor the driver while driving and warn him/her when drowsiness compromises safety. In occupational settings a simple test of postural control has showed sensitivity to work shift induced fatigue in drivers. Whether the test is feasible for surveillance purposes in roadside settings is unknown. The present research sought to evaluate the feasibility of using a force platform test of postural control as a breathalyzer-like drowsiness-test at the roadside.
Full-text available
A combination of linear and nonlinear methods for feature fusion is introduced and the performance of this methodology is illustrated on a real-world problem: the detection of sudden and non-anticipated lapses of attention in car drivers due to drowsiness. To achieve this, signals coming from heterogeneous sources are processed, namely the brain electric activity, variation in the pupil size, and eye and eyelid movements. For all the signals considered, the features are extracted both in the spectral domain and in state space. Linear features are obtained by the modified periodogram, whereas the nonlinear features are based on the recently introduced method of delay vector variance (DVV). The decision process based on such fused features is achieved by support vector machines (SVM) and learning vector quantization (LVQ) neural networks. For the latter also methods of metrics adaptation in the input space are applied. The parameters of all utilized algorithms are optimized empirically in order to gain maximal classification accuracy. It is also shown that metrics adaptation by weighting the input features can improve the classification accuracy, but only to a limited extent. Limited improvements are also obtained when fusing features of selected signals, but highest improvements are gained by fusion of features of all available signals. In this case test errors are reduced down to 9% in the mean, which clearly illustrates the potential of our methodology to establish a reference standard of drowsiness and microsleep detection devices for future online driver monitoring.
Full-text available
This study aimed to evaluate the value of measuring microsleeps as an indicator of driving performance impairment in drowsy drivers with sleep disorders. Drivers with sleep disorders such as obstructive sleep apnea/hypopena syndrome (OSAHS) are at increased risk for driving performance errors due to microsleep episodes, which presage sleep onset. To meet this aim, we tested the hypothesis that OSAHS drivers show impaired control over vehicle steering, lane position and velocity during microsleep episodes compared to when they are driving without microsleeps on similar road segments. A microsleep is defined as a 3-14 sec episode during which 4-7 Hz (theta) activity replaces the waking 8-13 Hz (alpha) background rhythm. Microsleep episodes were identified in the electroencephalography (EEG) record by a neurologist certified by the American Board of Sleep Medicine. Twenty-four drivers with OSAHS were tested using simulated driving scenarios. Steering variability, lane position variability, acceleration and velocity measures were assessed in the periods during a microsleep, immediately preceding (pre) microsleep, and immediately following (post) microsleep. In line with our introductory hypothesis, drivers with OSAHS did show significantly greater variation in steering and lane position during the microsleep episodes compared to the periods pre and post microsleep. The results indicate that identification of microsleep episodes can provide a marker for declining vehicle control of drivers with OSAHS.
Full-text available
The purpose of this study was to evaluate commercially available devices for driver fatigue monitoring with particular focus on the needs of the mining industry. We present an overview of fatigue monitoring technologies (FMTs) and propose means to evaluate the devices. Three video-based devices were selected and used in an overnight driving simulation study to test their accuracy. In total 14 healthy volunteers performed the driving simulation tasks in eight test runs separated by breaks of approximately 10 min. EEG and EOG were recorded during the driving periods. The output variable of the FMT devices (percentage of eye closures, PERCLOS), subjectively rated fatigue on the Karolinska sleepiness scale (KSS), and driving performance in terms of standard deviation of lateral position in lane (SDL) were also recorded throughout testing sessions. Regression analysis revealed that PERCLOS is significantly related to higher KSS scores and to SDL. Calculations at a finer temporal resolution as well as on an intra-subject level showed decreased correlation coefficients. Discriminant analysis of PERCLOS and EEG/EOG suggested that PERCLOS does not differentiate well between mild and strong fatigue. The results suggest that under laboratory conditions current FMT devices are reliable when temporal resolution is not too fine (>30 min) and data averaged across several subjects is utilized, but fail to give a valid prediction of subjective fatigue as well as of driving performance on an individual level.
Full-text available
This study examined if individuals who are at increased risk for drowsy-driving because of obstructive sleep apnea syndrome (OSAS), have impairments in driving performance in the moments during microsleep episodes as opposed to during periods of wakefulness. Twenty-four licensed drivers diagnosed with OSAS based on standard clinical and polysomnographic criteria, participated in an hour-long drive in a high-fidelity driving simulator with synchronous electroencephalographic (EEG) recordings for identification of microsleeps. The drivers showed significant deterioration in vehicle control during the microsleep episodes compared to driving performance in the absence of microsleeps on equivalent segments of roadway. The degree of performance decrement correlated with microsleep duration, particularly on curved roads. Results indicate that driving performance deteriorates during microsleep episodes. Detecting microsleeps in real-time and identifying how these episodes of transition between wakefulness and sleep impair driver performance is relevant to the design and implementation of countermeasures such as drowsy driver detection and alerting systems that use EEG technology.
Full-text available
To measure simulated driving performance in obstructive sleep apnea patients and its relationship with EEG defined attention lapses. Prospective, mixed design comparing apnea patients and control subjects over a 60-minute driving simulation task while continuously recording both driving performance and EEG measures. Sleep disorders center. 15 polysomnographically diagnosed obstructive sleep apnea patients (mean age 42 +/- 6 yrs.) and 15 healthy volunteers (mean age 38 +/- 6 yrs.). NA. A computer based driving simulator recorded lane position variability, speed variability, steering rate variability, and crash frequency. The frequency and duration of EEG-defined attention lapses were also measured. The results demonstrated that the apnea group had significantly greater variability in lane position, steering rate, and speed than the control group. The apnea group also had more crashes. In addition, the apnea group had more EEG-defined attention lapses of longer duration. Except for speed and steering rate variability, these differences increased over the 60-minute task. Measures of lane position variability and crash frequency had a significant positive correlation with attention lapse frequency and duration. The driving simulation task unmasked and quantified marked performance impairments in the sleep apnea group that increased over time. The poor performance appeared related to the EEG-defined attention lapses. Lane position variability appeared to be the most sensitive measure for assessing and quantifying impairment. This study suggests that poorer driving performance and crashes are not entirely due to overt sleep, but inattention due to sleepiness.
Full-text available
A warning system capable of reliably detecting lapses in responsiveness (lapses) has the potential to prevent many fatal accidents. We have developed a system capable of detecting lapses in real-time with second-scale temporal resolution. Data was from 15 subjects performing a visuomotor tracking task for two 1-hour sessions with concurrent electroencephalogram (EEG) and facial video recordings. The detector uses a neural network with normalized EEG log-power spectrum inputs from two bipolar EEG derivations, though we also considered a multichannel detector. Lapses, identified using a combination of video rating and tracking behavior, were used to train our detector. We compared detectors employing tapped delay-line linear perceptron, tapped delay-line multilayer perceptron (TDL-MLP), and long short-term memory (LSTM) recurrent neural networks operating continuously at 1 Hz. Using estimates of EEG log-power spectra from up to 4 s prior to a lapse improved detection compared with only using the most recent estimate. We report the first application of a LSTM to an EEG analysis problem. LSTM performance was equivalent to the best TDL-MLP network but did not require an input buffer. Overall performance was satisfactory with area under the curve from receiver operating characteristic analysis of 0.84 plusmn 0.02 (mean plusmn SE) and area under the precision-recall curve of 0.41 plusmn 0.08
A framework for automatic relevance determination based on artificial neural networks and an evolution strategy is presented. It is applied to an important problem in biomedicine, namely, the detection of unintentional episodes of sleep during sustained operations of subjects, so-called microsleep episodes. Human expert ratings based on video and biosignal recordings are necessary to judge microsleep episodes. Ratings are fused together with linear and nonlinear features which are extracted from three types of biosignals: electroencephalography, electrooculography, and eyetracking. Changes in signal modality due to nonlinearity and stochasticity are quantified by the ‘delay vector variance’ method. Results show large inter-individual variability. Though the framework is outperformed by support vector machines in terms of classification accuracy, the estimated relevance values provide knowledge of signal characteristics during microsleep episodes.
Our objective was to examine a novel standardized assessment methodology of detecting impaired driving performance due to drowsiness in a normative cohort. Thirty-one healthy subjects with no significant sleep, medical, and psychiatric pathology were assessed in a driving simulation paradigm. Thirty-minute simulations were repeated at two-hourly intervals (i.e., at 1000, 1200, 1400, and 1600 h). Convergent data sources included drivers' subjective ratings of sleepiness and alertness, electroencephalogram-verified microsleep (MS) episodes, and a variety of real-time driving simulator performance measures such as speed, lane tracking, reaction time (RT), and off-road events (crashes). Significant diurnal fluctuations were noted on objective measures of RT, velocity, tracking, and MS events, indicating the highest risk of impairment in the afternoon. By contrast, subjective ratings of sleepiness and alertness did not demonstrate significant circadian variation. The mean incidence of MS episodes and crash risk correlated highly (r = .748). This prospective study demonstrates the relevance of multiple convergent measures for comprehensive assessment. The divergence of subjective and objective assays of impairment implies that healthy individuals may not have full insights into neurophysiologically mediated performance deficits. These results will serve as normative comparators to patients presenting with daytime somnolence and may allow a more accurate prediction of potential crash risk than noninteractive daytime polysomnogram tests such as the mean sleep latency test or the maintenance of wakefulness test.
Microsleep characterisation utilizing neuroinformatic methods
  • D Sommer
Sommer, D. (2009). Microsleep characterisation utilizing neuroinformatic methods. PhD Thesis (in German). Ilmenau University of Technology, Ilmenau, Germany.