An overview of several methods of electroencephalography (EEG) analysis in order to assess driver sleepiness is presented. All methods were applied to one single data set obtained from overnight driving simulations in our lab. 10 young adults (age 22.4 ± 4.1 years) participated and drove on rural roads; time on task was 7 x 40 min and time since sl...
Martin Golz David Sommer Jarek Krajewski
Im Fahrsimulationslabor wurden an 16 Personen in je 2 Nächten Biosignale, vor allem das Elektronenzephalogramm (EEG), sowie Videos des Fahrerverhaltens aufgezeichnet. Sekundenschlafereignisse wurden bzgl. des Eintrittszeitpunkts und der Stärke durch a) mehrere Assistenten und b) einen Experten beurteilt. Mit einer Prozesskette des maschinellen Lern...
Tobias Anhalt Adolf Schenka David Sommer Martin Golz
Adolf Schenka M. Strüning David Sommer Martin Golz
Recognizing a pathological-in distinction from a healthy-heart rhythm presents a challenge of contemporary cardiovascular research. We propose a machine learning framework to determine the deciding features for a given discriminative problem. This approach is demonstrated by analyzing publicly available RR-interval recordings including a group of p...
Christian Heinze David Sommer Udo Trutschel Martin Golz
The concept of feature combination using Learn-ing Vector Quantization (LVQ) networks is introduced in order to increase the discrimination ability between two subject groups, one with normal sinus rhythm and one with congestive heart failure.
Udo Trutschel Christian Heinze David Sommer Martin Golz
We propose a machine learning framework that implements automated relevance determination in order to identify the deciding RR interval features for the discrimination between congestive heart failure and healthy condition. As a result, the most relevant features of heart rate variability (HRV) are narrowly located spectral components in the very-l...
Christian Heinze Udo Trutschel Martin Golz
Recognizing pathological heart rhythm features remains a challenge of cardiovascular research. We adopt a machine learning framework with empirically optimized parameters to distinguish heart failure from healthy condition, emphasizing on spectral and nonlinear features of heart rate variability. Fine grained spectral power densities of RR interval...
Christian Heinze David Sommer Udo Trutschel Martin Golz
Für den Warentransport eines regionalen Einzelhandelsunternehmens mit 284 Filialen wurden die Tourenplanung und die Tourenoptimierung mit vielfältigen Nebenbedingungen algorithmisch umgesetzt. Die Optimierung wurde mit drei ver-schiedenen Methoden vergleichend durchgeführt. Simulierte Ameisen-Kolonien erwiesen sich dabei als die praktikabelste Meth...
Christoph Schmidt Udo Trutschel Christian Heinze Martin Golz
Basierend auf empirischen Beobachtungen werden Kneippschen Kaltwasseranwendungen bei den oberen Extremitäten eine anregende, bei den unteren Extremitäten dagegen eine beruhigende Wirkung zugeschrieben. Kneipps Lehre selbst und medizinische Untersuchungen bieten kaum Grundlagen, um diese Effekte im physiologischen Sinne zu begründen. Daher wurde anh...
Christian Heinze Katarina Gille Udo Trutschel Martin Golz
Hochwertige und zugleich relativ preiswerte Geräte des IT-Massenmarktes, wie beispielsweise Smartphones, finden zunehmend Anwendung auch in der Medizintechnik. Wir gehen der Frage nach, ob mit den internen Beschleunigungs- und Winkelgeschwindigkeitssensoren posturografische Messungen erfolgen können, die zur quantitativen Einschätzung der Standstab...
Adolf Schenka M. Strüning David Sommer Martin Golz
The purpose of this study was to refine a commercial car driving simulation for occupational research. As the effects of ethanol on driving behavior are well established, we choose alcohol as a test compound to investigate the performance of subjects during simulation. We programmed a night driving scenario consisting of monotonous highway and a ru...
Axel Muttray Anais Breitinger Elisabeth Goetze Stephan Letzel
Martin Golz David Sommer Udo Trutschel David J Edwards
David Sommer Tobias Grimm Martin Golz
An experimental sleep-wake protocol of 30-minute cycles with an allowed 10-minute sleep episode and an enforced 20-minute wake episode was carried out over 48 hours. The sleep and wake conditions of the experiment are simulated using the two process model. A fitness function measuring the occurrence of Non-REM sleep in the 10 minute episodes betwee...
Christian Heinze Sven Schirmer Udo Trutschel Martin Golz
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 offe...
Martin Golz David Sommer
Based on questionnaires and diagnosis by one senior medical specialist 28 patients were evaluated with respect to their fall risk and categorized into two classes (low / high fall risk). Posturography stabilograms were quantitatively analyzed by means of time as well as spectral domain techniques. Feature sets were analyzed with three different met...
Thomas Schnupp Adolf Schenka L E Walther Martin Golz
The aim of this study is to evaluate whether frequency domain heart rate measures can be used to detect impaired driver performance. An overnight driving simulation scenario with partial sleep deprivation was utilized to induce driver performance impairment. Heart rate (HR) was recorded over the entire experiment; frequency domain HR-measures were...
Christian Heinze Sven Schirmer Udo Trutschel David J Edwards
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) patter...
Martin Golz David Sommer Udo Trutschel Bill Sirois
The development of the human sleep-wake cycle and the adaptation to the changing day and night condition on our planet took place over a time frame of 100000 years. As the result, a representative cross section of today's population sleeps between 4 and 11 hours, with a midsleep point between 1.00 and 9.00 am and a period length of the human circad...
Sven Schirmer Christian Heinze Martin Golz Udo Trutschel
Beyond the workload determination during driving, it would be important to identify the most dangerous situations of high workload and high fatigue in order to discriminate this condition from the other combinations of workload and fatigue. This would help to avoid critical incidences in air traffic control and ther occupations where extremely hig...
Udo Trutschel Christian Heinze Bill Sirois Martin Golz
The objective of this study was to assess the monotonic mental workload under changing conditions of operator fatigue during a night time driver simulation study. Several cardiovascular measures were used in order to differentiate between driving and a continuous tracking task. From all of the standard cardiovascular measures, heart rate in beats p...
Udo Trutschel Martin Golz Christian Heinze David J Edwards
Thomas Schnupp Adolf Schenka L Walther Martin Golz
Introduction Recently, two different methods were introduced to assess driver sleepiness based on pattern recognition in the EEG. One aims at machine learning to represent patterns occurring during microsleep events. Within the recall process the entire EEG is searched for microsleep-like patterns. The second method aims at detecting alpha burst ac...
Martin Golz David Sommer
In order to investigate the potential of heart rate measures to reflect changes in the circadian rhythm or in sleepiness, an ultrashort sleep-wake experimental protocol was used to unmask circadian- or sleepiness-related effects: Over a duration of 50 hours and always alternating, subjects attempted to fall asleep within 10 minutes and must stay aw...
Christian Heinze Udo Trutschel Martin Golz
Introduction Irregular sleep-wake behavior is common to a vast amount of people in industrialized nations. Many are working in shift schedules, other are travelling on long distant flights. Vigilance expert systems might be helpful managing sleep-wake behavior to become more regular. Mobile devices are needed to support adaptation of the expert sy...
David Sommer Martin Golz
