Classification of Blink Waveforms Toward the Assessment of Driver’s Arousal Levels - An EOG Approach and the Correlation with Physiological Measures

Ohsuga, Mieko; Kamakura, Yoshiyuki; Inoue, Yoshio; Noguchi, Yoshihiro; Nopsuwanchai, Roongroj

doi:10.1007/978-3-540-73331-7_86

Cited by 14 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the closing time did not show signiWcant results. This was due to the fact that the duration's change was aVected more by the reopening time than by the closing time, and this result was consistent with other studies (CaYer et al 2003;Ohsuga et al 2007;Ryu and Myung 2005).…”

Section: Discussionsupporting

confidence: 94%

Helmet-based physiological signal monitoring system

et al. 2008

View full text Add to dashboard Cite

A helmet-based system that was able to monitor the drowsiness of a soldier was developed. The helmet system monitored the electrocardiogram, electrooculogram and electroencephalogram (alpha waves) without constraints. Six dry electrodes were mounted at five locations on the helmet: both temporal sides, forehead region and upper and lower jaw strips. The electrodes were connected to an amplifier that transferred signals to a laptop computer via Bluetooth wireless communication. The system was validated by comparing the signal quality with conventional recording methods. Data were acquired from three healthy male volunteers for 12 min twice a day whilst they were sitting in a chair wearing the sensor-installed helmet. Experimental results showed that physiological signals for the helmet user were measured with acceptable quality without any intrusions on physical activities. The helmet system discriminated between the alert and drowsiness states by detecting blinking and heart rate variability (HRV) parameters extracted from ECG. Blinking duration and eye reopening time were increased during the sleepiness state compared to the alert state. Also, positive peak values of the sleepiness state were much higher, and the negative peaks were much lower than that of the alert state. The LF/HF ratio also decreased during drowsiness. This study shows the feasibility for using this helmet system: the subjects' health status and mental states could be monitored without constraints whilst they were working.

show abstract

Section: Discussionsupporting

confidence: 94%

Helmet-based physiological signal monitoring system

et al. 2008

View full text Add to dashboard Cite

show abstract

“…EOG is a human blink information, which peak, rise time and fall time of three characteristic parameters can reflect people's fatigue information [14] [14] . Changes in heart rate which can be obtained by ECG can also represent fatigue [15].…”

Section: Comfort Modelingmentioning

confidence: 99%

Smart car care systems and its technology prospects with service robots function

Zhang

et al. 2014

2014 IEEE International Conference on Information and Automation (ICIA)

View full text Add to dashboard Cite

Social and human demands promote the development of automobile technology. For general vehicles, the auxiliary driving or automated driving is from a safe and comfortable level to solve human driving requirements. As the growth of the social demand for cultural and health care, the demand is bound to be reflected during the vehicle driving or proposed by consumers. It is important to consider the driver who may be in fatigue, illness and disability. In this paper, the concept of service robots in the car environment is proposed from car security, cultural and health care. The characteristics of the intelligent service robot system and core technology are discussed and the design scheme is also proposed.

show abstract

“…() Shen et al() analyzed the importance and feasibility of Support Vector Machine for EEG features classification. Ohsuga et al obtained three parameters including peak amplitude, rise time, and fall time of EOG waveform. When the eye is closed, the electrode value reaches the maximum, at the same time, the waveform is shown as the peak amplitude.…”

Section: Related Workmentioning

confidence: 99%

Deep convolutional neural network for drowsy student state detection

Zhao

Liu

Wang

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Drowsy student state detection is helpful to understand the students' learning state, which is the necessary and basic aspect of teaching activities evaluation and assessment. The performance of traditional methods may deteriorate dramatically because of the external environment factors. In this paper, a novel drowsy student state detection method by integrating deep convolutional neural network is proposed at the first time in the literature. The proposed method avoids the complicated manual feature extraction operation and it can effectively reduce the interference of environmental factors in the application scenarios. Experimental results demonstrate that our approach can achieve high accuracy and lower error rate for drowsy student state detection. In addition, the results also show that our method outperforms traditional methods.

show abstract

Classification of Blink Waveforms Toward the Assessment of Driver’s Arousal Levels - An EOG Approach and the Correlation with Physiological Measures

Cited by 14 publications

References 3 publications

Helmet-based physiological signal monitoring system

Helmet-based physiological signal monitoring system

Smart car care systems and its technology prospects with service robots function

Deep convolutional neural network for drowsy student state detection

Contact Info

Product

Resources

About