Assessment of Driver’s Driving Performance and Alertness Using EEG-based Fuzzy Neural Networks

Lin, Chin‐Teng; Chen, Yu-Chieh; Wu, Ruei-Cheng; Liang, Sheng-Fu; Huang, Teng‐Yi

doi:10.1109/iscas.2005.1464547

Cited by 14 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Operator Screen fatigue-based monitoring neurotechnologies demonstrated that high correlations could be obtained between EEG activity and lane deviation performance on a simplified driving task under static and motion conditions [107]- [109]. Our team further extended this effort to demonstrate that auditory mitigations could be used to aid performance in this scenario [110], [111].…”

Section: Raven Systemmentioning

confidence: 99%

Real-World Neuroimaging Technologies

et al. 2013

View full text Add to dashboard Cite

Decades of heavy investment in laboratory-based brain imaging and neuroscience have led to foundational insights into how humans sense, perceive, and interact with the external world. However, it is argued that fundamental differences between laboratory-based and naturalistic human behavior may exist. Thus, it remains unclear how well the current knowledge of human brain function translates into the highly dynamic real world. While some demonstrated successes in real-world neurotechnologies are observed, particularly in the area of brain-computer interaction technologies, innovations and developments to date are limited to a small science and technology community. We posit that advancements in realworld neuroimaging tools for use by a broad-based workforce will dramatically enhance neurotechnology applications that have the potential to radically alter human-system interactions across all aspects of everyday life. We discuss the efforts of a joint government-academic-industry team to take an integrative, interdisciplinary, and multi-aspect approach to translate current technologies into devices that are truly fieldable across a range of environments. Results from initial work, described here, show promise for dramatic advances in the field that will rapidly enhance our ability to assess brain activity in real-world scenarios.

show abstract

Section: Raven Systemmentioning

confidence: 99%

Real-World Neuroimaging Technologies

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Figure 6 shows all network performances of study. Previous studies mainly focused on driver drowsiness or alertness prediction (Chin-Teng et al 2005a ; 2005b ; Liang et al 2005 ; Papadelis et al 2006 ; Nikhil et al 2008 ; Michail et al 2008 ), and different issues such as ride comfort (Mitsukura et al 2009 ), driving style (Chin-Teng et al 2006 ), and maximum band activity (Schier 2000 ; Chin-Teng et al 2008 ). The researchers used different types of preprocessing and analyzing methods, such as ICA, PCA, FA (Factor Analysis), neural networks and support vector machine.…”

Section: Discussionmentioning

confidence: 99%

“…Power spectra were computed to produce values of relative alpha activity and an increase was found in alpha activity as a result. Furthermore Chin-Teng et al ( 2005a ) suggested a system that combines EEG power spectra estimation, independent component analysis (ICA) and fuzzy neural network models to estimate drivers’ cognitive state in a dynamic virtual reality based environment. Also a relationship between driver’s style and driver’s ERP response was investigated (Chin-Teng et al 2006 ).…”

Section: Introductionmentioning

confidence: 99%

EEG-based analysis of human driving performance in turning left and right using Hopfield neural network

et al. 2013

View full text Add to dashboard Cite

In this article a quantitative analysis was devised assessing driver’s cognition responses by exploring the neurobiological information underlying electroencephalographic (EEG) brain signals in a left and right turning experiment on simulator environment. Driving brain signals have been collected by a 19-channel electroencephalogram recording system. The driving pathway has been selected with no obstacles, a set of indicators are used to inform the subjects when they had to turn left or right by means of keyboard left and right arrows. Subsequently in order to remove artifacts, preprocessing is performed on data to achieve high accuracy. Features of signals are extracted by using Fast Fourier Transform (FFT). Absolute power of FFT is used as a basic feature. Scalar Feature selection method is applied to reduce feature dimension. Thereafter dimension-reduced features are fed to Hopfield Neural Network (HNN) recognizing different brain potentials stimulated by turning to left and right. The performances of HNN are evaluated by considering five conditions; before feature extraction, after feature extraction, before reduction of features, after analyzing reduced features and finally subject-wise Hopfield performances respectively. An increase occurred in each level and continued until it has reached its highest 97.6% of accuracy on last condition.

show abstract

“…Therefore, a simple road scenario cannot be used to determine the type of fatigue induced in this study. Owing to the increasing trend of alpha wave power in monotonic and complex scenarios 10,11,12 , it is di cult to judge the type of fatigue using EEG. According to May and Baldwin 7 , the key to distinguishing between active and passive fatigue is the mental workload.…”

Section: Introductionmentioning

confidence: 99%

Electroencephalography Sample Entropy of Driver Passive Fatigue Threshold in Automated Driving

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

With the continuous improvement of automated vehicles, researchers have found that automated driving is more likely to cause insufficient mental workload for the driver, which induces passive fatigue and endangers traffic safety. To explore the impact of automation and scenario complexity on the passive fatigue of the driver, we developed a three-factor, 2 (automated driving, manual driving) × 2 (monotonic condition, engaging condition) × 6 (measurement stage: 1–6) mixed experiment. We collected electroencephalography (EEG), detection-response task (DRT) performance, and the subjective report scores of 48 drivers. We found that in automated driving under monotonic conditions, the topographic map’s activation range of the drivers brain was the smallest in the six stages, and the mental workload of this group continued to maintain the lowest state at each stage; however, the subjectively reported fatigue level was significantly increased; thus, the driver experienced passive fatigue. After simulating a low-load scenario for 40 min, the power of the alpha of the driver’s EEG indicators increased significantly, the accuracy of the detection reaction task decreased, and the reaction time became slower. The EEG sample’s entropy value of the driver’s passive fatigue was 0.243, and the judgement accuracy rate was 0.71. We proved that in automated driving under monotonic conditions, the driver is more prone to passive fatigue owing to insufficient mental workload.

show abstract

Assessment of Driver’s Driving Performance and Alertness Using EEG-based Fuzzy Neural Networks

Cited by 14 publications

References 8 publications

Real-World Neuroimaging Technologies

Real-World Neuroimaging Technologies

EEG-based analysis of human driving performance in turning left and right using Hopfield neural network

Electroencephalography Sample Entropy of Driver Passive Fatigue Threshold in Automated Driving

Contact Info

Product

Resources

About