Statistical validation of physiological indicators for non-invasive and hybrid driver drowsiness detection system

A hybrid system for detecting driver drowsiness was examined by using piezofilm movement sensors integrated into the car seat, seat belt and steering wheel. Statistical associations between increase in the driver drowsiness and the non-invasive and conventional physiological indicators were investigated. Statistically significant associations were established for the analysed physiological indicators – car seat movement magnitude and (electroencephalogram) EEG alpha band power percentage. All of the associastions were physiologically plausible with increase in probability of drowsiness associated with increases in the EEG alpha band power percentage and reduction in the seat movement magnitude. Adding a non-invasive measure such as seat movement magnitude to any combination of the EEG derived physiological predictors always resulted in improvement of associations. These findings can serve as a foundation for designing the vehicle-based fatigue countermeasure device as well as highlight potential difficulties and limitations of detection algorithm for such devices.

Download Full-text

Propofol Requirement and EEG Alpha Band Power During General Anesthesia Provide Complementary Views on Preoperative Cognitive Decline

Frontiers in Aging Neuroscience ◽

10.3389/fnagi.2020.593320 ◽

2020 ◽

Vol 12 ◽

Author(s):

Cyril Touchard ◽

Jérôme Cartailler ◽

Charlotte Levé ◽

José Serrano ◽

David Sabbagh ◽

...

Keyword(s):

Cognitive Decline ◽

General Anesthesia ◽

Logistic Models ◽

Alpha Band ◽

Target Concentration ◽

Operative Morbidity ◽

Band Power ◽

Cognitive Evaluation ◽

Eeg Alpha ◽

Better Than

Background: Although cognitive decline (CD) is associated with increased post-operative morbidity and mortality, routinely screening patients remains difficult. The main objective of this prospective study is to use the EEG response to a Propofol-based general anesthesia (GA) to reveal CD.Methods: 42 patients with collected EEG and Propofol target concentration infusion (TCI) during GA had a preoperative cognitive assessment using MoCA. We evaluated the performance of three variables to detect CD (MoCA < 25 points): age, Propofol requirement to induce unconsciousness (TCI at SEF95: 8–13 Hz) and the frontal alpha band power (AP at SEF95: 8–13 Hz).Results: The 17 patients (40%) with CD were significantly older (p < 0.001), had lower TCI (p < 0.001), and AP (p < 0.001). We found using logistic models that TCI and AP were the best set of variables associated with CD (AUC: 0.89) and performed better than age (p < 0.05). Propofol TCI had a greater impact on CD probability compared to AP, although both were complementary in detecting CD.Conclusion: TCI and AP contribute additively to reveal patient with preoperative cognitive decline. Further research on post-operative cognitive trajectory are necessary to confirm the interest of intra operative variables in addition or as a substitute to cognitive evaluation.

Download Full-text

An Investigation of Early Detection of Driver Drowsiness Using Ensemble Machine Learning Based on Hybrid Sensing

Applied Sciences ◽

10.3390/app10082890 ◽

2020 ◽

Vol 10 (8) ◽

pp. 2890

Author(s):

Jongseong Gwak ◽

Akinari Hirao ◽

Motoki Shino

Keyword(s):

Machine Learning ◽

Early Detection ◽

Driving Simulator ◽

Detection System ◽

Driving Performance ◽

Machine Learning Algorithms ◽

Drowsy Driving ◽

Physiological Indicators ◽

Driver Drowsiness ◽

Behavioral Indices

Drowsy driving is one of the main causes of traffic accidents. To reduce such accidents, early detection of drowsy driving is needed. In previous studies, it was shown that driver drowsiness affected driving performance, behavioral indices, and physiological indices. The purpose of this study is to investigate the feasibility of classification of the alert states of drivers, particularly the slightly drowsy state, based on hybrid sensing of vehicle-based, behavioral, and physiological indicators with consideration for the implementation of these identifications into a detection system. First, we measured the drowsiness level, driving performance, physiological signals (from electroencephalogram and electrocardiogram results), and behavioral indices of a driver using a driving simulator and driver monitoring system. Next, driver alert and drowsy states were identified by machine learning algorithms, and a dataset was constructed from the extracted indices over a period of 10 s. Finally, ensemble algorithms were used for classification. The results showed that the ensemble algorithm can obtain 82.4% classification accuracy using hybrid methods to identify the alert and slightly drowsy states, and 95.4% accuracy classifying the alert and moderately drowsy states. Additionally, the results show that the random forest algorithm can obtain 78.7% accuracy when classifying the alert vs. slightly drowsy states if physiological indicators are excluded and can obtain 89.8% accuracy when classifying the alert vs. moderately drowsy states. These results represent the feasibility of highly accurate early detection of driver drowsiness and the feasibility of implementing a driver drowsiness detection system based on hybrid sensing using non-contact sensors.

Download Full-text

Identification of Schizophrenia Using EEG Alpha Band Power During Hyperventilation and Post-hyperventilation

Journal of Medical and Biological Engineering ◽

10.1007/s40846-016-0192-2 ◽

2016 ◽

Vol 36 (6) ◽

pp. 901-911 ◽

Cited By ~ 1

Author(s):

Thilakavathi Bose ◽

Shenbaga Devi Sivakumar ◽

Bhanu Kesavamurthy

Keyword(s):

Alpha Band ◽

Band Power ◽

Eeg Alpha

Download Full-text

Invisible visual stimuli elicit increases in alpha-band power

Journal of Neurophysiology ◽

10.1152/jn.00550.2013 ◽

2014 ◽

Vol 112 (5) ◽

pp. 1082-1090 ◽

Cited By ~ 8

Author(s):

Isabelle Bareither ◽

Maximilien Chaumon ◽

Fosco Bernasconi ◽

Arno Villringer ◽

Niko A. Busch

Keyword(s):

Cortical Excitability ◽

Neuronal Response ◽

Detection Threshold ◽

Visual Stimuli ◽

Response Patterns ◽

Alpha Band ◽

Noise Pattern ◽

Band Power ◽

Wide Range ◽

Eeg Alpha

The cerebral cortex responds to stimuli of a wide range of intensities. Previous studies have demonstrated that undetectably weak somatosensory stimuli cause a functional deactivation or inhibition in somatosensory cortex. In the present study, we tested whether invisible visual stimuli lead to similar responses, indicated by an increase in EEG alpha-band power—an index of cortical excitability. We presented subliminal and supraliminal visual stimuli after estimating each participant's detection threshold. Stimuli consisted of peripherally presented small circular patches that differed in their contrast to a background consisting of a random white noise pattern. We demonstrate that subliminal and supraliminal stimuli each elicit specific neuronal response patterns. Supraliminal stimuli evoked an early, strongly phase-locked lower-frequency response representing the evoked potential and induced a decrease in alpha-band power from 400 ms on. By contrast, subliminal visual stimuli induced an increase of non-phase-locked power around 300 ms that was maximal within the alpha-band. This response might be due to an inhibitory mechanism, which reduces spurious visual activation that is unlikely to result from external stimuli.

Download Full-text

Non-Invasive Driver Drowsiness Detection System

Sensors ◽

10.3390/s21144833 ◽

2021 ◽

Vol 21 (14) ◽

pp. 4833

Author(s):

Hafeez Ur Rehman Siddiqui ◽

Adil Ali Saleem ◽

Robert Brown ◽

Bahattin Bademci ◽

Ernesto Lee ◽

...

Keyword(s):

Support Vector Machine ◽

Detection System ◽

Ultra Wideband ◽

Gradient Boosting ◽

Support Vector ◽

Drowsiness Detection ◽

Non Invasive ◽

Driver Drowsiness ◽

Uwb Radar ◽

Tree Classifier

Drowsiness when in command of a vehicle leads to a decline in cognitive performance that affects driver behavior, potentially causing accidents. Drowsiness-related road accidents lead to severe trauma, economic consequences, impact on others, physical injury and/or even death. Real-time and accurate driver drowsiness detection and warnings systems are necessary schemes to reduce tiredness-related driving accident rates. The research presented here aims at the classification of drowsy and non-drowsy driver states based on respiration rate detection by non-invasive, non-touch, impulsive radio ultra-wideband (IR-UWB) radar. Chest movements of 40 subjects were acquired for 5 m using a lab-placed IR-UWB radar system, and respiration per minute was extracted from the resulting signals. A structured dataset was obtained comprising respiration per minute, age and label (drowsy/non-drowsy). Different machine learning models, namely, Support Vector Machine, Decision Tree, Logistic regression, Gradient Boosting Machine, Extra Tree Classifier and Multilayer Perceptron were trained on the dataset, amongst which the Support Vector Machine shows the best accuracy of 87%. This research provides a ground truth for verification and assessment of UWB to be used effectively for driver drowsiness detection based on respiration.

Download Full-text