A Review on EEG-Based Automatic Sleepiness Detection Systems for Driver

Balandong, Rodney Petrus; Ahmad, Rana Fayyaz; Saad, Mohamad Naufal Mohamad; Malik, Aamir Saeed

doi:10.1109/access.2018.2811723

Cited by 107 publications

(52 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was focused to figure the readiness level by utilizing both EEG and EMG signals for developing the rightness of the assessment rate [6]. In our framework EMG and EEG signals were gained from 30 subjects.…”

Section: B Estimating Vigilance Level By Using Eeg and Ecg Signalsmentioning

confidence: 99%

“…To locate the potential eye positions and scales in the image is applied to the located eyes from facial points which are indicated for eyes. There are 6 points for each left and right eyes as shown in fig below The Eye Aspect Ratio is calculated as follows: leftEAR = eye_aspect_ratio(leftEye) rightEAR = eye_aspect_ratio(rightEye) ear = (leftEAR + rightEAR) / 2.0 The function eye_aspect_ratio calculated as: def eye_aspect_ratio(eye): A = dist.euclidean(eye [2], eye [6]) B = dist.euclidean(eye [3], eye [5]) C = dist.euclidean(eye [1], eye [4]) ear = (A + B) / (2.0 * C)…”

Section: F Eye Detection and Eye Openness Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Driver State Alert Control using Head Shoulder Inclination and Facial Landmarks

Ebrahim¹,

Harshima²,

Abahai³

2020

IJEAT

View full text Add to dashboard Cite

Driver sleepiness is one in all the most important causes of most of the accidents within the world. Detecting the driver’s eye weariness is the simplest way for detecting the somnolence of the driver. The prevailing systems in the literature cannot discover sleepiness in folks having lagophthalmos (condition that forestalls eyes from closing utterly) and monocular vision (person with one-eyed or sight loss in one eye). To solve this downside a Driver State Alert Control system is projected which makes the use of head-shoulder inclination, face detection, eye detection, emotion recognition, eye openness estimation and blink counts for detecting the sleepiness and collision liability associated with robust emotional factors. The projected framework endlessly analyses the head shoulder inclination and facial lineaments of the driver to alert the driver by activating the alarm once he/she is drowsy or showing emotion unstable to drive. The typical separation between upper eyelid and lower eyelid of adults suffering from lagophthalmos is about 1-5mm. The EAR (Eye Aspect Ratio) is calculated supporting this separately for each eye. Thus, the proposed technique can be used for folks with lagophthalmos and monocular vision. Also, the entities don’t solely rely on blink count to ascertain the sleepiness, collision risks related to robust emotional factors are considered too. The projected system which is enforced with one camera view on open CV and raspberry pi setting illustrates the systems good efficiency in particulars of authentic sleep identification results and thus reduces road mishaps. It is easy to place in any type of vehicle and price effective too.

show abstract

Section: B Estimating Vigilance Level By Using Eeg and Ecg Signalsmentioning

confidence: 99%

Section: F Eye Detection and Eye Openness Estimationmentioning

confidence: 99%

Driver State Alert Control using Head Shoulder Inclination and Facial Landmarks

Ebrahim¹,

Harshima²,

Abahai³

2020

IJEAT

View full text Add to dashboard Cite

show abstract

“…The proposed approach seems to be very promising since it is able to detect drowsiness level with a mean square error of 0.22, and it can predict the reaching of drowsiness level with a mean square error of 4.18 min. In [28], the authors proposed an algorithm which evaluates a driver's sleepiness level directly from cerebral activity. The results seem good, even though the authors confirmed that the method needs further investigation.…”

Section: Introductionmentioning

confidence: 99%

An Innovative Deep Learning Algorithm for Drowsiness Detection from EEG Signal

et al. 2019

View full text Add to dashboard Cite

The development of detection methodologies for reliable drowsiness tracking is a challenging task requiring both appropriate signal inputs and accurate and robust algorithms of analysis. The aim of this research is to develop an advanced method to detect the drowsiness stage in electroencephalogram (EEG), the most reliable physiological measurement, using the promising Machine Learning methodologies. The methods used in this paper are based on Machine Learning methodologies such as stacked autoencoder with softmax layers. Results obtained from 62 volunteers indicate 100% accuracy in drowsy/wakeful discrimination, proving that this approach can be very promising for use in the next generation of medical devices. This methodology can be extended to other uses in everyday life in which the maintaining of the level of vigilance is critical. Future works aim to perform extended validation of the proposed pipeline with a wide-range training set in which we integrate the photoplethysmogram (PPG) signal and visual information with EEG analysis in order to improve the robustness of the overall approach.

show abstract

“…This vision technology has achieved sufficient detection accuracy [31,32]. However, if the subjects wear glasses or do not look straight ahead, the camera cannot detect drowsy state robustly [33].…”

Section: Introductionmentioning

confidence: 99%

Classification of Drowsiness Levels Based on a Deep Spatio-Temporal Convolutional Bidirectional LSTM Network Using Electroencephalography Signals

Jeong

Lee

et al. 2019

Brain Sciences

View full text Add to dashboard Cite

Non-invasive brain-computer interfaces (BCI) have been developed for recognizing human mental states with high accuracy and for decoding various types of mental conditions. In particular, accurately decoding a pilot’s mental state is a critical issue as more than 70% of aviation accidents are caused by human factors, such as fatigue or drowsiness. In this study, we report the classification of not only two mental states (i.e., alert and drowsy states) but also five drowsiness levels from electroencephalogram (EEG) signals. To the best of our knowledge, this approach is the first to classify drowsiness levels in detail using only EEG signals. We acquired EEG data from ten pilots in a simulated night flight environment. For accurate detection, we proposed a deep spatio-temporal convolutional bidirectional long short-term memory network (DSTCLN) model. We evaluated the classification performance using Karolinska sleepiness scale (KSS) values for two mental states and five drowsiness levels. The grand-averaged classification accuracies were 0.87 (±0.01) and 0.69 (±0.02), respectively. Hence, we demonstrated the feasibility of classifying five drowsiness levels with high accuracy using deep learning.

show abstract

A Review on EEG-Based Automatic Sleepiness Detection Systems for Driver

Cited by 107 publications

References 124 publications

Driver State Alert Control using Head Shoulder Inclination and Facial Landmarks

Driver State Alert Control using Head Shoulder Inclination and Facial Landmarks

An Innovative Deep Learning Algorithm for Drowsiness Detection from EEG Signal

Classification of Drowsiness Levels Based on a Deep Spatio-Temporal Convolutional Bidirectional LSTM Network Using Electroencephalography Signals

Contact Info

Product

Resources

About