An attempt to prevent traffic accidents due to drowsy driving -Prediction of drowsiness by Bayesian estimation

Murata, Atsuo; Urakami, Yohei; Moriwaka, Makoto

doi:10.1109/sice.2014.6935295

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the models and the extracted features, which could achieve the best detection rate for each category, do not show any consistency, as evidenced by the following results: BPE 8 for threshold category (Acc = 90.4%), the combination of SHBP and BEP 5 and RBF-SVM model for binary classification category (Acc = 97.48%), Wavelet+ and LDA model of multi-class classification category (Acc = 97%) and LBP and RBF-SVR model for regression category (Acc = 93.2%). In addition, from the perspective of cross-category, we identified four studies for ground truth 1 [44,63,65,78] and four for ground truth 9 [73,77,81,84]. We found that the best overall accuracy for ground truth 1 was obtained using an RBF-SVR model, using log-transformed SHPB (1~30 Hz) features (Acc = 93.2%), and that for ground truth 9 by an RBF-SVM model, using SHPB (1~27 Hz); and BPE 5 features (Acc = 97.48%).…”

Section: Discussionmentioning

confidence: 99%

“…Hu et al employed the dominant frequency (DF), average power of the dominant peak (APDP), center of gravity frequency (CGF), frequency variability (FV), and mean power frequency (MPF) from δ band to β band as features [69]. Reports of using the MPF feature can also be found in [57,84]. Aboalayon et al proposed a method that uses integrated EEG (IEEG), SE, and STD, extracted from all the five EEG bands (δ to γ) as features [75].…”

Section: Fft+mentioning

confidence: 99%

“…Wierewille scale ≥ 3) Authors' self-assessment, based on the subjects' response during the experiment (The subjects need to accurately count the number of a visual stimulus shown [36]) Authors' self-assessment, based on the experimental video recording and the subjects' selfassessment [44] Authors' self-assessment, based on subjects' eye and head movements [35] Assessment of Driver's Vigilance and Warning according to Traffic Risk Estimation (AWAKE): Index ≥ 1 represents drowsiness [61] PERCLOS [76] Multi-class Subjects' self-assessment (ESS) [55,59] (Alert: ESS < 8; Drowsy: 8 ≤ ESS ≤ 11; Severe drowsy: ESS ≥ 24) Facial features that are manually identified by video recording (Wierewille scale) [24,70,79] Self-assessment (KSS) [71] RK (Wake, Stage I, Stage II) [72] Authors' self-assessment, based on their own experience [73] Unknown sleep scoring standard [40] Regression 1 Subjects' response time to lane departure event [62,77] Facial features that are manually identified by video recording [50] (Wierewille scale) Subjects' driving error index [31] Probabilistic PERCLOS [86,87] Self-assessment [56,84] (Subjects press buttons on the steering wheel when feeling arousal, a little bit drowsy and drowsy) Transfer 1 Subjects' response time to lane departure event [98]…”

Section: 𝐴𝑐𝑐mentioning

confidence: 99%

“…Several researchers employed a probabilistic model to predict driver drowsiness. For example, the dynamic Bayesian theory-based posterior probabilistic models (PPM) are proposed with PBP features by [91], and with FFT+ features by [57,84]. However, no mention was made of detection accuracies.…”

Section: Probabilistic Modelmentioning

confidence: 99%

See 3 more Smart Citations

Electroencephalogram-Based Approaches for Driver Drowsiness Detection and Management: A Review

Chung

2022

Sensors

View full text Add to dashboard Cite

Drowsiness is not only a core challenge to safe driving in traditional driving conditions but also a serious obstacle for the wide acceptance of added services of self-driving cars (because drowsiness is, in fact, one of the most representative early-stage symptoms of self-driving carsickness). In view of the importance of detecting drivers’ drowsiness, this paper reviews the algorithms of electroencephalogram (EEG)-based drivers’ drowsiness detection (DDD). To facilitate the review, the EEG-based DDD approaches are organized into a tree structure taxonomy, having two main categories, namely “detection only (open-loop)” and “management (closed-loop)”, both aimed at designing better DDD systems that ensure early detection, reliability and practical utility. To achieve this goal, we addressed seven questions, the answers of which helped in developing an EEG-based DDD system that is superior to the existing ones. A basic assumption in this review article is that although driver drowsiness and carsickness-induced drowsiness are caused by different factors, the brain network that regulates drowsiness is the same.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Fft+mentioning

confidence: 99%

Section: 𝐴𝑐𝑐mentioning

confidence: 99%

Section: Probabilistic Modelmentioning

confidence: 99%

See 2 more Smart Citations

Electroencephalogram-Based Approaches for Driver Drowsiness Detection and Management: A Review

Chung

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In 2011 and 2014, A. Murata. et al [40,41] proposed a Basic Bayesian Estimation (BBE) based posterior probabilistic model. They used shorter time window, 1 minute, to extract FFT-based EEG features and also conducted a simulated driving experiment to validate the proposed model.…”

Section: Discussionmentioning

confidence: 99%

Smartwatch-Based Wearable EEG System for Driver Drowsiness Detection

2015

View full text Add to dashboard Cite

Driver drowsiness is a major cause of mortality in traffic accidents worldwide. Many physiological signals have been proposed to detect driver drowsiness. Among these signals, Electroencephalographic (EEG) signal, which reflects the brain activities, is more directly related to drowsiness. Thus, many EEG-based driver drowsiness detection (DDD) models gained more and more attention in recent years. However, one limitation of these studies is that these models merely estimate discrete labels and thus did not allow for estimating relative severity of driver drowsiness. This study proposes Support Vector Machine based Posterior Probabilistic Model (SVMPPM) for DDD aimed at transforming the drowsiness level to any value of 0~1 instead of discrete labels. A fully wearable EEG system which consists of a Bluetooth-enabled EEG headband and a commercial smartwatch was used to evaluate the proposed model in real-time way. Twenty subjects who participated in one-hour monotonous driving simulation experiment were used to develop this model with fifteen subjects for building model and five subjects for testing model. According to a video-based reference, the proposed system obtained an accuracy of 91.25% accuracy for alert group (73 out of 80 datasets), 83.78% accuracy for early-warning group (93 out of 111 datasets) and 91.92% accuracy for full-warning group (91out of 99 datasets). These results indicate that the combination of proposed SVMPPM, EEG headband and wrist-worn smart device constitutes an effective, simple, and inexpensive wearable solution for DDD.Index Terms-Driver drowsiness detection, EEG, wearable devices, smartwatch, support vector machine.

show abstract