Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Total number of car accidents per year as observed by National Highway Traffic Safety Administration (NHTSA), USA
Source publication
Drowsiness/sleepiness is a serious issue that needs to be addressed for improvement in the safety of road driving. Past statistical data on road accidents has shown enormous increases in car crashes due to drowsy/sleepy feelings. This study comprehensively summarizes all aspects of the drowsy state and its effects during car driving: its symptoms,...
Context in source publication
Context 1
... Highway and Traffic Safety Administration (USA) has estimated that around 100,000 car crashes are due to drowsiness, sleepy feeling or fatigue [1,3,4]. Figure 1 plots the highway car crash data for the last 25 years in the USA. Sleep is a neurobiological need of healthy humans [5][6][7]. ...
Similar publications
As functional near-infrared spectroscopy (fNIRS) is developed as a neuroimaging technique and becomes an option to study a variety of populations and tasks, the reproducibility of the fNIRS signal is still subject of debate. By performing test–retest protocols over different functional tasks, several studies agree that the fNIRS signal is reproduci...
Assessing pain in patients unable to speak (also called non-verbal patients) is extremely complicated and often is done by clinical judgement. However, this method is not reliable since patients vital signs can fluctuate significantly due to other underlying medical conditions. No objective diagnosis test exists to date that can assist medical prac...
With an increase in consumer demand of video gaming entertainment, the game industry is exploring novel ways of game interaction such as providing direct interfaces between the game and the gamers’ cognitive or affective responses. In this work, gamer’s brain activity has been imaged using functional near infrared spectroscopy (fNIRS) whilst they w...
Introduction
Gestures characterize individuals' nonverbal communicative exchanges, taking on different functions. Several types of research in the neuroscientific field have been interested in the investigation of the neural correlates underlying the observation and implementation of different gestures categories. In particular, different studies h...
Functional near-infrared spectroscopy (fNIRS), a well-established neuroimaging technique, enables monitoring cortical activation while subjects are unconstrained. However, motion artifact is a common type of noise that can hamper the interpretation of fNIRS data. Current methods that have been proposed to mitigate motion artifacts in fNIRS data are...
Citations
... EEG may capture millisecond events and measure a person's mental tension, drowsiness, and emotional state [11,12]. The EEG is not prohibitively expensive and may quickly and painlessly be obtained from the scalp, making it popular in drowsiness and sleep investigations [13,14]. Earlier drowsiness detection techniques collected EEG signals from several brain regions using multi-channel EEG equipment [15]. ...
... Studies have shown that the fluctuation range and distribution range of blood oxygen saturation of drivers in fatigued driving are more extensive than those in everyday driving [33]. Therefore, distribution characteristics can be obtained by statistics of blood oxygen saturation of drivers in daily driving and fatigue driving, represented by mean value (Eq. ...
Driving fatigue is a physiological phenomenon that often occurs during driving. After the driver enters a fatigued state, the attention is lax, the response is slow, and the ability to deal with emergencies is significantly reduced, which can easily cause traffic accidents. Therefore, studying driver fatigue detection methods is significant in ensuring safe driving. However, the fatigue state of actual drivers is easily interfered with by the external environment (glasses and light), which leads to many problems, such as weak reliability of fatigue driving detection. Moreover, fatigue is a slow process, first manifested in physiological signals and then reflected in human face images. To improve the accuracy and stability of fatigue detection, this paper proposed a driver fatigue detection method based on image information and physiological information, designed a fatigue driving detection device, built a simulation driving experiment platform, and collected facial as well as physiological information of drivers during driving. Finally, the effectiveness of the fatigue detection method was evaluated. Eye movement feature parameters and physiological signal features of drivers’ fatigue levels were extracted. The driver fatigue detection model was trained to classify fatigue and non-fatigue states based on the extracted features. Accuracy rates of the image, electroencephalogram (EEG), and blood oxygen signals were 86%, 82%, and 71%, separately. Information fusion theory was presented to facilitate the fatigue detection effect; the fatigue features were fused using multiple kernel learning and typical correlation analysis methods to increase the detection accuracy to 94%. It can be seen that the fatigue driving detection method based on multi-source feature fusion effectively detected driver fatigue state, and the accuracy rate was higher than that of a single information source. In summary, fatigue driving monitoring has broad development prospects and can be used in traffic accident prevention and wearable driver fatigue recognition.
... The study conducted by (Singh & Bera, 2018) points to driver errors, such as speeding, fatigue, and alcohol consumption, as major causes of road accidents, emphasizing the collective responsibility of society to improve infrastructure, enforce stricter laws, and raising awareness about the dangers of reckless driving. To prevent accidents caused by drowsy driving, monitoring the driver's level of fatigue is essential, and technological advancements like driver monitoring systems with eye blink sensors are deployed to detect signs of drowsiness and provide timely warnings to drivers (Kamran et al., 2019;Selvaraj & Umakanth, 2021). ...
In the context of smart cities, ensuring road safety is crucial due to increasing urbanization and the interconnected nature of contemporary urban environments. Leveraging innovative technologies is essential to mitigate risks and create safer communities. Thus, there is a compelling imperative to develop advanced solutions to enhance road safety within smart city frameworks. In this article, we introduce a comprehensive vehicle safety framework tailored specifically for smart cities in the realm of Artificial Intelligence of Things (AIoT). This framework seamlessly integrates a variety of sensors, including eye blink, ultrasonic, and alcohol sensors, to bolster road safety. The utilization of eye blink sensor serves to promptly detect potential hazards, alerting drivers through audible cues and thereby enhancing safety on smart city roads. Moreover, ultrasonic sensors provide real time information about surrounding vehicle speeds, thereby facilitating smoother traffic flow. To address concerns related to alcohol consumption and its potential impact on road safety, our framework incorporates a specialized sensor that effectively monitors the driver's alcohol levels. In instances of high alcohol content, the system utilizes GPS and GSM technology to automatically adjust the vehicle's speed while simultaneously notifying pertinent authorities for prompt intervention. Additionally, our proposed system optimizes inter-vehicle communication in smart cities by leveraging Li-Fi technology, enabling faster and more efficient data transmission via visible light communication (VLC). The integration of Li-Fi enhances connectivity among connected vehicles, contributing to a more cohesive and intelligent urban transportation network. Through the structured integration of AIoT technologies, our framework lays a robust foundation for a safer, smarter, and more sustainable future in smart city transportation. It offers significant advancements in road safety and establishes the groundwork for further enhancement in intelligent urban transportation networks.
... Drowsiness is defined as a person's tendency to fall asleep. This situation is especially critical in driving scenarios, where the dangerous combination of driving and sleepiness commonly happens [1]. Particularly, the National Highway Traffic Safety Administration (NHTSA) reported between 2013 and 2019 a total of 5593 fatalities in motor vehicle crashes involving drowsy drivers. ...
Driver drowsiness is a significant concern and one of the leading causes of traffic accidents. Advances in cognitive neuroscience and computer science have enabled the detection of drivers’ drowsiness using Brain-Computer Interfaces (BCIs) and Machine Learning (ML). However, the literature lacks a comprehensive evaluation of drowsiness detection performance using a heterogeneous set of ML algorithms, being also necessary to study the performance of scalable ML models suitable for groups of subjects. To address these limitations, this work presents an intelligent framework employing BCIs and features based on electroencephalography for detecting drowsiness in driving scenarios. The SEED-VIG dataset is used to evaluate the best-performing models for individual subjects and groups. Results show that Random Forest (RF) outperformed other models used in the literature, such as Support Vector Machine (SVM), with a 78% f1-score for individual models. Regarding scalable models, RF reached a 79% f1-score, demonstrating the effectiveness of these approaches. This publication highlights the relevance of exploring a diverse set of ML algorithms and scalable approaches suitable for groups of subjects to improve drowsiness detection systems and ultimately reduce the number of accidents caused by driver fatigue. The lessons learned from this study show that not only SVM but also other models not sufficiently explored in the literature are relevant for drowsiness detection. Additionally, scalable approaches are effective in detecting drowsiness, even when new subjects are evaluated. Thus, the proposed framework presents a novel approach for detecting drowsiness in driving scenarios using BCIs and ML.
... Karolinska Sleepiness Scale (KKS) (Kaida et al., 2006) and Chalder Fatigue Scale (Chalder) (Cella and Chalder, 2010) were presented at the arrival and after each driving task for fatigue rating. From a conceptual and psychological point of view, mental fatigue and drowsiness are slightly different even if they are usually considered just as two different degrees of intensity on a scale from alertness to sleepiness (Kamran et al., 2019). Because of that, the redundant choice to ask the participants to fill out both questionnaires was made because, being contiguous phenomena, they are often hard to distinguish between each other, especially if considering the poor sensitivity of subjective measures. ...
The human factor plays a key role in the automotive field since most accidents are due to drivers' unsafe and risky behaviors. The industry is now pursuing two main solutions to deal with this concern: in the short term, there is the development of systems monitoring drivers' psychophysical states, such as inattention and fatigue, and in the medium-long term, there is the development of fully autonomous driving. This second solution is promoted by recent technological progress in terms of Artificial Intelligence and sensing systems aimed at making vehicles more and more accurately aware of their “surroundings.” However, even with an autonomous vehicle, the driver should be able to take control of the vehicle when needed, especially during the current transition from the lower (SAE < 3) to the highest level (SAE = 5) of autonomous driving. In this scenario, the vehicle has to be aware not only of its “surroundings” but also of the driver's psychophysical state, i.e., a user-centered Artificial Intelligence. The neurophysiological approach is one the most effective in detecting improper mental states. This is particularly true if considering that the more automatic the driving will be, the less available the vehicular data related to the driver's driving style. The present study aimed at employing a holistic approach, considering simultaneously several neurophysiological parameters, in particular, electroencephalographic, electrooculographic, photopletismographic, and electrodermal activity data to assess the driver's mental fatigue in real time and to detect the onset of fatigue increasing. This would ideally work as an information/trigger channel for the vehicle AI. In all, 26 professional drivers were engaged in a 45-min-lasting realistic driving task in simulated conditions, during which the previously listed biosignals were recorded. Behavioral (reaction times) and subjective measures were also collected to validate the experimental design and to support the neurophysiological results discussion. Results showed that the most sensitive and timely parameters were those related to brain activity. To a lesser extent, those related to ocular parameters were also sensitive to the onset of mental fatigue, but with a delayed effect. The other investigated parameters did not significantly change during the experimental session.
... steering wheel movement) [12]. Kamran et al. [13] comprehensively summarised the possible physiological cause of drowsiness, the related symptoms for crashes, and physiological strategies related to mishaps due to drowsiness. For this safety reason, sensors such as cameras, steering wheel-, breaking-, and pressure-based sensors are installed in the car to detect drowsiness. ...
Curbing road accidents havealways been one of the utmost priority of nations worldwide. In Malaysia, the Traffic Investigation and Enforcement Department reported that Malaysia’s total number of road accidents haveincreased from 373,071 to 533,875 in the last decade. One of the significant causes of road accidentsis the driver’s behaviors. However, to regulate drivers’ behavior by the enforcement team or fleet operatorsischallenging, especially for heavy vehicles. In our research, we have proposed the Internet of Things (IoT) scalability framework and its’ emerging technologies to monitor and alert driver’s behavioral and driving patterns to reduceroad accidents. To prove this work, we have implementeda lane tracking,and iris detection algorithm, to monitor and alert the driver’s behavior when the vehicle sways away from the lane, and to detect if the driver is feeling drowsy. We implemented electronic devices such as cameras, a global positioning system module, a global system communication module, and a microcontroller as the hardware for an intelligent system in the vehicle. We also appliedface recognition for person identification using the same in-vehicle camera and recorded the working duration for authentication and operation health monitoring. With the GPS module, we monitored and alerted against permissible vehicle’s speed accordingly. We integrated IoT on the system for the fleet centre to monitor and alert the driver’s behavioral activities in real-time through the user access portal. We have validated it successfully on Malaysian roads. The outcome of this pilot project ensuresthe safety of drivers, public road users, and passengers. The impact of this framework leads to a new regulation by the government agencies towards merit and demerit system, real-time fleet monitoring of intelligent transportation systems, and socio-economy such as cheaper health premiums. The big data can be used to predict the driver’s behavioral in the future.
... In safety-critical environments, such as medicine, nuclear industry or transportation, specifically in aviation and space flight, mental fatigue and drowsiness are considered major human factors that constitute a source of risk (Baykaner et al., 2015) contributing to incidents (Di Flumeri et al., 2022;Kamran et al., 2019). Recent works prove that fatigue influences both motor and cognitive performance (Abd-Elfattah et al., 2015;Rosa et al., 2022), followed by an impairment of vigilance, memory and prolongation of reaction times (RTs) (Bendak and Rashid, 2020;Chen et al., 2019). ...
... For scientific purposes more accurate methods of monitoring fatigue are available (Chen et al., 2019); (Kamran et al., 2019;Marchitto et al., 2016), based on more intrusive physiological measurements, such as electroencephalography (EEG), electrooculogram (EOG), electrocardiography (ECG), or pulseoximetry (Begum, 2013). One of the most reliable methods in identification of mental fatigue is EEG data analysis, with several indices selected as candidates for the mental fatigue/drowsiness detection. ...
... However, these are not universally accepted indicators, and discrepancies exist among different studies. To name a few, these include increases in frontal theta activity (Chai et al., 2016;Onton et al., 2005), decreases in the alpha band over parietal and frontal brain sites (Borghini et al., 2014), alpha and theta changes at Oz channel (Pal et al., 2008), changes of alpha power between the initial and final stages (Gharagozlou et al., 2015), alpha spindles (short narrowband bursts) (Simon et al., 2011), alpha and beta power at O2 location (Li and Chung, 2014), Global Field Power in the alpha band (Di Flumeri et al., 2022) and other spectral power measures and EEG-based indexes (see (Kamran et al., 2019) for a comprehensive review). ...
The article summarizes the results of an EEG validation study following the proposal of a methodology for identification and monitoring of air traffic controllers' fatigue level based on layered-voice analysis (LVA) described in the initial study (Kouba et al., 2020). 10 licensed air traffic controllers from APP Prague participated in the experiment that enabled the comparison of the state of vigilance during certain parts of the shifts rostering cycle. Methods for subjective assessment (Karolinska Sleepiness Scale) of fatigue were used as well as objective methods (Psychomotor Vigilance Task, Oddball Task and EEG power spectra analysis) to compare with the outputs of voice analysis. Our results indicate that the method of voice analysis reacts to changes in a person's mental state. Based on the results of current study, voice parameters marked as Stress and/or Energy levels seem to be the most suitable candidates for fatigue detection as shown by comparative statistics and correlations. The change in these parameters best reflected changes observed in EEG power in different band both during the cognitive testing and during the simulation exercise. According to our research voice analysis is able to identify differences in wakefulness and fatigue, as its results correlate with changes in brain activity. As our experiment likely induced not only fatigue but also changes in other mental states such as perceived stress which could have been reflected in the changes of other voice parameters , this could be the focus of the following studies.
... In the study "A Comprehensive Study of Fatigue and Sleep" by M. Ahmad Kamran et al [6] research the causes, symptoms, and signs of drowsiness, fatigue, and poor sleep to support an accurate sleep recognition method to help reduce car accidents. The authors have shown four stages of sleep, with each stage, the body will fall into deeper states of relaxation with different manifestations that can be recognized through methods such as electrocardiogram (ECG), electrooculogram (EOG), head movements, jaw movements, and eye blinks. ...
... In addition, M. Ahmad Kamran et al. also showed that, when leaving the state of fatigue or drowsiness, the distance between the eyelids (upper and lower eyelids) tends to decrease gradually with the degree of severity [6]. Accordingly, we record the average eye height during the first period of the lesson, or when a student's face appears on the desk, the system will record and calculate this average height and use it to compare with other times of the lesson or exam. ...
... Also, according to the study of M. Ahmad Kamran et al [6], the fact that students fall asleep on the study table means that sleep is falling into the 2nd stage of sleep, with the first stage being symptoms of signs and symptoms of drowsy. In stages 3 and 4 of sleep, it is tough for students to be awakened by low-intensity external influences, which is especially serious when most students participating in online classes and exams will choose Quiet spaces with little parental supervision. ...
Students who do not pay attention when studying negatively affect their learning results and will also adversely affect their test results. Usually, teachers will remind students if they detect that students are not paying attention. However, for online or face-to-face classes with large numbers of students, it can be challenging to know how focused students are on teachers for online or face-to-face classes with large numbers of students. In this article, a Smart Desk is designed by embedded and AI technologies equipped with hybrid processors and webcam, touch screen to detect Inattentive Students during studying and examinating time in the classroom. However, the embedded software is implemented on Smart Desk to be able to detect sleepiness, falling asleep, iris direction, face direction, and identify students who are inattentive. When detecting Inattentive Students, the system will remind and alert the teacher to know the student’s situation. The model that has been built is based on an embedded device using the 64-bit ARM Quad-Core, 128 GPUs, and 4GB of RAM with the detection algorithm of Inattentive Students. The test scenario in this experiment has reached to high video speed of 8 ~ 18 fps and 89 ~ 97% accuracy in a range of lighting conditions from 300–400 lux. This system is effectively applied in a real application in Smart Desk to support teachers to know their students, whether Inattentive or more attentive, while studying and taking examinations in their class.
... The study "A Comprehensive Study of Fatigue and Sleep" by M. Ahmad Kamran et al [5], Research into the causes, symptoms, and signs of drowsiness, fatigue, and poor sleep to assist in providing an accurate method of sleep recognition to help reduce car accidents. The detection of signs of drowsiness was synthesized by the authors' group of many assessment methods such as the Epworth sleepiness scale, Standord's sleepiness scale, calculating the degree of eye movement by EOG method, transducing jaw movement, head, and blinking action. ...
... Drowsiness [5] is a symptom indicating a state of wanting or yearning to sleep for some time. Many systems have been studied to detect sleepiness such as heart rate, breathing rate, brain wave measurement, etc. ...
... In addition, the comprehensive study by M. Ahmad Kamran et al showed that "In fatigue situations, the distance between the eyelids tends to decrease" [5], from which we also recorded the altitude average eye level, which is the distance between the upper and lower eyelids, was recorded at the beginning of the session (first 100 frames) because at this time the percentage of students who were awake was the greatest. This record will be used by the system to compare and warn the teacher when it notices that the average height of the students' eyes is decreasing to only 60% of the recorded height. ...
Students who do not concentrate when studying will find it difficult to absorb the lesson well. Usually, in order for all students to focus on the lesson, the teacher during the lecture will have to observe the students and come up with solutions if the students are not paying attention. However, in the case of many students, following to detect students who have not paid attention to the lesson is a task that requires teachers to put in a lot of effort. In this article, we propose to use machine learning algorithms based on the MediaPipe library to analyze facial features and expressions, including eyes closed, yawning, not looking at the board, or absent, to determine if students have been distracted or not to build a system to assist teachers in detecting student lack of concentration when studying in Smart Desks (Student desks are designed based on embedded devices, with cameras and screens). When detecting that students are not paying attention while studying, the system will warn the teacher so that the teacher can provide solutions. We tested the algorithm on a Jetson Nano embedded device with configuration [Quad- Core 64-bit ARM, 128-bit GPU CUDA, 4GB RAM] and obtained FPS: 8 ~ 18, accuracy achieved from 89 ~ 97% in lighting conditions from 300-400 lux
... Some of the physiological signals that have been used are electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram (EOG), photoplethysmogram (PPG), galvanic skin response (GSR), and functional near-infrared spectroscopy (FNIRS) [14][15][16][17][18][19][20]. EEG signals are used to analyze brain states such as sleep, alertness, fatigue, and stress and are most commonly used in sleep-related research [21]. Various time and frequency features of EEG signals have been used for drowsiness detection in previous studies. ...
Drowsiness is one of the main causes of road accidents and endangers the lives of road users. Recently, there has been considerable interest in utilizing features extracted from electroencephalography (EEG) signals to detect driver drowsiness. However, in most of the work performed in this area, the eyeblink or ocular artifacts present in EEG signals are considered noise and are removed during the preprocessing stage. In this study, we examined the possibility of extracting features from the EEG ocular artifacts themselves to perform classification between alert and drowsy states. In this study, we used the BLINKER algorithm to extract 25 blink-related features from a public dataset comprising raw EEG signals collected from 12 participants. Different machine learning classification models, including the decision tree, the support vector machine (SVM), the K-nearest neighbor (KNN) method, and the bagged and boosted tree models, were trained based on the seven selected features. These models were further optimized to improve their performance. We were able to show that features from EEG ocular artifacts are able to classify drowsy and alert states, with the optimized ensemble-boosted trees yielding the highest accuracy of 91.10% among all classic machine learning models.
