Driver Fatigue Research Articles

Research on Automatic Alignment for Corn Harvesting Based on Euclidean Clustering and K-Means Clustering

Aiming to meet the growing need for automated harvesting, an automatic alignment method based on Euclidean clustering and K-means clustering is proposed to address issues of driver fatigue and inaccurate driving in manually operated corn harvesters. Initially, the corn field environment is scanned using LiDAR to obtain point cloud data, which are then subjected to pass-through filtering and statistical filtering to remove noise and non-corn contour points. Subsequently, Euclidean clustering and K-means clustering methods are applied to the filtered point cloud data. To validate the impact of Euclidean clustering on subsequent clustering, two separate treatments of the obtained point cloud data were conducted during experimental validation: the first used the K-means clustering algorithm directly, while the second involved performing Euclidean clustering followed by K-means clustering. The results demonstrate that the combined method of Euclidean clustering and K-means clustering achieved a success rate of 81.5%, representing a 26.5% improvement over traditional K-means clustering. Additionally, the Rand index increased by 0.575, while accuracy improved by 57% and recall increased by 61%.

Internet of things assisted deep learning enabled driver drowsiness monitoring and alert system using CNN-LSTM framework

Abstract Driver fatigue has been generally viewed as a critical road safety factor and has been cited for contributing to a good percentage of traffic accidents. Developing systems to monitor and alert drowsy drivers is essential in reducing incidents. This research proposes a robust framework for driver drowsiness detection using a CNN-LSTM architecture developed by fusing facial landmark analysis with multiple aspect ratios. It uses, as key metrics in detecting drowsiness, the Eye Aspect Ratio (EAR), Pupil Circularity (PUC), the Mouth Aspect Ratio (MAR), and the Mouth over Eye Aspect Ratio (MOE). CNN-LSTM had been trained on YawDD, NITYMD, FL3D, and custom datasets. Data augmentation techniques such as flipping, scaling, shearing, rotation, brightness and contrast adjustment are used to generalize under different illumination conditions and driver postures. The system is implemented on NVIDIA’s 128-core Jetson Nano GPU platform and does real-time processing of video frames captured by a CSI camera. It detects eye closure and yawning as symptoms of driver fatigue and immediately raises an alert through vibrations in the seatbelt and pre-recorded voice messages. The Internet connectivity allows remote monitoring via mobile applications, making it safer by ensuring that alerts reach the driver and passengers. This CNN-LSTM model has been carefully tested for various scenarios, including day and night conditions, proving its effectiveness. The proposed framework indicated excellent performance concerning accuracy (98%), precision (95%), recall (93%), F1 score (94%), and AUC (99%), thereby revealing its efficiency in practical scenarios. By incorporating EAR, MAR, PUC, and MOE for the early detection of drowsiness in this CNN-LSTM architecture, the system will be able to alert the driver ahead of time so that necessary precautions can be taken to avoid an accident. The proposed approach enhances the driver's safety and is a scalable solution that adapts to different environments and populations.

Driving Fatigue Onset and Visual Attention: An Electroencephalography-Driven Analysis of Ocular Behavior in a Driving Simulation Task

Attentional deficits have tragic consequences on road safety. These deficits are not solely caused by distraction, since they can also arise from other mental impairments such as, most frequently, mental fatigue. Fatigue is among the most prevalent impairing conditions while driving, degrading drivers’ cognitive and physical abilities. This issue is particularly relevant for professional drivers, who spend most of their time behind the wheel. While scientific literature already documented the behavioral effects of driving fatigue, most studies have focused on drivers under sleep deprivation or anyhow at severe fatigue degrees, since it is difficult to recognize the onset of fatigue. The present study employed an EEG-driven approach to detect early signs of fatigue in professional drivers during a simulated task, with the aim of studying visual attention as fatigue begins to set in. Short-range and long-range professional drivers were recruited to take part in a 45-min-long simulated driving experiment. Questionnaires were used to validate the experimental protocol. A previously validated EEG index, the MDrow, was adopted as the benchmark measure for identifying the “fatigued” spans. Results of the eye-tracking analysis showed that, when fatigued, professional drivers tended to focus on non-informative portions of the driving environment. This paper presents evidence that an EEG-driven approach can be used to detect the onset of fatigue while driving and to study the related visual attention patterns. It was found that the onset of fatigue did not differentially impact drivers depending on their professional activity (short- vs. long-range delivery).

A Review of Current Research and Future Development of Autonomous Driving Technology

Abstract: At present, the automobile industry is undergoing a new round of technological revolution, and autonomous driving technology is also experiencing a period of rapid development, with very active research and technology iteration. Autonomous driving can prevent accidents that occur due to human errors such as inattentiveness and driver fatigue, thereby enhancing road safety. Additionally, autonomous technology helps alleviate traffic congestion and optimize flow by utilizing coordinated driving strategies, such as vehicle-to-vehicle communication (V2V) and vehicle-to-infrastructure communication (V2I), enabling platooning, intelligent rerouting, and other advanced driving techniques. The autonomous driving system can control the vehicle according to the optimal driving strategy, can drive the vehicle in a smoother way, optimize fuel consumption or power use, thereby reducing operating costs and improving travel experience, and has a wide range of application potential and potential social value. This paper summarizes the current research status and development trend of autonomous driving technology, summarizes the current research status of autonomous driving technology from the aspects of environmental perception, machine learning, control execution, etc., while also projecting future directions for the field. Advancements in this technology have the potential to revolutionize transportation, offering significant convenience and transforming daily life. Moreover, it can promote the development of major industries, increase national GDP, affect urban planning and layout, and even improve our living environment and benefit ecological construction.

Efficacy and feasibility of a breath sensor for detecting driver fatigue and drowsiness

Objectives Drowsiness has been shown to impair reaction times, decision-making abilities, and awareness of hazards critical to driving in a manner similar to the effects of driving under the influence of alcohol.1 Drowsy driving has been estimated to cause thousands of fatal crashes per year and has resulted in billions of dollars in lost revenue.2 However, while breathalyzers and ignition interlock devices can be used to mitigate the risk of drunk driving, no such devices are commercially available for roadside or behind-the-wheel diagnostics for drowsiness. To address this gap, the objective of this study was to demonstrate the efficacy and feasibility of a breath sensor to detect fatigue and drowsiness in a simulated driving environment. Data and methods Solid state breath sensors calibrated to previously identified breath biomarkers of fatigue and drowsiness were arrayed to determine changes in the breath profiles of subjects undergoing a full-motion driving simulation designed to elicit driver fatigue. A multi-sensor approach was used rather than relying on a single biomarker. The biomarker profile targeted compounds such as benzene derivatives (e.g., benzene, benzaldehyde, toluene, phenol), 2-butanone, and 2-ethyl-1-hexanol, among others. To address potential confounders such as eating/drinking, cigarette smoke, alcohol, and medical conditions like COPD or diabetes, the study was conducted under controlled conditions: participants refrained from eating for a couple of hours before the experiment, were nonsmokers, had not consumed alcohol for the past day, and had no known medical conditions. The breath biomarker profiles were then correlated with established drowsiness metrics, specifically the PERCLOS (Percentage of Eye Closure) and the Karolinska Sleepiness Scale (KSS). Results The breath sensor array collected breath biomarker profiles for 61 subjects. The biomarker profiles demonstrated a trend consistent with increasing PERCLOS and KSS responses (see Figure). During the 60-minute driving simulation designed to elicit driver fatigue, the PERCLOS showed a steady increase in response over time, while the KSS did not show an increase in perceived sleepiness until the 60 min mark. Similarly, the breath biomarker sensor response showed a significant increase at the 60-minute timepoint, consistent with increases in both the PERCLOS and the KSS, demonstrating evidence of increased driver fatigue and drowsiness. Conclusions These findings suggest that integrating drowsiness breath sensor arrays into vehicle systems could significantly enhance drowsiness detection, thereby reducing crashes, injuries, and fatalities. Moreover, the scalability and non-invasiveness of the proposed system lays the groundwork for broader applications, extending beyond vehicles to fields such as aviation and healthcare.

The method of driver fatigue detection in intelligent driving

Abstract. Fatigue driving is one of the main causes of traffic accidents, and currently available methods for detecting driver fatigue include sensor detection and intelligent driving assistance. The importance of driver fatigue detection lies in timely detection of the driver condition, which helps reduce fatigue driving accidents. The research on fatigue detection technology has also provided more sensors and data processing techniques for intelligent driving systems, promoting the improvement and optimization of intelligent driving systems. This article reviews the technologies available for fatigue detection, summarizes existing research on driver fatigue detection, analyzes various modal detection methods and the use of AI in fatigue monitoring, and proposes future research and development trends for fatigue detection systems. This paper discussed three parts of fatigue monitoring technology: sensor technology, data processing technology, and algorithm optimization, and analyzed their advantages, disadvantages, and future development trends. The conclusion is that fatigue monitoring technology should use the advantages of different sensors and combine them with intelligent driving. The accuracy of this technology still needs to be improved.

Accident Prevention System for Cars, Buses, Trucks

Driver drowsiness is a significant factor in road accidents, contributing to a large number of crashes annually. To enhance road safety, the development of a Drivers Drowsiness Detection System is essential. This system builds to detect early signs of lazyness in drivers and provide timely alerts to prevent accidents. The proposed system uses to track key indicators of drowsiness, such as eye closure, head position, yawning, and blink rate. By utilizing a camera-based real-time monitoring system, it continuously analyzes the driver’s facial expressions. The system employs cadcade algorithms to distinguish a featurebased object detection algorithm to detect objects from images between alert and drowsy states based on collected data. When drowsiness is detected, the system triggers alerts like audio warnings, seat vibrations, or even vehicle slowing mechanisms, depending on the integration. This technology has the potential to significantly reduce the number of road accidents related to driver fatigue and could be applied in both personal vehicles and commercial fleets. The implementation of such systems represents a critical step toward improving road safety and decreasing driver-related incidents. Nowadays it is very challenging to stay active all the time due to busy schedules. Falling asleep while driving can lead to serious consequences, accidents, and even death. This situation is much more common and therefore it is very important to solve this problem. So, to solve this problem, we developed a sleep alarm system for drivers. This system alerts the user when he falls asleep at the wheel, thus the main concern is preventing accidents and saving lives. This system is useful for long- distance travelers and late-night drivers.

Systematic review of cognitive impairment in drivers through mental workload using physiological measures of heart rate variability.

The intricate interplay between driver cognitive dysfunction, mental workload (MWL), and heart rate variability (HRV) provides a captivating avenue for investigation within the domain of transportation safety studies. This article provides a systematic review and examines cognitive hindrance stemming from mental workload and heart rate variability. It scrutinizes the mental workload experienced by drivers by leveraging data gleaned from prior studies that employed heart rate monitoring systems and eye tracking technology, thereby illuminating the correlation between cognitive impairment, mental workload, and physiological indicators such as heart rate and ocular movements. The investigation is grounded in the premise that the mental workload of drivers can be assessed through physiological cues, such as heart rate and eye movements. The study discovered that HRV and infrared (IR) measurements played a crucial role in evaluating fatigue and workload for skilled drivers. However, the study overlooked potential factors contributing to cognitive impairment in drivers and could benefit from incorporating alternative indicators of cognitive workload for deeper insights. Furthermore, investigated driving simulators demonstrated that an eco-safe driving Human-Machine Interface (HMI) significantly promoted safe driving behaviors without imposing excessive mental and visual workload on drivers. Recommendations were made for future studies to consider additional indicators of cognitive workload, such as subjective assessments or task performance metrics, for a more comprehensive understanding.

Predicting Drowsy Driver Break Taking During Long Drives.

The current study investigated the factors that predict drowsy drivers' decisions regarding whether to take breaks versus continue driving during long simulator drives. Driver drowsiness contributes to substantial numbers of motor vehicle crashes, injuries, and deaths. Previous research has shown that taking a nap and consuming caffeine can temporarily mitigate drowsiness and enable continued safe driving. Ninety drivers completed a 150-mile highway drive in a driving simulator after a day of partial sleep restriction. Drivers passed several simulated rest areas where they could take breaks. To replicate drivers' motivation to reach their destination safely but also quickly, drivers were told that they would be paid more for completing the simulated drive faster but would forfeit their payment if they crashed. Break taking was predicted by drivers' self-ratings of drowsiness and by the severity of lane departures. However, even at the highest levels of drowsiness, most drivers bypassed simulated rest areas without stopping. In comparing self-rated drowsiness to drowsiness measured by eye closures, drivers often under- and over-estimate their own level of drowsiness. Drowsy drivers use their own self-assessed drowsiness when deciding whether to take breaks. These self-assessments are often incorrect, and even when drivers rate themselves as severely drowsy they are unlikely to stop to rest during long drives. The findings reveal the need for effective drowsy driving countermeasures to motivate drivers to stop to take breaks. Results underscore the need to educate and/or motivate drivers to respond sooner to warning signs of drowsiness.

Clustering for mitigating subject variability in driving fatigue classification using electroencephalography source-space functional connectivity features.

While Electroencephalography (EEG)-based driver fatigue state classification models have demonstrated effectiveness, their real-world application remains uncertain. The substantial variability in EEG signals among individuals poses a challenge in developing a universal model, often necessitating retraining with the introduction of new subjects. However, obtaining sufficient data for retraining, especially fatigue data for new subjects, is impractical in real-world settings. In response to these challenges, this paper introduces a hybrid solution for fatigue detection that combines clustering with classification. Unsupervised clustering groups subjects based on their EEG functional connectivity in an alert state, and classification models are subsequently applied to each cluster for predicting alert and fatigue states. Results indicate that classification on clusters achieves higher accuracy than scenarios without clustering, suggesting successful grouping of subjects with similar functional connectivity characteristics through clustering, thereby enhancing the classification process. Furthermore, the proposed hybrid method ensures a practical and realistic retraining process, improving the adaptability and effectiveness of the fatigue detection system in real-world applications.&#xD.

Dynamic evolution of high-speed railway driver fatigue across scheduling shifts – a simulator study in China

ABSTRACT Scheduling significantly contributes to fatigue among high-speed rail (HSR) drivers, impacting both driving performance and safety. This study aims to analyse distinctiveness and evolutionary patterns of driver fatigue across different scheduling shifts, leveraging an HSR simulator and wearable devices. Through an extensive statistical examination, differences in most heart rate variability features were identified across shifts. The evolution of self-reported fatigue and physiological fatigue was investigated using a Markov chain and a hidden Markov model (HMM) that is extended using softmax regression, respectively. Results indicated a similarity in the initial fatigue state distribution and evolution trends across shifts, albeit with varying degrees of fluctuation. Morning shifts exhibited a higher likelihood of fatigue accumulation. The study revealed that even adequate pre-rest did not entirely counterbalance the impact of circadian rhythms. These findings may contribute to comprehending the temporal dynamics of driver fatigue evolution and offer insights for optimizing driver scheduling practices.

The Relationship Between Physical And Mental Workload On Job Fatigue In Maxim Car Drivers In Kupang City In 2024

Transportation is a system consisting of certain facilities along with the flow and control system that allows people or goods to move from one place to another efficiently at any time to support human activities. Indonesia as a developing country certainly has a very rapid development of services in the fields of land, sea and air transportation. Transportation owned by the Indonesian Nation certainly has innovations from past to present in order to advance transportation services, one of which is an online provider company. Online transportation companies offer transportation services such as online motorcycle taxis, online taxis, delivery of goods, food delivery and so on, thus making this service in demand by many people. Likewise in Kupang City where there are several online transportation options, one of which is Maxim car transportation which has the advantage of being quite cheap. The high demand for Maxim online transportation in Kupang City has an impact on the fatigue experienced by online transportation drivers. One of them is also felt by Maxim Mobil drivers. Based on the researcher's initial survey of Maxim drivers in Kupang city, fatigue often occurs in Maxim Car drivers due to the increase in Maxim Car users in Kupang City. This type of research is quantitative using analytic survey method and cros sectional research design. The sample in this study amounted to 81 respondents from a total population of 430 drivers selected using accidental sampling method. The results showed that there was no significant relationship between physical load and work fatigue and there was a significant relationship between mental load and fatigue in maxim car drivers in Kupang City.

Could music reduce driver fatigue? An investigation on music effects in various weather conditions

Fatigue impairs drivers’ performance and increases the occurrence likelihood of traffic incidents. This study aims to explore the capability of music as an intervention to reduce driver fatigue under different weather conditions by conducting a driving simulation experiment. The Eysenck Personality Questionnaire-Neuroticism (EPQ-N) scale is used to assess drivers’ personalities. A mixed factorial analysis of variance (ANOVA) is applied to analyze the influence of music on the driving behavior of different drivers under various weather conditions, including sunny, rainy, and foggy scenarios. Results indicated that drivers’ fatigue levels are reduced by the music under less complicated weather conditions, such as sunny and foggy conditions. The results also revealed that drivers with low EPQ-N scores could demonstrate better physical reactions and driving performance in sunny and rainy conditions, whereas those with high EPQ-N scores perform better in foggy conditions. These findings could help prevent traffic accidents caused by driving fatigue in sunny and foggy conditions through the strategic use of music.

Drowsy Driver Warn System Using OpenCV

The "Drowsy Driver Alarm" project leverages cutting-edge machine learning and face recognition technologies to address the critical issue of driver drowsiness on the road. Drowsy driving is a major cause of accidents and fatalities worldwide, highlighting the urgent need for effective countermeasures. Our research focuses on developing an intelligent system capable of detecting signs of drowsiness in real-time, providing timely warnings, and ultimately preventing accidents.

A multi-aware graph convolutional network for driver drowsiness detection

Driver drowsiness is a leading cause of traffic accidents. Utilizing deep neural networks, facial feature-based methods have achieved promising results in drowsiness detection. However, these methods suffer from two limitations. Firstly, they only focus on features from one or two facial regions, thus overlooking the relationships between features across different facial regions. Secondly, these methods struggle to account for individual driver variability, a common phenomenon where drivers may display dissimilar signs of drowsiness. These limitations lead to inaccurate drowsiness detection. To address these issues, in this paper we propose a multi-aware graph convolutional network (MAGCN). At the heart of MAGCN are two feature extractors: the class- and attention-aware extractor (CAAE), and the composite temporal-aware extractor (CTAE). The CAAE explores interdependencies within global and local facial features, while the CTAE leverages temporal information to capture dynamic changes in features. Moreover, a task-oriented graph convolutional network is designed to refine the drowsiness feature space for precise detection. Experiment results show that the proposed MAGCN exhibits competitive detection performance, when compared with state-of-the-art drowsiness detection approaches on two public datasets. In summary, the proposed model not only learns and analyzes correlations between features from various facial regions, but also tackles individual driver variability.

Fatigue Driving Detection Based on Facial Multi-Information Feature Fusion

Abstract Driver fatigue driving risk detection is one of the important areas of road traffic safety research in China. According to statistics, more than 40% of China’s traffic accidents every year are related to driver fatigue. In order to reduce this risk, this paper proposes a new method based on facial multi-information feature fusion to realize real-time fatigue driving detection. The method includes using the camera to capture the driver’s face image in real time, combining the face recognition in Dlib library and the detection of 68 key points, and implementing the face detection through OpenCV. Further, the opening and closing states of eyes and mouth were analyzed based on EAR and MAR algorithms, and a reasonable threshold was set to judge fatigue behavior. The HPE head pose estimation method is used to judge the fatigue state by considering the pitch Angle and roll Angle information. Finally, the improved rough set theory comprehensive evaluation method is used to carry out decision fusion processing on the feature results, and intuitively display the system detection results, which is convenient to evaluate the fatigue state of the current driver. The experimental results show that the multi-feature fusion detection method has good real-time performance, the accuracy rate is 94.55%, and the fatigue state can be detected quickly and accurately under various driving attitudes.

Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model

Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model

An optimized deep hybrid learning for multi-channel EEG-based driver drowsiness detection

Driver drowsiness is a severe issue that has contributed to numerous fatal accidents and injuries. Thus, detecting driver drowsiness is an important task that has been the subject of intensive research in recent years. There have been numerous proposed physiological signals for detecting driver drowsiness. However, the Electroencephalographic (EEG) signal is the most commonly used due to its direct relationship with drowsiness and its simplicity of acquisition. Recently, different Machine Learning (ML) and Deep Learning (DL) models have been proposed to detect driver drowsiness. This study utilized a publicly accessible dataset containing twelve healthy participants. Reading numerous research papers, we determined no specific EEG-based drowsiness preprocessing parameter values. Consequently, as a first step, and for the first time, to our knowledge in this field, we applied an optimization algorithm to determine the optimal preprocessing parameter values using a CNN model and accuracy as the objective function. The obtained results demonstrated the importance of selecting the correct values, as the mean accuracy score increased from 91% before optimization to 95% after optimization for the proposed CNN. The training time has been reduced. Also, as a second step, we have used the Optuna Hyperparameter optimization framework to select the optimal CNN Hyperparameters, which increased the mean accuracy from 95% to 97%. Finally, to take advantage of Deep Hybrid learning, we have fused the CNN “features extractor” with seven ML classifiers, with the CNN-SVM classifier achieving the highest average accuracy of 99.9%, and the training time has been reduced to a shallow value.

A Real-Time Embedded System for Driver Drowsiness Detection Based on Visual Analysis of the Eyes and Mouth Using Convolutional Neural Network and Mouth Aspect Ratio.

Currently, the number of vehicles in circulation continues to increase steadily, leading to a parallel increase in vehicular accidents. Among the many causes of these accidents, human factors such as driver drowsiness play a fundamental role. In this context, one solution to address the challenge of drowsiness detection is to anticipate drowsiness by alerting drivers in a timely and effective manner. Thus, this paper presents a Convolutional Neural Network (CNN)-based approach for drowsiness detection by analyzing the eye region and Mouth Aspect Ratio (MAR) for yawning detection. As part of this approach, endpoint delineation is optimized for extraction of the region of interest (ROI) around the eyes. An NVIDIA Jetson Nano-based device and near-infrared (NIR) camera are used for real-time applications. A Driver Drowsiness Artificial Intelligence (DD-AI) architecture is proposed for the eye state detection procedure. In a performance analysis, the results of the proposed approach were compared with architectures based on InceptionV3, VGG16, and ResNet50V2. Night-Time Yawning-Microsleep-Eyeblink-Driver Distraction (NITYMED) was used for training, validation, and testing of the architectures. The proposed DD-AI network achieved an accuracy of 99.88% with the NITYMED test data, proving superior to the other networks. In the hardware implementation, tests were conducted in a real environment, resulting in 96.55% and 14 fps on average for the DD-AI network, thereby confirming its superior performance.

A novel deep learning‐based technique for driver drowsiness detection

AbstractEvery year, many people lose their lives because of road accidents. It is evident from statistics that drowsiness is one of the main causes of a large number of car accidents. In our research, we wish to solve this major problem by measuring the drowsiness level of the human brain while driving. The study aims to develop a novel technique to detect different alertness levels (i.e., awake, moderately drowsy, and maximally drowsy) of a person while driving. A hybrid model using a stacked autoencoder and hyperbolic tangent Long Short‐Term Memory (TLSTM) network with attention mechanism is designed for this purpose. The designed model uses different biopotential signals, such as electroencephalography (EEG), facial electromyography (EMG), and different biomarkers, such as pulse rate, respiration rate galvanic skin response, and head movement to detect a person's alertness level. Here, the stacked autoencoder model is used for automated feature extraction. TLSTM is used to predict a person's alertness level using stacked autoencoder network‐extracted features. The proposed model can classify awake, moderately drowsy, and maximally drowsy states of a person with accuracies of 99%, 98.3%, and 98.6%, respectively. The novel contributions of the paper includes (i) incorporation of an attention mechanism into the TLSTM network of the proposed hybrid model to focus on the emphatic states to enhance classification accuracy, and (ii) utilization of EEG, facial EMG, pulse rate, respiration rate, galvanic skin reaction, and head movement pattern to assess a person's alertness level.