Driver Fatigue Research Articles

Hubungan Pengetahuan, Sikap dan Kelelahan Kerja dengan Perilaku Safety Riding pada Pengendara Go-Jek di Kota Malang

East Java is a Province in Indonesia with the highest of traffic accident cases on 2022 years, it is 3.555 cases. Efforts to prevent and reduce cases of traffic accidents can be done by safety riding. The application of safety riding can be realized if it was balanced with a good knowledge and attitude by drivers on the road. Along Malang City Road are dominated by Gojek drivers with an infinite population each year. Based on preliminary studies, it was known that Gojek drivers often experience work fatigue and supported by erratic work durations even exceeded standards, which can lead to unsafe behavior when driving. The purpose of this research was to determine a relationship between knowledge, attitudes and work fatigue with safety riding behavior on Gojek drivers in Malang City. This research method used a cross sectional design with a quantitative approach and accidental sampling technique. Sample of 60 Gojek drivers in Malang City. The bivariate test used a chi square test. The results showed that there was no relationship between knowledge and attitude with safety riding behavior (p=0,697 dan p=1,000), and there was a relationship between work fatigue with safety riding behavior (p=0,000). It can be concluded that the higher level of Gojek drivers fatigue, it make more unsafe their safety riding behavior. So, it was recommended to pay more attention an enough rest time and focus while working.

Advanced Vehicle Safety: A Prototype Circuit for Accident Prevention and Emergency Response

In contemporary society, the pursuit of robust accident prevention, detection, and reporting systems is paramount, particularly within the context of vehicular safety. This study introduces a meticulously designed prototype circuit, adaptable for deployment across diverse vehicle types. This intelligent circuitry endeavors to mitigate accidents and safeguard human lives by employing a multifaceted approach.The system's primary functions encompass the verification of seat belt usage and the assessment of alcohol consumption by the driver. Additionally, it incorporates a vibration sensor to detect accidents promptly. Complementing these features, the integration of GPS and GSM modules facilitates the rapid notification of emergency services, ensuring prompt assistance in the event of an accident.The core of this system is an Arduino microcontroller, orchestrating the interconnected components to process data and trigger actions based on predefined conditions. The circuit's performance has been rigorously tested, initially through simulation in Proteus software, and subsequently via real-world hardware implementation. Comparative analysis of software and hardware results lends insights into the system's functionality and reliability.The overarching objective of this study is to curtail accidents arising from intoxicated driving, unforeseen driver fatigue, and road obstructions. In instances of accidents, the electronic apparatus employed has the capacity to dispatch spontaneous and precise distress signals to law enforcement and medical personnel, thereby expediting casualty recovery and potentially saving lives. This research advances the fusion of technology and safety measures to augment road safety comprehensively.[6] Upadhyay, V., Gupta, S., Chaturvedi, S. and Singh, D. [2020], ‘Integrated accident prevention detectionand response system (iapdrs)’,International journal of engineering and advanced technology9(3), 2086–2089.[7] Vitkar, S. P., Banare, A. and Nadar, J. [2022], ‘Conceptual framework for accident detection and pre-vention’,Journal of Pharmaceutical Negative Resultspp. 7449–7455.[8] Wu, C., Zhang, P., Zhang, Z., Zheng, W., Xu, B., Wang, W., Yu, Z., Dai, X., Zhang, B. and Zang, K. [2023],‘Slip partitioning and crustal deformation patterns in the tianshan orogenic belt derived from gpsmeasurements and their tectonic implications’,Earth-Science Reviewsp. 104362.[9] Xu, X., Hu, X., Zhao, Y., Lü, X. and Aapaoja, A. [2023], ‘Urban short-term traffic speed prediction withcomplicated information fusion on accidents’,Expert Systems with Applicationsp. 119887.

Two-Stream Spatial–Temporal Transformer Networks For Driver Drowsiness Detection

<p>For driver drowsiness detection in the real world, the existing methods have good performance in general. However, when the face is blocked, the light is dim, and the driver’s head posture changes, the performance will deteriorate significantly. In this paper, a two-stream Spatial-Temporal transformer network intended to perform diver drowsiness detection task is proposed to solve the above problems. The spatial-temporal graph is extracted from the video and then the results are obtained from 2s-STTN. The model is a two-stream transformer network model. In our model, the Spatial Self-Attention module is used to learn the embedding of different facial landmarks, and the Temporal Self-Attention module is used to learn the correlation between the frames of facial feature points. Different activated facial landmarks are separated and recognized by class activation mapping technology. Each flow recognizes different activated facial features, extracts spatial or temporal features, and integrates the information about facial features, so as to improve the performance of the system. 2s-STTN can not only mine the long-term dependence of driver behavior from video, but also mine the driver drowsiness information provided by the unobstructed facial signs when the face is blocked. By conducting experiments and comparing our model with other models, it is demonstrated that the proposed model has good performance in driver drowsiness detection.</p> <p> </p>

Driving Behaviors, Cardiovascular Disease Risk Factors, Road Traffic Crashes, and Their Association with Fatigue in Urban Taxi Drivers

Driving Behaviors, Cardiovascular Disease Risk Factors, Road Traffic Crashes, and Their Association with Fatigue in Urban Taxi Drivers

ROAD SAFETY BY REAL TIME EYE DETECTION FOR DRIVER DROWSINESS

Automobile has become a major part in our lives. They are used for transportation of people, items and many other from one place to another. Even though the driver is tired, sleepy or has consumed alcohol he/she tries to drive a vehicle without any anxiety. As a result, it causes road accidents, injuries, loss of lives and damage to property. The proposed solution will be implemented using image processing, computer vision and facial recognition techniques to increase the efficiency and the accuracy of the system. To avoid such problems, an Eye-tracing system based on camera is proposed. By using this system, it detects and gives alert to the driver's Distraction or sleepiness. For this the dashboard is chosen as best position for camera without giving difficulties to the driver. The system will detect the driver's face and eyes by using Viola-Jones Algorithm that includes Hear Classifiers that shows advantage in processing accurate time and detection algorithms. A prepared framework is tested in a simulator provides real driving conditions in an indoor environment. The system is added in real-vehicle for testing it in an outdoor environment. If the system detects that the driver is under distraction or sleepiness it gives an alert to the driver by displaying message on a screen and an audible sound for more attention. Key Words: Computer vision and facial recognition techniques, Viola-jones algorithm, Stimulator.

EEG-Based Cross-Subject Driver Drowsiness Recognition With an Interpretable Convolutional Neural Network.

In the context of electroencephalogram (EEG)-based driver drowsiness recognition, it is still challenging to design a calibration-free system, since EEG signals vary significantly among different subjects and recording sessions. Many efforts have been made to use deep learning methods for mental state recognition from EEG signals. However, existing work mostly treats deep learning models as black-box classifiers, while what have been learned by the models and to which extent they are affected by the noise in EEG data are still underexplored. In this article, we develop a novel convolutional neural network combined with an interpretation technique that allows sample-wise analysis of important features for classification. The network has a compact structure and takes advantage of separable convolutions to process the EEG signals in a spatial-temporal sequence. Results show that the model achieves an average accuracy of 78.35% on 11 subjects for leave-one-out cross-subject drowsiness recognition, which is higher than the conventional baseline methods of 53.40%-72.68% and state-of-the-art deep learning methods of 71.75%-75.19%. Interpretation results indicate the model has learned to recognize biologically meaningful features from EEG signals, e.g., alpha spindles, as strong indicators of drowsiness across different subjects. In addition, we also explore reasons behind some wrongly classified samples with the interpretation technique and discuss potential ways to improve the recognition accuracy. Our work illustrates a promising direction on using interpretable deep learning models to discover meaningful patterns related to different mental states from complex EEG signals.

Deep Learning for Detecting Multi-Level Driver Fatigue Using Physiological Signals: A Comprehensive Approach.

A large share of traffic accidents is related to driver fatigue. In recent years, many studies have been organized in order to diagnose and warn drivers. In this research, a new approach was presented in order to detect multi-level driver fatigue. A multi-level driver tiredness diagnostic database based on physiological signals including ECG, EEG, EMG, and respiratory effort was developed for this aim. The EEG signal was used for processing and other recorded signals were used to confirm the driver's fatigue so that fatigue was not confirmed based on self-report questionnaires. A customized architecture based on adversarial generative networks and convolutional neural networks (end-to-end) was utilized to select/extract features and classify different levels of fatigue. In the customized architecture, with the objective of eliminating uncertainty, type 2 fuzzy sets were used instead of activation functions such as Relu and Leaky Relu, and the performance of each was investigated. The final accuracy obtained in the three scenarios considered, two-level, three-level, and five-level, were 96.8%, 95.1%, and 89.1%, respectively. Given the suggested model's optimal performance, which can identify five various levels of driver fatigue with high accuracy, it can be employed in practical applications of driver fatigue to warn drivers.

Detection of driver drowsiness using transfer learning techniques

Detection of driver drowsiness using transfer learning techniques

Computer vision-based driver fatigue detection framework with personalization threshold and multi-feature fusion

Computer vision-based driver fatigue detection framework with personalization threshold and multi-feature fusion

Face Positioned Driver Drowsiness Detection Using Multistage Adaptive 3D Convolutional Neural Network

Accidents due to driver drowsiness are observed to be increasing at an alarming rate across all countries and it becomes necessary to identify driver drowsiness to reduce accident rates. Researchers handled many machine learning and deep learning techniques especially many CNN variants created for drowsiness detection, but it is dangerous to use in real time, as the design fails due to high computational complexity, low evaluation accuracies and low reliability. In this article, we introduce a multistage adaptive 3D-CNN model with multi-expressive features for Driver Drowsiness Detection (DDD) with special attention to system complexity and performance. The proposed architecture is divided into five cascaded stages: (1) A three level Convolutional Neural Network (CNN) for driver face positioning (2) 3D-CNN based Spatio-Temporal (ST) Learning to extract 3D features from face positioned stacked samples. (3) State Understanding (SU) to train 3D-CNN based drowsiness models (4) Feature fusion using ST and SU stages (5) Drowsiness Detection stage. The Proposed system extract ST values from the face positioned images and then merges it with SU results from each state understanding sub models to create conditional driver facial features for final Drowsiness Detection (DD) model. Final DD Model is trained offline and implemented in online, results show the developed model performs well when compared to others and additionally capable of handling Indian conditions. This method is applied (Trained and Evaluated) using two different datasets, Kongu Engineering College Driver Drowsiness Detection (KEC-DDD) own dataset and National Tsing Hua University Driver Drowsiness Detection (NTHU-DDD) Benchmark Dataset. The proposed system trained with KEC-DDD dataset produces accuracy of 77.45% and 75.91% using evaluation set of KEC-DDD and NTHU-DDD dataset and capable to detect driver drowsiness from 256×256 resolution images at 39.6 fps at an average of 400 execution seconds.

Behavior Based Human Driver Fatigue Detection System Using Deep Learning

The "Driver Fatigue Detection System Using Deep Learning" project is an innovative initiative that aims to improve road safety by utilizing advanced technology. It addresses the problem of accidents caused by driver fatigue, which leads to numerous injuries and fatalities each year. The project focuses on developing a smart real- time monitoring system that employs deep learning algorithms to identify and counteract driver fatigue. This system uses sophisticated deep learning techniques, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks, to process a variety of data sources such as in-cabin camera feeds, vehicle performance metrics, and biometric data like eye movements and facial expressions. By analyzing this data, the system can accurately determine the driver's level of alertness and detect signs of fatigue. The key components of the system involve data preprocessing, extracting relevant features, training the model, and providing real-time alerts. When significant indicators of fatigue are detected, the system immediately issues alerts, such as audio warnings or adjustments to adaptive cruise control, to help the driver regain focus and prevent accidents caused by fatigue. This project not only showcases the adaptability of deep learning but also highlights its potential to revolutionize driver monitoring, thereby significantly improving road safety. Keywords: Fatigue Detection, Audio Warning, Safety.

Psychophysiology of Monotonous Driving, Fatigue and Sleepiness in Train and Non-Professional Drivers: Driver Safety Implications.

Fatigue and sleepiness are complex bodily states associated with monotony as well as physical and cognitive impairment, accidents, injury, and illness. Moreover, these states are often characteristic of professional driving. However, most existing work has focused on motor vehicle drivers, and research examining train drivers remains limited. As such, the present study psychophysiologically examined monotonous driving, fatigue, and sleepiness in a group of passenger train drivers and a group of non-professional drivers. Sixty-three train drivers and thirty non-professional drivers participated in the present study, which captured 32-lead electroencephalogram (EEG) data during a monotonous driving task. Fatigue and sleepiness were self-evaluated using the Pittsburgh Sleep Quality Index, the Epworth Sleepiness Scale, the Karolinksa Sleepiness Scale, and the Checklist of Individual Strength. Unexpectedly, fatigue and sleepiness scores did not significantly differ between the groups; however, train drivers generally scored lower than non-professional drivers, which may be indicative of individual and/or industry attempts to reduce fatigue. Across both groups, fatigue and sleepiness scores were negatively correlated with theta, alpha, and beta EEG variables clustered towards the fronto-central and temporal regions. Broadly, these associations may reflect a monotony-associated blunting of neural activity that is associated with a self-reported fatigue state.

Efficient automated method to extract EOG artifact by combining Circular SSA with wavelet and unsupervised clustering from single channel EEG

The emergence of affordable single-channel electroencephalography (EEG) headbands has introduced new possibilities for applications in brain–computer interface (BCI) systems and health monitoring. However, these EEG signals are often contaminated by electrooculogram (EOG) activity caused by eyelid blinking. This poses a challenge, especially in portable EEG devices that typically have limited or single EEG channels. The presence of eye-blink artifacts can mislead the diagnosis of brain state activity. Consequently, there is a growing demand to extract eye-blink artifacts from single-channel EEG signals. However, during the process of removing these artifacts from contaminated EEG signals, low-frequency artifact components in non-artifact regions are also inadvertently eliminated. In this work, an automated, robust and efficient framework is presented by combining Circular Singular Spectral Analysis (Ci_SSA) with wavelet analysis and unsupervised clustering. This framework aims to remove artifact segments while preserving the low-frequency content in non-artifact regions. Simulations were carried out on both synthetic and real data, and the results were compared with alternative methods. The performance of the proposed method is evaluated by metrics such as Relative Root Mean Square Error (RRMSE), Mean Absolute Error (MAE), Correlation Coefficient (CC) and Artifact Rejection Ratio (ARR) for synthetic signals, as well as Signal-to-Error Ratio (SER) and Artifact-to-Residue Ratio (AReR) for real EEG signals. After applying the proposed algorithm to filter the contaminated EEG signal, a noticeable enhancement in the detection accuracy of driver fatigue is observed as compared to the pre-filtering stage.

Deteksi Kantuk Untuk Keamanan Berkendara Berbasis Pengolahan Citra

Traffic accidents are increasing in Indonesia. One of the main causes of accidents is driver fatigue. Drowsiness generally occurs at night when the body needs rest. However, some are caused by fatigue during activities. When driving a car, this situation must be taken into account to avoid the number of accidents caused by fatigue. Because of these problems, we need a tool that can detect automatically whether the driver is asleep or conscious using the facial landmark method. The initial process starts with streaming the camera by the webcam which will be processed by the raspberry pi 3b to detect the face area using the eye aspect ratio then the algorithm on the eye aspect ratio is used to detect sleepy eyes with the output in the form of a speaker, where the speaker will emit a sound that can be changed according to at the will of the driver. This research succeeded in designing a drowsiness detection device and obtaining data from tests that have been carried out by detecting closed or closed eyes with accuracy results using the facial landmark method and eye aspect ratio detecting drowsiness with an average accuracy of 90.4%.

Driver drowsiness modeling based on spatial factors and electroencephalography using machine learning methods: A simulator study

Driver drowsiness is one of the leading causes of fatal road traffic accidents (RTA). While studies have illustrated the effectiveness of spatial criteria on driver drowsiness, the effects of these factors on drowsy driver behavior have yet to be mapped or spatially modeled properly. Meanwhile, driver behavior has been known as a major factor in the RTA occurrence. This paper investigated the effect of four spatial criteria of chainage, distance traveled after a horizontal curve, horizontal curvature, and slope on drowsy driver behavior in a simulated driving task. Accordingly, the drowsiness level on a monotone 108 km virtual expressway in northeastern Iran was determined by modeling the EEG data of 20 subjects. Four machine learning (ML) algorithms, namely bagged decision trees (BDT), multi-layer perceptron (MLP), random forest (RF), and support vector regression (SVR), were used to analyze electroencephalogram (EEG) signals and to estimate driver drowsiness based on spatial criteria. The results of the receiver operating characteristic curve (ROC) showed that BDT (0.925), RF (0.919), MLP (0.807), and SVR (0.706) had the highest accuracy in estimating drowsiness level on the virtual road using EEG signals, respectively. Using the estimated drowsiness level by BDT and spatial criteria values, ML algorithms were trained to map driver drowsiness on the Tehran-Mashhad road. Based on ROC results, MLP (0.921), BDT (0.918), RF (0.917), and SVR (0.896) had the most accurate performance in mapping driver drowsiness, respectively. Generated drowsiness level maps were validated, and the estimations of BDT and RF were more consistent with real drowsy driving accident black spots in the study area. In conclusion, mapping driver drowsiness by applying ML algorithms and spatial criteria detects high-risk areas and helps to improve road safety.

All‐Weather Self‐Powered Intelligent Traffic Monitoring System Based on a Conjunction of Self‐Healable Piezoresistive Sensors and Triboelectric Nanogenerators

AbstractA self‐powered and sustainable traffic monitoring system is highly required for future urban development. Herein, self‐healable piezoresistive sensors and triboelectric nanogenerators (TENGs) are constructed by in situ polymerization of polyvinyl alcohol‐polyacrylamide double network hydrogel in the presence of sodium alginate and tannic acid‐modified cellulose nanocrystals (denoted as PPC) for all‐weather self‐powered intelligent traffic monitoring applications. Because of hydrogen bonding and boron ester bonding, the resultant PPC‐based strain sensor can rapidly self‐heal and restore its sensing ability within 1 min with a self‐healing efficiency of 97.4%. Based on piezoresistive effect, the ions in sodium alginate endow the PPC‐based strain sensor with a relatively high gauge factor of 8.39, which can monitor the motion and fatigue of drivers. Based on triboelectrification effect, the PPC‐based TENG sensor can detect instantaneous vehicle speed, judge traffic accident liability, evaluate vehicle weight, and alert the driver to prevent accidents caused by drowsy driving. After partially replacing water in the PPC with glycerin, the resulting PPC‐based TENG sensor exhibits stable performance at temperatures ranging from ‐30 to 40 °C, ensuring its all‐weather monitoring ability. The all‐weather and self‐powered intelligent traffic monitoring system is promising for ensuring the security of future cities.

A Deep-Learning Approach to Driver Drowsiness Detection

Drowsy driving is a widespread cause of traffic accidents, especially on highways. It has become an essential task to seek an understanding of the situation in order to be able to take immediate remedial actions to detect driver drowsiness and enhance road safety. To address the issue of road safety, the proposed model offers a method for evaluating the level of driver fatigue based on changes in a driver’s eyeball movement using a convolutional neural network (CNN). Further, with the help of CNN and VGG16 models, facial sleepiness expressions were detected and classified into four categories (open, closed, yawning, and no yawning). Subsequently, a dataset of 2900 images of eye conditions associated with driver sleepiness was used to test the models, which include a different range of features such as gender, age, head position, and illumination. The results of the devolved models show a high degree of accountability, whereas the CNN model achieved an accuracy rate of 97%, a precision of 99%, and recall and F-score values of 99%. The VGG16 model reached an accuracy rate of 74%. This is a considerable contrast between the state-of-the-art methods in the literature for similar problems.

Research on the segmentation method of a highway landscape corridor zone

Highway landscaping is an important part of highway construction, which plays a role in highway engineering to ensure traffic safety, alleviate visual fatigue, manifest culture, and many other roles. In the actual highway landscape design, the concept of highway landscape planning and design remains unclear, the content is complex, and the design lags behind the main construction of the problem. Different landscape themes should be set for different sections of the road to enable the motorway landscape to play its role, and the reasonable division of the highway landscape paragraph nodes and the determination of different landscape themes are the keys to the problem. This study collects natural and humanistic materials along the highway, arranges and classifies them through the cluster analysis method, and then divides the highway landscape into paragraphs through the fusion of cluster analysis and node control method. Then, the landscape resources in the paragraphs are integrated and refined to define the theme of the paragraphs, the landscape of the paragraphs based on the theme of the paragraphs is generated to bring out the regional cultural connotation, and a highway paragraph landscape theme division process is constructed. Finally, based on the survey of the landscape status quo of the Zhunxing Highway, the landscape theme division method is applied to verify its scientificity. The research results show that the highway paragraph landscape division method based on the cluster analysis method can effectively reflect the landscape characteristics of different road sections, enrich the road landscape design content, reflect the regional cultural characteristics, reduce the phenomenon of driver fatigue due to the landscape content of a single driving, and protect the traffic safety of the highway. This method can effectively guide the highway landscape paragraph planning and node design, has simple operation, and has strong practicality.

The Influence of Visual Landscapes on Road Traffic Safety: An Assessment Using Remote Sensing and Deep Learning

Rapid global economic development, population growth, and increased motorization have resulted in significant issues in urban traffic safety. This study explores the intrinsic connections between road environments and driving safety by integrating multiple visual landscape elements. High-resolution remote sensing and street-view images were used as primary data sources to obtain the visual landscape features of an urban expressway. Deep learning semantic segmentation was employed to calculate visual landscape features, and a trend surface fitting model of road landscape features and driver fatigue was established based on experimental data from 30 drivers who completed driving tasks in random order. There were significant spatial variations in the visual landscape of the expressway from the city center to the urban periphery. Heart rate values fluctuated within a range of 0.2% with every 10% change in driving speed and landscape complexity. Specifically, as landscape complexity changed between 5.28 and 8.30, the heart rate fluctuated between 91 and 96. This suggests that a higher degree of landscape richness effectively mitigates increases in driver fatigue and exerts a positive impact on traffic safety. This study provides a reference for quantitative assessment research that combines urban road landscape features and traffic safety using multiple data sources. It may guide the implementation of traffic safety measures during road planning and construction.

Machine Learning Approaches for Detecting Driver Drowsiness: A Critical Review

Driver drowsiness is a serious issue that poses a significant threat to road safety, as it can lead to accidents and injuries. In response to this problem, a thorough review of machine learning techniques for detecting driver drowsiness was conducted. The review examined a range of techniques, including more recent approaches that use machine learning and deep learning algorithms as well as different types of data sources driver behaviours, physiological signals, and vehicle behaviours. The primary objective of this paper was to critically analyse and provide a comprehensive overview of the current state-of-the-art in detecting driver drowsiness, evaluate the effectiveness of each technique in terms of accuracy and reliability, and identify potential areas for future research and improvement. In order to achieve this, a systematic review of relevant research studies was undertaken. The review determined that machine learning-based techniques can improve the accuracy and reliability of driver drowsiness detection systems. However, certain limitations, such as the need for large amounts of data, feature extraction, and model structure, must be addressed. By overcoming these limitations, machine learning-based systems have the potential to enhance road safety and prevent accidents. In conclusion, this paper provides a thorough review of machine learning techniques for driver drowsiness detection, evaluates their effectiveness, identifies potential research directions, and highlights their significance and contribution to road safety. The insights gained from this study can be used to guide the development of more effective driver drowsiness detection systems and improve road safety for the community.