Driver Safety Research Articles

Sistem Manajemen Daya Listrik Pada Pengamanan Kendaraan Berbasis Android

The power safety system is a series of monitoring and control technologies in the form of features designed to anticipate and increase power safety for drivers and maintain the stability of the vehicle's electrical system while driving. Several power security systems are generally found in most vehicles. Power security systems are a feature in maintaining the vehicle's electrical condition in addition to security devices for a machine against criminal acts such as theft on vehicles which are increasingly common nowadays so it is hoped that it will be able to minimize the shortage of power system requirements on the machine with control and monitoring carried out using an Android-based mobile application. For this reason, this research will create a power monitoring application and security system for vehicle engines in anticipation of additional power consumption when installing engine security against criminal acts through application-based control. The output produced in this research is an Android mobile application as well as a security system device along with power consumption calculations.

MmDrive: Fine-grained Fatigue Driving Detection Using mmWave Radar

Early detection of fatigue driving is pivotal for the safety of drivers and pedestrians. Traditional approaches mainly employ cameras and wearable sensors to detect fatigue features, which are intrusive to drivers. Recent advances in radio frequency (RF) sensing enable non-intrusive fatigue feature detection from the signal reflected by driver’s body. However, existing RF-based solutions only detect partial or coarse-grained fatigue features, which reduces the detection accuracy. To tackle the above limitations, we propose a mmWave-based fatigue driving detection system, called mmDrive, which can detect multiple fine-grained fatigue features from different body parts. However, achieving accurate detection of various fatigue features during driving encounters practical challenges. Specifically, normal driving activities and driver’s involuntary facial movements inevitably cause interference to fatigue features. Thus, we exploit unique geometric and behavioral characteristics of fatigue features and design effective signal processing methods to remove noises from fatigue-irrelevant activities. Based on the detected fatigue features, we further develop a fatigue determination algorithm to decide the driver’s fatigue state. Extensive experiment results from both simulated and real driving environments show that the average accuracy for detecting nodding and yawning features is about 96%, and the average errors for estimating eye blink, respiration, and heartbeat rates are around 2.21 bpm , 0.54 bpm , and 2.52 bpm , respectively. And the accuracy of the fatigue detection algorithm we proposed reached 97.63%.

Assessment of musculoskeletal disorders and contributing factors in professional drivers

Musculoskeletal disorders (MSDs) are the leading global cause of disability and pose a significant public health issue, particularly among professional drivers who are prone to such conditions due to prolonged sitting, poor posture, and exposure to whole-body vibrations. The objectives of this study are to assess the demographic, general, lifestyle, and wellness profiles of professional drivers, gauge their work environment characteristics, and measure the proportion of musculoskeletal symptoms using the modified Nordic questionnaire. This descriptive study collected data from 67 professional drivers at major bus stands in Lahore using a structured questionnaire. The data were analyzed using frequencies, percentages, means, and standard deviations. The results revealed that the drivers, predominantly middle-aged (average age 39.72 ± 9.53 years) and married (95.52%), reported limited formal education (average 7.56 ± 3.91 years). Lifestyle assessments indicated high rates of smoking (61.19%) and frequent consumption of soft drinks (88.06%). In their work environment, most drivers (68.66%) worked daytime shifts, and a significant proportion (56.72%) experienced vibration exposure. The most frequently reported musculoskeletal symptoms were in the lower back (58.21% in the past 12 months, 43.28% in the past 7 days) and hips/thighs (61.19% in the past 12 months), impacting their ability to work. These findings highlight the critical need for targeted ergonomic and lifestyle interventions to improve the occupational health and safety of drivers, potentially reducing musculoskeletal discomfort and enhancing overall well-being and productivity.

Impact of Monitoring Requests on Publics’ Assignment of Blame and Praise towards ADS Level 3 Vehicles

As vehicle automation capabilities increase, driving control shifts from the human to the vehicle system. However, concerns arise regarding responsibility following critical events and the publics’ trust and acceptance of vehicles equipped with automated driving systems (ADS). The current study examined how participants assigned blame and praise to ADS-equipped vehicles and human drivers following collisions or near-misses and how these attributions were impacted by a virtual driving assistant that administered monitoring requests. Based on literature, our primary hypothesis was that more blame would be assigned to the human and more praise assigned to the ADS when the driving assistant was present. Additionally, we hypothesized greater reported trust towards ADS-equipped vehicles when the driving assistant was present. Participants read vignettes of automated driving, watched corresponding videos, and then self-reported trust, acceptance, anthropomorphism, and assignment of blame and praise. All hypotheses were supported indicating that significant effects were observed: participants assigned greater blame to the human when asked to actively monitor the driving environment and assigned greater praise to the ADS when it alerted the human driver. Additionally, participants reported greater trust and anthropomorphism of the ADS when the driving assistant was present. These findings suggest that explicitly communicating monitoring responsibility through a driving assistant significantly impacts the publics’ opinion of responsibility following critical events. These findings provide initial support for a solution to improve driver safety as well as policy implications regarding positive perceptions and the adoption of ADS-equipped vehicles.

Innovative stacked liquid crystal panel for automotive display: driver-oriented privacy and passenger accessibility.

We propose a switchable privacy display with liquid crystals for co-driver displays (CDDs) in vehicles. The display minimizes driver distraction while allowing the co-driver to enjoy infotainment content. By combining electrically controllable birefringence (ECB) and hybrid-aligned nematic (HAN) cells, we control the viewing angle of the display. Our device achieves an operating angle of 30°, effectively blocking the driver's view while providing a wide viewing angle for the co-driver. It maintains excellent transmittance properties in privacy and public modes, with symmetric luminance characteristics. The versatility of the proposed display extends to various technologies like LCDs, OLEDs, and micro-LEDs. This switchable privacy display has the potential to enhance driver safety and infotainment experiences in vehicles.

A safety-oriented framework for sound event detection in driving scenarios

The safety of drivers has become increasingly important in today's rapidly evolving transportation landscape, especially with the rise of autonomous and smart vehicles. This paper proposes a safety-oriented framework for sound event detection in smart vehicles using deep learning models. The goal of this framework is to increase driver awareness, prevent accidents, and provide acoustic forensic analysis. To achieve this, a meaningful taxonomy of event classes in a driving scenario is introduced, taking into account the event classes that are known to be related to major driving distractors. Based on this taxonomy, a dataset has been created to train and evaluate a fully-convolutional sound event detection model that was inspired by the well-known YOLO vision model. Experimental results demonstrated that the proposed model offers competitive results, outperforming a state-of-the-art baseline using recurrent connections. This comprehensive framework for sound event detection in smart vehicles aligns with the recommended directions for future mobility scenarios and has the potential to significantly improve the safety and performance of smart vehicles.

Blink-related EEG activity measures cognitive load during proactive and reactive driving

Assessing drivers’ cognitive load is crucial for driving safety in challenging situations. This research employed the occurrence of drivers’ natural eye blinks as cues in continuously recorded EEG data to assess the cognitive workload while reactive or proactive driving. Twenty-eight participants performed either a lane-keeping task with varying levels of crosswind (reactive) or curve road (proactive). The blink event-related potentials (bERPs) and spectral perturbations (bERSPs) were analyzed to assess cognitive load variations. The study found that task load during reactive driving did not significantly impact bERPs or bERSPs, possibly due to enduring alertness for vehicle control. The proactive driving revealed significant differences in the occipital N1 component with task load, indicating the necessity to adapt the attentional resources allocation based on road demands. Also, increased steering complexity led to decreased frontal N2, parietal P3, occipital P2 amplitudes, and alpha power, requiring more cognitive resources for processing relevant information. Interestingly, the proactive and reactive driving scenarios demonstrated a significant interaction at the parietal P2 and occipital N1 for three difficulty levels. The study reveals that EEG measures related to natural eye blink behavior provide insights into the effect of cognitive load on different driving tasks, with implications for driver safety.

A Federated Learning Approach With Imperfect Labels in LoRa-Based Transportation Systems

Intelligent Transportation System (ITS) helps to improve vehicle health, driver safety, and passenger comfort. Remotely sharing the information of ITS to train the machine and deep learning models hamper data privacy and generate security threats to the passenger, driver, and vehicle owners. Moreover, sharing the information requires huge networking resources such as high data rate, low latency, and low packet loss. Federated learning provides privacy-preserving model training on the vehicle without sharing the information. However, due to poor annotation mechanisms, federated learning may suffer from imperfect labels. This paper proposes a federated learning approach for ITS that can handle imperfect labels in the datasets of the participants. The approach also uses a Long-Range network to provide communication efficient connectivity. The approach initially estimates class-wise centroids of the datasets at the participants and server and then identifies participants with imperfect labels using similarity scores. Such participants demand the fraction of the correctly annotated dataset at the server to improve performance. We further derive the expression for the optimal fraction of the dataset requested by a participant. We finally verify the effectiveness of the proposed approach using the existing model and publicly available dataset.

Distracted driving recognition based on functional connectivity analysis between physiological signals and perinasal perspiration index

Automatic detection of distracted driving is essential to ensure safety of drivers. In this paper, a novel set of features were extracted from thermal and physiological signals in order to detect and recognize distraction of drivers. Thermal video data which measured the temperature of different areas of the face, heart rate, breathing rate and behavioural signals were used while various types of distractions including cognitive, emotional and sensory-motor were applied to the subjects. The proposed discriminator features were extracted by different functional connectivity methods between the perinasal perspiration extracted from thermal images of the face and physiological variables of heart rate and breathing rate. After feature extraction, binary classification methods were applied to detect the distractions. The results showed that using functional connectivity features significantly increased the accuracy of distraction detection system (up to 99.16% with a highly acceptable F1 score of 0.99). Hence, the proposed model significantly improved (p-value<0.001) the detection of driver’s distraction compared to previous studies. Functional connectivity between perinasal perspiration and breathing signals was the most informative feature for distraction detection purpose. This feature set explained almost all modulations in physiological changes by distractions. For the first time, we designed a system capable of recognizing types of distractions including sensory-motor, cognitive, emotional distractions and also normal state. We used the same feature set to recognize different types of distractions by using three-class and four-class classifiers. The suggested methods distinguished three types of distractions with the best accuracy of 81.94% related to cognitive, sensory-motor distraction and no-distraction states. We also tried to discriminate two types of cognitive distractions, analytic and mathematical distractions. The recognition system classified two types of cognitive distractions with an accuracy of 91.78%. The results suggest that there is important and complementary information in the connectivity between facial temperature signals and physiological variables for distraction detection and recognition.

Does users’ experience and evaluation of level 3 automated driving functions predict willingness to use: Results from an on-road study

To ensure the successful deployment of Automated Vehicles (AVs), it is important to understand users’ acceptance and willingness to use. The majority of previous studies which have investigated Willingness to Use of automated functionalities in vehicles, have relied on users’ imagination of system operational features, without any actual hands-on experience. To close this research gap, we conducted an extensive questionnaire study with participants who had experienced either a Motorway (N = 294) or an Urban (N = 144) Automated Driving Function (ADF) in an on-road study using prototype vehicles, conducted as part of the large-scale European L3Pilot project. We investigated the impact of participants’ demographic characteristics, and their evaluation of the ADFs, on their Willingness to Use these ADFs again in the future. Findings revealed that age was a significant predictor but had a small effect, with younger users showing a higher Willingness to Use the Motorway ADF, but not the Urban ADF. Other user characteristics, such as safety drivers versus ordinary drivers, system familiarity, and gender, did not predict Willingness to Use, for either system. Factors related to users’ Feelings of Ease (e.g., perceived safety, fun, comfort, trust) and Perceived Usefulness of the system, were the most important predictors, with more positive ratings for these factors leading to a higher Willingness to Use, for both systems. Other factors that showed an effect on Willingness to Use include System Monitoring Requirements (i.e., willingness to engage in other tasks instead of monitoring the system), System Information (i.e., wanting to know more about the system’s limitations) and System Expectations being met. This study shows the importance of ensuring that users have a good experience and perceive the system as useful to increase their Willingness to Use the ADF.

Gesture Controlled Robot Car

Abstract: A noteworthy achievement in automotive technology is the creation of an automatic hand gesture-controlled robot that can operate and control a variety of car operations. By enabling drivers to keep their hands on the wheel and their eyes on the road, this technology improves driver comfort and safety by lowering distractions, increasing driving focus, and lowering the chance of accidents. It is especially useful in circumstances where quick access to particular functions is necessary. Additionally, the technology encourages accessibility for people with physical limitations, enabling them to drive independently. However, precision and dependability are essential for a successful implementation, and user education are required to guarantee that drivers comprehend and use the movements the system detects.The automatic hand gesture-controlled car system shows promise in enhancing convenience, safety, and accessibility, but further research and development are needed to improve accuracy, reliability, and user-friendliness.

Impact Fracture Simulation of Laminated Glass Based on Thick Shell Elements and a Cohesive Zone Model.

Laminated glass is extensively used in automotive windshields, making it crucial to have a comprehensive understanding of its fracture mechanism to ensure driver and pedestrian safety in various windshield impact scenarios. Current research on the cohesive zone model of glass impact failure has encountered challenges related to accuracy and computational efficiency. This paper addresses these issues by utilizing the finite element software LS-DYNA, which integrates a cohesive zone model and thick shell (Tshell) elements to simulate and analyze the impact failure process of laminated glass. The combination of Tshell and cohesive elements was validated using a DCB example. Subsequently, the proposed method was applied to simulate the impact damage on an automobile's front windshield, providing valuable insights from the obtained results. Finally, the influence of curvature, the number of layers, and the thickness ratio of each layer were investigated, leading to some valuable conclusions. Firstly, an increase in the thickness of the upper glass layer correlates with a decrease in the peak acceleration of the dummy-head model due to the ductility of PVB material. Secondly, when a curvature exists, the arched configuration of the windshield promotes higher resistance against impact, consequently leading to increased peak acceleration.

Toward a Generic Vehicular Cloud Network Architecture: A Case of Virtual Vehicle as a Service

In recent years, cloud computing has gained more and more popularity. The motivation towards implementing cloud computing in vehicular networks is due to the availability of communication, storage, and computing resources represented by communication, vehicles, roadside units (RSUs), and central servers. These resources can be utilized and provided to vehicles, drivers on the road, travellers, and customers on the internet. Intelligent Transportation System (ITS) applications can utilize vehicular cloud computing to provide efficient real-time services, as well as to improve transportation safety, mobility, and comfort levels for drivers. In this paper, all possible vehicular cloud models are presented. Each vehicular cloud model offers different services. Integrating all vehicular cloud models into one integrated system will provide all services and serve internet users, passengers, and vehicles. Therefore, a generic vehicular cloud model is proposed. After that, a new service called Virtual Vehicle is proposed in vehicular cloud computing. The virtual vehicle is a virtual machine that migrates from one physical vehicle to another. It provides the same services as the physical vehicle according to the consumer's requirements.

Real-time driver monitoring system with facial landmark-based eye closure detection and head pose recognition

This paper introduces a real-time Driver Monitoring System (DMS) designed to monitor driver behavior while driving, employing facial landmark estimation-based behavior recognition. The system utilizes an infrared (IR) camera to capture and analyze video data. Through facial landmark estimation, crucial information about the driver’s head posture and eye area is extracted from the detected facial region, obtained via face detection. The proposed method consists of two distinct modules, each focused on recognizing specific behaviors. The first module employs head pose analysis to detect instances of inattention. By monitoring the driver’s head movements along the horizontal and vertical axes, this module assesses the driver’s attention level. The second module implements an eye-closure recognition filter to identify instances of drowsiness. Depending on the continuity of eye closures, the system categorizes them as either occasional drowsiness or sustained drowsiness. The advantages of the proposed method lie in its efficiency and real-time capabilities, as it solely relies on IR camera video for computation and analysis. To assess its performance, the system underwent evaluation using IR-Datasets, demonstrating its effectiveness in monitoring and recognizing driver behavior accurately. The presented real-time Driver Monitoring System with facial landmark-based behavior recognition offers a practical and robust approach to enhance driver safety and alertness during their journeys.

Traffic safety performance evaluation in a connected vehicle environment with queue warning and speed harmonization applications

With the increased adoption of connected vehicle (CV) technologies, safety information is becoming increasingly available to drivers. This study investigates three main questions (1) Do CV-based traffic management applications improve safety on roadways with existing infrastructure-based traffic management systems? (2) Can combining two CV technologies have a greater impact on safety than a single CV technology? and (3) Do geometric and traffic composition factors impact the efficiency of CV technologies? We applied a rarely-used CV dataset and conducted a comprehensive simulation analysis of varying conditions and CV penetration rates that studies have not considered. Two CV applications (queue warning and speed harmonization) implemented in the Intelligent Network Flow Optimization experiment in Seattle, WA were evaluated. Results showed that driver safety performance, based on speed metrics (standard deviation and percentage of extreme values) improved under the CV driving conditions. Combining conventional variable speed limit systems with queue warnings also improved safety for CV drivers. Furthermore, the implementation of a single CV application (queue warning) showed positive changes in the aforementioned speed metrics, congestion mitigation, and reduced conflicts. With the two CV applications combined, no significant differences were observed. Additional tests investigated the impacts of lane changes and roadway attributes on safety in the CV environment.

Promoting transportation safety in adolescence: the drivingly randomized controlled trial

BackgroundThe impact of young drivers’ motor vehicle crashes (MVC) is substantial, with young drivers constituting only 14% of the US population, but contributing to 30% of all fatal and nonfatal injuries due to MVCs and 35% ($25 billion) of the all medical and lost productivity costs. The current best-practice policy approach, Graduated Driver Licensing (GDL) programs, are effective primarily by delaying licensure and restricting crash opportunity. There is a critical need for interventions that target families to complement GDL. Consequently, we will determine if a comprehensive parent-teen intervention, the Drivingly Program, reduces teens’ risk for a police-reported MVC in the first 12 months of licensure. Drivingly is based on strong preliminary data and targets multiple risk and protective factors by delivering intervention content to teens, and their parents, at the learner and early independent licensing phases.MethodsEligible participants are aged 16-17.33 years of age, have a learner’s permit in Pennsylvania, have practiced no more than 10 h, and have at least one parent/caregiver supervising. Participants are recruited from the general community and through the Children’s Hospital of Philadelphia’s Recruitment Enhancement Core. Teen-parent dyads are randomized 1:1 to Drivingly or usual practice control group. Drivingly participants receive access to an online curriculum which has 16 lessons for parents and 13 for teens and an online logbook; website usage is tracked. Parents receive two, brief, psychoeducational sessions with a trained health coach and teens receive an on-road driving intervention and feedback session after 4.5 months in the study and access to DriverZed, the AAA Foundation’s online hazard training program. Teens complete surveys at baseline, 3 months post-baseline, at licensure, 3months post-licensure, 6 months post-licensure, and 12 months post-licensure. Parents complete surveys at baseline, 3 months post-baseline, and at teen licensure. The primary end-point is police-reported MVCs within the first 12 months of licensure; crash data are provided by the Pennsylvania Department of Transportation.DiscussionMost evaluations of teen driver safety programs have significant methodological limitations including lack of random assignment, insufficient statistical power, and reliance on self-reported MVCs instead of police reports. Results will identify pragmatic and sustainable solutions for MVC prevention in adolescence.Trial RegistrationClinicalTrials.gov # NCT03639753.

Voltage fault diagnosis and misdiagnosis analysis of battery systems using the modified Shannon entropy in real-world electric vehicles

Power battery systems fault diagnosis of electric vehicles (EVs) is a key technical approach to ensure the safety and reliable operation of the vehicle, of which avoiding misdiagnosis not only can reduce the driver's safety concerns, but also is a reflection of the reliability of the diagnostic method. This paper first proposes a modified Shannon entropy-based battery fault diagnosis method for identifying cells with abnormal voltage fluctuations in battery systems, and the method is implemented online by calculating the Shannon entropy of the voltage sequence in a moving time window. Then, the defined sensitivity factor (SF) can provide an efficient and accurate assessment of the extent of abnormal voltage fluctuations. Further, to improve the fault diagnosis accuracy of the method, we validated the diagnostic model by using battery operation data from a battery monitoring cloud platform with a sampling frequency of 0.1 Hz and eventually found a large number of false alarm cells in the diagnostic results. Based on this, we have analysed the fault diagnosis mechanisms of the model and thus obtained the causes of misdiagnosis. Finally, a solution to reduce misdiagnosis is proposed and its effectiveness is verified. To further test its comprehensive performance, we compared the accuracy of the method before and after optimization based on normal vehicle data, and the results showed a 81.9 % reduction in the average relative misdiagnosis rate of the model, thus greatly improving the reliability of this fault diagnosis strategy, creating conditions for the online application of the method and providing ideas for the analysis and improvement of the accuracy rate of other fault diagnosis methods.

Forward Chaining Method Implementation for AI-Powered Passenger Ojek Online and Drive Solutions

This research explores the application of artificial intelligence (AI)-based technology in the Grab application, an online passenger transportation service company in Southeast Asia. The main aim of this research is to improve service quality, safety and efficiency for Grab passengers and drivers, while solving traffic and location problems. The use of AI in this application opens up opportunities to optimize passenger pick-up and drop-off processes, improve navigation, and improve real-time traffic management. Special emphasis is placed on the application of the Forward Chaining method, an artificial intelligence technique that allows systems to make decisions based on predetermined rules. By implementing this method, Grab can predict passenger movements and arrange the best routes automatically, increasing time efficiency and reducing congestion. The implications of this research are very significant in the context of improving the quality of online transportation services, by providing a better experience for passengers and ensuring safety on every trip. The main contribution of this research is the development of an efficient and reliable AI system, as well as the application of Forward Chaining in the context of the Grab application. Additionally, this research provides an in-depth understanding of how AI technology can overcome traffic and location challenges, creating effective and reliable solutions for ride-hailing companies in the future. The results of this research provide a valuable contribution to the development of transportation technology, providing a basis for similar companies to explore the potential of applying artificial intelligence in their services. Thus, this research paves the way to greater innovation in the field of online transportation, creating a more efficient, safe and comfortable environment for users, and creating significant added value for the industry.

Data-Driven Safe Deliveries: The Synergy of IoT and Machine Learning in Shared Mobility

Shared mobility is one of the smart city applications in which traditional individually owned vehicles are transformed into shared and distributed ownership. Ensuring the safety of both drivers and riders is a fundamental requirement in shared mobility. This work aims to design and implement an adequate framework for shared mobility within the context of a smart city. The characteristics of shared mobility are identified, leading to the proposal of an effective solution for real-time data collection, tracking, and automated decisions focusing on safety. Driver and rider safety is considered by identifying dangerous driving behaviors and the prompt response to accidents. Furthermore, a trip log is recorded to identify the reasons behind the accident. A prototype implementation is presented to validate the proposed framework for a delivery service using motorbikes. The results demonstrate the scalability of the proposed design and the integration of the overall system to enhance the rider’s safety using machine learning techniques. The machine learning approach identifies dangerous driving behaviors with an accuracy of 91.59% using the decision tree approach when compared against the support vector machine and K-nearest neighbor approaches.

Reference Generator for a Platoon of Position-Controlled Vehicles on a Curved Path

&lt;div&gt;Vehicular automation in the form of a connected and automated vehicle platoon is demanding as it aims to increase traffic flow and driver safety. Controlling a vehicle platoon on a curved path is challenging, and most solutions in the existing literature demonstrate platooning on a straight path or curved paths at constant speeds. This article proposes an algorithmic solution with leader-following (LF) communication topology and constant distance (CD) spacing for platooning homogeneous position-controlled vehicles (PCVs) on a curved path, with each vehicle capable of cornering at variable speeds. The lead vehicle communicates its reference position and orientation to all the follower vehicles. A follower vehicle stores this information as a virtual trail of the lead vehicle for a specific period. An algorithm uses this trail to find the follower vehicle’s reference path by solving an optimization problem. This algorithm is feasible and maintains a constant inter-vehicle distance. The PCVs can be holonomic or nonholonomic. For simulations, this article considers a holonomic four-wheel independent steering four-wheel independent drive (4WIS4WID) PCV for platooning. This vehicle has superior maneuverability and traction and can extend the applications of vehicle platoons from highways to paths with smaller radii of curvature. Simulation of a five-vehicle platoon suggests a satisfactory performance of the proposed approach. This article also presents an alternate curved platooning approach where the lead vehicle communicates its reference longitudinal and lateral velocities and yaw rate to a follower vehicle. The follower vehicle directly follows these communicated signals for platooning. This approach does not store the communicated signals and also cuts the cost of the position controller for the follower vehicles. Simulation results show that this alternative approach is applicable to constant-speed motion.&lt;/div&gt;