Design and Implementation of a Two-Wheeled Vehicle Safe Driving Evaluation System.

The delivery market in Republic of Korea has experienced significant growth, leading to a surge in motorcycle-related accidents. However, there is a lack of comprehensive data collection systems for motorcycle safety management. This study focused on designing and implementing a foundational data collection system to monitor and evaluate motorcycle driving behavior. To achieve this, eleven risky behaviors were defined, identified using image-based, GIS-based, and inertial-sensor-based methods. A motorcycle-mounted sensing device was installed to assess driving, with drivers reviewing their patterns through an app and all data monitored via a web interface. The system was applied and tested using a testbed. This study is significant as it successfully conducted foundational data collection for motorcycle safety management and designed and implemented a system for monitoring and evaluation.

A qualitative study of perception related to risky driving behavior in Debre Markos City, North West Ethiopia, 2021.

BACKGROUND: About 1.35 million deaths and around 50 million injuries are attributed to road traffic crashes every year in the world. In Ethiopia, road traffic crashes contributed to a fatality rate of 37 per 100,000 populations per year, and 83% of traffic crashes were attributed to risky driving behavior. This study aimed to explore perceptions related to risky driving behavior among public transport vehicle drivers in Debre Markos City, North West Ethiopia, in 2021. METHODS: A generic qualitative study was conducted from August 05- September 15, 2021. A total of 17 participants (10 drivers, 4 drivers' training school instructors, and 3 traffic police officers) were selected by a purposive heterogeneous sampling technique. An open-ended interview guide was used during the interview, and all interviews were audio recorded. Data collected in the local language was transcribed verbatim and translated into English. The ATLAS-TI version 7.5 software was used to code the data, and finally, thematic analysis was done. RESULT: Four themes were identified. The first theme was "transport safety rule and enforcement problem," which includes gaps in the transport safety rule itself and gaps in the implementation of the rule. The second theme was "Drivers' training curriculum and application gaps," which focuses on gaps in the training curriculum and its application during recruitment, training, and examination of trainees. The third theme was "technical and financial problems". This theme includes problems related to the vehicles' technical issues and the appropriateness of transport tariffs. The final theme was "passenger and vehicle owners' related problems". This theme is about the influence of passengers' and vehicle owners' practices on drivers' risky driving behavior. CONCLUSION: Revising transport safety rules and strictly following the implementation of the drivers' training curriculum and transport safety rules should be given due attention. In addition, behavior change communications tailored to drivers and vehicle owners could be beneficial in reducing risky driving behaviors.

Sensation seeking predicts risky driving behavior: The mediating role of difficulties in emotion regulation.

The purpose of this study was to explore the mediating effect of difficulties in emotion regulation on the relationship between sensation seeking and driving behavior based on the dual-process model of aberrant driving behavior. A sample of 299 drivers in China completed the Difficulties in Emotion Regulation Scale, the Driver Behavior Questionnaire, and the Sensation Seeking Scale V (SSS). The relationships among sensation seeking, difficulties in emotion regulation, and driving behavior were investigated using pathway analysis. The results showed that (1) disinhibition and boredom susceptibility are positively and significantly related to difficulties in emotion regulation and risky driving behaviors; (2) difficulties in emotion regulation are positively and significantly associated with risky driving behaviors; (3) difficulties in emotion regulation mediate the effect of sensation seeking on driving behaviors, supporting the dual-process model of driving behavior; and (4) professional drivers score higher in terms of difficulties in emotion regulation and risky driving behaviors than nonprofessional drivers. The findings of this study could provide valuable insights into the selection of suitable drivers and the development of certain programs that benefit road safety.

On-Board Unit (OBU)-Supported Longitudinal Driving Behavior Monitoring Using Machine Learning Approaches.

Driving behavior recognition can provide an important reference for the intelligent vehicle industry and probe vehicle-based traffic estimation. The identification of driving behavior using mobile sensing techniques such as smartphone- and vehicle-mounted terminals has gained significant attention in recent years. The present work proposed the monitoring of longitudinal driving behavior using a machine learning approach with the support of an on-board unit (OBU). Specifically, based on velocity, three-axis acceleration and three-axis angular velocity data were collected by a mobile vehicle terminal OBU; through the process of data preprocessing and feature extraction, seven machine learning algorithms, including support vector machine (SVM), random forest (RF), k-nearest neighbor algorithm (KNN), logistic regression (LR), BP neural network (BPNN), decision tree (DT), and the Naive Bayes (NB), were applied to implement the classification and monitoring of the longitudinal driving behavior of probe vehicles. The results show that the three classifiers SVM, RF and DT achieved good performances in identifying different longitudinal driving behaviors. The outcome of the present work could contribute to the fields of traffic management and traffic safety, providing important support for the realization of intelligent transport systems and the improvement of driving safety.

Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks.

To drive safely, the driver must be aware of the surroundings, pay attention to the road traffic, and be ready to adapt to new circumstances. Most studies on driving safety focus on detecting anomalies in driver behavior and monitoring cognitive capabilities in drivers. In our study, we proposed a classifier for basic activities in driving a car, based on a similar approach that could be applied to the recognition of basic activities in daily life, that is, using electrooculographic (EOG) signals and a one-dimensional convolutional neural network (1D CNN). Our classifier achieved an accuracy of 80% for the 16 primary and secondary activities. The accuracy related to activities in driving, including crossroad, parking, roundabout, and secondary activities, was 97.9%, 96.8%, 97.4%, and 99.5%, respectively. The F1 score for secondary driving actions (0.99) was higher than for primary driving activities (0.93-0.94). Furthermore, using the same algorithm, it was possible to distinguish four activities related to activities of daily life that were secondary activities when driving a car.

A Hybrid Model for Vehicle Acceleration Prediction.

Accurate prediction of vehicle acceleration has significant practical applications. Deep learning, as one of the methods for acceleration prediction, has shown promising applications in acceleration prediction. However, due to the influence of multiple factors on acceleration, a single data model may not be suitable for various driving scenarios. Therefore, this paper proposes a hybrid approach for vehicle acceleration prediction by combining clustering and deep learning techniques. Based on historical data of vehicle speed, acceleration, and distance to the preceding vehicle, the proposed method first clusters the acceleration patterns of vehicles. Subsequently, different prediction models and parameters are applied to each cluster, aiming to improve the prediction accuracy. By considering the unique characteristics of each cluster, the proposed method can effectively capture the diverse acceleration patterns. Experimental results demonstrate the superiority of the proposed approach in terms of prediction accuracy compared to benchmarks. This paper contributes to the advancement of sensor data processing and artificial intelligence techniques in the field of vehicle acceleration prediction. The proposed hybrid method has the potential to enhance the accuracy and reliability of acceleration prediction, enabling applications in various domains, such as autonomous driving, traffic management, and vehicle control.

The Effects of ADAS on Driving Behavior: A Case Study.

The presence of numerous sensors inside modern vehicles leads to the development of new driving assistance tools, the real usefulness of which depends, however, on the environmental context. This study proposes a procedure capable of quantifying the effectiveness of some warnings produced by an On-Board Unit (OBU) inside the vehicle in a specific environmental context, even if limited only to the considered road. The experimentation was carried out by means of a driving simulator with a sample of young users with sufficiently homogeneous characteristics. The collected data were treated by ANOVA to highlight any differentiation between a traditional driving condition, without any instrumental support, and another involving the OBU was present. The results showed that only in relation to the investigated road, the OBU ensured the advantage of sending information of interest to the driver without invalidating their performance in terms of longitudinal and transverse acceleration, speeding, and steering angle. This research could be of interest to the infrastructure managers who, in case of inappropriate use of a road, could intensify active and passive safety devices for users' safety.

Integrating Surrounding Vehicle Information for Vehicle Trajectory Representation and Abnormal Lane-Change Behavior Detection.

The detection of abnormal lane-changing behavior in road vehicles has applications in traffic management and law enforcement. The primary approach to achieving this detection involves utilizing sensor data to characterize vehicle trajectories, extract distinctive parameters, and establish a detection model. Abnormal lane-changing behaviors can lead to unsafe interactions with surrounding vehicles, thereby increasing traffic risks. Therefore, solely focusing on individual vehicle perspectives and neglecting the influence of surrounding vehicles in abnormal lane-changing behavior detection has limitations. To address this, this study proposes a framework for abnormal lane-changing behavior detection. Initially, the study introduces a novel approach for representing vehicle trajectories that integrates information from surrounding vehicles. This facilitates the extraction of feature parameters considering the interactions between vehicles and distinguishing between different phases of lane-changing. The Light Gradient Boosting Machine (LGBM) algorithm is then employed to construct an abnormal lane-changing behavior detection model. The results indicate that this framework exhibits high detection accuracy, with the integration of surrounding vehicle information making a significant contribution to the detection outcomes.

Ecological Interface Design and Head-Up Displays: The Contact-Analog Visualization Tradeoff.

OBJECTIVE: This study investigated how the visualization of an ecological interface affects its subjective and objective usefulness. Therefore, we compared a simple 2D visualization against a contact-analog 3D visualization. BACKGROUND: Recently, head-up displays (HUDs) have become contact-analog and visualizations have been enabled to be merged with the real environment. In this regard, ecological interface design visualizing boundaries of acceptable performance might be a perfect match. Because the real-world environment already provides such boundaries (e.g., lane markings), the interface might directly use them. However, visual illusions and undesired interference with the environment might influence the overall usability. METHOD: To allow for a comparison, 49 participants tested the same ecological interface in two configurations, contact-analog (3D) and two dimensional (2D). Both visualizations were shown in the car's head-up display (HUD). RESULTS: The driving simulator experiment reveals that 3D was rated as more demanding and more disturbing, but also more innovative and appealing. However, regarding driving performance, the 3D representation decreased the accuracy of speed control by 6% while significantly increasing lane stability by 20%. CONCLUSION: We conclude that, if we want environmental boundaries guiding our behavior, the indicator for the behavior should be visualized contact-analog. If we desire artificial boundaries (e.g., speed limits) to guide behavior, the behavioral indicator should be visualized in 2D. This is less prone to optical illusions and allows for a more precise control of behavior. APPLICATION: These findings provide guidance to human factors engineers, how contact-analog visualizations might be used optimally.

[Cognition and driving ability in chronic pain syndrome]. / Kognition und Kraftfahreignung bei chronischem Schmerzsyndrom.

Cognitive impairments in patients with chronic pain are increasingly attracting interest in scientific research. The consequences of these cognitive impairments on coping with pain, everyday life and the driving ability are rarely included in clinical practice although half of all patients are affected. This article summarizes the current research situation and discusses possibilities of the integration in clinical and therapeutic care.

Association of risky driving behavior with psychiatric disorders among Iranian drivers: A case-control study.

PURPOSE: This study aimed to investigate the possible association between psychological disorders and risky driving behavior (RDB) in Iran. METHODS: This case-control study conducted in Shiraz, Iran in 2021. The case group included drivers with psychological disorders and the control group included those without any disorders. The inclusion criteria for selecting patients were: active driving at the time of the study, being 18 - 65 years old, having a driving license, having a psychological disorder including depression, bipolar disorder, anxiety spectrum disorder, or psychotic disorder spectrum confirmed by a psychiatrist, and completing an informed consent form. The exclusion criterion was the existence of conditions that interfered with answering and understanding the questions. The inclusion criteria for selecting the healthy cases were: active driving at the time of the study, being 18 - 65 years old, having a driving license, lack of any past or present history of psychiatric problems, and completing an informed consent form. The data were gathered using a researcher-made checklist and Manchester driving behavior questionnaire. First, partition around medoids method was used to extract clusters of RDB. Then, backward logistic regression was applied to investigate the association between the independent variables and the clusters of RDB. RESULTS: The sample comprised of 344 (153 with psychological disorder and 191 without confirmed psychological disorder) drivers. Backward elimination logistic regression on total data revealed that share of medical expenditure ≤ 10% of total household expenditure (OR = 3.27, 95% CI: 1.48 - 7.24), psychological disorder (OR = 3.08, 95% CI: 1.67 - 5.70), and substance abuse class (OR = 6.38, 95% CI: 3.55 - 11.48) were associated with high level of RDB. CONCLUSION: Substance abuse, psychological illnesses, and share of medical costs from total household expenditure were found to be main predictors of RDB. Further investigations are necessary to explain the impact of different psychological illnesses on driving behavior.

Relationship between self-perceived driving ability and neuropsychological performance in neurological and psychiatric patients.

BACKGROUND: Neurological and psychiatric patients want to keep driving but several sensory, motor, and cognitive deficits could limit this purpose. However, some drivers "self-regulate" driving behavior to minimize the risk of accidents. A good predictor of this behavior seems to be the self-perceived driving ability. The purpose of this study was to evaluate whether the neuropsychological profile of neurological and psychiatric active drivers correlates to self-reported and caregiver-referred driving behavior. METHODS: Sixty-three active drivers diagnosed with a neurological or psychiatric condition were enrolled and underwent cognitive assessment plus two behavioral questionnaires (Driver Behavior Questionnaire - DBQ and Barratt Impulsiveness Scale-version 11). DBQ and IADL (Instrumental Activities of Daily Living) were also administered to thirty-nine caregivers, to assess autonomy in daily life and the frequency of errors and violations committed by drivers. Spearman's Rho non-parametric analysis was used to investigate the relationship between performances at neuropsychological tests and DBQ responses. Cohen's weighted kappa coefficient was also adopted to verify the strength of agreement between the two groups at the DBQ. RESULTS: Results suggested an overall agreement between self-reported and caregiver-referred driving behavior; moreover, a relationship between self-referred driving behavior and impulsiveness was found. However, neuropsychological performances were not related to self-perceived driving ability. CONCLUSIONS: These results provide new insight regarding the risk of incurring road accidents and can be useful to promote a more appropriate evaluation of risk accidents in neurological and psychiatric patients.

Factors influencing changes in medication-taking and driving behavior after warnings about prescription medications that prohibit driving: an online survey.

BACKGROUND: This study examined warning messages as a strategy for preventing automobile crashes by drivers on medications. We investigated the degree of awareness regarding the effects of medication on automobile driving and changes in medication-taking and driving behavior. We also assessed associations between socio-environmental factors and the driving and medication-taking behavior adopted by individuals after being warned about driving-related risks. METHODS: Responses to an online questionnaire from 1200 people with a driving license who were taking prescription medications at the time of inquiry (March 2019) were collected and analyzed. The items surveyed were sex, age, educational history, health literacy, current medications, and medication-taking and driving behavior after being warned. RESULTS: Of the total respondents, 30% were taking medicine that prohibited driving. Of those taking prohibited medications, 25.7% did not receive a warning about driving from healthcare professionals. Most respondents taking prohibited medications received euphemistic warnings, such as "practice caution" (30%), "refrain from calling attention" (29.4%), and "avoid driving" (19.8%); 16% of the direct warnings were about not driving. Medication's effects on driving were recognized by 80% of the total respondents. The degree of awareness was significantly higher among respondents taking medications that prohibit driving than among those taking medications that did not prohibit driving or those taking unknown medications. Awareness of medicine's influence on driving was associated with health literacy. No association was found between age, gender, health literacy, history of side effects, and driving and medication-taking behavior. Approximately 22% of respondents adjusted their medication use at their discretion and 39% maintained treatment compliance but continued driving. Among respondents taking medications that prohibit driving, whether driving was required for work was a significant factor in their driving and medication-taking behavior after being warned. CONCLUSIONS: Healthcare professionals do not always fully inform patients about the driving-related risks of medications. To encourage patients who are taking medications that have a significant impact on their driving to either stop driving or consult a healthcare professional, healthcare professionals must first understand the patient's social environment, such as whether driving is required for work, and then create an environment conducive to advice-seeking.

Data-Driven Estimation of a Driving Safety Tolerance Zone Using Imbalanced Machine Learning.

Predicting driving behavior and crash risk in real-time is a problem that has been heavily researched in the past years. Although in-vehicle interventions and gamification features in post-trip dashboards have emerged, the connection between real-time driving behavior prediction and the triggering of such interventions is yet to be realized. This is the focus of the European Horizon2020 project "i-DREAMS", which aims at defining, developing, testing and validating a 'Safety Tolerance Zone' (STZ) in order to prevent drivers from risky driving behaviors using interventions both in real-time and post-trip. However, the data-driven conceptualization of STZ levels is a challenging task, and data class imbalance might hinder this process. Following the project principles and taking the aforementioned challenges into consideration, this paper proposes a framework to identify the level of risky driving behavior as well as the duration of the time spent in each risk level by private car drivers. This aim is accomplished by four classification algorithms, namely Support Vector Machines (SVMs), Random Forest (RFs), AdaBoost, and Multilayer Perceptron (MLP) Neural Networks and imbalanced learning using the Adaptive Synthetic technique (ADASYN) in order to deal with the unbalanced distribution of the dataset in the STZ levels. Moreover, as an alternative approach of risk prediction, three regression algorithms, namely Ridge, Lasso, and Elastic Net are used to predict time duration. The results showed that RF and MLP outperformed the rest of the classifiers with 84% and 82% overall accuracy, respectively, and that the maximum speed of the vehicle during a 30 s interval, is the most crucial predictor for identifying the driving time at each safety level.

Farm Vehicle Following Distance Estimation Using Deep Learning and Monocular Camera Images.

This paper presents a comprehensive solution for distance estimation of the following vehicle solely based on visual data from a low-resolution monocular camera. To this end, a pair of vehicles were instrumented with real-time kinematic (RTK) GPS, and the lead vehicle was equipped with custom devices that recorded video of the following vehicle. Forty trials were recorded with a sedan as the following vehicle, and then the procedure was repeated with a pickup truck in the following position. Vehicle detection was then conducted by employing a deep-learning-based framework on the video footage. Finally, the outputs of the detection were used for following distance estimation. In this study, three main methods for distance estimation were considered and compared: linear regression model, pinhole model, and artificial neural network (ANN). RTK GPS was used as the ground truth for distance estimation. The output of this study can contribute to the methodological base for further understanding of driver following behavior with a long-term goal of reducing rear-end collisions.

A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning.

Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven recognition methods of ADB, which are caused by the problems such as the improper processing of the dataset with imbalanced class distribution and one single classifier utilized. Aiming to deal with these disadvantages, an ensemble learning-based recognition method of ADB is proposed in this paper. First, the majority class in the dataset is grouped employing the self-organizing map (SOM) and then are combined with the minority class to construct multiple class balance datasets. Second, three deep learning methods, including convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU), are employed to build the base classifiers for the class balance datasets. Finally, the ensemble classifiers are combined by the base classifiers according to 10 different rules, and then trained and verified using a multi-source naturalistic driving dataset acquired by the integrated experiment vehicle. The results suggest that in terms of the recognition of ADB, the ensemble learning method proposed in this research achieves better performance in accuracy, recall, and F1-score than the aforementioned typical deep learning methods. Among the ensemble classifiers, the one based on the LSTM and the Product Rule has the optimal performance, and the other one based on the LSTM and the Sum Rule has the suboptimal performance.

mm-DSF: A Method for Identifying Dangerous Driving Behaviors Based on the Lateral Fusion of Micro-Doppler Features Combined.

To address the dangerous driving behaviors prevalent among current car drivers, it is necessary to provide real-time, accurate warning and correction of driver's driving behaviors in a small, movable, and enclosed space. In this paper, we propose a method for detecting dangerous behaviors based on frequency-modulated continuous-wave radar (mm-DSF). The highly packaged millimeter-wave radar chip has good in-vehicle emotion recognition capability. The acquired millimeter-wave differential frequency signal is Fourier-transformed to obtain the intermediate frequency signal. The physiological decomposition of the local micro-Doppler feature spectrum of the target action is then used as the eigenvalue. Matrix signal intensity and clutter filtering are performed by analyzing the signal echo model of the input channel. The signal classification is based on the estimation and variety of the feature vectors of the target key actions using a modified and optimized level fusion method of the SlowFast dual-channel network. Nine typical risky driving behaviors were set up by the Dula Hazard Questionnaire and TEIQue-SF, and the accuracy of the classification results of the self-built dataset was analyzed to verify the high robustness of the method. The recognition accuracy of this method increased by 1.97% compared with the traditional method.

Fitness to drive after acquired brain injury: Results from patient cognitive screening and on-road assessment compared to age-adjusted norm values.

Fitness to drive after acquired brain injury or disease is a common question in rehabilitation settings. The aim of the study was to compare age-matched norms with patient cognitive test results used to predict fitness to drive. A second aim was to analyze the contribution from an on-road assessment to a final decision on resumption of driving after an acquired brain injury. Retrospective cognitive test results from four traffic medicine units (n = 333) were compared with results from a healthy norm population (n = 410) in Sweden. Patients were dichotomized according to the final decision as fit or unfit to drive made by the traffic medicine team. The norm group had significantly better results in all age groups for all cognitive tests compared with the patients considered unfit to drive and fit to drive. A binary regression analysis for the patient group showed an explained value for fit to drive/unfit to drive of 88%, including results for the Nordic Stroke Driver Screening Assessment total score, Useful Field of View total score and the final outcome from an on-road assessment. Results from the present study illustrate the importance of using several tests, methods and contexts for the final decision regarding fitness to drive.

Driving Behavior Recognition Algorithm Combining Attention Mechanism and Lightweight Network.

In actual driving scenes, recognizing and preventing drivers' non-standard driving behavior is helpful in reducing traffic accidents. To resolve the problems of various driving behaviors, a large range of action, and the low recognition accuracy of traditional detection methods, in this paper, a driving behavior recognition algorithm was proposed that combines an attention mechanism and lightweight network. The attention module was integrated into the YOLOV4 model after improving the feature extraction network, and the structure of the attention module was also improved. According to the 20,000 images of the Kaggle dataset, 10 typical driving behaviors were analyzed, processed, and recognized. The comparison and ablation experimental results showed that the fusion of an improved attention mechanism and lightweight network model had good performance in accuracy, model size, and FLOPs.

Driving maneuver classification from time series data: a rule based machine learning approach.

Drivers' improper driving behavior plays a vital role in road accidents. Different approaches have been proposed to classify and evaluate driving performance to ensure road safety. However, most of the techniques are based on neural networks which work like a black box and make the logical reasoning behind the classification decision unclear. In this paper, we propose a rule-based machine learning technique using a sequential covering algorithm to classify the driving maneuvers from time-series data. In the sequential covering algorithm, the impact of each rule is measured as the metrics of coverage and accuracy, where the coverage and accuracy indicate the amount of covered and correctly identified instances in a maneuver class, respectively. The final ruleset for each maneuver class is formed with only the significant rules. In this way, the rules are learned in an unsupervised manner and only the best performance of the rules are included in the ruleset. The set of rules is also optimized by pruning based on the performance of the test data. Application of the proposed system is beneficial compared to the traditional machine learning and deep learning approaches which typically require a larger dataset and higher computational time and complexity.