FIGURE 1 - uploaded by Soukaina Bouhsissin
Content may be subject to copyright.
Source publication
Driver behavior is receiving increasing attention as a result of the staggering number of road accidents. Many road safety reports regard human behavior as the most important factor in the likelihood of accidents. The detection and classification of aggressive or abnormal driver behavior is an essential requirement in the real world to avoid deadly...
Contexts in source publication
Context 1
... is a common daily activity for many people [22]. By analyzing driver behavior with ML and DL techniques, we can better understand and address the factors that contribute to risky driving and work towards improving safety on the road. DB describes the driver's actions as they relate to the driving scene and the general environment [23] (see Fig. 1). DB is generally evaluated in terms of environmental variables such as traffic signs, road geometry, and pedestrians as well as vehicle variables such as distance, speed, acceleration, and other related variables [24]. The connections between the driver, the car, and the environment must be investigated to understand driver behavior. ...
Context 2
... this section, we will identify and analyze the applications of machine learning, deep learning, and statistical techniques and algorithms in the field of driver behavior assessment and classification. Fig. 10 presents in percentage form the number of papers that have developed ML, DL, or statistical analysis. It shows that machine learning (ML) algorithms are the most used; they are present in 60% of previous studies. Then deep learning (DL) algorithms took 34.87%. Finally, statistical methods are less used, with 5.13%. In this SLR, we have ...
Context 3
... are present in 60% of previous studies. Then deep learning (DL) algorithms took 34.87%. Finally, statistical methods are less used, with 5.13%. In this SLR, we have extracted twenty machine learning (ML) algorithms used to classify driver behavior. We have SVM, LR, RF, KNN, kmeans clustering, BN, DT, AdaBoost, and other algorithms presented in Fig. 11. In addition, twenty deep learning (DL) algorithms, we have LSTM, CNN, ANN, RNN, DNN, SFNet, FCN, autoencoders, and other algorithms presented in Fig. 11. Six statistical techniques used, such as the T-test, ANOVA, and ANCOVA. The algorithms SVM, LR, LSTM, ANN, KNN, RF, and CNN are the most commonly used, they present 49.72% of the ...
Context 4
... SLR, we have extracted twenty machine learning (ML) algorithms used to classify driver behavior. We have SVM, LR, RF, KNN, kmeans clustering, BN, DT, AdaBoost, and other algorithms presented in Fig. 11. In addition, twenty deep learning (DL) algorithms, we have LSTM, CNN, ANN, RNN, DNN, SFNet, FCN, autoencoders, and other algorithms presented in Fig. 11. Six statistical techniques used, such as the T-test, ANOVA, and ANCOVA. The algorithms SVM, LR, LSTM, ANN, KNN, RF, and CNN are the most commonly used, they present 49.72% of the articles studied. Fig. 11 shows the interest that each algorithm received in previous ...
Context 5
... addition, twenty deep learning (DL) algorithms, we have LSTM, CNN, ANN, RNN, DNN, SFNet, FCN, autoencoders, and other algorithms presented in Fig. 11. Six statistical techniques used, such as the T-test, ANOVA, and ANCOVA. The algorithms SVM, LR, LSTM, ANN, KNN, RF, and CNN are the most commonly used, they present 49.72% of the articles studied. Fig. 11 shows the interest that each algorithm received in previous ...
Context 6
... the level of the dataset, Fig. 12 shows for each dataset the classification algorithms used to predict and classify driver behavior. LSTM is the most commonly used algorithm for UAH-DriveSet with 11.42%. Then, SVM, RF, and DT algorithms are often used in the SHRP2 dataset, with 5.71% in each one. SVM and ANN are used with 2.87% in the Driving dataset, and RNN, LSTM, ...
Context 7
... with 2.87% in the Driving dataset, and RNN, LSTM, and GRU are used in Driver Behavior Dataset with 2.85% in each one. In general, the LSTM algorithm is the most used in driver behavior classification from the extracted dataset, with almost 17.14%, followed by SVM with 14.29%, and RF with 11.43%, and the other algorithms percentages are shown in Fig. 12. We can also conclude that ML algorithms are the most commonly used to classify driver behavior from datasets, accounting for 51.43% of the total, while DL algorithms account for ...
Context 8
... addition, from Fig. 13, SVM and LR algorithms are mostly used to analyze smartphone sensor data. Also, for simulator data the SVM algorithm is recommend. In general, the SVM algorithm is the most used in the data source for the classification of driver behavior with 19.60%, then LR and LSTM with 9.49 and 8.23%, respectively, and the percentage of other ...
Context 9
... LR algorithms are mostly used to analyze smartphone sensor data. Also, for simulator data the SVM algorithm is recommend. In general, the SVM algorithm is the most used in the data source for the classification of driver behavior with 19.60%, then LR and LSTM with 9.49 and 8.23%, respectively, and the percentage of other algorithms is shown in Fig. 13. ML algorithms account for 62.66% of the algorithms used for the classification of driver behavior based on different data sources, followed by the DL algorithm with 32.91% and the statistical method with ...
Context 10
... model performance is crucial to understanding and quantifying its effectiveness. Through this process, we can determine which model is the best to use for a classification or regression task. The Fig. 14 show that the most popular performance metrics considered in the chosen studies are accuracy, F1-score, recall, and ...
Context 11
... terms of the best performing algorithm, we cannot decide exactly which of the algorithms illustrated above (see Fig. 11) performs better than the others, as in most of the studies selected above, their data source, features, sample size, study environment, number of participants, metrological data, and other factors are all different. To analyze the model's performance, we project in Table 10 the algorithm used in the datasets detailed in Table 5 and ...
Context 12
... algorithms identified earlier were used to assess driver behavior generally in three forms: (1) detecting driver behavior; (2) predicting and classifying driver behavior; and (3) using statistics to study driver behavior. Fig. 15 is plotted to describe the driver behavior study techniques and models. 49.15% of studies use algorithms to predict driver behavior, followed by 32.20% that use detection models, and 18.64% that use statistical ...
Context 13
... the authors use 54% ML algorithms and 44% DL algorithms. The same thing happens in prediction models: ML algorithms account for 64.29%, DL algorithms for 33.67%, and statistical models for 2.04%. While in statistical models, researchers also use more ML algorithms with 57.14% and statistical algorithms like ARIMA and others with 42.86% (see Fig. 16). For each type of driver behavior study, we need to know the most commonly chosen type of algorithm (Fig. 17). Machine learning algorithms are the most frequently used algorithms in driving simulator studies, field driving studies, naturalistic driving studies, and questionnaire studies, with 60.98%, 62.82%, 54.17%, and 64.29%, ...
Context 14
... algorithms account for 64.29%, DL algorithms for 33.67%, and statistical models for 2.04%. While in statistical models, researchers also use more ML algorithms with 57.14% and statistical algorithms like ARIMA and others with 42.86% (see Fig. 16). For each type of driver behavior study, we need to know the most commonly chosen type of algorithm (Fig. 17). Machine learning algorithms are the most frequently used algorithms in driving simulator studies, field driving studies, naturalistic driving studies, and questionnaire studies, with 60.98%, 62.82%, 54.17%, and 64.29%, respectively. Then, with 37.50% in naturalistic driving studies and 34.62% in field driving studies, deep learning ...
Citations
... In recent years, growing urbanization and the increasing number of vehicles on the road have introduced new challenges related to transportation safety, efficiency, and sustainability, leading to growing interest in the Internet of Vehicles (IoV) [1]. Within this framework, the monitoring systems of driver, vehicle, and road conditions have become key components of Intelligent Transportation Systems (ITSs) and smart cities [2]. These systems leverage advanced technologies, including sensors, IoT devices, and Artificial Intelligence (AI) to collect, analyze, and utilize real-time data. ...
In recent years, the growing number of vehicles on the road have exacerbated issues related to safety and traffic congestion. However, the advent of the Internet of Vehicles (IoV) holds the potential to transform mobility, enhance traffic management and safety, and create smarter, more interconnected road networks. This paper addresses key road safety concerns, focusing on driver condition detection, vehicle monitoring, and traffic and road management. Specifically, various models proposed in the literature for monitoring the driver’s health and detecting anomalies, drowsiness, and impairment due to alcohol consumption are illustrated. The paper describes vehicle condition monitoring architectures, including diagnostic solutions for identifying anomalies, malfunctions, and instability while driving on slippery or wet roads. It also covers systems for classifying driving style, as well as tire and emissions monitoring. Moreover, the paper provides a detailed overview of the proposed traffic monitoring and management solutions, along with systems for monitoring road and environmental conditions, including the sensors used and the Machine Learning (ML) algorithms implemented. Finally, this review also presents an overview of innovative commercial solutions, illustrating advanced devices for driver monitoring, vehicle condition assessment, and traffic and road management.
... Key elements such as driver error, vehicle overturning, and mechanical issues are consistent with studies that identify these factors as significant contributors to accident severity. Both datasets highlight the substantial impact of human error, reinforcing earlier research that emphasizes the universal influence of driver conduct on road incidents [60][61][62][63][64][65]. Additionally, the increase in crash severity during nighttime driving is supported by road safety trends, where reduced visibility is linked to higher accident risks [66] This study also advances the understanding of vehicle-related factors by identifying technical defects as a major predictor of crash severity in Jordan, which reflects challenges seen in other developing regions where aging vehicle fleets and inadequate maintenance standards prevail. ...
Understanding the cultural and environmental influences on roadway crash patterns is essential for designing effective prevention strategies. This study applies advanced AI techniques, including Bidirectional Encoder Representations from Transformers (BERT) and Shapley Additive Explanations (SHAP), to examine traffic crash patterns in the United States and Jordan. By analyzing tabular data and crash narratives, the research reveals significant regional differences: in the USA, vehicle overturns and roadway conditions, such as guardrails, are major factors in fatal crashes, whereas in Jordan, technical defects and driver behavior play a more critical role. SHAP analysis identifies “driver” and “damage” as pivotal terms across both regions, while country-specific terms such as “overturn” in the USA and “technical” in Jordan highlight regional disparities. Using BERT/Bi-LSTM models, the study achieves up to 99.5% accuracy in crash severity prediction, demonstrating the robustness of AI in traffic safety analysis. These findings underscore the value of contextualized AI-driven insights in developing targeted, region-specific road safety policies and interventions. By bridging the gap between developed and developing country contexts, the study contributes to the global effort to reduce road traffic injuries and fatalities.
... As shown in Figure 8, the determinant coefficient (R 2 ) was achieved at 0.99, meaning that input features can produce a 99% variation in energy consumption. HistGBRT predictive modeling ability in transportation research field and will expand to encompass various new energy vehicles, such as plug-in hybrids, and explore novel machine learning methodologies like Bidirectional Gated Recurrent Unit renowned for their robust predictive capabilities (Kotapati et al. 2023;Abediasl et al. 2023;Bouhsissin's, Sael, and Benabbou 2023). ...
... • Complexity of Driver Behavior: Despite advancements in ITS technology, understanding and predicting driver behavior remains challenging due to the multifaceted nature of human behavior [3]. ...
... It is a multifaceted concept influenced by many factors, rendering its precise description and analysis challenging. It includes different types such as speeding, distracted driving, aggressive driving, drowsy driving, and other categories described in this systematic literature review [3]. ...
The advancement of intelligent transportation systems is crucial for improving road safety and optimizing traffic flow. In this paper, we present SafeSmartDrive, an integrated transportation monitoring system designed to detect and assess critical elements in the driving environment while simultaneously monitoring driver behavior. The system is structured into four key layers: perception, filtering and preparation, detection and classification, and alert. SafeSmartDrive focuses on two primary objectives: (1) detecting and assessing essential traffic elements, including vehicles (buses, cars, motorcycles, trucks, bicycles), traffic signs and lights, pedestrians, animals, infrastructure damage, accident classification, and traffic risk assessment, and (2) evaluating driver behavior across various road types, such as highways, secondary roads, and intersections. Machine learning and deep learning algorithms are employed throughout the system’s components. For traffic element detection, we utilize YOLOv9 in this paper, which outperforms previous versions like YOLOv7 and YOLOv8, achieving a precision of 83.1%. Finally, we present the evaluation of the SafeSmartDrive system’s real-time detection capabilities in a specific scenario in Casablanca. SafeSmartDrive’s comprehensive architecture offers a novel approach to improving road safety through the integration of advanced detection, classification, and risk assessment capabilities.
... Recently, there has been increasing interest in the development of Driver Monitoring Systems (DMS), which are expected to have a high potential in terms of driver's state/behavior estimation and situation awareness assessment [4], [5]. Situation awareness, an overarching research field covering multiple scientific domains (e.g., human factors, system engineering, dynamic systems) and industrial fields (e.g. ...
This paper presents a cognitive model designed to reproduce human drivers’ errors in predicting the motion of nearby vulnerable road users. We aim to define a computational model that, given both the trajectory of the eye gaze of a human driver and the trajectory of a bicycle, can compute the probability distribution of where the human driver believes the bicycle will be in the near future. For the design and validation of the proposed cognitive model, we tested
subjects in immersive virtual reality scenarios. The results indicate that the proposed model can generate probability distributions of the human drivers’ beliefs about the future bicycle position that are very similar, though not statistically equivalent, to those obtained experimentally. Such models could easily be generalized to describe how drivers misjudge the motion of other road users. This may enable ADAS to evaluate and improve drivers’ situational awareness. In the future, these models could also be used by autonomous cars to evaluate situational awareness of nearby humans, enabling a safer coexistence of autonomous vehicles and vulnerable road users.
... Various strategies have been proposed by governmental and social communities as well as by the OEMs (automotive industry) to reduce errors made by human drivers on urban roads and to enhance driving behavior to prevent safetycritical events [1]. However, despite the growth of vehicle automation, the number of car crashes is still unacceptably high. ...
... Deep learning uses artificial neural networks to learn complex patterns and relationships from data, while Bayesian networks are graphical models that mimic the human driving behavior by cognitive hypotheses and represent conditional dependencies between variables [9]. Various schemes have been proposed to predict driving behavior during car-following using machine learning techniques [1][2][3][4][5][6]. It explores various features, such as vehicle dynamics and driver characteristics, and applies classification algorithms to predict driver actions [7]. ...
This paper discusses the impact of Connected Cooperative and Automated Mobility (CCAM) on safety-critical events. The replacement of human drivers by autonomous vehicles (AVs) is promising improved traffic efficiency and reduction of car- crashes to zero using a baseline network traffic. Predicting driving behavior during car-following has been crucial for enhancing road safety while developing advanced driver assistance systems with adaptive cruise control. Human factors significantly influence the driving behavior of a vehicle. Thus, understanding the causal relations between human factors and driving behavior is essential for accurate prediction of vehicle behavior. This is important when autonomous vehicles are expected to behave (cooperatively, according to traffic rules and good praxis) in a human predictable manner, while driving in mixed traffic, involving autonomous, automated, and human driven vehicles. In this paper, we propose a methodology that combines convolutional neural networks (CNNs) with human factors analysis to predict driving behavior during car-following under adverse weather conditions (AWCs).
... On the other hand, driver behavior is a multidimensional concept, influenced by many factors, making its accurate description and analysis challenging [3]. These factors include social, cultural, psychological, and environmental factors [4], along with individual driver attributes [5]. ...
... In the literature, a wide range of machine learning techniques has been investigated and employed for the classification of driver behavior. The classification of driving behavior relies heavily on the utilization of these diverse ML algorithms, as highlighted in the literature [3]. The algorithms utilized in this paper are outlined below. ...
... Moreover, the literature frequently employs certain features in the analysis of driver behavior. Bouhsissin et al. [3], these commonly utilized features include speed, acceleration, accelerator pedal, rotation angle, lateral and longitudinal acceleration, as well as time of impact. The frequency of these features suggests a consensus in the literature regarding their significance and relevance for understanding diverse aspects of driver actions. ...
Machine learning (ML) techniques empower computers to learn from data and make predictions or decisions in various domains, while preprocessing methods assist in cleaning and transforming data before it can be effectively utilized by ML. Feature selection in ML is a critical process that significantly influences the performance and effectiveness of models. By carefully choosing the most relevant and informative attributes from the dataset, feature selection enhances model accuracy, reduces overfitting, and minimizes computational complexity. In this study, we leverage the UAH-DriveSet dataset to classify driver behavior, employing Filter, embedded, and wrapper methods encompassing 10 distinct feature selection techniques. Through the utilization of diverse ML algorithms, we effectively categorize driver behavior into normal, drowsy, and aggressive classes. The second objective is to employ feature selection techniques to pinpoint the most influential features impacting driver behavior. As a results, random forest emerges as the top-performing classifier, achieving an impressive accuracy of 96.4% and an F1-score of 96.36% using backward feature selection in 7.43 s, while K-nearest neighbour (K-NN) attains an accuracy of 96.29% with forward feature selection in 0.05 s. Following our comprehensive results, we deduce that the primary influential features for studying driver behavior include speed (km/h), course, yaw, impact time, road width, distance to the ahead vehicle, vehicle position, and number of detected vehicles.
... The amount of research on DBVAR has motivated various researchers to perform state-of-the-art studies. In the study by Bouhsissin et al. [22], 93 articles were reviewed between 2015 and 2022, from which it was highlighted that ML algorithms occupied the predominant position with 60%, followed by deep learning (DL) algorithms and statistical methods (with 34.87% and 5.15%, respectively). The most-used algorithms were support vector machine (SVM), logistic regression (LR), LSTM, artificial neural network (ANN), knearest neighbors (KNN), RF, and convolutional neural network (CNN). ...
... In the study by Paredes et al. [23], 27 articles were analyzed between 2015 and 2020, finding 17 ML algorithms in which Bayesian algorithms and decision trees mainly stood out. In addition, 21 relevant factors were identified in this context, coinciding with the results of Bouhsissin et al. [22], where the most used were acceleration, deceleration, and speed. Likewise, in the research of Elassad et al. [24], 82 articles from the period 2009-2019 were reviewed, and the factors and prediction aspects were analyzed. ...
Road accidents are on the rise worldwide, causing 1.35 million deaths per year, thus encouraging the search for solutions. The promising proposal of autonomous vehicles stands out in this regard, although fully automated driving is still far from being an achievable reality. Therefore, efforts have focused on predicting and explaining the risk of accidents using real-time telematics data. This study aims to analyze the factors, machine learning algorithms, and explainability methods most used to assess the risk of vehicle accidents based on driving behavior. A systematic review of the literature produced between 2013 and July 2023 on factors, prediction algorithms, and explainability methods to predict the risk of traffic accidents was carried out. Factors were categorized into five domains, and the most commonly used predictive algorithms and explainability methods were determined. We selected 80 articles from journals indexed in the Web of Science and Scopus databases, identifying 115 factors within the domains of environment, traffic, vehicle, driver, and management, with speed and acceleration being the most extensively examined. Regarding machine learning advancements in accident risk prediction, we identified 22 base algorithms, with convolutional neural network and gradient boosting being the most commonly used. For explainability, we discovered six methods, with random forest being the predominant choice, particularly for feature importance analysis. This study categorizes the factors affecting road accident risk, presents key prediction algorithms, and outlines methods to explain the risk assessment based on driving behavior, taking vehicle weight into consideration.
... After completing the preprocessing of the vehicle historical trajectory data, reference [18,19] selected a series of important and descriptive driving behavior characteristics data, as shown in Table 1. These descriptive statistics provide detailed information about vehicle driving behavior. ...
In order to improve the accuracy of vehicle trajectories and ensure driving safety, and considering the differences in driver behavior and the impact of these differences on vehicle trajectories, a vehicle trajectory-prediction method (DBC-Informer) based on the categorization of driver behavior is proposed: firstly, the characteristic driver feature data are extracted through data preprocessing; secondly, descriptive statistical data are obtained through the classification of the driver’s behavior into categories; finally, based on the Informer model, a two-layer driver category trajectory-prediction network architecture is established, which inputs the vehicle trajectories of different driving types into independent prediction sub-networks, respectively, to realize the accurate prediction of vehicle trajectories. The experimental results show that the MAE and MSE values of trajectory prediction of the DBC-Informer model in different time domains are much smaller than those of other comparative models, and the improvement of accuracy is more obvious in the long-term domain trajectory-prediction task scenario, and the increase in prediction error of the DBC-Informer model is significantly reduced after the prediction time exceeds 1 s. The on-line behavioral categorization is achieved by comparing different categorization models; it reaches 98% in classification accuracy and, according to the results of ablation experiments, the addition of the driver behavior-classification method to the prediction model improves the accuracy of prediction in longitudinal and lateral motion by 56% and 61%, respectively, which verifies the effectiveness of the driver behavior-classification method. It can be seen that the DBC-Informer model can more accurately portray the effects of different driving behaviors on vehicle trajectories and improve the accuracy of vehicle trajectory prediction, which provides important data support for vehicle warning systems.
... The latter study aims to demonstrate the ability to make environmental decisions with the support of travel information that does not align with the point of interest in this research. In the articles of Bouhsissin et al. [131] and Zaidan et al. [132], the aim of the study is to highlight and analyze the different types of driver behavior, data sources, datasets, characteristics, and artificial intelligence techniques used to classify driver behavior and its performance. Both of these secondary studies do not focus on developing countries and the associated issues. ...
The traffic in developing countries presents its own specificity, notably due to the heterogeneous traffic and a
weak-lane discipline. This leads to differences in driver behavior between these countries and developed countries.
Knowing that the analysis of the drivers from developed countries leads the design of the majority of driver models,
it is not surprising that the simulations performed using these models do not match the field data of the developing
countries. This article presents a systematic review of the literature on modeling driving behaviors in the context of
developing countries. The study focuses on the microsimulation approaches, and specifically on the multiagent
paradigm, that are considered suitable for reproducing driving behaviors with accuracy. The major contributions
from the recent literature are analyzed. Three major scientific challenges and related minor research directions are
described.