Driver Behavior Classification Research Articles

Enhancing machine learning algorithm performance through feature selection for driver behavior classification

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.

Vehicle Trajectory-Prediction Method Based on Driver Behavior-Classification and Informer Models

Vehicle Trajectory-Prediction Method Based on Driver Behavior-Classification and Informer Models

Three stage classification framework with ranking scheme for distracted driver detection using heuristic-assisted strategy

In recent days, the number of road accidents are greatly increased in world wide. The people around the world died due to the rapid road crush. The driver behavior must be detected to neglect the occurrence of road accidents. In this work, the three stage deep learning-based techniques are developed to detect the distracted driver action. The developed model is implemented in three phase to detect the distracted behavior of the driver during the driving process. In the first stage, the images are gathered from standard public resources regarding various drivers while driving. Next, the deep features retrieved using VGG16 and Inception and Xception networks. Then, the weighted fusedfusion is done by gathered features, where the weight parameter is optimized through the Adaptive Gradient-based Optimizer (AGBO) algorithm. Further, the driver behavior classification is done through a Deep Belief Network (DBN) with Radial Basis Functions Neural Networks (RBF), where the hyperparameters of DBN and RBF are optimized through the same AGBO algorithm. Finally, the first set of classified outcomes is attained from the images. In the second stage, the gathered images are fed to the feature extraction stage, where the texture features and motion features are gathered from the images. These collected features are fed to the same optimized DBN with RBF and the second set of classified outcomes with human behaviors has been attained.In the third stage, the gathered image fralgoriom the dataset is fed to the PCA for extracting the features. The gathered features are given to the same optimized DBN with the RBF classifier to get the classified outcome. Later, the classified outcomes from the three stages are fed to the ranking procedure for detecting the distracted driver action. When considering the evaluation indices, the suggested distracted driver prediction model attains 97.67% of accuracy, 97.68% of sensitivity, 97.67% of specificity, and 97.55% of precision value. Thus, the performance of the developed model in the distracted driver prediction is enhanced than the existing approaches.

SIFDriveNet: Speed and Image Fusion for Driving Behavior Classification Network

SIFDriveNet: Speed and Image Fusion for Driving Behavior Classification Network

GLMDriveNet: Global–local Multimodal Fusion Driving Behavior Classification Network

Driving behavior classification plays an important role in many fields, such as Advanced Driving Assistance System (ADAS), traffic safety, and energy saving. In this paper, we propose a Global–local Multimodal Fusion Driving Behavior Classification Network (GLMDriveNet) which classifies driver behaviors into normal driving, aggressive driving, and drowsy driving. First of all, we design a Global–local Interaction Channel Attention Module (GLI-CAM) to extract effective features in both the roadside image and the spectrogram generated from the current prediction time and its previous four seconds of vehicle speeds. Furthermore, a learnable positional embedding is introduced to fuse the global and local information of the channels for better screening of the extracted features. Secondly, we propose a Multi-scale Feature Representation Fusion Module (MS-FRFM) to associate the high-scale and low-scale information of images and spectrograms and assign different importances for different modal information, making the network more inclined to useful modal information. Our model is evaluated on a public dataset UAH-DriveSet and achieves the best performance (98.4% F1-score on all roads, 97.4% F1-score on the motorway road, and 99.8% F1-score on the secondary road) compared to other state-of-the-art methods. Our model has a very fast speed (142 FPS) and strong generalization which has been verified through extensive experiments on multiple datasets. The code is available on https://github.com/liuwenzhuo1/GLMDrivenet.

Vehicle Trajectory Data Mining for Artificial Intelligence and Real-Time Traffic Information Extraction

It aims to improve the efficiency of information collection and extraction in the current intelligent transportation system, and accurately mine the vehicle trajectory data By using Artificial Intelligence (AI) and Deep Learning methods, the trajectory data generated during vehicle driving are deeply mined and analyzed, and the characteristics of driving behavior of vehicle drivers are modeled and analyzed in detail. Then, a method of mining driving behavior characteristics based on Convolutional Neural Network (CNN) and vehicle trajectory is proposed. Based on the mathematical principle of wavelet packet and Least Square Support Vector Machine (LSSVM), a combined model of trajectory mining is constructed and applied to the short-term prediction of traffic flow. The traffic flow of Binjiang Road and Renmin Road in Guangzhou, Guangdong Province from August 19 to August 21, 2021 is predicted to verify the accuracy of the trajectory mining combined model. The results show that the combination model of data mining has good fitting effect, and the average accuracy is above 0.8. Besides, the effectiveness of the Deep Learning model in driver behavior classification is verified. The accuracy of the classification model is 75.2% for trajectory, and that is 76.8% for driver behavior characteristics. It is of great significance to effectively utilize the knowledge data in Intelligent Transportation System (ITS) and extract valuable information from it, which has certain reference value for the subsequent refined prediction of vehicle behavior.

Remaining driving range prediction for electric vehicles: Key challenges and outlook

AbstractRemaining driving range (RDR) research has continued to consistently evolve with the development of electric vehicles (EVs). Accurate RDR prediction is a promising approach to alleviate distance anxiety when power battery technology is not yet fully matured. This paper first introduces the research motivation of RDR prediction, summarizes the previous research progress, and classifies the influencing factors of RDR. Second, conduct research and analysis on the physical model of EVs, mainly including battery and vehicle models. Based on the physical model, the energy flow problem of EVs is analyzed and discussed. Third, four key challenges of RDR prediction are summarized: battery state estimation, driving behavior classification and recognition, driving condition prediction and speed prediction, and RDR calculation method. Finally, given the four challenges faced by RDR, a driving range prediction method based on vehicle‐cloud collaboration is proposed, which combines the advantages of cloud computing and machine learning to provide further research trends.

Driver Behavior Classification: A Systematic Literature Review

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 road accidents and to protect road users. The automatic detection of the driver’s behavior aids in the prevention of dangerous situations for the driver and all other participants in the driving environment, as well as the implementation of corrective measures. This paper presents a systematic literature review (SLR) of the classification of driver behavior. The study aim is to highlight and analyze the different types of driver behavior, data sources, datasets, features, and artificial intelligence techniques used to classify driver behavior and its performance. Based on the results obtained from the analysis of the selected works, we aim to identify the key contributions and challenges of studying driver behavior classification and propose potential avenues for further directions for practitioners and researchers.

Modeling Driving Behavior of Human Drivers for Trajectory Planning

Extracted driving behavior of human driven vehicles can benefit the development of various applications like trajectory prediction or planning, abnormal driving detection, driving behavior classification, traffic simulation modeling, etc. In this paper, we focus on modeling human driving behavior in order to find simplifications for trajectory planning. Using a time-discrete kinematic bicycle model with the vehicle’s acceleration and steering rate as inputs, we model the human driven trajectories of an urban intersection drone dataset for different input sampling times. While most planning algorithms are using input sampling times below 0.33s, we are able to model 98.2% of the human driven trajectories of the investigated dataset with a sampling time of 0.6s. Using longer input sampling times can result in smoother trajectories and longer planning horizons, and thus more efficient trajectories. In a next step, we analyze the correlations between the input of our model and the current state/last input. Such a priori knowledge could simplify common planning algorithms like model predictive control or tree-search based planners by limiting the action space of the ego-vehicle. We propose nonlinear transformations for steering rate and steering angle to represent correlations between speed, acceleration, steering angle and steering rate. In the transformed space the statistics are very well modeled by multivariate Gaussian distributions. Using a multivariate Gaussian, a fast usable behavior model is extracted which is independent of the environment.

Fuzzy Ontology-Based System for Driver Behavior Classification.

Intelligent transportation systems encompass a series of technologies and applications that exchange information to improve road traffic and avoid accidents. According to statistics, some studies argue that human mistakes cause most road accidents worldwide. For this reason, it is essential to model driver behavior to improve road safety. This paper presents a Fuzzy Rule-Based System for driver classification into different profiles considering their behavior. The system’s knowledge base includes an ontology and a set of driving rules. The ontology models the main entities related to driver behavior and their relationships with the traffic environment. The driving rules help the inference system to make decisions in different situations according to traffic regulations. The classification system has been integrated on an intelligent transportation architecture. Considering the user’s driving style, the driving assistance system sends them recommendations, such as adjusting speed or choosing alternative routes, allowing them to prevent or mitigate negative transportation events, such as road crashes or traffic jams. We carry out a set of experiments in order to test the expressiveness of the ontology along with the effectiveness of the overall classification system in different simulated traffic situations. The results of the experiments show that the ontology is expressive enough to model the knowledge of the proposed traffic scenarios, with an F1 score of 0.9. In addition, the system allows proper classification of the drivers’ behavior, with an F1 score of 0.84, outperforming Random Forest and Naive Bayes classifiers. In the simulation experiments, we observe that most of the drivers who are recommended an alternative route experience an average time gain of 66.4%, showing the utility of the proposal.

Density-based clustering multiple linear regression model of energy consumption for electric vehicles

With the increasing popularity of electric vehicles, energy consumption has become a key performance indicator for electric vehicle drivers, automakers and policy makers. Accurate and real-time prediction of energy consumption under real-world driving conditions is critical to reducing “range anxiety” and can support optimization of battery size, energy-saving route planning and charging facility operation. In this paper, data collected from 988 electric vehicles of the same model for one year in Zhengzhou, China, are obtained to study the energy consumption of electric vehicles in actual driving conditions. An improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model were established to classify the driving behaviors of the drivers. Then the key factors of energy consumption including velocity, accelerated velocity and temperature are studied and modeled. With that, an improved density-based clustering multiple linear regression model for energy prediction were established with driving behavior classification. The density-based clustering multiple linear regression model (DBC-MLR) has better prediction accuracy and can grasp the training features in energy consumption prediction in real driving. The proposed method shows a root mean error (RMSE) of 3.008 kwh/100 km, which is reduced by 11.3 % and 18.4 % compared to conventional machine learning method and multiple linear regression method respectively.

Driving behavior classification at signalized intersections using vehicle kinematics: Application of unsupervised machine learning

Driving behavior is considered as a unique driving habit of each driver and has a significant impact on road safety. This study proposed a novel data-driven Machine Learning framework that can classify driving behavior at signalized intersections considering two different signal conditions. To the best of our knowledge, this is the first study that investigates driving behavior at signalized intersections with two different conditions that are mostly used in practice, i.e., the control setting with the signal order of green-yellow-red and a flashing green setting with the signal order of green-flashing green-yellow-red. A driving simulator dataset collected from participants at Qatar University’s Qatar Transportation and Traffic Safety Center, driving through multiple signalized intersections, was used. The proposed framework extracts volatility measures from vehicle kinematic parameters including longitudinal speed and acceleration. K-means clustering algorithm with elbow method was used as an unsupervised machine learning to cluster driving behavior into three classes (i.e., conservative, normal, and aggressive) and investigate the impact of signal conditions. The framework confirmed that in general driving behavior at a signalized intersection reflects drivers’ habits and personality rather than the signal condition, still, it manifests the intersection nature that usually requires drivers to be more vigilant and cautious. Nonetheless, the results suggested that flashing green condition could make drivers more conservative, which could be due to the limited capabilities of human to estimate the remaining distance and the prolonged duration of the additional flashing green interval. The proposed framework and findings of the study were promising that can be used for clustering drivers into different styles for different conditions and might be beneficial for policymakers, researchers, and engineers.

Ratemaking Model of Usage Based Insurance Based on Driving Behaviors Classification

Based on the present situation of usage based insurance (UBI) research and application, this paper puts forward the UBI rating model based on driving behavior classification, and applies the technology of data mining to the evaluation of driving behavior. The actual driving behavior data and the risk data of 400 drivers are used as experimental data. Finally, an example shows that the driving behavior classification model is superior to the driving behavior score model for the identification of accident risk, which can make UBI rate more scientific and reasonable.

New LSTM Deep Learning Algorithm for Driving Behavior Classification

Road safety is an important topic of interest around the world. The road traffic accidents claim more than 1.2 million lives and cause as many as 50 million injuries each year without forgetting their huge impact on health and development. Several factors may result in the high number of accidents among which we can state the driving behavior. This paper focused on the study of drivers’ behavior and aimed to help reduce the number of accidents and consequently improve road safety. To this end, the driving behavior was classified into three categories (normal, drowsy and aggressive) based on smartphone sensors data. A new stacked Long Short-Term Memory (stacked LSTM) Recurrent Neural Networks architecture was proposed for the driving behaviors classification. The accuracy of the obtained drivers’ states results was improved with the use of the Dempster-Shafer (DS) theory of belief functions that overcame the uncertainty of data. The obtained results are clearly better than those existing in other driving behavior classification studies since the obtained F1-measure score achieves 97%.

Deriving Driver Behavioral Pattern Analysis and Performance Using Neural Network Approaches

It has been observed that driver behavior has a direct and considerable impact upon factors like fuel consumption, environmentally harmful emissions, and public safety, making it a key consideration of further research in order to monitor and control such related hazards. This has fueled our decision to conduct a study in order to arrive at an efficient way of analyzing the various parameters of driver behavior and find ways and means of positively impacting such behavior. It has been ascertained that such behavioral patterns can significantly impact the analysis of traffic-related conditions and outcomes. In such cases, the specific vehicular behavior can be detected and related data mined in order to analyze the spatial or temporal patterns of movement patterns as well as to position/track the prominent trends. This analysis seeks to determine the efficacy of such an exercise and whether the various parameters employed can help efficiently determine the various criteria for defining the driver’s style. To that end, the analysis of a driver’s behavioral pattern and performance utilizes a computer modeled application for generating a set of classifications based on the autonomous driving data as well as indicators that are characteristic of driver aggression. In order to draw such insights from the driver’s behavior, the application is modeled using various categories of data, for instance, the steering wheel’s angle, braking conditions, acceleration conditions, the vehicle speed, etc. Unlike the previously developed mechanisms for analyzing the system-based driver behavioral patterns, which were not very efficacious, this endeavor assimilates the contemporary breakthroughs in real-world scenario analysis approaches and driver behavior classification methods. Based on the system capabilities and desired outcomes, distinct strategies can be employed in order to detect the target driver’s behavior. In this specific case, neural network algorithms were utilized in order to conduct an intensive study to determine and analyze the prevailing driver behavior and driving styles. This proposed approach evaluated multiple factors that were determinants in identifying specific driver behavior and driving styles. The results of this experiment that utilized Python, indicated that the driver model in question was successful in achieving a 90% accuracy in terms of logistic regression.

Driving Behavior Classification and Sharing System Using CNN-LSTM Approaches and V2X Communication

Despite advances in autonomous driving technology, traffic accidents remain a problem to be solved in the transportation system. More than half of traffic accidents are due to unsafe driving. In addition, aggressive driving behavior can lead to traffic jams. To reduce this, we propose a 4-layer CNN-2 stack LSTM-based driving behavior classification and V2X sharing system that uses time-series data as an input to reflect temporal changes. The proposed system classifies driving behavior into defensive, normal, and aggressive driving using only the 3-axis acceleration of the driving vehicle and shares it with the surroundings. We collect a training dataset by composing a road that reflects various environmental factors using a driving simulator that mimics a real vehicle and IPG CarMaker, an autonomous driving simulation. Additionally, driving behavior datasets are collected by driving real-world DGIST campus to augment training data. The proposed network has the best performance compared to the state-of-the-art CNN, LSTM, and CNN-LSTM. Finally, our system shares the driving behavior classified by 4-layer CNN-2 stacked LSTM with surrounding vehicles through V2X communication. The proposed system has been validated in ACC simulations and real environments. For real world testing, we configure NVIDIA Jetson TX2, IMU, GPS, and V2X devices as one module. We performed the experiments of the driving behavior classification and V2X transmission and reception in a real world by using the prototype module. As a result of the experiment, the driving behavior classification performance was confirmed to be ~98% or more in the simulation test and 97% or more in the real-world test. In addition, the V2X communication delay through the prototype was confirmed to be an average of 4.8 ms. The proposed system can contribute to improving the safety of the transportation system by sharing the driving behaviors of each vehicle.

Triboelectric nanogenerator based self-powered sensor with a turnable sector structure for monitoring driving behavior

During a journey, a driver’s aggressive behavior may greatly increase the occurrence of traffic accidents and even lead to major traffic accidents. Here, we use a sector-shaped triboelectric nanogenerator (TENG) to collect the opening and closing information of the accelerator and brake pedals, and fabricate a TENG with symmetrical double turnable structure (DT-TENG) to detect the steering angle of car steering wheel. The DT-TENG with excellent sensitivity only needs two channels to collect signals, and the output voltage is up to 10 V. The driver’s driving behavior is divided into safe driving behavior and aggressive driving behavior based on the information collected by TENG, then the results are fed back to the driver so that they can analyze and correct their driving habits. These two types of TENGs collect voltage signals through the driver's actions, which not only will not infringe on the driver's privacy, but also have higher monitoring accuracy and are less likely to be deceived, demonstrating the feasibility of a self-powered sensor based on TENG with high-sensitivity in intelligent transportation systems. A triboelectric nanogenerator (TENG) with a symmetrical double turntable structure and a sector structure is used as a self-powered sensor for monitoring driver behavior. It can collect information on the driver's actions during driving, such as stepping on the accelerator, stepping on the brake, and turning the steering wheel. Moreover, the four parameters of high-speed turning, intense braking, rapid acceleration, frequent lane changes are distinguished according to the characteristics of the voltage waveform. These four parameters are scored to determine the driver's driving behavior classification. We divides driving behavior into aggressive driving behavior and safe driving behavior in this work, and displays the proportion of illegal operations to remind drivers to improve their bad driving habits. • A TENG with a symmetrical double turntable structure is fabricated and used to measure the angle of steering wheel rotation. • The voltage signals collected by TENG have the advantage of being stable and intuitive, which can reduce the complexity of algorithm processing. • These TENGs can be used in intelligent transportation systems, where drivers get feedback through driving evaluation to improve safety.

Identification of Driving Safety Profiles in Vehicle to Vehicle Communication System Based on Vehicle OBD Information

Driver behavior is a determining factor in more than 90% of road accidents. Previous research regarding the relationship between speeding behavior and crashes suggests that drivers who engage in frequent and extreme speeding behavior are overinvolved in crashes. Consequently, there is a significant benefit in identifying drivers who engage in unsafe driving practices to enhance road safety. The proposed method uses continuously logged driving data to collect vehicle operation information, including vehicle speed, engine revolutions per minute (RPM), throttle position, and calculated engine load via the on-board diagnostics (OBD) interface. Then the proposed method makes use of severity stratification of acceleration to create a driving behavior classification model to determine whether the current driving behavior belongs to safe driving or not. The safe driving behavior is characterized by an acceleration value that ranges from about ±2 m/s2. The risk of collision starts from ±4 m/s2, which represents in this study the aggressive drivers. By measuring the in-vehicle accelerations, it is possible to categorize the driving behavior into four main classes based on real-time experiments: safe drivers, normal, aggressive, and dangerous drivers. Subsequently, the driver’s characteristics derived from the driver model are embedded into the advanced driver assistance systems. When the vehicle is in a risk situation, the system based on nRF24L01 + power amplifier/low noise amplifier PA/LNA, global positioning system GPS, and OBD-II passes a signal to the driver using a dedicated liquid-crystal display LCD and light signal. Experimental results show the correctness of the proposed driving behavior analysis method can achieve an average of 90% accuracy rate in various driving scenarios.

Micro-analysis of a single vehicle driving volatility and impacts on emissions for intercity corridors

A deep understanding of driver behavior is an important step to improve road safety and environmental performance. Volatility can be defined as the extent of variations in driving, which can be characterized by accelerations/braking, lane change, and unusual high speed for roadways conditions. There is a lack of knowledge on what concerns the relationship between driver’s volatility and exhaust emissions and how driving volatility can be used as safety eco-indicator. This article explores a driving volatility concept for assessing tailpipe emissions and driving behavior classification. For that purpose, an empirical approach that combined vehicle activity and emission rates for light duty vehicles was used. Field measurements were collected from four probe vehicles in one partly urban/rural, and two highway routes using Portable Emission Measurement Systems, Global Positioning System receivers, and On-board Diagnostic scan tool, to measure real-world tailpipe emissions, position and engine activity data. Acceleration-based parameters, including relative positive acceleration and mean of positive acceleration, acceleration, vehicular jerk, and power demand thresholds were used to detect differences in emissions for different driving styles. Results indicated that vehicular jerk impacted carbon dioxide and nitrogen oxides per unit distance regardless of driving style and route type, especially from negative to null jerk values and during positive accelerations. There is potential to incorporate the analyzed thresholds into a driver decision support algorithm by considering safety and environmental aspects through warning messages.

Driver Behavior Classification at Stop-Controlled Intersections Using Video-Based Trajectory Data

Understanding how drivers behave at stop-controlled intersection is of critical importance for the control and management of an urban traffic system. It is also a critical element of consideration in the burgeoning field of smart infrastructure and connected and autonomous vehicles (CAV). A number of past efforts have been devoted to investigating the driver behavioral patterns when they pass through stop-controlled intersections. However, the majority of these studies have been limited to qualitative descriptions and analyses of driver behavior due to the unavailability of high-resolution vehicle data and sound methodology for classifying various driver behaviors. In this paper, we introduce a methodology that uses computer-vision vehicle trajectory data and unsupervised clustering techniques to classify different types of driver behaviors, infer the underlying mechanism and compare their impacts on safety. Two major types of behaviors are investigated, including vehicle stopping behavior and vehicle approaching patterns, using two clustering algorithms: a bisecting K-means algorithm for classifying stopping behavior, and the improved density-based spatial clustering of applications with noise (DBSCAN) algorithm for classifying vehicle approaching patterns. The methodology is demonstrated using a case study involving five stop-controlled intersections in Montreal, Canada. The results from the analysis show that there exist five distinctive classes of driver behaviors representing different levels of risk in both vehicle stopping and approaching processes. This finding suggests that the proposed methodology could be applied to develop new safety surrogate measures and risk analysis methods for network screening and countermeasure analyses of stop-controlled intersections.