Driver Behavior Research Articles

ANALISIS RISIKO TERHADAP PERILAKU YANG MEMBAHAYAKAN PADA PENGEMUDI DUMP TRUCK DALAM PENGANGKUTAN BATUBARA DI PT BAHANA BUMI MANDIRI KABUPATEN LAHAT PROVINSI SUMATERA SELATAN

PT Bahana Bumi Mandiri is an experienced logistics and contractor transportation provider company since 2016 located in South Sumatera. One of the accident prevention programs at PT Bahana Bumi Mandiri’s operations is to emphasize the importance of communication with dump truck drivers, and one form of implementing this programis to ensure that the unit is on the dump truck driver when operating. The aim of this research is to find out the risk of dangerous behavior of dump truck drivers when transporting coal and to find out efforts to improve or solve the risk and behavior that have been caused by dump truck drivers when transporting coal. The standard used at PT Bahana Bumi Mandiri is P2H (Daily Inspection and Checking). The implementation of safe driving at PT Bahana Bumi Mandiri is still relatively minimal so it is necessary to add safety driving to reduce potential dangers that could occur. However, it is necessary to know first the attitude of dump truck drivers by asking question in the form of a questionnaire so the data is processed so that the results can be known. If the need for safe driving in mines is not implemented more fully, it can increase the risk of accidents or incidents in the work emvironment.

Nighttime driver behavior prediction using taillight signal recognition via CNN-SVM classifier

Nighttime driver behavior prediction using taillight signal recognition via CNN-SVM classifier

Research Progress of Dangerous Driving Behavior Recognition Methods Based on Deep Learning

In response to the rising frequency of traffic accidents and growing concerns regarding driving safety, the identification and analysis of dangerous driving behaviors have emerged as critical components in enhancing road safety. In this paper, the research progress in the recognition methods of dangerous driving behavior based on deep learning is analyzed. Firstly, the data collection methods are categorized into four types, evaluating their respective advantages, disadvantages, and applicability. While questionnaire surveys provide limited information, they are straightforward to conduct. The vehicle operation data acquisition method, being a non-contact detection, does not interfere with the driver’s activities but is susceptible to environmental factors and individual driving habits, potentially leading to inaccuracies. The recognition method based on dangerous driving behavior can be monitored in real time, though its effectiveness is constrained by lighting conditions. The precision of physiological detection depends on the quality of the equipment. Then, the collected big data are utilized to extract the features related to dangerous driving behavior. The paper mainly classifies the deep learning models employed for dangerous driving behavior recognition into three categories: Deep Belief Network (DBN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). DBN exhibits high flexibility but suffers from relatively slow processing speeds. CNN demonstrates excellent performance in image recognition, yet it may lead to information loss. RNN possesses the capability to process sequential data effectively; however, training these networks is challenging. Finally, this paper concludes with a comprehensive analysis of the application of deep learning-based dangerous driving behavior recognition methods, along with an in-depth exploration of their future development trends. As computer technology continues to advance, deep learning is progressively replacing fuzzy logic and traditional machine learning approaches as the primary tool for identifying dangerous driving behaviors.

Implementation of Driver Behaviors Risk Detection and Safety Alert System in Road Transport Management: A Case Study of Nong Khai Border Checkpoint

Implementation of Driver Behaviors Risk Detection and Safety Alert System in Road Transport Management: A Case Study of Nong Khai Border Checkpoint

COUNTERPRODUCTIVE WORK BEHAVIOR: PENGARUH JOB DEMAND DAN KNOWLEDGE MANAGEMENT

The study highlights the impact of job demand and knowledge management in the company towards the counterproductive work behavior of drivers and co-drivers in a bus company. Conducted at PT Gunung Harta Transport Solutions, Malang, Indonesia, the research involved 79 bus crew consists of drivers and co-driver that are selected through simple random sampling from a population of 382 crew. Data for the research were collected via questionnaire and analyzed using the Structural Equation Model Partial Least Square (SEM-PLS) method. The result reveal that knowledge management had a significant negative impact towards counterproductive work behavior and that job demand positively and significantly influence counterproductive work behavior. These findings can be valuable for human resource management to manage and mitigate employee’s counterproductive work behavior with the help of a good knowledge management and the right amount of job demand.

Investigating the impacts of auditory and visual feedback in advanced driver assistance systems: a pilot study on driver behavior and emotional response

In the autonomous vehicle industry, Advanced Driver Assistance Systems (ADAS) are recognized for their capacity to enhance service quality, improve on-road safety, and increase driver comfort. Driver Assistance Systems are able to provide multi-modal feedback including auditory cues, visual cues, vibrotactile cues and so on. The study will concentrate on assessing the impacts of auditory and visual feedback from assistive driving systems on drivers. A group consisting of five participants (N = 5) was recruited to take part in two sets of driving experiments. During the experimental sessions, they were exposed to several reminders designed for drivers in audio-only format and audio-visual format, respectively. Their driving behaviors and performances were under researcher’s observation, while their emotions were evaluated by YOLO v5 detecting model. The results reveal that the participants higher compliance rate and strong emotional reactions (especially the feelings of anger, sadness and surprise) towards the unimodal feedback of audio-only driving reminders. There is no strong evidence showing that the bimodal ADAS feedback of audio-visual cues effectively improve drivers’ performance during driving period. However, both the emotion data and user satisfaction results indicate that participants experienced an increase in feelings of happiness when they were able to visualize the AI assistant while hearing the audio reminders from the assistant. The study serves as one of the pioneering studies aimed at enhancing the theoretical foundation in the field of automotive user interface design, particularly concerning the design of auditory functions.

Open source head and face estimation as a complement to commercial eye-tracking

Eye-tracking solutions are a mainstay in driver modeling research; however, their limitations motivate exploration of complementary methods. One such is available in a class of machine vision models that estimate head pose, eye gaze, facial landmarks, and facial action units. In this article, we share lessons learned from using an open source tool to measure driver behavior. We selected a tool called OpenFace and applied it to an existing drowsy driving dataset that was collected with a commercial camera-based driver monitoring system. Forty participants each drove for around three hours in the early morning. Variables from the driver monitoring system combined with other simulator data and a set of videos from different cameras were recorded as part of the simulator video capture software. OpenFace was used to process the driver-facing video and integrate its output into the dataset. We considered a set of measures appropriate for modeling driver drowsiness, including eye closure, gaze dispersion, head movements, head stillness, and facial contortions (e.g., yawns, brow furrowing, etc.). We present comparisons of similar data between the commercial system and open-source model. Several lessons learned on topics including camera placement, ambient lighting, and data synchronization are shared, along with recommendations for future work.

Partially temporally constrained modeling of speeding crash-injury severities on freeways and non-freeways before, during, and after the stay-at-home order.

Speeding crashes remain high injury severities after the stay-at-home order in California, highlighting a need for further investigation into the fundamental cause of this increment. To systematically explore the temporal impacts of the stay-at-home order on speeding behaviors and the corresponding crash-injury outcomes, this study utilizes California-reported single-vehicle speeding crashes on freeways (access-controlled) and non-freeways (non-access-controlled) before, during, and after the order. Significant injury factors and in-depth heterogeneity across observations are identified by random parameter logit models with heterogeneity in means and variances. Without segmenting the data by periods, the partially temporally constrained approach is employed to statistically determine varying and stabilized parameters over time through the whole dataset. Different likelihood ratio tests reveal significant temporal instabilities and stabilities of factors between two roadways and three periods. The potential impacts of observation selection issues on the marginal effect calculations of the partially constrained models are also systematically investigated. Significant variations in the probability of severe injury rate per week after the order are also found based on the Mann-Whitney U tests. The hysteretic effects of the order on the crash frequency and severity are observed on both freeways and non-freeways. Overall, seven variables are found to have stable effects, while fifteen variables exhibit unstable effects over time. Significant temporal variations in driver behaviors, including driving under the influence, cell phone usage, hit-and-run, failure to use seat belt, entering or leaving the ramp, and reaction to previous collisions, are observed before, during, or after the order. Specific countermeasures and effects of heterogeneity in means and variances are also discussed. These findings provide insights into understanding the temporal impacts of the stay-at-home order on injury severities, which are valuable to decision-makers and researchers for future order practice, restriction improvement, and complementary policy development.

Identifying factors affecting driver takeover time and crash risk during the automated driving takeover process

This study aims to develop prediction models of driver takeover time and crash risks during the automated driving takeover process. A driving simulator experiment was conducted to collect vehicle trajectory and driver behavior data. The random-parameter duration model was first built to model driver takeover time. Results indicated that young drivers, novice drivers, takeover request lead time, and traffic volume had varying impacts on takeover time due to the unobserved heterogeneity. Then, an explainable machine learning model was utilized to predict and explore various predictors’ impacts on takeover crashes. Validation results revealed that the developed model provided satisfactory accuracy in predicting crashes. SHAP was used to interpret the estimated results by examining contributory factors’ main effects and interactive effects on crash risks. Takeover crash risk is positively correlated with vehicle speed, takeover time, maximum lateral acceleration, traffic volume, and tasks of watching videos and playing games. Additionally, takeover request lead time and the maximum longitudinal deceleration were found to affect crash risks negatively. Research findings shed insights into modeling takeover time and predicting crash risks during the takeover process, and highlight the importance of considering the heterogeneity of drivers when designing automated driving systems (ADS) to improve driver takeover performance.

Smart ETA Predictions: Leveraging AI and Neutrosophic Fuzzy Soft Sets for Real-Time Accuracy

In this paper we aims to provide a clear definition of Neutrosophic Fuzzy Soft Sets and explain its fundamental operations through relevant examples. This work examines the computation of static Expected Time of Arrival (ETA) utilizing neutrosophic fuzzy soft set values and the fundamental Expected Time of Arrival. Our research also investigates the incorporation of sophisticated artificial intelligence (AI) methods to create reliable and adaptable dynamic Expected Time of Arrival(ETA) prediction models. Through the utilization of many types of data, such as current traffic statistics, weather conditions, road conditions, vehicle status, and driver behavior, we suggest a comprehensive system that adapts to changing circumstances and consistently enhances its ability to make accurate predictions. Our methodology utilizes cutting-edge machine learning algorithms to analyze and interpret vast amounts of diverse data. In addition, we tackle the difficulties of managing uncertainty and indeterminacy in data by utilizing Neutrosophic Fuzzy Soft Sets, which improve the model’s resilience and dependability.

Design of workplace and destination-based EV charging networks considering driver behavior, habits, and preferences

Design of workplace and destination-based EV charging networks considering driver behavior, habits, and preferences

Driver behavior in developing countries: evidence from modeling anger and aggression performance of Nigerian drivers on inter-city trips

Driver behavior in developing countries: evidence from modeling anger and aggression performance of Nigerian drivers on inter-city trips

Time-dependent effect of advanced driver assistance systems on driver behavior based on connected vehicle data

Time-dependent effect of advanced driver assistance systems on driver behavior based on connected vehicle data

Clustering and Investigation of Human Driving Behavior using Autoencoder and Risk Assessment

Clustering and Investigation of Human Driving Behavior using Autoencoder and Risk Assessment

Risk factors in young car drivers of the Metropolitan Area of Guadalajara, Mexico

In the Guadalajara Metropolitan Area (GMA), Mexico, the main cause ofpremature death in young adults is injuries caused by traffic accidents (TA).Exposure and vulnerability factors to traffic accidents in young drivers wereanalyzed for this area. To do so, a mixed research was conducted, based on aninterpretive paradigm. To determine the exposure and vulnerability of youngpeople to TA, secondary data sources and interviews with young people aged 16to 24 years, with a history of TA as a driver, were used. Recommendations foraction are proposed. As a result, driver behaviors (73%) stood out as anexposure factor to TA and emotional disturbance (84%) as a vulnerability factor.The GMA is characterized by a high number of vehicles per capita, mobilitymainly by private cars, poor road culture, dispersed urban growth withoutplanning, and a favorable context for TA. Reducing AT in young people requiresreducing exposure: changing risk behaviors and driver attention, road education,regulatory monitoring, reducing the number of vehicles per capita, prioritizingnon-motorized mobility by improving public transportation and roadinfrastructure, creating safe environments, and evaluating the effectiveness ofimplemented measures.

Exploring service quality and pricing ethics of motorcycle drivers in cabanatuan: Perspectives of student clients

This study explores the service quality and pricing ethics of motorcycle drivers in Cabanatuan City, focusing on the perceptions of student clients. Motorcycle services, widely used for their affordability and accessibility, often face challenges related to professionalism, safety, and ethical pricing practices. This research evaluated the factors influencing customer satisfaction and trust among students, including safety, professionalism, punctuality, vehicle condition, and pricing transparency. A descriptive quantitative research design was employed, collecting data from 35 student respondents through a structured questionnaire disseminated via Google Forms. The results revealed moderate satisfaction with professionalism, punctuality, and vehicle condition but highlighted significant gaps in safety measures, transparency in pricing, and driver behavior. Ethical concerns, including inconsistent fare practices and perceived overcharging, were particularly evident during peak demand periods, undermining student trust. The findings emphasize the need for targeted interventions such as mandatory driver training, standardized pricing mechanisms, and improved service coverage to enhance the reliability and equity of motorcycle services. However, the study's scope was limited to a single semester and a small sample of 35 respondents, restricting the generalizability of the results. Future research should expand the sample size and include broader demographics to comprehensively understand the issues.

Design and Development of A Microcontroller-Based Driving Behavior Monitoring Device as A Form of Mass Transportation Oversight

Design and Development of A Microcontroller-Based Driving Behavior Monitoring Device as A Form of Mass Transportation Oversight

Aggressive Driving Behavior Recognition based on K-means Clustering

Accurate identification of aggressive driving behavior is crucial for improving traffic safety and promoting social responsibility, and it is also a key component in the realization of intelligent transportation systems. This paper proposes a method for aggressive driving behavior recognition and data modeling based on K-means clustering. First, the NGSIM (Next Generation Simulation) vehicle trajectory dataset is used for preprocessing the raw data, and effective behavioral feature representations are obtained through feature extraction. Next, Principal Component Analysis (PCA) is applied to reduce the dimensionality of the data, extracting three main components to simplify the data structure. Subsequently, the K-means clustering algorithm is employed to classify the reduced data and identify potential patterns of aggressive driving behavior. Experimental results demonstrate that the proposed method effectively identifies aggressive driving behavior, providing technical support for improving traffic system safety and raising awareness of social responsibility.

Cockpit-Llama: Driver Intent Prediction in Intelligent Cockpit via Large Language Model

The cockpit is evolving from passive, reactive interaction toward proactive, cognitive interaction, making precise predictions of driver intent a key factor in enhancing proactive interaction experiences. This paper introduces Cockpit-Llama, a novel language model specifically designed for predicting driver behavior intent. Cockpit-Llama predicts driver intent based on the relationship between current driver actions, historical interactions, and the states of the driver and cockpit environment, thereby supporting further proactive interaction decisions. To improve the accuracy and rationality of Cockpit-Llama’s predictions, we construct a new multi-attribute cockpit dataset that includes extensive historical interactions and multi-attribute states, such as driver emotional states, driving activity scenarios, vehicle motion states, body states and external environment, to support the fine-tuning of Cockpit-Llama. During fine-tuning, we adopt the Low-Rank Adaptation (LoRA) method to efficiently optimize the parameters of the Llama3-8b-Instruct model, significantly reducing training costs. Extensive experiments on the multi-attribute cockpit dataset demonstrate that Cockpit-Llama’s prediction performance surpasses other advanced methods, achieving BLEU-4, ROUGE-1, ROUGE-2, and ROUGE-L scores of 71.32, 80.01, 76.89, and 81.42, respectively, with relative improvements of 92.34%, 183.61%, 95.54%, and 201.27% compared to ChatGPT-4. This significantly enhances the reasoning and interpretative capabilities of intelligent cockpits.

Adaptive Software Component for Predicting Energy Consumption of an Electric Vehicle on a Planned Route

This paper presents the development of an adaptive software component for forecasting the energy consumption of electric vehicles along planned routes. It includes a conceptual framework, architectural design, and modular software composition, introducing mathematical models for managing energy consumption with a model-based design approach for precise predictions and optimization. The importance of data sources such as route information, vehicle condition, and driver behavior is emphasized to create a comprehensive state vector for energy optimization. Following ISO 26262 and A-SPICE 3.1 standards, the implementation uses a model-based approach with Simulink and aligns with the V-Model for rigorous validation. The methodology details segmenting routes and optimizing energy consumption for each segment, considering driving style and environmental conditions. The gradient search method adjusts energy consumption to minimize usage while maximizing comfort and ensuring route completion. This research lays the groundwork for future advancements in predictive energy management systems for electric vehicles, with potential real-world applications. Future work will focus on refining predictive models, exploring machine learning for improved accuracy, and integrating real-time data from connected vehicle technologies for dynamic optimization.