Search Results (776)

Many traffic-sign detection systems are available to assist drivers with particular conditions such as small and distant signs, multiple signs on the road, objects similar to signs, and other challenging conditions. Real-time object detection is an indispensable aspect of these detection systems, with detection speed and efficiency being critical parameters. In terms of these parameters, to enhance performance in road-sign detection under diverse conditions, we proposed a comprehensive methodology, SSAM_YOLOv5, to handle feature extraction and small-road-sign detection performance. The method was based on a modified version of YOLOv5s. First, we introduced attention modules into the backbone to focus on the region of interest within video frames; secondly, we replaced the activation function with the SwishT_C activation function to enhance feature extraction and achieve a balance between inference, precision, and mean average precision (mAP@50) rates. Compared to the YOLOv5 baseline, the proposed improvements achieved remarkable increases of 1.4% and 1.9% in mAP@50 on the Tiny LISA and GTSDB datasets, respectively, confirming their effectiveness. Full article

This paper evaluates the effectiveness of driver training programmes aimed at the proper use of Advanced Driver Assistance Systems (ADASs). Participants (N = 49) were divided into the following three groups based on the type of training received: practical training, e-learning, and brief manual instruction. The effectiveness of the training methods was assessed using selected parameters obtained from driving simulator studies, including reaction times and system activation attempts. Given the large volume and nonlinear nature of the input data, a heuristic, expert-based approach was used to identify key evaluation criteria, structure the decision-making process, and define fuzzy rule sets and membership functions. This phase served as the foundation for the development of a fuzzy logic model in the MATLAB environment. The model processes inputs to generate a quantitative performance score. The results indicate that practical training (mean score = 4.0) demonstrates superior effectiveness compared to e-learning (3.09) and manual instruction (mean score = 3.01). The primary contribution of this work is a transparent, data-driven evaluation tool that overcomes the inherent subjectivity and bias of traditional trainer-based assessments. This model provides a standardised and reproducible approach for assessing driver competence, offering a significant advancement over purely qualitative, trainer-based assessments and supporting the development of more reliable certification processes. Full article

This paper details the design and implementation of a fuzzy logic control system for an advanced driver-assistance system (ADAS) that adjusts brake force based on proximity sensing, vehicle speed, and road conditions. By employing a cost-effective ultrasonic sensor (HC-SR04) and an STM32 microcontroller, the system facilitates real-time adjustments to braking force, enhancing both vehicle safety and driver comfort. The fuzzy logic controller processes three inputs to deliver a smooth and adaptive brake response, thus addressing the shortcomings of traditional binary systems that can lead to abrupt and unsafe braking actions. The effectiveness of the system is validated through several test cases, demonstrating improved responsiveness and safety across various driving scenarios. This paper presents a cost-effective model for a straightforward braking system using fuzzy logic, laying the groundwork for the development of more advanced systems in emerging technologies. Full article

The development of Advanced Driver Assistance Systems (ADASs) has reached a stage where, in addition to the traditional challenges of path planning and control, there is an increasing focus on the behavior of these systems. Assistance functions shall be personalized to deliver a full user experience. Therefore, driver modeling is a key area of research for next-generation ADASs. One of the most common tasks in everyday driving is lane keeping. Drivers are assisted by lane-keeping systems to keep their vehicle in the center of the lane. However, human drivers often deviate from the center line. It has been shown that the driver’s choice to deviate from the center line can be modeled by a linear combination of preview curvature information. This model is called the Linear Driver Model. In this paper, we fit the LDM parameters to real driving data. The drivers are then clustered based on the individual parameters. It is shown that clusters are not only formed by the numerical similarity of the driver parameters, but the drivers in a cluster actually have similar behavior in terms of path selection. Finally, an Extended Kalman Filter (EKF) is proposed to learn the model parameters at run-time. Any new driver can be classified into one of the driver type groups. This information can be used to modify the behavior of the lane-keeping system to mimic human driving, resulting in a more personalized driving experience. Full article

The integration of connected autonomous vehicles (CAVs), advanced driver assistance systems (ADAS), and conventional vehicles necessitates the development of robust methodologies to enhance traffic efficiency and ensure safety across heterogeneous traffic streams. A comprehensive understanding of vehicle interactions and operating speed variability is essential to support informed decision-making in traffic management and infrastructure design. This study presents operating speed models aimed at estimating the 85th percentile speed (V₈₅) on straight road segments, utilizing floating car data (FCD) for both calibration and validation purposes. The dataset encompasses approximately 2000 km of the Italian road network, characterized by diverse geometric features. Speed observations were analyzed under three traffic conditions: general traffic, free-flow, and free-flow with dry pavement. Results indicate that free-flow conditions improve the model’s explanatory power, while dry pavement conditions introduce greater speed variability. Initial models based exclusively on geometric parameters exhibited limited predictive accuracy. However, the inclusion of posted speed limits significantly enhanced model performance. The most influential predictors identified were the V₈₅ on the preceding curve and the length of the straight segment. These findings provide empirical evidence to inform road safety evaluations and geometric design practices, offering insights into driver behavior in mixed-traffic environments. The proposed model supports the development of data-driven strategies for the seamless integration of automated and non-automated vehicles. Full article

This study investigates the knowledge, perception and trust in Advanced Driver Assistance Systems (ADAS) among drivers in Eastern Sicily, a Mediterranean region characterized by infrastructural and socio-economic differences. A structured survey (N = 961) was conducted to assess user attitudes towards eight key ADAS technologies using two validated indices: the Knowledge Index (KI) and the Importance Index (II). To capture user consistency, a normalized product (z(KI) × z(II)) was calculated for each technology. This composite metric enabled the identification of three latent dimensions through exploratory factor analysis: Emergency-Triggered Systems, Adaptive and Reactive Systems and Driver Vigilance and Stability Systems. The results show a clear discrepancy between perceived importance (56.6%) and actual knowledge (35.1%). Multivariate analyses show that direct experience with ADAS-equipped vehicles significantly increases both awareness and confidence. Age is inversely correlated with knowledge, while gender has only a marginal influence. The results are consistent with established acceptance models such as TAM and UTAUT, which emphasize the role of perceived usefulness and trust. The study presents an innovative integration of psychometric metrics and behavioral theory that provides a robust and scalable framework for assessing user readiness in evolving mobility contexts, particularly in regions facing infrastructural heterogeneity and cultural changes in travel behavior. Full article

The integration of intelligent voice-control systems represents a critical pathway for enhancing driver comfort and reducing cognitive distraction in modern vehicles. Currently, voice assistants capable of accessing real-time vehicular data (e.g., engine parameters) or controlling actuators (e.g., door locks) remain exclusive to premium brands. While aftermarket solutions like Amazon’s Echo Auto provide multimedia functionality, they lack access to critical vehicle systems. To address this gap, we develop a novel architecture leveraging the OBD-II port to enable voice-controlled telematics and actuation in mass-production vehicles. Our system interfaces with a Toyota Hilux (2020) and Mazda CX-3 SUV (2021), utilizing an MCP2515 CAN controller for engine control unit (ECU) communication, an Arduino Nano for data processing, and an ESP01 Wi-Fi module for cloud transmission. The Blynk IoT platform orchestrates data flow and provides user interfaces, while a Voiceflow-programmed Alexa skill enables natural language commands (e.g., “unlock doors”) via Alexa Auto. Experimental validation confirms the successful real-time monitoring of engine variables (coolant temperature, air–fuel ratio, ignition timing) and secure door-lock control. This work demonstrates that high-end vehicle capabilities—previously restricted to luxury segments—can be effectively implemented in series-production automobiles through standardized OBD-II protocols and IoT integration, establishing a scalable framework for next-generation in-vehicle assistants. Full article

This study proposes an automatic gear shift classification algorithm in M1 category vehicles using data acquired through the onboard diagnostic system (OBD II) and GPS. The proposed approach is based on the analysis of identification parameters (PIDs), such as manifold absolute pressure (MAP), revolutions per minute (RPM), vehicle speed (VSS), torque, power, stall times, and longitudinal dynamics, to determine the efficiency and behavior of the vehicle in each of its gears. In addition, the unsupervised K-means algorithm was implemented to analyze vehicle gear changes, identify driving patterns, and segment the data into meaningful groups. Machine learning techniques, including K-Nearest Neighbors (KNN), decision trees, logistic regression, and Support Vector Machines (SVMs), were employed to classify gear shifts accurately. After a thorough evaluation, the KNN (Fine KNN) model proved to be the most effective, achieving an accuracy of 99.7%, an error rate of 0.3%, a precision of 99.8%, a recall of 99.7%, and an F1-score of 99.8%, outperforming other models in terms of accuracy, robustness, and balance between metrics. A multiple linear regression model was developed to estimate instantaneous fuel consumption (in L/100 km) using the gear predicted by the KNN algorithm and other relevant variables. The model, built on over 66,000 valid observations, achieved an R² of 0.897 and a root mean square error (RMSE) of 2.06, indicating a strong fit. Results showed that higher gears (3, 4, and 5) are associated with lower fuel consumption. In contrast, a neutral gear presented the highest levels of consumption and variability, especially during prolonged idling periods in heavy traffic conditions. In future work, we propose integrating this algorithm into driver assistance systems (ADAS) and exploring its applicability in autonomous vehicles to enhance real-time decision making. Such integration could optimize gear shift timing based on dynamic factors like road conditions, traffic density, and driver behavior, ultimately contributing to improved fuel efficiency and overall vehicle performance. Full article

Revealing the complex system of transboundary conflicts would help to understand the behavior of states and anticipate potential actions that would collectively reflect the state doctrine. However, a specific approach to the state political doctrine (SPD) for governing transboundary water has not been formalized. The core academic contribution of this research is to formalize the structure of the SPD for transboundary water, which might assist in fostering water cooperation and peacebuilding in one of the most conflict-prone regions—the Middle East and South Africa—by examining the upstream countries’ behavior. Case studies include Turkey in the Euphrates–Tigris Basins, Israel in the Jordan River Basin, and Ethiopia in the Nile River Basin. The theoretical framework presents a new paradigm that systematically links a state’s essential drivers, political philosophy, and potential actions, employing the Hegelian dialectic of thesis–antithesis–synthesis and the three Doctrines of Being, Essence, and Concept to articulate the state’s behavior and its indispensable core principles for survival. It is integrated with Arnold Toynbee’s challenge-and-response theory to analyze upstream motives. This study reviewed 328 documents and pieces of literature alongside 105 expert discussions. The key findings include the three upstream countries embracing different SPDs to address specific challenges at the state level, where Turkey employs the Water-Bank Doctrine, Israel utilizes the Identity-Seeking Doctrine, and Ethiopia adopts the Nation Rise Power Doctrine. Besides the critical external challenges that limit water availability, such as the impact of climate change, the time factor is a crucial key to shifting the bargaining power and impacting the adopted SPD, thereby affecting water diplomacy and regional water cooperation. Full article

This study explores the potential of freely available tools for collecting, processing, and applying information in the management of mechanized fieldwork. A hierarchical approach was developed, integrating operational, logistical, and strategic levels of decision-making based on crop type, land conditions, machinery, labor, and time constraints. Various technological and technical solutions were evaluated through simulations and manual data processing. The proposed methodology was applied to a real-world case in Kalipetrovo, Bulgaria. The results include a 3.5-fold reduction in required tractors and a 50% decrease in tractor driver needs, achieved through extended working hours and shift scheduling. Additional benefits were identified from replacing conventional tillage with deep tillage, resulting in higher fuel consumption but improved soil preparation. Detailed resource schedules were created for machinery, labor, and fuel, highlighting seasonal peaks and optimization opportunities. The approach relies on spreadsheets and free AI-assisted platforms, proving to be a low-cost, accessible solution for mid-sized farms lacking advanced digital infrastructure. The findings demonstrate that structured information integration can support the effective renewal and utilization of tractor and machinery fleets while offering a scalable basis for decision support systems in agricultural engineering. Full article

With the rapid development of intelligent transportation systems, voice assistants are increasingly integrated into driving environments, providing an effective means to mitigate the risks of fatigued driving. This study explored drivers’ interaction preferences with voice assistants under different fatigue states and proposed a fatigue-state-based dialogue-awakening mechanism. Using Grounded Theory and the Stimulus–Organism–Response (SOR) framework, in-depth interviews were conducted with 25 drivers from diverse occupational backgrounds. To validate the qualitative findings, a driving simulation experiment was carried out to examine the effects of different voice interaction styles on driver fatigue arousal across various fatigue levels. Results indicated that heavily fatigued drivers preferred highly stimulating and interactive voice communication; mildly fatigued drivers tended toward gentle and socially supportive dialogue; while drivers in a non-fatigued state preferred minimal voice interference, activating voice assistance only when necessary. Significant occupational differences were also observed: long-haul truck drivers emphasized practicality and safety in voice assistants, taxi drivers favored voice interactions combining navigation and social content, and private car owners preferred personalized and emotional support. This study enriches the theoretical understanding of fatigue-sensitive voice interactions and provides practical guidance for the adaptive design of intelligent voice assistants, promoting their application in driving safety. Full article

Computer vision is one of the key technologies of advanced driver assistance systems (ADAS), but the incorporation of a vision-based driver assistance system (still) poses a great challenge due to the special characteristics of the algorithms, the neural network architecture, the constraints, and the strict hardware/software requirements that need to be met. The aim of this study is to show the influence of image resolution in traffic lane detection using a virtual dataset from virtual simulation environment (CARLA) combined with a real dataset (TuSimple), considering four performance parameters: Mean Intersection over Union (mIoU), F1 precision score, Inference time, and processed frames per second (FPS). By using a convolutional neural network (U-Net) specifically designed for image segmentation tasks, the impact of different input image resolutions (512 × 256, 640 × 320, and 1024 × 512) on the efficiency of traffic line detection and on computational efficiency was analyzed and presented. Results indicate that a resolution of 512 × 256 yields the best trade-off, offering high mIoU and F1 scores while maintaining real-time processing speeds on a standard CPU. A key contribution of this work is the demonstration that combining synthetic and real datasets enhances model performance, especially when real data is limited. The novelty of this study lies in its dual analysis of simulation-based data and image resolution as key factors in training effective lane detection systems. These findings support the use of synthetic environments in training neural networks for autonomous driving applications. Full article

LiDAR is a technology that uses laser pulses to measure an object’s distance, an essential technology for Advanced Driver Assistance Systems (ADASs). However, it can be affected by adverse weather environments that may reduce the safety of ADASs. This paper proposes a convolutional neural network that utilizes lightweight network nodes with multiple repetitions instead of the traditional large-scale model. The proposed approach reduces the parameter size, and a consistent pre-processing method is designed to control the input parameters of the network. This process reduces the data size while retaining sufficient features for neural network training. The method was tested on a LiDAR system, demonstrating its ability to run on simple embedded systems and be deployed in heavy rain environments for real-time processing. The proposed convolutional neural Repetitive Lightweight Feature-preserving Network (RLFN) for LiDAR noise filtering demonstrates significant potential for generalization across various adverse weather conditions and environments. This paper discusses the theoretical and practical aspects of the model’s generalization capabilities. By theoretical justification, the design of our model incorporates several key features that enhance its ability to generalize: (1) Adaptive pre-processing—The adaptive pre-processing method standardizes input sizes while preserving essential features. This ensures that the model can handle varying data distributions and noise patterns, making it robust to different types of adverse weather conditions. (2) Inception and residual structures—The use of inception modules and residual connections allows the model to capture multi-scale features and maintain gradient flow, respectively. These structures are known for their robustness and ability to generalize well across different tasks and datasets. (3) Lightweight network design: The lightweight nature of the network, combined with repetitive loops, ensures efficient computation without sacrificing performance. This design is particularly beneficial for deployment on embedded systems, which often have limited computational resources. As verified by testing on a dataset, WADS, the RLFN demonstrated 98.53% accuracy, with a 96.31% F1 score. Full article

Truck drivers are essential to global freight operations but face disproportionate safety risks due to fatigue, distraction, and demanding working conditions, all of which significantly elevate crash likelihood. This systematic review assesses how monitoring technologies have been used to improve safety among professional truck drivers, focusing on the types of technologies deployed, the variables monitored, and reported safety outcomes. Conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, the review includes 40 peer-reviewed articles published in English between 2009 and 2024, identified through systematic searches in PubMed, Scopus, Web of Science, and IEEE Xplore. Due to methodological heterogeneity, a formal risk of bias assessment was not conducted. Most studies examined wearable devices, in-vehicle cameras, telematics systems, and AI-driven platforms. These technologies monitored variables such as fatigue, stress, distraction, speed, and environmental conditions. While the findings demonstrate considerable potential to enhance safety outcomes, persistent challenges include implementation costs, privacy concerns, and variability in effectiveness. The evidence is also geographically concentrated in high-income regions, limiting broader applicability. This review highlights the urgent need for harmonized evaluation frameworks, robust validation protocols, and context-sensitive strategies to support the effective adoption of monitoring technologies in the trucking sector. Full article

Pedestrian safety at crosswalks remains a critical concern as traffic accidents frequently result from drivers’ failure to yield, leading to severe injuries or fatalities. In response, various jurisdictions have enacted pedestrian priority laws to regulate driver behavior. Nevertheless, intersections lacking clear traffic signage and environments with limited visibility continue to present elevated risks. The scarcity and difficulty of collecting data under such complex conditions pose significant challenges to the development of accurate detection systems. This study proposes a CyclicGAN-based loop-learning framework, in which the learning process begins with a set of manually annotated images used to train an initial labeling model. This model is then applied to automatically annotate newly generated synthetic images, which are incorporated into the training dataset for subsequent rounds of model retraining and image generation. Through this iterative process, the model progressively refines its ability to simulate and recognize diverse contextual features, thereby enhancing detection performance under varying environmental conditions. The experimental results show that environmental variations—such as daytime, nighttime, and rainy conditions—substantially affect the model performance in terms of F1-score. Training with a balanced mix of real and synthetic images yields an F1-score comparable to that obtained using real data alone. These results suggest that CycleGAN-generated images can effectively augment limited datasets and enhance model generalization. The proposed system may be integrated with in-vehicle assistance platforms as a supportive tool for pedestrian-crossing detection in data-scarce environments, contributing to improved driver awareness and road safety. Full article