Viktor Nagy

57401387800

Publications - 15

Driver Distraction Detection in Extreme Conditions Using Kolmogorov–Arnold Networks

Szabolcs Fischer János Hollósi Mykola Sysyn Gábor Kovács Dmytro Kurhan Viktor Nagy

Publication Name: Computers

Publication Date: 2025-05-01

Volume: 14

Issue: 5

Page Range: Unknown

Description:

Driver distraction can have severe safety consequences, particularly in public transportation. This paper presents a novel approach for detecting bus driver actions, such as mobile phone usage and interactions with passengers, using Kolmogorov–Arnold networks (KANs). The adversarial FGSM attack method was applied to assess the robustness of KANs in extreme driving conditions, like adverse weather, high-traffic situations, and bad visibility conditions. In this research, a custom dataset was used in collaboration with a partner company in the field of public transportation. This allows the efficiency of Kolmogorov–Arnold network solutions to be verified using real data. The results suggest that KANs can enhance driver distraction detection under challenging conditions, with improved resilience against adversarial attacks, particularly in low-complexity networks.

Open Access: Yes

DOI: 10.3390/computers14050184

Dynamic Vehicle Dashboard Design for Reduced Driver Distraction

Viktor Nagy Ágoston Pál Sándor

Publication Name: Mechanisms and Machine Science

Publication Date: 2025-01-01

Volume: 174 MMS

Issue: Unknown

Page Range: 645-654

Description:

In the context of contemporary vehicle dashboard systems, advanced In-Vehicle Information Systems (IVIS) often employ touchscreen functionalities, and multi-layered menu structures. However, these solutions have been identified as more distracting for drivers compared to traditional tactile switches and buttons with single, dedicated functions. Our primary focus is on exploring the design capabilities of dynamic vehicle center console interfaces, leading to the inception of the Dynamic Human-Computer Interface System (DHCIS). DHCIS employs a context-aware, adaptive functional framework structure, which, rather than relying on deep menu layers, enhances the safety level in varied traffic situations by simplifying controls to one-touch features. The design concept has been compared with a generic user interface in terms of the handling method, operational steps and layout design.

Open Access: Yes

DOI: 10.1007/978-3-031-80512-7_63

Eclipse SUMO and Unity 3D integration for emission studies based on driving behaviour in virtual reality environment

Viktor Nagy Viktor Nagy Csaba József Májer Sámuel Lepold

Publication Name: Procedia Computer Science

Publication Date: 2025-01-01

Volume: 257

Issue: Unknown

Page Range: 396-403

Description:

This paper explores the development of a traffic simulator that harnesses the power of OpenStreetMap (OSM) data, integrating it into a unified framework using Blender, SUMO (Simulation of Urban MObility), and Unity 3D. The project aims to provide a realistic and versatile platform for simulating complex transportation scenarios for urban planning, traffic management, and virtual environment creation. The process begins with the extraction and preprocessing of OSM data, ensuring the representation of road networks and geographic features. Blender, a 3D modelling software, is used to visualise and enhance the environment. The resulting 3D models are loaded into Unity. SUMO - a microscopic traffic simulation software - plays a role in modelling vehicle dynamics, traffic flow, and interactions within the simulated environment. Via an integration hub, bringing together the visuality of Unity 3D environment and SUMO's precise traffic simulation. Through this collaboration, the simulator offers real-time interaction and analysis. With the help of SUMO's free emissions module, the pollution resulting from driving behaviour can be measured not only at the individual level but also the impact on the network as well. The combination of OSM data, SUMO, Blender, and Unity 3D provides a powerful and free tool to study and optimise urban mobility, ultimately contributing to the development of smarter and more sustainable transportation systems.

Open Access: Yes

DOI: 10.1016/j.procs.2025.03.052

Detection of Bus Driver Mobile Phone Usage Using Kolmogorov-Arnold Networks

Á Ballagi Szabolcs Fischer János Hollósi Gábor Kovács Viktor Nagy

Publication Name: Computers

Publication Date: 2024-09-01

Volume: 13

Issue: 9

Page Range: Unknown

Description:

This research introduces a new approach for detecting mobile phone use by drivers, exploiting the capabilities of Kolmogorov-Arnold Networks (KAN) to improve road safety and comply with regulations prohibiting phone use while driving. To address the lack of available data for this specific task, a unique dataset was constructed consisting of images of bus drivers in two scenarios: driving without phone interaction and driving while on a phone call. This dataset provides the basis for the current research. Different KAN-based networks were developed for custom action recognition tailored to the nuanced task of identifying drivers holding phones. The system’s performance was evaluated against convolutional neural network-based solutions, and differences in accuracy and robustness were observed. The aim was to propose an appropriate solution for professional Driver Monitoring Systems (DMS) in research and development and to investigate the efficiency of KAN solutions for this specific sub-task. The implications of this work extend beyond enforcement, providing a foundational technology for automating monitoring and improving safety protocols in the commercial and public transport sectors. In conclusion, this study demonstrates the efficacy of KAN network layers in neural network designs for driver monitoring applications.

Open Access: Yes

DOI: 10.3390/computers13090218

Area of Interest Tracking Techniques for Driving Scenarios Focusing on Visual Distraction Detection

P. Földesi György Istenes Viktor Nagy

Publication Name: Applied Sciences Switzerland

Publication Date: 2024-05-01

Volume: 14

Issue: 9

Page Range: Unknown

Description:

On-road driving studies are essential for comprehending real-world driver behavior. This study investigates the use of eye-tracking (ET) technology in research on driver behavior and attention during Controlled Driving Studies (CDS). One significant challenge in these studies is accurately detecting when drivers divert their attention from crucial driving tasks. To tackle this issue, we present an improved method for analyzing raw gaze data, using a new algorithm for identifying ID tags called Binarized Area of Interest Tracking (BAIT). This technique improves the detection of incidents where the driver’s eyes are off the road through binarizing frames under different conditions and iteratively recognizing markers. It represents a significant improvement over traditional methods. The study shows that BAIT performs better than other software in identifying a driver’s focus on the windscreen and dashboard with higher accuracy. This study highlights the potential of our method to enhance the analysis of driver attention in real-world conditions, paving the way for future developments for application in naturalistic driving studies.

Open Access: Yes

DOI: 10.3390/app14093838

Bus Driver Head Position Detection Using Capsule Networks under Dynamic Driving Conditions

Á Ballagi Szabolcs Fischer János Hollósi Gábor Kovács Viktor Nagy

Publication Name: Computers

Publication Date: 2024-03-01

Volume: 13

Issue: 3

Page Range: Unknown

Description:

Monitoring bus driver behavior and posture in urban public transport’s dynamic and unpredictable environment requires robust real-time analytics systems. Traditional camera-based systems that use computer vision techniques for facial recognition are foundational. However, they often struggle with real-world challenges such as sudden driver movements, active driver–passenger interactions, variations in lighting, and physical obstructions. Our investigation covers four different neural network architectures, including two variations of convolutional neural networks (CNNs) that form the comparative baseline. The capsule network (CapsNet) developed by our team has been shown to be superior in terms of efficiency and speed in facial recognition tasks compared to traditional models. It offers a new approach for rapidly and accurately detecting a driver’s head position within the wide-angled view of the bus driver’s cabin. This research demonstrates the potential of CapsNets in driver head and face detection and lays the foundation for integrating CapsNet-based solutions into real-time monitoring systems to enhance public transportation safety protocols.

Open Access: Yes

DOI: 10.3390/computers13030066

Automatized Driving Data Analyzer: A Synchronized and Modular Application for Data Logging and Analysis †

Viktor Nagy Ágoston Pál Sándor

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

The Automated Driving Data Analyzer (ADDA) is a modular application written in Python for the synchronized acquisition and analysis of physiological, vehicle, and interface data. It provides a managed data acquisition process and one-click data analysis. It also provides raw data storage and systematic archiving of data sets. ADDA integrates real-time data from a BeamNG vehicle simulation, Pupil Labs eye-tracking system, hand-tracking, and cardiac data. This integration allows the simultaneous recording and analysis of multiple data streams, which can be visualized and controlled through a graphical user interface (GUI) built with Tkinter. The application is designed to help researchers and engineers analyze driving behavior under different conditions, enabling a deeper understanding of the interactions between the driver and automated driving functions.

Open Access: Yes

DOI: 10.3390/engproc2024079018

Comparative Analysis of Driver Interface Systems in Ultra-Efficient Lightweight Electric Vehicles: a Study on Energy Efficiency and Driver Focus

Zoltan Pusztai Viktor Nagy István Kecskeméti

Publication Name: Chemical Engineering Transactions

Publication Date: 2024-01-01

Volume: 114

Issue: Unknown

Page Range: 997-1002

Description:

This paper presents a comprehensive examination of two driver interface systems within the context of Ultra-Efficient Lightweight Electric Vehicles (ULEV) aimed at enhancing energy efficiency and optimizing driver focus. The vehicle employs two interface systems: a 10.1-inch touchscreen tablet with a custom Graphical User interface (GUI) that offers comprehensive data management, diagnostics, and control functionalities and a 5.5-inch wide, passive OLED display designed for ultra-low energy consumption. The tablet's advanced features come with the potential for driver distraction. In contrast, the OLED display takes a minimalist approach by presenting only critical information. This enhances driving focus and efficiency. This research utilizes a wearable eye-tracking device to measure drivers' focus and distraction levels while also logging driving performance and energy consumption data. The aim is to determine the most effective interface for promoting efficient driving practices. The study achieved significant insights into the balancing of information accessibility and cognitive load in driving while also optimizing energy efficiency. The results demonstrate the advantages of assistant systems, which reduce energy consumption by 11-15%, provide concentrated information projection, and minimize driver distraction.

Open Access: Yes

DOI: 10.3303/CET24114167

Experimental Analysis of a Solar-Powered Centre Pivot Irrigation Site and Hyperlocal Evapotranspiration Data

Renato Kalocsai Nóra Gombköto Viktor Nagy Lajos Kubina Bálint Süle Viktor Nagy Zsolt Giczi

Publication Name: Chemical Engineering Transactions

Publication Date: 2024-01-01

Volume: 114

Issue: Unknown

Page Range: 787-792

Description:

In countries such as Hungary, the utilisation of solar energy for irrigation represents a pivotal consideration. As a consequence of climate change, the crop rotation period is characterised by an increased availability of sunny and bright days. A paucity of cloud cover and precipitation has distinguished recent Hungarian summers. The necessity for adaptation in agriculture, which produces raw materials for food, will also arise as a result of the increasingly extreme weather conditions caused by global climate change. The irrigation of crops is a vital process during increasingly frequent periods of drought. However, the cost of irrigation can be expected to rise significantly in response to elevated energy prices. The objective of this research is to ascertain the viability of utilising irrigation systems powered by renewable energy sources. Hungary is on the verge of a significant investment in its national irrigation infrastructure. Nevertheless, the investment may prove to be unprofitable as a result of the expense associated with the energy required for irrigation. In three research areas, the energy production of the solar farms associated with the pivot irrigation system has been monitored, and the hyper-local evapotranspiration data has been calculated. Regression analysis was employed to evaluate the results. The findings indicate that the dataset is significant. The field results and analysis can be useful for upfront investment in such projects. Precipitation, as a third variable, has a positive impact on the relationship between energy production and crop water demand.

Open Access: Yes

DOI: 10.3303/CET24114132

Evaluation of Autonomous Vehicle Takeover Performance in Work-Zone Environment †

Attila Borsos Viktor Nagy Ágoston Pál Sándor Diovane Mateus da Luz

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

The advent of autonomous vehicles (AV) could revolutionize the automotive industry by significantly improving safety, efficiency, and accessibility. Despite their potential to improve traffic safety by reducing human error, their integration into existing transportation systems presents significant challenges. This is particularly evident in scenarios involving takeover events, where there is a transition of control from the vehicle to the human driver. Our driving simulator study, involving 14 drivers in a work-zone environment, provides critical insights into the takeover performance of level 3 to level 5 AVs. The findings suggest that the successful integration of AVs depends on their seamless incorporation into existing systems and the readiness of drivers to adapt to this emerging technology.

Open Access: Yes

DOI: 10.3390/engproc2024079059

Effects of Biostimulant and Zinc (Zn) Treatment on Qualitative and Quantitative Indicators of Winter Rape (Brassica Napus L.)

Renato Kalocsai Zoltán Molnár Viktor Nagy Lajos Kubina Bálint Süle Viktor Nagy Zsolt Giczi

Publication Name: Chemical Engineering Transactions

Publication Date: 2024-01-01

Volume: 114

Issue: Unknown

Page Range: 769-774

Description:

Winter rapeseed production has completely changed in Hungary in recent years. The use of hybrids has become commonplace, and intensive cultivation techniques are widespread. At the same time, average yields also increased, making rapeseed one of the most profitable crops. Maintaining profitability is a priority task, and in addition to further increasing average yields, improving quality parameters and crop safety is also decisive. Rapeseed production today faces significant challenges. As a result of climate change, the cultivation routine of decades is changing, and biostimulators are becoming more and more perspective in addition to foliar fertilisation with macro- and microelements. During this research, a 3-year small-plot field experiment was set up with a winter rapeseed indicator. The main objective of the experiment was to study the physiological reactions of rape plants to different doses of Zn and the combined reaction of the biostimulator and Zn. During the experiment, the reaction of the rapeseed test plant on zinc-deficient calcareous chernozem soils was investigated under the influence of different doses of Zn and combined doses of Zn and biostimulation. The aim of the study is to determine whether rapeseed plants respond to zinc supplementation and the combined effect of the bio stimulator and zinc with increased yield and improved nutritional values (protein content, oil content). In the first annual study, two treatments were performed, one in autumn (BBCH 16-18 phenological stage) and one in spring (BBCH 29 phenological stage). Zinc tetramine hydroxide was used in 4 different doses (2, 5, 10, 20 L/ha), zinc tetramine hydroxide enriched with copper in 2 different doses (5 and 10 L/ha), Quantis in the manufacturer's prescribed dose of 2 L/ha, biostimulant enriched with zinc, and a usual foliar fertiliser used in rapeseed growing with Wuxal boron at the dose recommended by the manufacturer. During the growing season, the development of root mass, root length, SPAD values, as well as the yield and oleic acid content were evaluated by mathematical statistical method. It can be stated that there was no significant difference in the root mass, root length, and SPAD values, but there was a significant yield difference in the amount of the crop in the second-year experiment (P = 10 %). Studies have shown that biostimulants have the greatest influence on the development of measured parameters.

Open Access: Yes

DOI: 10.3303/CET24114129

Face Detection Using a Capsule Network for Driver Monitoring Application

Á Ballagi Szabolcs Fischer János Hollósi Gábor Kovács Viktor Nagy

Publication Name: Computers

Publication Date: 2023-08-01

Volume: 12

Issue: 8

Page Range: Unknown

Description:

Bus driver distraction and cognitive load lead to higher accident risk. Driver distraction sources and complex physical and psychological effects must be recognized and analyzed in real-world driving conditions to reduce risk and enhance overall road safety. The implementation of a camera-based system utilizing computer vision for face recognition emerges as a highly viable and effective driver monitoring approach applicable in public transport. Reliable, accurate, and unnoticeable software solutions need to be developed to reach the appropriate robustness of the system. The reliability of data recording depends mainly on external factors, such as vibration, camera lens contamination, lighting conditions, and other optical performance degradations. The current study introduces Capsule Networks (CapsNets) for image processing and face detection tasks. The authors’ goal is to create a fast and accurate system compared to state-of-the-art Neural Network (NN) algorithms. Based on the seven tests completed, the authors’ solution outperformed the other networks in terms of performance degradation in six out of seven cases. The results show that the applied capsule-based solution performs well, and the degradation in efficiency is noticeably smaller than for the presented convolutional neural networks when adversarial attack methods are used. From an application standpoint, ensuring the security and effectiveness of an image-based driver monitoring system relies heavily on the mitigation of disruptive occurrences, commonly referred to as “image distractions,” which represent attacks on the neural network.

Open Access: Yes

DOI: 10.3390/computers12080161

Testing Road Vehicle User Interfaces Concerning the Driver’s Cognitive Load

P. Földesi Szabolcs Fischer Szabolcs Szalai Mykola Sysyn Gábor Kovács Dmytro Kurhan Viktor Nagy

Publication Name: Infrastructures

Publication Date: 2023-03-01

Volume: 8

Issue: 3

Page Range: Unknown

Description:

This paper investigates the usability of touch screens used in mass production road vehicles. Our goal is to provide a detailed comparison of conventional physical buttons and capacitive touch screens taking the human factor into account. The pilot test focuses on a specific Non-driving Related Task (NDRT): the control of the on-board climate system using a touch screen panel versus rotating knobs and push buttons. Psychological parameters, functionality, usability and, the ergonomics of In-Vehicle Information Systems (IVIS) were evaluated using a specific questionnaire, a system usability scale (SUS), workload assessment (NASA-TLX), and a physiological sensor system. The measurements are based on a wearable eye-tracker that provides fixation points of the driver’s gaze in order to detect distraction. The closed road used for the naturalistic driving study was provided by the ZalaZONE Test Track, Zalaegerszeg, Hungary. Objective and subjective results of the pilot study indicate that the control of touch screen panels causes higher visual, manual, and cognitive distraction than the use of physical buttons. The statistical analysis demonstrated that conventional techniques need to be complemented in order to better represent human behavior differences.

Open Access: Yes

DOI: 10.3390/infrastructures8030049

Car Simulator Study for the Development of a Bring-Your-Own-Device (BYOD) Dashboard Concept

P. Földesi Gábor Kovács Viktor Nagy Ágoston Pál Sándor

Publication Name: Chemical Engineering Transactions

Publication Date: 2023-01-01

Volume: 107

Issue: Unknown

Page Range: 415-420

Description:

In-Vehicle Information Systems (IVIS) have evolved with the integration of advanced technologies like touchscreens, enhancing vehicle functionality and infotainment features. However, the development of sustainable and user-centric dashboard interfaces embracing the Bring-Your-Own-Device (BYOD) concept remains limited. This research aims to explore the usability, advantages, and disadvantages of the BYOD concept within the context of IVIS. Specifically, it investigated the control of the onboard air conditioning system and selected Advanced Driver Assistance System (ADAS) functions. To accomplish this, a complex simulation environment using Unity, Blender, and C# was developed. Eye-tracking technology was utilized to record participants' gaze patterns and attention allocation during experimental tasks. Following the simulation, participants provided subjective usability assessments of the system through questionnaires. The integration of a mobile phone with a suitable user interface as part of the BYOD concept generally led to enhanced usability and reduced distraction. This study underscores the potential benefits of integrating the BYOD concept into IVIS, emphasizing improved usability, sustainability, and user-friendliness. These findings hold significance for advancing the design of user-centric, sustainable interfaces in automotive technology.

Open Access: Yes

DOI: 10.3303/CET23107070

Operation and applicability issues of powertrain models in electric vehicle development

István Lakatos Peter Koros Viktor Nagy

Publication Name: Mesa 2014 10th IEEE ASME International Conference on Mechatronic and Embedded Systems and Applications Conference Proceedings

Publication Date: 2014-10-24

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The paper deals with researches started several years ago at the Department of Road and Rail Vehicles and Research Center of Vehicle Industry, Széchenyi István University. Simulation of electric driven vehicles and utilization of results are in focus.

Open Access: Yes

DOI: 10.1109/MESA.2014.6935610