Search in Publications

Found 6674 publications

Real-Time Out of Distribution Detection in 2D Object Detection for Autonomous Cars

Andrea Ádámné Major Zoltán Weltsch Lóránt Szabó

Publication Name: Engineering Perspective

Publication Date: 2025-01-01

Volume: 5

Issue: Special-Issue

Page Range: 28-35

Description:

The development of autonomous transportation systems represents a critical step toward achieving intelligent and reliable mobility. Ensuring accurate, real-time environmental perception and the robust detection of unexpected or rare events remains a major challenge for autonomous vehicles operating in complex and dynamic environments. To address this, we propose a novel processing pipeline that constructs Bird’s Eye View (BEV) representations from raw 3D LiDAR point clouds using both intensity and height map channels, thereby retaining essential geometric and reflective features. On top of these BEV representations, an optimized YOLOv11-based deep learning model is applied for high-precision object detection. A key contribution of our work is the integration of a real-time Out-of-Distribution (OOD) detection module, which employs lightweight statistical techniques in conjunction with learned feature representations to ensure minimal computational overhead while maintaining operational robustness. The proposed architecture enables the reliable identification of standard traffic objects as well as the detection of atypical or previously unseen events, such as overturned vehicles or unknown obstacles. Experimental evaluation on representative driving scenarios demonstrates that our method achieves approximately 95% detection accuracy, outperforming conventional baselines in both speed and reliability. Overall, the results highlight the potential of combining state-of-the-art deep neural detection frameworks with efficient, statistically grounded OOD analysis for enhancing the safety and trustworthiness of autonomous vehicle perception systems.

Open Access: Yes

DOI: 10.64808/engineeringperspective.1814718

The legal consequences of supporting candidates on recommendation sheets in an illegal way

Klára Nagy

Publication Name: Acta Juridica Hungarica

Publication Date: 2015-03-01

Volume: 56

Issue: 1

Page Range: 30-38

Description:

In 2014 there were three elections in Hungary: the election of Members of Parliaments, the election of members of the European Parliament, furthermore, the elections of representatives and mayors of municipalities and of representatives of national minority local self-governments. The Hungarian Parliament passed a new act on electoral procedure in 2013 and we have had a new Criminal Code since 2012. This study examines a new legal institution, the recommendation sheets, which raise many questions, including criminal liability. The main theme of the study is the misuses related to recommendation sheets.

Open Access: Yes

DOI: 10.1556/026.2015.56.1.4

Prediction of Scour Depth for Diverse Pier Shapes Utilizing Two-Dimensional Hydraulic Engineering Center’s River Analysis System Sediment Model

Muhanad Al-Jubouri Ethar H. Abbas Richard P. Ray

Publication Name: Fluids

Publication Date: 2024-11-01

Volume: 9

Issue: 11

Page Range: Unknown

Description:

Examining scouring around bridge piers is crucial for ensuring water-related infrastructure’s long-term safety and stability. Accurate forecasting models are essential for addressing scour, especially in complex water systems where traditional methods fall short. This study investigates the application of the HEC-RAS 2D sedimentation model, which has recently become available for detailed sediment analysis, to evaluate its effectiveness in predicting scoring around various pier shapes and under different water conditions. This study offers a comprehensive assessment of the model’s predictive capabilities by focusing on variables such as water velocity, shear stress, and riverbed changes. Particular attention was paid to the influence of factors like floating debris and different pier geometries on scour predictions. The results demonstrate that while the HEC-RAS 2D model generally provides accurate predictions for simpler pier shapes—achieving up to 85% precision—it shows varied performance for more complex designs and debris-influenced scenarios. Specifically, the model overpredicted scouring depths by approximately 20% for diamond-shaped piers and underpredicted by 15% for square piers in debris conditions. Elliptical piers, in contrast, experienced significantly less erosion, with scour depths up to 30% shallower compared to other shapes. This study highlights the novel application of the HEC-RAS 2D model in this context and underscores its strengths and limitations. Identified issues include difficulties in modeling water flow and debris-induced bottlenecks. This research points to the improved calibration of sediment movement parameters and the development of advanced computational techniques to enhance scour prediction accuracy in complex environments. This work contributes valuable insights for future research and practical applications in civil engineering, especially where traditional scour mitigation methods, such as apron coverings, are not feasible.

Open Access: Yes

DOI: 10.3390/fluids9110247

Single-stroke character recognition with fuzzy method

János Botzheim Alex Tormasi

Publication Name: Studies in Computational Intelligence

Publication Date: 2013-01-01

Volume: 417

Issue: Unknown

Page Range: 27-46

Description:

In this paper an on-line single-stroke recognition method based on fuzzy logic is introduced. Each of the characters is defined by only one nine dimensional fuzzy rule. In addition to the low resource requirement the solution is able to satisfy many of the user's current demands in handwriting recognizers, like speed and learning. Eight of the nine features are extracted using a four-by-four grid. For the learning phase we designed a new punish/reward bacterial evolutionary algorithm which tunes the character parameters represented by fuzzy sets. © 2013 Springer-Verlag Berlin Heidelberg.

Open Access: Yes

DOI: 10.1007/978-3-642-28959-0_2

Effects of Wheel Surface Defects on Ground Borne Vibration

Szabolcs Fischer Farshad Astaraki R. M. Movahedi Milad Kazemian Milad Akbarivarmaziar Ahmad Mohammadi Doost

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2022-01-01

Volume: 19

Issue: 6

Page Range: 129-141

Description:

Wheel ground borne vibrations, may have a significant impact on human activity and on nearby buildings. In metropolitan cities, metro lines and their development may cause such vibrations. Despite many works and solutions for path and receiver, the excitation source could also have a great effect. Wheel and rail damages are the two sources of vibration which can increase the damage impact by a factor of 5x. Wheel damage would increase dynamic vertical force noticeably and an increase in ground-borne vibration is expected. In this study with the help of finite element modelling, wheel damage including wheel flat, spalling and wheel oval is studied for a slab track and results are discussed. The studied parameters are velocity and wheel damage and their effect on ground-borne vibrations are examined.

Open Access: Yes

DOI: DOI not available

Dynamic Modeling Possibilities of Embedded Rail Structures

Szabolcs Fischer Zoltán Major Attila Németh Vivien Jóvér Nándor Liegner

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2025-01-01

Volume: 22

Issue: 4

Page Range: 29-43

Description:

In Hungarian design practice, the Zimmermann-Eisenmann quasi-static design method is employed to dimension track structures with embedded rails. This method determines the mean values of deformations and stresses using an infinitely long elastically embedded beam as the static frame. After establishing these mean values, the effects of track condition and speed are considered through Eisenmann multiplication, enabling the definition of design values. Conversely, international practices include methods that calculate deformations and stresses based on dynamic models incorporating viscoelastic embedding, directly accounting for speed but not dynamic effects due to track characteristics. This paper presents a solution to the dynamic problem, extending it to studying rotating frames beyond the commonly considered uniaxial solution. Each factor's effect is separately analyzed for track structures with embedded rail tracks, leading to a recommendation for the value of the "load multiplication factor".

Open Access: Yes

DOI: 10.12700/APH.22.4.2025.4.3

Investigation of the long-term stability of various tinctures belonging to the lamiaceae family by HPLC and spectrophotometry method

E. Lakatos V. Kapcsándi Rita Székelyhidi Beatrix Sik Zsolt Ajtony

Publication Name: Chemical Papers

Publication Date: 2021-11-01

Volume: 75

Issue: 11

Page Range: 5781-5791

Description:

The aim of the current study was to analyze the stability of rosmarinic acid in ethanolic tinctures of lemon balm (Melissa officinalis L.), oregano (Origanum vulgare L.), peppermint (Mentha x piperita), rosemary (Rosmarinus officinalis L.), sage (Salvia officinalis L.), and thyme (Thymus vulgaris L.). High-performance liquid chromatography with diode-array detection (HPLC–DAD) was employed to monitor the concentration of the marker compound over a six month period. Furthermore, the tinctures were also evaluated for caffeic acid, total phenolic content, and 2,2-diphenyl-1-picrylhydrazyl (DPPH) scavenging activity. We observed that the concentration of rosmarinic acid in tincture stored in closed amber glasses at ambient temperature decreased significantly during 6-month storage. Furthermore, our study squarely confirms the fact that a part of rosmarinic acid is converted to caffeic acid. The tested tinctures can be listed in the following order according to the greatest stability of the marker compound: rosemary > peppermint > oregano > lemon balm > thyme > sage. The results of the study indicated a linear relationship between DPPH values and total phenolic (R2 = 0.92) or rosmarinic acid (R2 = 0.85) contents.

Open Access: Yes

DOI: 10.1007/s11696-021-01755-z

Unveiling the Role of Edaphic Microalgae in Soil Carbon Sequestration: Potential for Agricultural Inoculants in Climate Change Mitigation

Györgyi Kovács Z. Molnár Jun Bin Zhao István Mihály Kulmány Wogene Kabato Zainulabdeen Khalaf Hashim Agampodi Gihan Shyamal Dharmendra De Silva Zainulabdeen Khalaf Hashim

Publication Name: Agriculture Switzerland

Publication Date: 2024-11-01

Volume: 14

Issue: 11

Page Range: Unknown

Description:

Agricultural soil has great potential to address climate change issues, particularly the rise in atmospheric CO2 levels. It offers effective remedies, such as increasing soil carbon content while lowering atmospheric carbon levels. The growing interest in inoculating soil with live microorganisms aims to enhance agricultural land carbon storage and sequestration capacity, modify degraded soil ecosystems, and sustain yields with fewer synthetic inputs. Agriculture has the potential to use soil microalgae as inoculants. However, the significance of these microorganisms in soil carbon sequestration and soil carbon stabilization under field conditions has yet to be fully understood. Large-scale commercial agriculture has focused on the development and use of inoculation products that promote plant growth, with a particular emphasis on enhancing yield attributes. Gaining more profound insights into soil microalgae’s role in soil carbon cycling is necessary to develop products that effectively support soil carbon sequestration and retention. This review comprehensively explores the direct and indirect mechanisms through which soil microalgae contribute to soil carbon sequestration, highlighting their potential as microbial inoculants in agricultural settings. This study underlines the need for more research to be conducted on microalgae inoculation into agricultural soil systems aimed at mitigating carbon emissions in the near future.

Open Access: Yes

DOI: 10.3390/agriculture14112065

Translational Pitfalls in SCI Bladder Research: The Hidden Role of Urinary Drainage Techniques in the Rat Model

Peter Törzsök Lukas Lusuardi Sophina Bauer Karin Roider Martha Georgina Brandtner Elena E. Keller Evelyn Beyerer Michael Kleindorfer Ludwig Aigner

Publication Name: Biology

Publication Date: 2025-08-01

Volume: 14

Issue: 8

Page Range: Unknown

Description:

Spinal cord injury (SCI) frequently leads to neurogenic lower urinary tract dysfunction, for which appropriate bladder management is essential. While clinical care relies on continuous low-pressure drainage in the acute phase, rat models commonly use twice-daily manual bladder expression—a method known to generate high intravesical pressures and retention. This study evaluated the impact of this standard practice on bladder tissue remodeling by comparing it to continuous drainage via high vesicostomy in a rat SCI model. 32 female Lewis rats underwent thoracic contusion SCI and were assigned to either manual expression or vesicostomy-based bladder management. Over eight weeks, locomotor recovery, wound healing, and bladder histology were assessed. Vesicostomy proved technically simple but required tailored wound care and calibration. Results showed significantly greater bladder wall thickness, detrusor muscle hypertrophy, urothelial thickening, collagen deposition, and mast cell infiltration in the manual expression group compared to both vesicostomy and controls. In contrast, vesicostomy animals exhibited near-control levels across most parameters. These findings highlight that commonly used bladder emptying protocols in rat SCI models may overestimate structural bladder changes and inflammatory responses. Refined drainage strategies such as vesicostomy can minimize secondary damage and improve the translational relevance of preclinical SCI research.

Open Access: Yes

DOI: 10.3390/biology14080928