Search Everything

Tip: Search using "First Name + Last Name", e.g.
János Kiss instead of Kiss János.

Publications - 6383

Navigating Inflation Challenges: AI-Based Portfolio Management Insights

Tibor Bareith László Vancsura Tatay Tibor

Publication Name: Risks

Publication Date: 2024-03-01

Volume: 12

Issue: 3

Page Range: Unknown

Description:

After 2010, the consumer price index fell to a low level in the EU. In the euro area, it remained low between 2010 and 2020. The European Central Bank has even had to take action against the emergence of deflation. The situation changed significantly in 2021. Inflation jumped to levels not seen for 40 years in the EU. Our study aims to use artificial intelligence to forecast inflation. We also use artificial intelligence to forecast stock index changes. Based on the forecasts, we propose portfolio reallocation decisions to protect against inflation. The forecasting literature does not address the importance of structural breaks in the time series, which, among other things, can affect both the pattern recognition and prediction capabilities of various machine learning models. The novelty of our study is that we used the Zivot–Andrews unit root test to determine the breakpoints and partitioned the time series into training and testing datasets along these points. We then examined which database partition gives the most accurate prediction. This information can be used to re-balance the portfolio. Two different AI-based prediction algorithms were used (GRU and LSTM), and a hybrid model (LSTM–GRU) was also included to investigate the predictability of inflation. Our results suggest that the average error of the inflation forecast is a quarter of that of the stock market index forecast. Inflation developments have a fundamental impact on equity and government bond returns. If we obtain a reliable estimate of the inflation forecast, we have time to rebalance the portfolio until the inflation shock is incorporated into government bond returns. Our results not only support investment decisions at the national economy level but are also useful in the process of rebalancing international portfolios.

Open Access: Yes

DOI: 10.3390/risks12030046

Performance Degradation of Object Detection Neural Networks Under Natural Visual Contamination in Autonomous Driving

Janos Hollosi Dániel Csikor

Publication Name: Computers

Publication Date: 2026-04-01

Volume: 15

Issue: 4

Page Range: Unknown

Description:

The operation of driver assistance systems and autonomous vehicles requires a sensor system and a control algorithm. Sensors provide information to detect people, vehicles and objects in the vehicle’s environment; however, their performance can be degraded by adverse environmental conditions and contamination. This literature review identified factors that reduce sensor visibility, such as weather conditions and external contamination. In this study, the detection efficiency of state-of-the-art neural network-based object detectors was examined in a simulation environment using a synthetic dataset. A custom dataset comprising six urban and suburban traffic scenarios was created, including clean images and ten contaminated variants per scene with increasing mud coverage. The results show that contamination leads to a measurable reduction in detection performance across all models. Smaller variants are more sensitive to degradation, while medium-complexity models provide a favorable balance between robustness and computational cost. Increasing model size yields limited additional robustness, and performance differences between architectures highlight the importance of model design. Furthermore, the spatial distribution of contamination, particularly near the image center, has a significant impact on performance in addition to its overall extent.

Open Access: Yes

DOI: 10.3390/computers15040254

A Call for Consensus: A Narrative Review of GPS-Based External Training Load Monitoring in Male Youth Soccer Players

Ferenc Ihász Bence Kopper Gábor Schuth János Matlák Krisztián Havanecz Sándor Sáfár Gábor Géczi

Publication Name: Sports

Publication Date: 2026-04-01

Volume: 14

Issue: 4

Page Range: Unknown

Description:

Background: Global positioning system (GPS) technology is widely used to quantify external training load (ETL) in youth soccer. Despite its extensive application in training and match contexts, considerable heterogeneity is present in the selection, definition, and interpretation of GPS-derived variables, limiting comparability between studies and practical implementation by coaches. Objective: This narrative review aimed to summarize and critically evaluate the current literature on GPS-based ETL monitoring in youth soccer players, with a focus on commonly used variables, methodological considerations, and practical applications in training and match contexts. Methods: A narrative literature search was conducted using PubMed, SPORTDiscus, and Scopus databases. Peer-reviewed studies published in English between the years of 2012 and 2025 were included. Data were extracted on participant characteristics, GPS technology, monitored ETL variables, and contextual settings. Results: The 34 reviewed studies primarily reported total distance (TD; m), high-speed running distance (HSR; m), sprint distance (SD; m), distance per minute (m·min−1), peak speed (km·h−1), and acceleration- and deceleration-based (ACC, DEC; count) ETL variables. Substantial variability was observed in speed thresholds, acceleration definitions, and data processing methods. Positional roles, training formats (e.g., small-sided games), and seasonal phase influenced ETL demands, although methodological inconsistencies limited cross-study comparisons. Conclusion: GPS technology provides valuable insights into the ETL demands of youth soccer. The lack of standardized variable definitions and thresholds remains a major limitation. Greater methodological consistency and clearer reporting standards are required to enhance the practical usefulness of GPS monitoring for coaches in youth soccer.

Open Access: Yes

DOI: 10.3390/sports14040152

Exploring the impact of compressibility on reconstructed porous materials: A numerical study

H. Szűcs

Publication Name: Journal of Engineering Research Kuwait

Publication Date: 2025-09-01

Volume: 13

Issue: 3

Page Range: 1987-2003

Description:

This study underscores fluid density's significance in CFD simulations for porous materials, addressing its impact on accuracy and computational efficiency. The paper proposes a tailored form of Navier-Stokes equations that accounts for fluid density's influence on CFD analyses of porous materials in industrial contexts, including cases where the solid phase is deformable. Numerical analyses demonstrate fluid density's significance (ρ≠constant) and explore the importance of the energy equation in governing equations. The energy equation is essential in setting up the governing equations, as it calculates thermal characteristic length based on cell temperatures. By examining various porous material samples, the study suggests a streamlined approach: employing a single coupled CFD-FEM simulation to directly determine each geometrical parameter. Additionally, the study investigates the capability to accurately simulate turbulent fluid motion at the pore scale and analyze the flow field characterization within porous media. Computational cost analyses underscore the advantages of coupled simulations, establishing their profitability over separate parameter-specific simulations.

Open Access: Yes

DOI: 10.1016/j.jer.2024.07.018

Environment Protection - Monument Preservation

András Veöreös

Publication Name: Epites Epiteszettudomany

Publication Date: 2023-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The preservation of existing buildings is desirable not only for the purpose of saving architectural values, but equally important is that it is an environmentally friendly-environmentally conscious activity as well, since by renovating existing houses less waste is generated, the environmental impact from transport decreases, the material and energy invested in the structures already built do not get lost and no additional energy is needed for demolition.

Open Access: Yes

DOI: 10.1556/096.2023.00081

Energy in the backseat? Investigating decarbonization dialogue in supply chain tweets during and after COVID-19

Gagan Deep Sharma Tuhin Sengupta Umer Shahzad Amar Rao

Publication Name: Annals of Operations Research

Publication Date: 2026-04-01

Volume: 359

Issue: 1

Page Range: 581-613

Description:

While we move into the seventh year of the signing of Paris agreement, research scholars and supply chain firms have paid a lot of emphasis on environmental sustainability with the aim of achieving net zero targets by 2050. However, the global pandemic has somewhat disturbed the focus from environment to resilience due to severe economic implications of COVID-19. In this paper, we contribute to the very scant discussion on Twitter Analytics by analysing supply chain tweets with COVID-19 at the backdrop. Our approach involves analysing how decarbonization related discussions have evolved by capturing the tweets across three timelines: pre pandemic, pandemic and post pandemic. By integrating descriptive analytics, content analytics and machine learning algorithm in topic modelling, we extract textual intelligence related to emissions and pollution from leading firms involving supply chain management. We find that although decarbonization related discussions are at bare minimum in terms of the proportion of discussions within the supply chain context, the overall emotion of tweets indicate fear across all three timelines. Moreover, it was surprising to note that although pollution levels came down due to low economic activity during pandemic, we found more discussions during COVID in comparison to pre-COVID times. Pollution and waste caused by plastics, fuel consumption, reduction in greenhouse gas emission are some of the key topics that emerged during pandemic times. Our paper makes a modest contribution on the role of social media analytics within supply chain context around COVID-19.

Open Access: Yes

DOI: 10.1007/s10479-023-05806-4

Representation of loss aversion and impatience concerning time utility in supply chains

János Botzheim Péter Földesi Edit Süle

Publication Name: Smart Innovation Systems and Technologies

Publication Date: 2011-12-01

Volume: 10 SIST

Issue: Unknown

Page Range: 273-282

Description:

The paper deals with the investigation of the critical time factor of supply chain. The literature review gives a background to understand and handle the reasons and consequences of the growing importance of time, and the phenomenon of time inconsistency. By using utility functions to represent the value of various delivery-times for the different participants in the supply chain, including the final customers, it is shown that the behaviour and willingness of payment of time-sensitive and non time-sensitive consumers are different for varying lead times. Longer lead times not only generate less utility but impatience influences the decision makers, that is the time elasticity is not constant but it is function of time. For optimization soft computing techniques (particle swarm optimization in this paper) can be efficiently applied. © 2011 Springer-Verlag Berlin Heidelberg.

Open Access: Yes

DOI: 10.1007/978-3-642-22194-1_28

A novel unified approach to invariance conditions for a linear dynamical system

Yunfei Song Tamás Terlaky Zoltán Horváth

Publication Name: Applied Mathematics and Computation

Publication Date: 2017-04-01

Volume: 298

Issue: Unknown

Page Range: 351-367

Description:

In this paper, we propose a novel, simple, and unified approach to explore sufficient and necessary conditions, i.e., invariance conditions, under which four classic families of convex sets, namely, polyhedra, polyhedral cones, ellipsoids, and Lorenz cones, are invariant sets for a linear discrete or continuous dynamical system. For discrete dynamical systems, we use the Theorems of Alternatives, i.e., Farkas lemma and S-lemma, to obtain simple and general proofs to derive invariance conditions. This novel method establishes a solid connection between optimization theory and dynamical system. Also, using the S-lemma allows us to extend invariance conditions to any set represented by a quadratic inequality. Such sets include nonconvex and unbounded sets. For continuous dynamical systems, we use the forward or backward Euler method to obtain the corresponding discrete dynamical systems while preserves invariance. This enables us to develop a novel and elementary method to derive invariance conditions for continuous dynamical systems by using the ones for the corresponding discrete systems. Finally, some numerical examples are presented to illustrate these invariance conditions.

Open Access: Yes

DOI: 10.1016/j.amc.2016.10.007

Real network test of an iterative origin-destination matrix estimator in urban public transport

Richárd Horváth Balázs Horváth

Publication Name: 2014 18th International Conference on System Theory Control and Computing Icstcc 2014

Publication Date: 2014-12-11

Volume: Unknown

Issue: Unknown

Page Range: 715-719

Description:

The estimation of origin-destination matrices in urban public transport is an evergreen issue due to the fact that the key of the planning of public transport systems is the accurate prediction of the traffic load which requires a well-functioning assignment method and reliable passenger data (i.e. time-dependent OD matrix). This paper describes the theory of lately developed iterative estimation method and the first real network test results.

Open Access: Yes

DOI: 10.1109/ICSTCC.2014.6982502