TY - JOUR AU - Rahimian, Pegah AU - Van Haaren, Jan AU - Toka, László TI - Towards maximizing expected possession outcome in soccer JF - INTERNATIONAL JOURNAL OF SPORTS SCIENCE AND COACHING J2 - INT J SPORT SCI COACHING VL - 19 PY - 2024 IS - 1 SP - 230 EP - 244 PG - 15 SN - 1747-9541 DO - 10.1177/17479541231154494 UR - https://m2.mtmt.hu/api/publication/33652677 ID - 33652677 N1 - Correspondence Address: Rahimian, P.; Department of Telecommunications and Media Informatics, Hungary; email: pegah.rahimian@edu.bme.hu AB - Soccer players need to make many decisions throughout a match in order to maximize their team’s chances of winning. Unfortunately, these decisions are challenging to measure and evaluate due to the low-scoring, complex, and highly dynamic nature of soccer. This article proposes an end-to-end deep reinforcement learning framework that receives raw tracking data for each situation in a game, and yields optimal ball destination location on the full surface of the pitch. Using the proposed approach, soccer players and coaches are able to analyze the actual behavior in their historical games, obtain the optimal behavior and plan for future games, and evaluate the outcome of the optimal decisions prior to deployment in a match. Concisely, the results of our optimization model propose more short passes (Tiki-Taka playing style) in all phases of a ball possession, and higher propensity of low distance shots (i.e. shots in attack phase). Such a modification will let the typical teams to increase their likelihood of possession ending in a goal by 0.025. LA - English DB - MTMT ER - TY - JOUR AU - Ács, Balázs AU - Kovács, Roland AU - Toka, László TI - A career handbook for professional soccer players JF - INTERNATIONAL JOURNAL OF SPORTS SCIENCE AND COACHING J2 - INT J SPORT SCI COACHING VL - 19 PY - 2024 IS - 1 SP - 444 EP - 458 PG - 15 SN - 1747-9541 DO - 10.1177/17479541231155598 UR - https://m2.mtmt.hu/api/publication/33652661 ID - 33652661 N1 - Funding Agency and Grant Number: Ministry of Innovation and Technology of Hungary [128233, 135074]; National Research, Development and Innovation Fund [FK_18, FK_20] Funding text: The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: Projects no. 128233 and no. 135074 have been implemented with the support provided by the Ministry of Innovation and Technology of Hungary from the National Research, Development and Innovation Fund, financed under the FK_18 and FK_20 funding schemes, respectively. AB - The success of a soccer player is not entirely pre-destined by their physical ability, talent, and motivation. There are certain decisions along the way that greatly affect the arc of their career: which skills to develop, and which club to sign a contract with. In this paper, we identify the optimal strategic choices toward multiple potential aims a soccer player can have and we seek the knowledge of what made the greatest soccer players in terms of those decisions. Our two main data sources are Transfermarkt and Sofifa from which we collect data for the period between 2007 and 2021 with 29,231 players. We perform time series analysis on skill features of soccer players, and network analysis of the players’ acquaintance graph, i.e., a graph that indicates whether two given players have ever been teammates before. Finally, we create key performance indicators to check the differences in certain features, i.e., individual player skills and connectivity attributes, between top-tier and the rest of the players, and use dynamic time warping for validation. The outcome of this work is a recommendation tool that helps players to find what needs to be improved in order to achieve their desired goals. The source code and the career advisor tool for soccer players that we have implemented are available online. LA - English DB - MTMT ER - TY - JOUR AU - Almousa, Salah Al-Deen Afif Said AU - Horváth, Gábor AU - Telek, Miklós TI - Correction to: Transient analysis of piecewise homogeneous Markov fluid models (Annals of Operations Research, (2020), 10.1007/s10479-020-03831-1) JF - ANNALS OF OPERATIONS RESEARCH J2 - ANN OPER RES VL - 332 PY - 2024 SP - 1251 EP - 1251 PG - 1 SN - 0254-5330 DO - 10.1007/s10479-021-03934-3 UR - https://m2.mtmt.hu/api/publication/32242266 ID - 32242266 N1 - Correction to: Annals of Operations Research https://doi.org/10.1007/s10479-020-03831-1 [31797535] AB - Affiliation for author Miklos Telek was missing in the original publication and should be read as: Department of Networked Systems and Services, Budapest University of Technology and Economics, Budapest, Hungary and MTA-BME Information Systems Reseach Group, Hungary. Along with Department of Networked Systems and Services, Budapest University of Technology and Economics, Budapest, Hungary. Original article has been updated. © 2021, Springer Science+Business Media, LLC, part of Springer Nature. LA - English DB - MTMT ER - TY - JOUR AU - Kuruc, Gábor AU - Heszberger, Zalán TI - Artificial Intelligence based Routing Domains in 6th Generation Mobile Networks JF - IEEE COMMUNICATIONS MAGAZINE J2 - IEEE COMMUN MAG PY - 2024 SN - 0163-6804 UR - https://m2.mtmt.hu/api/publication/32237457 ID - 32237457 LA - English DB - MTMT ER - TY - CHAP AU - Rahimian, Pegah AU - da Silva Guerra Gomes, Dayana Grayce AU - Berkovics, Fanni AU - Toka, László ED - Brefeld, Ulf ED - Davis, Jesse ED - Van Haaren, Jan ED - Zimmermann, Albrecht TI - Let’s Penetrate the Defense. A Machine Learning Model for Prediction and Valuation of Penetrative Passes TS - A Machine Learning Model for Prediction and Valuation of Penetrative Passes T2 - Machine Learning and Data Mining for Sports Analytics VL - 1783 CCIS PB - Springer Science+Business Media CY - Cham SN - 9783031275272 T3 - Communications in Computer and Information Science, ISSN 1865-0929 ; 1783 CCIS. PY - 2023 SP - 41 EP - 52 PG - 12 DO - 10.1007/978-3-031-27527-2_4 UR - https://m2.mtmt.hu/api/publication/33733381 ID - 33733381 N1 - Budapest University of Technology and Economics, Budapest, Hungary MTA-BME Information Systems Research Group, Budapest, Hungary Correspondence Address: Rahimian, P.; Budapest University of Technology and EconomicsHungary; email: pegah.rahimian@edu.bme.hu LA - English DB - MTMT ER - TY - JOUR AU - Szigeti, György AU - Schuth, Gábor AU - Kovács, Tamás AU - Revisnyei, Péter AU - Pašić, Alija AU - Szilas, Ádám AU - Gabbett, Tim AU - Pavlik, Gábor TI - Football movement profile analysis and creatine kinase relationships in youth national team players JF - PHYSIOLOGY INTERNATIONAL J2 - PHYSIOL INT VL - 110 PY - 2023 IS - 1 SP - 74 EP - 86 PG - 13 SN - 2498-602X DO - 10.1556/2060.2023.00160 UR - https://m2.mtmt.hu/api/publication/33630596 ID - 33630596 N1 - Online Publication Date: 24 Jan 2023 Publication Date: 24 Jan 2023 LA - English DB - MTMT ER - TY - JOUR AU - Rahimian, Pegah AU - Toka, László TI - A data-driven approach to assist offensive and defensive players in optimal decision making JF - INTERNATIONAL JOURNAL OF SPORTS SCIENCE AND COACHING J2 - INT J SPORT SCI COACHING VL - 19 PY - 2023 IS - 1 PG - 12 SN - 1747-9541 DO - 10.1177/17479541221149481 UR - https://m2.mtmt.hu/api/publication/33604271 ID - 33604271 N1 - Correspondence Address: Rahimian, P.; Department of Telecommunication and Media Informatics, Hungary; email: pegah.rahimian@edu.bme.hu AB - Among all the popular sports, soccer is a relatively long-lasting game with a small number of goals per game. This renders the decision-making cumbersome, since it is not straightforward to evaluate the impact of in-game actions apart from goal scoring. Although several action valuation metrics and counterfactual reasoning have been proposed by researchers in recent years, assisting coaches in discovering the optimal actions in different situations of a soccer game has received little attention of soccer analytics. This work proposes the application of deep reinforcement learning on the event and tracking data of soccer matches to discover the most impactful actions at the interrupting point of a possession. Our optimization framework assists players and coaches in inspecting the optimal action, and on a higher level, we provide for the adjustment required for the teams in terms of their action frequencies in different pitch zones. The optimization results have different suggestions for offensive and defensive teams. For the offensive team, the optimal policy suggests more shots in half-spaces (i.e. long-distance shots). For the defending team, the optimal policy suggests that when locating in wings, defensive players should increase the frequency of fouls and ball outs rather than clearances, and when located in the centre, players should increase the frequency of clearances rather than fouls and ball outs. LA - English DB - MTMT ER - TY - JOUR AU - Horváth, Illés AU - Mészáros, András Gergely AU - Telek, Miklós TI - Numerical inverse Laplace transformation beyond the Abate–Whitt framework JF - JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS J2 - J COMPUT APPL MATH VL - 418 PY - 2023 PG - 12 SN - 0377-0427 DO - 10.1016/j.cam.2022.114651 UR - https://m2.mtmt.hu/api/publication/33091248 ID - 33091248 N1 - ELKH-BME Information Systems Research Group, Budapest, Hungary Department of Networked Systems and Services, Budapest University of Technology and Economics, Budapest, Hungary Export Date: 13 September 2022 Correspondence Address: Horváth, I.; ELKH-BME Information Systems Research GroupHungary; email: pollux@math.bme.hu AB - Among the numerical inverse Laplace transformation (NILT) methods, those that belong to the Abate–Whitt framework (AWF) are considered to be the most efficient ones currently. It is a characteristic feature of the AWF NILT procedures that they are independent of the transform function and the time point of interest. In this work we propose an NILT procedure that goes beyond this limitation and optimize the accuracy of the NILT utilizing also the transform function and the time point of interest. LA - English DB - MTMT ER - TY - JOUR AU - Heszberger, Zalán TI - Hyperbolic Trees for Distributed Computing JF - JOURNAL OF SUPERCOMPUTING J2 - J SUPERCOMPUT PY - 2023 SN - 0920-8542 UR - https://m2.mtmt.hu/api/publication/32239765 ID - 32239765 LA - English DB - MTMT ER - TY - JOUR AU - Heszberger, Zalán TI - Entropy Rate Function Approximations JF - ELECTRONICS (SWITZ) PY - 2023 SN - 2079-9292 UR - https://m2.mtmt.hu/api/publication/32237488 ID - 32237488 LA - English DB - MTMT ER -