Early access articles

Infocommunications Journal provides early access publications for articles that have been reviewed and accepted. This practice allows the scientific community to find and read the latest proceedings in the infocommunications domain. Papers appearing in the early access section are under completion for upcoming journal issues.

----------------------------------------------------------------------------------------

EARLY ACCESS ARTICLES

Kristián Fodor, Zoltán Balogh, and György Molnár
From the Ring to the Model: Forecasting WWE Outcomes with Machine Learning

Professional wrestling, particularly WWE, com­bines athletic performance with narrative storytelling, making it a unique and complex domain for predictive analytics. This study explores the feasibility of predicting WWE match out­comes using machine learning models, leveraging historical win-loss records and performance metrics from the 2023 sea­son. Employing Random Forest and XGBoost classifiers, key features were analyzed, including Win Streaks, Total Matches, and Current Champion status, to determine their impact on match outcomes. Initial models revealed high accuracy but exhibited overfit­ting due to feature leakage, particularly with the use of Win Ratio. By refining feature selection and implementing cross-validation, generalization and robustness were achieved. XG­Boost outperformed Random Forest with an overall accuracy of 97.5%, demonstrating the effectiveness of boosting algorithms in narrative-driven sports environments. The results highlight the influence of consistent performance and championship status on match outcomes, reflecting WWE's booking patterns. This study contributes to sports analytics by showcasing machine learning's potential in a narrative sports context, despite the predetermined nature of WWE match out­comes. This paper not only advances the application of predictive modeling in sports entertainment but also provides insights into the strategic storytelling mechanisms within professional wres­tling.

Download 

Kristóf Szentmihályi, Dávid Márk Nemeskey, András Márk Szekeres, Bence György Gortka, Balázs Indig,Gábor Palkó, Balázs Nagy, László Vidács
Pretraining GPT-style models in Hungarian 
In this paper, we introduce two bilingual large language models, named OTP-1.5B and OTP-13B, designed with a focus on both English and Hungarian languages. Both models utilize an 8k token context window and are trained on a dataset of 640 billion tokens, allowing the models to capture a broad range of linguistic nuances and generalize effectively across languages. Notably, their performance in Hungarian is on par with the results reported for equivalent models in English, such as GPT-3, marking a significant breakthrough in bilingual model development and evaluation. This achievement demonstrates the viability of scaling language models to perform robustly in lessresourced languages like Hungarian, a critical advancement for linguistic diversity in AI research. In addition, we introduce new benchmark datasets specifically designed to evaluate Hungarian language capabilities, addressing a significant gap in the current landscape of multilingual large language model (LLM) assessment. These benchmarks offer a comprehensive framework for measuring performance in non-English contexts, enabling more precise and culturally relevant evaluations of LLMs.  Our models achieve state-of-the-art results in Hungarian, underscoring their proficiency and utility for a wide range of applications in both English and Hungarian language tasks.

Download 

Cite: Kristóf Szentmihályi, Dávid Márk Nemeskey, András Márk Szekeres, Bence György Gortka, Balázs Indig,Gábor Palkó, Balázs Nagy, László Vidács "Pretraining GPT-style models in Hungarian", Infocommunications Journal

Tamara Zuhair Fadhil, Noor Asniza Murad, and Mohamad Rijal Hamid 
Broadside Gain Enhancement of Wideband Monopole Circular Shaped Antenna Using FSS for Sub-6 GHz Applications
This paper introduces a wideband circular patch antenna designed with a frequency selective surface (FSS) for sub-6 GHz applications. The proposed antenna features a monopole circular-shaped patch with a partial ground plane, delivering an omnidirectional radiation pattern in the azimuth plane, resulting in relatively uniform gain in all directions. An FSS metamaterial enhances the antenna's gain and improves the broadside radiation pattern. The design incorporates three inner circular patches connected to the main patch. The FSS utilizes hybrid square/circle loop-based unit cells. The antenna and FSS are simulated using CST software and subsequently fabricated on an FR-4 substrate. The measured results demon strate an impedance bandwidth of 1.6 GHz with a peak gain of 5.4 dB at 3.5 GHz. The omnidirectional radiation pattern is converted into a directional one by placing a reflector FSS as a bottom substrate layer. The overall structure size is compact, measuring (0.34λ0 × 0.27λ0 × 0.016λ0), where λ0 is the free space wavelength corresponding to the lowest resonant fre quency within the operational bandwidth. This design achieves significant antenna size reduction and is well-suited for future sub-6 GHz applications.

Download 

Cite: Tamara Zuhair Fadhil, Noor Asniza Murad, and Mohamad Rijal Hamid  "Broadside Gain Enhancement of Wideband Monopole Circular Shaped Antenna Using FSS for Sub-6 GHz Applications", Infocommunications Journal

Guangmao Li, Gang Du, Hongbin Wang, Hongling Zhou, Jie Yang, and Zhikai Pang
Distributed Edge Computing Aided Environmental Severity Monitoring for Power Grid Equipment in Nakagami-m Fading Channels

This study explores the concept of multiuser mobile edge computing (MEC) networks aided environmental severity monitoring for power grid equipment, where an MEC server facilitates the computation of tasks from N users via wireless transmission in the presence of Nakagami-m fading channels. To analyze the system performance, we first define the system outage probability based on energy consumption, where the outage event is triggered when the energy required to complete the users’ tasks exceeds a specified threshold. We then develop an analytical expression for the system outage probability in Nakagami-m fading channels and provide a high signal-to-noise ratio (SNR) asymptotic analysis. Additionally, we optimize the system performance by adjusting the task offloading ratios. Finally, simulation and numerical results in Nakagami-m fading channels validate the proposed methods. The results show that the performance of multiuser MEC networks can be improved by increasing the bandwidth or energy consumption threshold for environmental severity monitoring in power grid equipments.

Download 

Cite: Guangmao Li, Gang Du, Hongbin Wang, Hongling Zhou, Jie Yang, and Zhikai Pang, "Distributed Edge Computing Aided Environmental Severity Monitoring for Power Grid Equipment in Nakagami-m Fading Channels", Infocommunications Journal