Ferenc Erdos

Dr. Ferenc Erdos

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 June 2025 in Computers and Education: Artificial Intelligence
Verified
Journal Article
Open access
AAAsmae Azzi
Asmae Azzi
FEFerenc Erdos
Ferenc Erdos
RNRichárd Németh
Richárd Németh
VVVijayakumar Varadarajan
Vijayakumar Varadarajan
SAStephen Afrifa
Stephen Afrifa

5 August 2024 in Edelweiss Applied Science and Technology
Verified
Journal Article
Open access
PDF file
LKLászló Koloszár
László Koloszár
ÉBÉva Bednárik
Éva Bednárik
FEFerenc Erdos
Ferenc Erdos
RTRajermani AP Thinakaran
Rajermani AP Thinakaran
ATAlexandra Takáts
Alexandra Takáts
Industry 4.0 focuses on the digitalization of production processes and technological innovation. The concept of Industry 5.0 puts the focus on human-centricity, sustainability, and resilience at the heart of research and development and innovation (R&D&I) processes to allow industry to serve humanity with a long-term vision that considers planetary boundaries. Replacing the technology-driven approach with a fundamentally human-centric approach requires a deep understanding of the working environment and workers interacting with machines to optimize worker well-being, working conditions, and job outcomes. Analyzing computer work User eXperience (UX) in industrial environments is vital. However, user perceptions are usually hidden and a challenge to detect. Therefore, measuring and monitoring perceptions, emotional reactions, subjective elements, preferences, and attitudes in the relationships between usability, work performance, and workload is crucial. This study provides conclusions of a literature review on user experience studies focusing on UX testing methods and the disciplines linked to industrial diversification. Based on literature analysis, it identifies UX testing methods and create own grouping to analyze them. It also examines the disciplinary context of user experience testing.

1 January 2016 in Gazdaság és Társadalom
Verified
Journal Article
Open access
FEFerenc Erdos
Ferenc Erdos
LKLászló Koloszár
László Koloszár
Az informatika mára átszövi az élet minden területét, az oktatás, ezen belül a felsőoktatás is részese ennek. A technológia nem pusztán hátteret ad, hanem a hagyományos folyamatokat is átalakítja. A felsőoktatást korábban jellemző, nagyelőadásokon és a kapcsolódó, limitált interakciót biztosító szemináriumok rendszerén keresztül zajló hierarchikus tudáselosztást egy állandó interakciót biztosító, uniformizálás helyett akár kisebb csoportonként vagy hallgatónként is testre szabható elektronikus platform egészíti ki. A virtuális tanulókörnyezetet létrehozó eszközök az oktatási tananyagok megújítása (pl. multimédia, önellenőrző előrehaladás) mellett az oktatásmódszertan megújításának (pl. konstruktivista pedagógia, élményalapú tanulás, gamification) lehetőségét is magukban hordozzák. Mindez azt is jelenti, hogy az e-learning felsőoktatási bevezetése komplex gazdasági kérdés. Nem csak szoftverbe, hanem a humán erőforrásba, valamint a kapcsolódó szervezetfejlesztésbe is be kell fektetni a valós sikerhez. A tanulmány e döntéshez próbál elméleti összegzéssel muníciót adni. Áttekintjük azon gazdaságossági elemzési módszereket, amelyek alkalmasak lehetnek e-learning típusú beruházások értékeléséhez, kiemelve a sajátosságokat, nehézségeket. Erre alapozva megkezdhető lehet egy olyan adatgyűjtés, amely a valós módszertani megújulással egybekötött e-learning projekt gazdaságossági hátterét feltárhatja.

1 January 2026 in Computers, Materials & Continua
Verified
Journal Article
Open access
FEFerenc Erdos
Ferenc Erdos
VVVijayakumar Varadarajan
Vijayakumar Varadarajan
VBViorel-Costin Banţa
Viorel-Costin Banţa
SAStephen Afrifa
Stephen Afrifa
Standard retrieval-augmented generation (RAG) can perform poorly in AI for IT Operations (AIOps) settings because it is topology-blind. Basic RAG retrieves isolated, flat text snippets without enforcing structural or causal constraints, causing large language models to generate explanations that contradict the running system’s actual dependency structure. To address this gap, we conducted a systematic review following PRISMA 2020, searching Scopus, IEEE Xplore, Web of Science, and Google Scholar (last searched 31 January 2026). We included empirical or systems-oriented studies applying graph-based retrieval to ground a generative model in an IT, cloud, or software-operations setting, and excluded generic RAG without an operational context and graph-only methods without a generative component. Of 139 unique records, 31 met the criteria. Because reported metrics, tasks, and hardware were too heterogeneous for pooled effect estimates, we performed a descriptive quantitative synthesis of reporting frequencies for five outcome variables (localization accuracy, text/classification scores, MTTR, retrieval/inference latency, and graph construction cost), with values harmonized to common units. The synthesis reveals that hybrid-fusion approaches have become the dominant retrieval strategy, outpacing standalone traversal in adoption for Root Cause Analysis (RCA) tasks by fusing semantic vector search with strict structural constraints. However, our evaluation matrix exposes a critical production barrier: in 73% of Service Dependency Graph (SDG)-centric studies, topology drift or streaming-update handling is not explicitly described, with many pipelines evaluated on static or periodically refreshed snapshots. We outline Event-Sourced Streaming GraphRAG (ES-GraphRAG) as a reference architecture that frames concrete design requirements for latency and drift constraints based on an event-sourced, streaming construction pattern for snapshot-consistent retrieval. The framework also incorporates strict retrieval-time governance and budget-aware traversal to help keep LLM grounding topologically accurate and compliant with incident-response Service Level Objectives (SLOs).

1 January 2025 in Applied Computational Intelligence and Soft Computing
Verified
Journal Article
Open access
SAStephen Afrifa
Stephen Afrifa
TZTao Zhang
Tao Zhang
VVVijayakumar V.
Vijayakumar V.
YGYanzhang Geng
Yanzhang Geng
PAPeter Appiahene
Peter Appiahene
FEFerenc Erdos
Ferenc Erdos
Maternal childbirth experiences are crucial indicators of health care quality, patient satisfaction, and emotional health. The increasing use of social media platforms, such as Facebook, provides a unique opportunity to examine public sentiment and narratives around maternity care. However, limited studies have employed deep learning (DL)–based sentiment analysis (SA) to comprehensively analyze childbirth experiences in low‐resource environments. This study utilizes a hybrid technique that integrates unsupervised topic modeling with supervised DL sentiment classification to capture both thematic breadth and emotional tone of birthing experiences. A dataset of Facebook comments was preprocessed and analyzed using word frequency analysis, latent Dirichlet allocation (LDA) for thematic extraction, sentiment classification using convolutional neural networks (CNNs), and robustly optimized BERT pretraining approach (RoBERTa). Statistical correlations between sentiment polarity and hospital service variables were examined using the chi‐square test. The word frequency analysis revealed significant themes such as maternal care, labor and childbirth experiences, informal childbirth discussions, spiritual beliefs, and personal childbirth stories. SA found a majority positive sentiment (5106 instances) with widespread sentiments of trust and joy, although considerable occurrences of fear (1,851), sadness (1,564), and anger (1,114) indicated traumatic delivery experiences. The CNN model outperformed RoBERTa, which had an AUC of 0.9988 and an accuracy of 87%. Statistical study (chi‐square test, p < 0.0001) showed a significant correlation between sentiment polarity and hospital service variables, indicating the influence of treatment quality on patient views. This study emphasizes the significance of SA in assessing maternal health care experiences and improving hospital practices. The findings highlight the need of increased communication, empathetic midwifery care, and patient‐centered approaches in addressing unfavorable childbirth experiences. This study provides policymakers with data‐driven insights to improve maternal health care policies, increase patient experiences, and ensure valuable maternity services.

27 June 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MSMohamad Shatnawi
Mohamad Shatnawi
EEEnas Elshebli
Enas Elshebli
FEFerenc Erdos
Ferenc Erdos
PFPéter Földesi
Péter Földesi
The intersection area between two arbitrarily rotated ellipses is a recurring geometric primitive in imaging, computer vision, and robotics. In the general case, its evaluation is often associated with intersection-point recovery, topology-dependent case handling, adaptive refinement, or dense boundary approximation. This study presents a fixed-cost computational framework for ellipse–ellipse intersection based on a rotated-frame slice formulation. A coordinate-frame rotation expresses one ellipse in axis-aligned form while representing the second as a general conic. This yields a hybrid formulation that reduces the intersection area to a one-dimensional overlap integral of vertical slice height over the admissible horizontal interval. The integral is evaluated using fixed-order quadrature, with optional sine mapping to improve conditioning near grazing configurations. Numerical evaluation on 100,000 synthetic ellipse pairs shows that the proposed formulation reaches a low-error regime earlier than polygonal approximation while remaining substantially faster across the tested range. The formulation is further examined through a tree-crown delineation case study on the BAMFORESTS dataset, a benchmark forest dataset of very-high-resolution UAV imagery. In this case study, ellipse proxies derived from axis-aligned and oriented bounding box detections are used for overlap computation during non-maximum suppression (NMS). Using ellipse-proxy overlap during NMS preserves nearly the same peak F1 score of 0.785 while modestly shifting NMS behavior toward lower thresholds and producing slightly broader near-peak intervals.