A5025718815- Rough Sets and Fuzzy Logic
- Advanced Database Systems and Queries
- Data Management and Algorithms
- Sentiment Analysis and Opinion Mining
- Diverse Approaches in Healthcare and Education Studies
- Handwritten Text Recognition Techniques
- Advanced Image and Video Retrieval Techniques
- Data Quality and Management
- Model-Driven Software Engineering Techniques
- Multimodal Machine Learning Applications
- Data Visualization and Analytics
- Formal Methods in Verification
- Web Data Mining and Analysis
- Complex Network Analysis Techniques
- Sports Performance and Training
- Semantic Web and Ontologies
- Topic Modeling
- Spam and Phishing Detection
- Neural dynamics and brain function
- Neural Networks and Reservoir Computing
- Advanced Memory and Neural Computing
- Multimedia Communication and Technology
- Advanced Software Engineering Methodologies
- Sports injuries and prevention
Sapientia Hungarian University of Transylvania
2010-2024
Babeș-Bolyai University
2016
Early Big Data solutions were not based on database management system principles.As the popularity of these have increased and are applied in more data scenarios recent years, DBMS principles, being recognized as important factors becoming newly developed solutions.Big collections do enforce document structure, but just because a store is schema-less, it does mean structure stored documents will play an role overall performance flexibility application.In this paper we explore method for...
Predicting burnout from texts by using AI necessitates an interdisciplinary approach, combining sports science, psychology, and machine learning. This research is essential to understanding the psychological signs of methods gauge it, coupled with expertise in NLP sentiment analysis techniques. Collecting athletes' textual data, like logs or interviews, crucial, along possible metrics stamina fatigue. The role AI, particular significantly advanced models BERT GPT-3, analyze these texts,...
Real-time multilingual phrase detection from/during online video presentations—to support instant remote diagnostics—requires near real-time visual (textual) object and preprocessing for further analysis. Connecting specialists sharing specific ideas is most effective using the native language. The main objective of this paper to analyze propose—through DEtection TRansformer (DETR) models, architectures, hyperparameters—recommendation, procedures with simplified methods achieve reasonable...
Choosing the Event-B formal method to model and develop distributed railway interlocking systems can give us a great advantage over general purpose programming languages, especially in case of safety analysis these systems. Despite its many benefits, suffers from an efficient reuse mechanism, which is highly disadvantageous development large In this paper we propose structured approach modelling developing geographical systems, combining communication models session types with entity...
Data extractors are generally difficult to maintain. To simplify the tasks of integrating new data sources and handling structural changes within existing sources, we have implemented a approach called RK. RK is tool which serves as guide for extraction purposes; semantic tree generated by rules (used input), describes pattern that represents structure source. Our system supports from hierarchical-structured sources. Results experiments using proved feasibility our enhancing in terms precision speed.
Abstract In our ever-evolving world, the importance of social networks is bigger now than ever. The purpose this paper to develop a sentiment analyzer for Hungarian language, which we can then use analyze any text and conduct further experiments. One such experiment an application interface with networks, run analysis on logged-in users friends’ posts comments, while other in order visualize evolution relationships between characters text.