Computational Intelligence Research Group (CIRG)

✕
Sapientia.ro Sapientia.ro
Neptun  Moodle  ISSUU  Könyvtár 
✕
Computational Intelligence Research Group (CIRG)

Fontosabb kutatási témáink: klaszterező és részlegesen felügyelt klaszterező algoritmusok, evolúciós algoritmusok, digitális jel- és képfeldolgozás, beszédtechnológia: folyamatos beszédfelismerés, beszédszintézis, nyelvi erőforrások fejlesztése, alkalmazások nagy adatbázisokkal, élettani rendszerek modellezése és szimulációja, protein együtthatási hálózatainak tanulmányozása, virtualizációs technikák.

 

A kitatócsoport tagjai

  • SZILÁGYI László– a csoport vezetője
  • Senior kutatók: ANTAL Margit, BIRÓ Attila, DÉNES-FAZAKAS Lehel, DOMOKOS József, GYŐRFI Ágnes, ICLĂNZAN David Andrei, LEFKOVITS László, JÁNOSI-RANCZ Katalin Tünde
  • PhD hallgtók: CSAHOLCZI Szabolcs, NAGHI Mirtill-Boglárka, KOCSIS (FERENCZ) Katalin, Pisak-Lukáts Ioan Marius, Palatka József, ROMÁN Róbert, KIS Gerlinda-Boglárka, KOVÁCS Attila
  • Technikusok: KISS Konrád József
  • Halggatók 2010 óta: Fülöp Tímea, Kucsván Zsolt-Levente, Kapás Zoltán, Borsos Bálint, Szabó Zsófia, Kőble Andrea-Melinda, Vidámi Mózes, Nagy Lajos Lóránd, Darabont Örs, Dénesi Gellért, Fábián Emese, Varga Zsuzsa Réka, Medvés Lehel, Crăciun Lehel, Szabó Lehel

Partner intézmények

  • BME Budapest (Hungary), Dept. of Control Engineering and Information Technology, Benyó Balázs, http://iit.bme.hu
  • Canterbury University of Christchurch (New Zealand), Geoffrey Chase
  • Queens University of Kingston (Canada), Fichtinger Gábor
  • University of Málaga, Antonio Cuesta-Vargas
  • Óbuda University, Budapest (Hungary), Kovács, Levente Eigner György
  • University of Lyon, France, Egyed-Zsigmond Előd
  • Mircea Giurgiu, Speech Processing Group, Technical University of Cluj-Napoca, http://speech.utcluj.ro 
  • UMFST Tg. Mureş, Szilágyi Sándor Miklós

Támogatott kutatási projektek

  • KPI grant: Multi-atlas based segmentation of medical images for diagnostics and therapy planning (2019/05-2021/05, 10000 EUR)
  • KPI grant: Detection and segmentation of tubular shapes and structures in low-resolution volumetric image data (2017/03–2018/08, 20000 RON)  
  • KPI grant: MRI brain tumor segmentation applying machine learning algorithms (2017/03–2018/08, 20000 RON)  
  • János Bolyai Kutatási Ösztöndíj (Szilágyi László), 2018/09-2021/08, 4.5m HUF
  • János Bolyai Kutatási Ösztöndíj (Szilágyi László), 2010/09-2013/08, 4.5m HUF
  • Collegium Talentum Ösztöndíj (Fülöp Tímea), 2019/09-2020/07, 1.5m HUF
  • Collegium Talentum Ösztöndíj (Naghi Mirtill-Boglárka), 2023/09-2026/07, 3x1.5m HUF
  • Collegium Talentum Ösztöndíj (Roman Robert), 2025/09-2026/07, 1.5m HUF
  • Székely Előfutár Ösztöndíj (Kapás Zoltán, 2016-2017, 1000 USD), (Borsos Bálint, 2018-2019, 1000 USD)
  • Accenture Hallgatói Ösztöndíj (Szabó Zsófia, 2018, 4000 RON), (Borsos Bálint, 2018, 4000 RON) 

Konferencia szervezés

  • INES 2020. 2021, 2022, 2023, 2024, 2025, INES 2026 ¬– Program Committee Co-chair: László Szilágyi
  • ICONIP 2019 – Program Committee members: László Szilágyi, David Iclănzan
  • PSIVT 2017 – Program Committee member: László Szilágyi
  • MDAI 2012, 2013, 2014, … 2023, 2024, 2025, 2026 – Program Committee member: László Szilágyi

Konferencia részvétel

  • ICONIP 2016 – International Conference on Neural Information Processing – Kyoto (Japan)
  • ICONIP 2017 – International Conference on Neural Information Processing – Guangzhou (China)
  • ICONIP 2018 – International Conference on Neural Information Processing – Siem Reap (Cambodia)
  • ICONIP 2019 – International Conference on Neural Information Processing – Sydney (Australia)
  • ICONIP 2020 – International Conference on Neural Information Processing – Bangkok (Thailand) – online
  • IEEE SMC 2019 – IEEE International Conference on Systems, Man, and Cybernetics – Bari (Italy)
  • IEEE SMC 2020 – IEEE International Conference on Systems, Man, and Cybernetics – Toronto (Canada) – online
  • IEEE SMC 2023 – IEEE International Conference on Systems, Man, and Cybernetics – Honolulu (USA)
  • IEEE SMC 2024 – IEEE International Conference on Systems, Man, and Cybernetics – Kuching (Malaysia)
  • MDAI 2016 – Modeling Decision for Artificial Intelligence – Sant Julia de Loria (Andorra)
  • MDAI 2018 – Modeling Decision for Artificial Intelligence – Palma de Mallorca (Spain)
  • MDAI 2019 – Modeling Decision for Artificial Intelligence – Milan (Italy)
  • PSIVT 2017 – Pacific-Rim Symposium on Image and Video Technology – Wuhan (China)
  • CIARP 2017 – Ibero-American Congress on Pattern Recognition – Valparaíso (Chile)
  • CIARP 2019 – Ibero-American Congress on Pattern Recognition – La Habana (Cuba)
  • CIARP 2024 – Ibero-American Congress on Pattern Recognition – Talca (Chile)
  • MICCAI 2017 – Medical Image Computation and Computer Assisted Interventions – Athens (Greece)
  • FSKD 2018 – International Conference on Fuzzy Systems and Knowledge Discovery – Huangshan (China)
  • EMBC 2019 – Annual International Conference of the IEEE EMBS – Berlin (Germany)
  • IFAC World Congress 2023 – Yokohama (Japan)
  • IFAC World Congress 2026 – Busan (S. Korea)

 

Publikációl

Impakt faktoros folyóirat cikkek:

  1. Biró A, Kovács L, Szilágyi L: Bioinformatics-Inspired IMU Stride Sequence Modeling for Fatigue Detection Using Spectral–Entropy Features and Hybrid AI in Performance Sports. SENSORS 26(2):525, 2026
  2. Dénes-Fazakas L, Mateas IC, Berciu AG, Szilágyi L, Kovács L, Dulf EH: A Real Time Multi Modal Computer Vision Framework for Automated Autism Spectrum Disorder Screening. ELECTRONICS 15 (6), 1287, 2026
  3. Kis GB, Kovács L, Szilágyi L: Automated Retinal Vessel Segmentation Using U-Net Deep Learning Model. ACTA POLYTECHNICA HUNGARICA 22 (12):127-142, 2026
  4. Dénes -Fazakas L, Kovács L, Eigner Gy, Szilágyi L: Enhanced U-Net for Infant Brain MRI Segmentation: A (2+1)D Convolutional Approach. SENSORS 25(5):1531, 2025
  5. Dénes -Fazakas L, Kovács L, Eigner Gy, Szilágyi L: Enhancing Brain Tumor Diagnosis with L-Net: A Novel Deep Learning Approach for MRI Image Segmentation and Classification. BIOMEDICINES 12(10):2388, 2024
  6. Dénes-Fazakas L, Szilágyi L, Kovács L, Di Gaetano A, Eigner Gy: Reinforcement Learning: A Paradigm Shift in Personalized Blood Glucose Management for Diabetes. BIOMEDICINES 12(9):2143, 2024
  7. Dénes-Fazakas L, Simon B, Hartveg Á, Szilágyi L, Kovács L, Mosavi A, Eigner Gy: Personalized food consumption detection with deep learning and Inertial Measurement Unit sensor. COMPUTERS IN BIOLOGY AND MEDICINE 182:109167, 2024
  8. Biró A, Cuesta-Vargas AI, Szilágyi L: AI-Assisted Fatigue and Stamina Control for Performance Sports on IMU-Generated Multivariate Times Series Datasets. SENSORS 24(1):132, 2024
  9. Dénes-Fazakas L, Simon B, Hartveg Á, Kovács L, Dulf ÉH, Szilágyi L, Eigner Gy: Physical Activity Detection for Diabetes Mellitus Patients Using Recurrent Neural Networks. SENSORS 24(8):2412, 2024
  10. Simon B, Hartveg Á, Dénes-Fazakas L, Eigner Gy, Szilágyi L: Advancing Medical Assistance: Developing an Effective Hungarian-Language Medical Chatbot with Artificial Intelligence. INFORMATION 15(6):297, 2024
  11. Szilágyi L, Kovács L: Special Issue: Artificial Intelligence Technology in Medical Image Analysis. APPLIED SCIENCES 14(5):2180, 2024
  12. Biró A, Szilágyi SM, Szilágyi L: Optimal Training Dataset Preparation for AI-Supported Multilanguage Real-Time OCRs Using Visual Methods. APPLIED SCIENCES 13(24):13107, 2023.
  13. Bíró A, Szilágyi SM, Szilágyi L, Cuesta-Vargas AI, Martín-Martín J: Machine Learning on Prediction of Relative Physical Activity Intensity Using Medical Radar Sensor and 3D Accelerometer. SENSORS 23(7):3595, 2023
  14. Bíró A, Cuesta-Vargas AI, Martín-Martín J, Szilágyi L, Szilágyi SM: Synthetized Multilanguage OCR Using CRNN and SVTR Models for Realtime Collaborative Tools. APPLIED SCIENCES 13(7):4419, 2023
  15. Szepesi P, Szilágyi L: Detection of pneumonia using convolutional neural networks and deep learning. BIOCYBERNETICS AND BIOMEDICAL ENGINEERING 42:1012-1022, 2022
  16. Dénes-Fazakas L, Siket M, Szilágyi L, Kovács L, Eigner Gy: Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals. SENSORS 22(21):8568, 2022
  17. Kopcsóné Németh IA, Nádor Cs, Szilágyi L, Lehotsky Á, Haidegger T: Establishing a Learning Model for Correct Hand Hygiene Technique in a NICU. JOURNAL OF CLINICAL MEDICINE 11:4276, 2022
  18. Bíró A, Jánosi-Rancz KT, Szilágyi L, Cuesta-Vargas AI, Martín-Martín J, Szilágyi SM: Visual Object Detection with DETR to Support Video-Diagnosis Using Conference Tools. APPLIED SCIENCES 12:5977, 2022
  19. Lefkovits Sz, Lefkovits L, Szilágyi L: HGG and LGG Brain Tumor Segmentation in Multi-modal MRI Using Pretrained Convolutional Neural Networks of Amazon Sagemaker, Applied Sciences 12(7):3620, 2022
  20. Győrfi Á, Szilágyi L, Kovács L: A fully automatic procedure for brain tumor segmentation from multi-spectral MRI records using ensemble learning and atlas-based data enhancement. Applied Sciences 11(2):564, 2021
  21. Szilágyi L, Lefkovits Sz, Szilágyi SM: Self-tuning possibilistic c-means clustering models. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 27(Suppl. 1): 143-159, 2019.
  22. Antal M, Egyed-Zsigmond E: Intrusion detection using mouse dynamics, IET Biometrics, 8(5):285-294, 2019, IET Digital Library, IF: 1.836.
  23. Antal M, Szabó LZs, Tordai T: Online Signature Verification on MOBISIG Finger-Drawn Signature Corpus. MOBILE INFORMATION SYSTEMS, Volume 2018 (2018), Article ID 3127042, 15 pages
  24. Lehotsky Á, Szilágyi L, Bánsághi Sz, Szerémy P, Wéber Gy, Haidegger T: Towards objective hand hygiene technique assessment – validation of the UV dye based hand rubbing quality assessment procedure. Journal of Hospital Infection 97(1):26-29, 2017, ISSN 0195-6701, IF: 3.354
  25. Frigy A, Magdás A, Moga VD, Coteţ OG, Kozlovszky M, Szilágyi L: Increase of short-term heart rate variability induced by blood pressure measurements during ambulatory blood pressure monitoring. Computational and Mathematical Methods in Medicine, article ID 5235319, pp. 1–5, 2017, ISSN 1748-6718, IF: 1.545
  26. Szilágyi L, Szilágyi SM: A modified two-stage Markov clustering algorithm for large and sparse networks. Computer Methods and Programs in Biomedicine 135:15-26, 2016, ISSN 0169-2607, IF: 2.503
  27. Lehotsky Á, Szilágyi L, Demeter-Iclănzan A, Haidegger T, Wéber Gy: Education of hand rubbing technique to prospective medical staff, employing UV-based digital imaging technology. Acta Microbiologica et Immunologica Hungarica 63(2):217-228, 2016, ISSN 1217-8950, IF: 0.921
  28. Magdás A, Szilágyi L, Incze A: Can ambulatory blood pressure variability contribute to individual cardiovascular risk stratification? Computational and Mathematical Methods in Medicine, article ID 7816830, pp. 1–5, 2016, ISSN 1748-6718, IF: 0.937
  29. Varga V, Jánosi-Rancz KT, Kálmán B: Conceptual Design of Document NoSQL Database with Formal Concept Analysis, ACTA POLYTECHNICA HUNGARICA, Journal of Applied Sciences, Volume 13, Number 2, p. 229-248, 2016
  30. Lehotsky Á, Szilágyi L, Ferenci T, Kovács L, Pethes R, Wéber Gy, Haidegger T: Quantitative impact of direct, personal feedback on hand hygiene technique. Journal of Hospital Infection 91(1):81–84, 2015, ISSN 0195-6701, IF: 2.655
  31. Gosztolya G, Szilágyi L: Application of fuzzy and possibilistic c-means clustering models in blind speaker clustering. Acta Polytechnica Hungarica 12(7):41-56 (2015), ISSN 1785-8860, IF: 0.544
  32. Szilágyi L, Szilágyi SM: Generalization rules for the suppressed fuzzy c-means algorithm. Neurocomputing 139:298–309, 2014, ISSN 0925-2312, IF: 2.083
  33. Szilágyi SM, Szilágyi L: A fast hierarchical clustering algorithm for large-scale protein sequence data sets. Computers in Biology and Medicine 48:94–101, 2014, ISSN 0010-4825, IF: 1.240
  34. Szilágyi L: Lessons to learn from a mistaken optimization. Pattern Recognition Letters 36(1):29–35, 2014, ISSN 0167-6855, IF: 1.551
  35. Magdás A, Szilágyi L, Belényi B, Incze A: Ambulatory monitoring derived blood pressure variability and cardiovascular risk factors in elderly hypertensive patients. Bio-Medical Materials and Engineering 24(6):2563–2569, 2014, ISSN 0959-2989, IF: 1.091
  36. Szilágyi L, Haidegger T, Lehotsky Á, Nagy M, Csonka EA, Sun XY, Ooi KL, Fisher D: A large-scale assessment of hand hygiene quality and the effectiveness of the “WHO 6-steps”. BMC Infectious Diseases 13(249):1-10, 2013, ISSN 1471-2334, IF: 2.561
  37. Szilágyi L: Robust spherical shell clustering using fuzzy-possibilistic product partition. International Journal of Intelligent Systems 28(6):524-539, 2013, ISSN 1098-111X, IF: 1.411
  38. Szilágyi L, Szilágyi SM, Benyó B: Efficient inhomogeneity compensation using fuzzy c-means clustering models. Computer Methods and Programs in Biomedicine 108(1):80-89, 2012, ISSN 0169-2607, IF: 1.555
  39. Szilágyi SM, Szilágyi L, Benyó Z: A patient specific electro-mechanical model of the heart. Computer Methods and Programs in Biomedicine 101(2):183-200, 2011, ISSN 0169-2607, IF: 1.516
  40. Szilágyi L, Szilágyi SM, Benyó B, Benyó Z: Intensity inhomogeneity compensation and segmentation of MR brain images using hybrid c-means clustering models. Biomedical Signal Processing and Control 6(1):3-12, 2011, ISSN 1746-8094, IF: 1.000
  41. Szilágyi L, Medvés L, Szilágyi SM: A modified Markov clustering approach to unsupervised classification of protein sequences. Neurocomputing 73(13-15):2332-2345, 2010, ISSN 0925-2312, IF: 1.429
  42. Szilágyi L, Szilágyi SM, Benyó Z: Analytical and numerical evaluation of the suppressed fuzzy c-means algorithm: a study on the competition in c-means clustering models. Soft Computing 14(5):495-505, 2010, ISSN 1432-7643, IF: 1.512
  43. Naghi MB, Kovács L, Szilágyi L: A generalized fuzzy-possibilistic c-means clustering algorithm. Acta Universitatis Sapientiae – Informatica 15(2):404–431, 2023.
  44. Biró A, Cuesta-Vargas AI, Szilágyi L: Precognition of mental health and neurogenerative disorders using AI-parsed text and sentiment analysis. Acta Universitatis Sapientiae – Informatica 15(2):359–403, 2023.
  45. Palatka J, Kovács L, Szilágyi L: Enhanced imagistic methodologies augmenting radiological image processing in interstitial lung diseases. Acta Universitatis Sapientiae, Informatica 15(1):146–139, 2023.
  46. Pisak-Lukáts IM, Kovács L, Szilágyi L: A feature selection strategy using Markov clustering, for the optimization of brain tumor segmentation from MRI data. Acta Universitatis Sapientiae, Informatica 14(2):316–337, 2022
  47. Győrfi Á, Kovács L, Szilágyi L: A two-stage U-net approach to brain tumor segmentation from multi-spectral MRI records. Acta Universitatis Sapientiae, Informatica 14(2):223–247, 2022
  48. Szilágyi L, Lefkovits L, Iclănzan D: A review on suppressed fuzzy c-means clustering models. Acta Universitatis Sapientiae, Informatica 12(2):302–324, 2020, ISSN 2066-7760
  49. Borsos B, Nagy L, Iclănzan D, Szilágyi L: Automatic detection of hard and soft exudates from retinal fundus images. Acta Universitatis Sapientiae, Informatica 11(1):65-79, 2019, ISSN 2066-7760
  50. Szilágyi L, Iclănzan D, Kapás Z, Szabó Zs, Győrfi Á, Lefkovits L: Low and high grade glioma segmentation in multispectral brain MRI data. Acta Universitatis Sapientiae 10(1):110-132, 2018, ISSN 2066-7760

 

Konferencia dolgozatok

  1. Biró A, Kovács L, Szilágyi L: A Bioinformatics-Driven, Biostatistical Pathway Framework with Multimodal Machine Learning for Athlete Burnout Prediction on Physiological Signals. ICCC 2026 Brisbane/Uluru, pp. N/A
  2. Biró A, Kovács L, Szilágyi L: Bioinformatics-Guided NSGA-II Pathway-Sparse Optimization for Interpretable Neurodegenerative Risk Detection. ICCC 2026 Brisbane/Uluru, pp. N/A
  3. Biró A, Kovács L, Szilágyi L: Risk-Aware Genetic Algorithms for Reliable Triathlon Relays: A Cantelli-Regularized Applied Mathematics Pipeline. ICCC 2026 Brisbane/Uluru, pp. N/A
  4. Roman R, Kovács L, Szilágyi L: Automatic Detection of Bacterial and Viral Pneumonia from X-Ray Scans. ICCC 2026 Brisbane/Uluru, pp. N/A
  5. Simon B, Borkó B, Borkó B, Héger A, Hartveg A, Szász L, Dénes-Fazakas L, Eigner Gy, Kovács L, Szilágyi L: Sleep Efficiency Prediction with Machine Learning and Deep Neural Networks. SAMI 2026 Stará Lesná (SK), pp. 579-584
  6. Biró A, Kovács L, Szilágyi L: Bioinformatics-Inspired Robust Smith-Waterman-Guided Lineup Optimization in Basketball Using HMM Surrogates, PWMs, and Cantelli-Bounded Genetic Algorithms. SAMI 2026 Stará Lesná (SK), pp. 565-572.
  7. Biró A, Kovács L, Szilágyi L: Adapting Hidden Markov Models and Local Alignment Algorithms for Real-Time Lineup Change Decisioning in Ice Hockey. SAMI 2026 Stará Lesná (SK), pp. 379-384
  8. Biró A, Kovács L, Szilágyi L: Bayesian Biostatistical and Physiological Modeling for Optimal Triathlon Relay Team Assembly from Historical Results. SAMI 2026 Stará Lesná  (SK), pp. 707-714
  9. Naghi MB, Derzsi D, Kovács L, Szilágyi L: Automatic Hyperparameter Optimization of Self-Tuning Possibilistic Fuzzy C-Means Using Genetic Algorithms. CINTI 2025 Budapest, pp. 799-804.
  10. Biró A, Kovács L, Szilágyi L: Tactical Lineup Changes Simulation in Competitive High-Speed Team Sports via Hoeffding’s Inequality and Concentration Bounds. CINTI 2025 Budapest, pp. 713-720.
  11. Biró A, Kovács L, Szilágyi L: Disrupting the Critical 10 Seconds: An Optimization Framework for Lineup Changes and Strategy Shifts in Ice Hockey. CINTI 2025 Budapest, pp. 805-812.
  12. Biró A, Kovács L, Szilágyi L: Game-Based Learning and Gamified Efficiency for Team Performance Estimation in Professional Basketball. ICETA 2025 Stará Lesná (SK), pp. 95-100.
  13. Lam LD, Szilágyi L, Dung NV, Chuyen MT: Sparse Deep Neural Networks for Pubic Symphysis-Fetal Head Segmentation. ICHST 2025 DaNang (Vietnam), 1-6,
  14. Simon B, Hartveg Á, Dénes-Fazakas L, Eigner Gy, Szilágyi L: Medical Assistant Chatbot on Microcontroller. INES 2025 Palermo, pp. 125–130.
  15. Simon B, Hartveg Á, Szász L, Dénes-Fazakas L, Szilágyi L, Eigner Gy: Enhancing Diabetes Management Through LSTM Analysis of Physical Activity Effects. INES 2025 Palermo, pp. 115–120.
  16. Palatka J, Dénes-Fazakas L, Kovács L, Szilágyi L: Advancing Interstitial Lung Disease Diagnosis: a CNN Approach for High-Resolution Computed Tomography Image Classification. INES 2025 Palermo, pp. 15–20.
  17. Roman R, Kovács L, Szilágyi L: Detection of Pneumonia from X-Ray Scans Using Deep Learning Algorithms and Computer Vision. INES 2025 Palermo, pp. 137–142.
  18. Biró A, Szilágyi L: An Enhanced AI Pipeline for the Detection and Preliminary Diagnosis of Pneumonia and Pulmonary Malformations in Athletes with YOLOv11. INES 2025 Palermo, pp. 231–236.
  19. Csaholczi Sz, Kovács L, Szilágyi L: Brain Tumor Segmentation from Multi-Spectral MRI Records: Classical Machine Learning or Convolutional Neural Networks? ICCC 2025 Seychelles, pp. 97–102.
  20. Biró A, Szilágyi L: Gamified AI-Driven Video Monitoring for Enhanced Rehabilitation in Performance Sports. ICCC 2025 Seychelles, pp. 47–52.
  21. Dénes-Fazakas L, Simon B, Hartveg Á, Csaholczi Sz, Eigner Gy, Kovács L, Szilágyi L: Exploring Vision Transformer Architectures for Brain Tumor Classification: A Comprehensive Study. SACI 2025 Timisoara-Budapest, pp. 343–348.
  22. Naghi MB, Kovács L, Szilágyi L: A Parameter Selection Strategy for the Generalized Fuzzy-Possibilistic C-Means Algorithm. SAMI 2025 Stará Lesná (SK), pp. 533–538.
  23. Biró A, Cuesta-Vargas AI, Szilágyi L: Enhanced Spatial-Temporal Analysis for EEG-Based Microsleep Detection: Integrating Kalman Filtering with Voronoi Tessellation and Adaptive Coverage Control. IEEE SMC 2024 Kuching (Malaysia), pp. 4855–4860.
  24. Naghi MB, Kreinovich V, Kovács L, Szilágyi L: A Self-Tuning Version for the Fuzzy-Possibilistic Product Partition c-Means Algorithm. IEEE SMC 2024 Kuching (Malaysia), pp. 4861–4867.
  25. Csaholczi Sz, Györfi Á, Kovács L, Szilágyi L: Segmentation of Brain Tumor Parts from Multi-spectral MRI Records Using Deep Learning and U-Net Architecture. CIARP 2024 Talca (Chile), LNCS vol. 15369, pp. 191–204.
  26. Dénes-Fazakas L, Sándor-Rokaly K, Szász L, Csuzi H, Kovács L, Szilágyi L, Eigner Gy: Exploring the Integration of Differential Equations in Neural Networks: Theoretical Foundations, Applications, and Future Directions. CINTI 2024 Budapest, pp. 221–226.
  27. Dénes-Fazakas L, Szilágyi L, Eigner Gy, Kosheleva O, Kreinovich V, Phuong NH: Why Bump Reward Function Works Well in Training Insulin Delivery Systems. AICI 2024 Hanoi. Studies in Systems, Decision and Control (SSDC), 543:7–13, 2024.
  28. Biró A, Jánosi-Rancz TK, Szilágyi L: Real-time Artificial Intelligence Text Analysis for Identifying Burnout Syndromes in High-Performance Athletes. SAMI 2024 Stará Lesná (SK), pp. 253–258.
  29. Biró A, Cuesta-Vargas AI, Szilágyi L: AI-controlled training method for performance hardening or injury recovery in sports. SAMI 2024 Stará Lesná (SK), pp. 259–264.
  30. Román R, Dávid L, Szilágyi L: Development of A Novel Solar Photovoltaic Energy Converter To Increase Off-Grid Solar Powerplant Energy Efficiency, Decrease Energy Storage Costs And Increase Monetary Return On Investment. SAMI 2024 Stará Lesná (SK), pp. 303–308.
  31. Simon B, Hartveg Á, Siket M, Dénes-Fazakas L, Eigner Gy, Kovács L, Szilágyi L: Data Collection Studies for the Better Understanding of Factors in Type 1 Diabetes Management. ICCC 2024 Hanoi, pp. 375–380.
  32. Csaholczi Sz, Kovács L, Szilágyi L: Brain Tumor Classification Using Convolutional Neural Networks and Deep Learning. ICCC 2024 Hanoi, pp. 399–404.
  33. Simon B, Hartveg Á, Siket M, Dénes-Fazakas L, Eigner Gy, Kovács L, Szilágyi L: Translating Hungarian language dialects using natural language processing models. SACI 2024 Timisoara, pp. 375–380.
  34. Nagy M, Simon B, Szász L, Siket M, Dénes-Fazakas L, Eigner Gy, Süli PP, Kovács L, Szilágyi L: Web application development for diabetes patients. SACI 2024 Timisoara, pp. 573–579.
  35. Potyok C, Simon B, Hartveg Á, Siket M, Dénes-Fazakas L, Eigner Gy, Balázs M, Kovács L, Szilágyi L: Mobile application development for diabetes patient. SACI 2024 Timisoara, pp. 559–564.
  36. Dénes-Fazakas L, Dénes-Fazakas G, Eigner Gy, Kovács L, Szilágyi L: Review of Reinforcement Learning-Based Control Algorithms in Artificial Pancreas Systems for Diabetes Mellitus Management. SACI 2024 Timisoara, pp. 565–571.
  37. Dénes-Fazakas L, Csaholczi Sz, Eigner Gy, Kovács L, Szilágyi L: Using Resizing Layer in U-Net to Improve Memory Efficiency. Lecture Notes in Networks and Systems (LNNS), 1026:38–48, 2024.
  38. Biró A, Martín-Martín J, Szilágyi L: Applied AI for real-time detection of lesions and tumors following severe head injuries, SISY 2023 Pula (HR), pp. 653–658.
  39. Dénes-Fazakas L, Kovács L, Eigner Gy, Szilágyi L: A Modified VGG Architecture for Brain Tumor Classification (a.k.a. Brain Tumor Segmentation from Multi-Spectral MRI Records Using a U-net Cascade Architecture). IEEE SMC 2023 Honolulu, pp. 3003–3008.
  40. Györfi Á, Kovács L, Szilágyi L: Brain Tumor Segmentation from Multi-Spectral MRI Records Using a U-Net Cascade Architecture. IEEE SMC 2023 Honolulu, pp. 1327–1332.
  41. Dénes-Fazakas L, Siket M, Szilágyi L, Eigner Gy, Kovács L: Effect of Hyperparameters of Reinforcement Learning in Blood Glucose Control. IEEE SMC 2023 Honolulu, pp. 1333–1340.
  42. Biró A, Martín-Martín J, Szilágyi L: SRPE and ACWR to Control Fatigue Levels and Minimize Injuries in Performance Sports. IEEE SMC 2023 Honolulu, pp. 2808–2813.
  43. Simon B, Hartveg Á, Dénes-Fazakas L, Eigner Gy, Szilágyi L: Translating Hungarian language dialects using natural language processing models. CINTI 2023 Budapest, pp. 309–315.
  44. Dénes-Fazakas L, Szilágyi L, Eigner Gy, Kosheleva O, Ceberio M, Kreinovich V: Which activation function works best for training artificial pancreas: empirical fact and its theoretical explanation. SSCI 2023 Ciudad de Mexico, pp. 496–500.
  45. Szilágyi L, Györfi Á, Dénes-Fazakas L, Csaholczi Sz, Pisak-Lukáts IM, Kovács L: Challenges and Difficulties of Multi-Spectral MRI Based Brain Tumor Detection and Segmentation. ICHST 2023, Hanoi, paper no. 16, pp. 1–6.
  46. Naghi MB, Kovács L, Szilágyi L: A self-tuning version for the possibilistic fuzzy c-means clustering algorithm. FUZZIEEE 2023, Incheon (S. Korea), paper no. 123, pp. 1-6.
  47. Dénes-Fazakas L, Eigner Gy, Kovács L, Szilágyi L: Two U-net Architectures for Infant Brain Tissue Segmentation from Multi-Spectral MRI Data. 22nd IFAC World Congress (IFAC WC 2023, Yokohama JP), paper no. 1892, 6pp.
  48. Dénes-Fazakas L, Siket M, Szilágyi L, Kovács L, Eigner Gy: Investigation of reward functions for controlling blood glucose level using reinforcement learning. SACI 2023 Timișoara, pp. 387-392.
  49. Naghi MB, Kovács L, Szilágyi L: A review on advanced c-means clustering models based on fuzzy logic. SAMI 2023, Herl’any (SK), pp. 293-298.
  50. Dénes-Fazakas L, Siket M, Kertész G, Szilágyi L, Kovács L, Eigner Gy: Control of Type 1 Diabetes Mellitus using direct reinforcement learning based controller. IEEE SMC 2022 Prague, pp. 1512-1517.
  51. Győrfi Á, Csaholczi Sz, Pisak-Lukáts IM, Dénes-Fazakas L, Kőble A, Shvets O, Eigner Gy, Kovács L, Szilágyi L: Effect of spectral resolution on the segmentation quality of magnetic resonance imaging data. INES 2022, Chania (GR), pp. 53-58.
  52. Dénes-Fazakas L, Eigner Gy, Szilágyi L: Segmentation of 6-month infant brain tissues from multi-spectral MRI records using a U-Net neural network architecture. ICCC 2022, Reykjavík, pp. 77-82.
  53. Pisak-Lukáts IM, Szilágyi L: Markov clustering based feature selection for brain tumor segmentation from multi-spectral MRI records. SAMI 2022 Poprad, (SK), 6p, 2022.
  54. Kőble A, Győrfi Á, Csaholczi Sz, Surányi B, Dénes-Fazakas L, Kovács L, Szilágyi L: Identifying the most suitable histogram normalization technique for machine learning based segmentation of multispectral brain MRI data. AFRICON 2021 Online, pp. 71-76, 2021.
  55. Iclănzan D, Lung RI, Kucsván ZsL, Surányi B, Kovács L, Szilágyi L: The role of atlases and multi-atlases in brain tissue segmentation based on multispectral magnetic resonance image data. AFRICON 2021 Online, pp. 55-60, 2021.
  56. Csaholczi Sz, Kovács L, Szilágyi L: Automatic segmentation of brain tumor parts from MRI data using a random forest classifier. SAMI 2021 Herl'any, (SK), pp. 471–475.
  57. Surányi B, Kovács L, Szilágyi L: Segmentation of brain tissues from infant MRI records using machine learning techniques. SAMI 2021 Herl'any, (SK), pp. 455–460, 2021.
  58. Csaholczi Sz, Iclanzan D, Kovács L, Szilágyi L: Brain tumor segmentation from multi-spectral MR image data using random forest classifier. ICONIP 2020 Bangkok online, Lecture Notes in Computer Science vol. 12532, pp. 174-184, 2020.
  59. Vidámi M, Szilágyi L, Iclanzan D: Real valued card counting strategies for the game of Blackjack. ICONIP 2020 Bangkok online. Lecture Notes in Computer Science vol. 12533, pp. 63-73, 2020.
  60. Dénes-Fazakas L, Szilágyi L, Tasic J, Kovács L, Eigner Gy: Detection of physical activity using machine learning methods. CINTI 2020 Budapest, pp. 167–172, 2020.
  61. Győrfi Á, Csaholczi Sz, Fülöp T, Kovács L, Szilágyi L: Brain tumor segmentation from multi-spectral magnetic resonance image data using an ensemble learning approach. IEEE SMC 2020 Toronto, online), pp. 1699-1704.
  62. Fülöp T, Győrfi Á, Surányi B, Kovács L, Szilágyi L: Brain tumor segmentation from MRI data using ensemble learning and multi-atlas. SAMI 2020, Herl'any (SK), pp. 111-116, 2020. The paper received the Baltazár Frankovic Award.
  63. Győrfi Á, Fülöp T, Kovács L, Szilágyi L: The effect of spectral resolution upon the accuracy of brain tumor segmentation from multi-spectral MRI data. SAMI 2020, Herl'any (SK), pp. 325-328, 2020.
  64. Iclănzan D, Szilágyi L: Learning to generate ambiguous sequences. ICONIP 2019 Sydney. Lecture Notes in Computer Science vol. 11953, pp. 110-121, 2019.
  65. Győrfi Á, Kovács L, Szilágyi L: Brain tumor segmentation from multispectral MR image data using ensemble learning methods. CIARP 2019 La Habana (Cuba), Lecture Notes in Computer Science vol. 11896, pp. 326-335.
  66. Győrfi Á, Karetka-Mezei Z, Iclanzan D, Kovács L, Szilágyi L: A study on histogram normalization for brain tumor segmentation from multispectral MR image data. CIARP 2019 La Habana (Cuba). Lecture Notes in Computer Science vol. 11896, pp. 375-384.
  67. Győrfi Á, Kovács L, Szilágyi L: Brain tumor detection and segmentation from magnetic resonance image data using ensemble learning methods. IEEE SMC 2019, Bari (Italy), pp. 919-924.
  68. Győrfi Á, Kovács L, Szilágyi L: A feature ranking and selection algorithm for brain tumor segmentation in multi-spectral magnetic resonance image data. IEEE EMBC 2019 Berlin, pp. 804-807.
  69. Lefkovits Sz, Lefkovits L, Szilágyi L: Applications of different CNN architectures for palm vein identification. MDAI 2019, Milano. Lecture Notes in Computer Science vol. 11676, pp. 295-306, 2019
  70. Lefkovits Sz, Lefkovits L, Szilágyi L: CNN architectures for dorsal hand vein identification. WSCG 2019 Plzen (Czechia), 10 pp, 2019,
  71. Lefkovits Sz, Szilágyi L, Lefkovits L: Brain tumor segmentation and survival prediction using a cascade of random forests. BrainLesMICCAI 2018, Lecture Notes in Computer Science vol. 11384, pp. 334-345, 2019.
  72. Iclănzan D, Szilágyi SM, Szilágyi L: Evolving computationally efficient hashing for similarity search. ICONIP 2018 Siem Reap (Cambodia). Lecture Notes in Computer Science vol. 11302, pp. 552-563, 2018.
  73. Szilágyi L, Lefkovits Sz, Kucsván ZsL: A self-tuning possibilistic c-means clustering algorithm. MDAI 2018, Palma de Mallorca. Lecture Notes in Computer Science vol. 11144, pp. 255-266, 2018.
  74. Umenhoffer T, Tóth M, Kacsó EÁ, Szécsi L, Szlávecz Á, Somogyi P, Szilágyi L, Kubovje A, Szerafin T, Szirmay-Kalos L, Benyó B: Modelling and simulation framework of aortic valve for hemodynamic evaluation of aortic root replacement surgery outcomes. IFAC BMS 2018 Sao Paolo (Brazil), IFAC-PapersOnLine 51(27):258-263, 2018.
  75. Szabó Zs, Kapás Z, Lefkovits L, Győrfi Á, Szilágyi SM, Szilágyi L: Automatic segmentation of low-grade brain tumor using a random forest classifier and Gabor features. FSKD 2018 Huangshan (China), pp. 1106-1113.
  76. Kapás Z, Lefkovits L, Iclănzan D, Győrfi Á, Iantovics BL, Lefkovits Sz, Szilágyi SM, Szilágyi L: Automatic brain tumor segmentation in multispectral MRI volumes using a random forest approach. PSIVT 2017, Wuhan. Lecture Notes in Computer Science vol. 10749, pp. 137-149, 2018
  77. Lefkovits Sz, Emerich S, Szilágyi L: Biometric system based on registration of dorsal hand vein configurations. PSIVT 2017, Wuhan. Human Behavior Analysis Workshop. Lecture Notes in Computer Science vol. 10799, pp. 17-29, 2018
  78. Szilágyi L, Szilágyi SM: A possibilistic c-means clustering model with cluster size estimation. CIARP 2017 Valparaíso (Chile). Lecture Notes in Computer Science vol. 10659, pp. 661-668, 2018
  79. Lefkovits L, Lefkovits Sz, Szilágyi L: Brain Tumor Segmentation with Optimized Random Forest. BrainLesMICCAI 2016, Lecture Notes in Computer Science vol. 10154, pp. 88-99, 2016
  80. Kapás Z, Lefkovits L, Szilágyi L: Automatic detection and segmentation of brain tumor using random forest approach. MDAI 2016 Andorra, Lecture Notes in Computer Science vol. 9880, pp. 301-312, 2016
  81. Szilágyi L, Dénesi G, Enăchescu C: Fast color quantization via fuzzy clustering. ICINIP 2016 Kyoto. Lecture Notes in Computer Science vol. 9950, pp. 95-103 2016.
  82. Szilágyi L, Szilágyi SM, Enăchescu C: A study on cluster size sensitivity of fuzzy c-means algorithm variants. ICINIP 2016 Kyoto. Lecture Notes in Computer Science vol. 9948, pp. 470-478, 2016.
  83. Szilágyi L: A unified theory of fuzzy c-means clustering models with improved partition. MDAI 2015 Skövde (SWE). Lecture Notes in Computer Science vol. 9321, pp. 129-140. 2015.
  84. Szilágyi L, Nagy LL, Szilágyi SM: Recent advances in improving the memory efficiency of the TRIBE MCL algorithm. ICONIP 2015, Istanbul. Lecture Notes in Computer Science vol. 9490, pp. 28-35, 2015.
  85. Szilágyi L, Lefkovits L, Iantovics BL, Iclănzan D, Benyó B: Automatic brain tumor segmentation in multispectral MRI volumetric records. ICONIP 2015, Istanbul. Lecture Notes in Computer Science vol. 9492, pp. 174-181, 2015.
  86. Iantovics BL, Szilágyi L, Pintea CM: Societal intelligence – A new perspective for highly intelligent systems. ICONIP 2015, Istanbul. Lecture Notes in Computer Science vol. 9492, pp. 606-614, 2015.
  87. Iclănzan D, Szilágyi L: Neural population coding of stimulus features. ICONIP 2015, Istanbul. Lecture Notes in Computer Science vol. 9492, pp. 263-270, 2015.
  88. Szilágyi L, Lefkovits L, Benyó B: Automatic brain tumor segmentation in multispectral MRI volumes using a fuzzy c-means cascade algorithm. FSKD 2015 Zhangjiajie (China), pp. 310-316
  89. Szilágyi L, Szilágyi SM, Hirsbrunner B: A fast and memory-efficient hierarchical graph clustering algorithm. ICONIP 2014 Kuching (Malaysia). LNCS vol. 8834, pp. 247-254, 2014.
  90. Szilágyi L, Kovács L, Szilágyi SM: Synthetic test data generation for hierarchical graph clustering methods. ICONIP 2014 Kuching (Malaysia). LNCS vol. 8835, pp. 303-310, 2014.
  91. Szalay P, Szilágyi L, Benyó Z, Szilágyi SM: Sensor drift compensation using fuzzy inference system and sparse-grid quadrature filter in blood glucose control. ICONIP 2014 Kuching (Malaysia). LNCS vol. 8835, pp. 445-453, 2014.
  92. Szilágyi L, Varga ZsR, Szilágyi SM: Application of the fuzzy-possibilistic product partition in elliptic shell clustering. MDAI 2014 Tokyo. LNCS vol. 8825, pp. 158-169, 2014.
  93. Szilágyi L, Dénesi G, Szilágyi SM: Fast color reduction using approximative c-means clustering models. FUZZ-IEEE 2014 Beijing, pp. 194-201, 2014.
  94. Szilágyi L, Szilágyi SM: Fast implementations of Markov clustering for protein sequence grouping. MDAI 2013 Barcelona. LNCS vol. 8234, pp. 214-225, 2013.
  95. Haidegger T, Nagy M, Lehotsky Á, Szilágyi L: Digital imaging for the education of proper surgical hand disinfection. MICCAI 2011 Toronto. LNCS vol. 6893, pp. 619-626, 2011
  96. Szilágyi L: Fuzzy-Possibilistic Fuzzy Partition: a novel robust approach to c-means clustering. MDAI 2011. LNCS vol. 6820, pp. 150-161, 2011.
  97. Szilágyi L, Szilágyi SM, Benyó Z: A unified approach to c-means clustering models. FUZZ-IEEE 2009 Jeju Island (S. Korea), pp. 456-461, 2009
  98. Szilágyi L, Iclănzan D, Szilágyi SM, Dumitrescu D, Hirsbrunner B: A generalized c-means clustering model optimized via evolutionary computation. FUZZ-IEEE 2009, Jeju Island (S. Korea), pp. 451-455, 2009
  1. Szilágyi L, Iclănzan D, Szilágyi SM, Dumitrescu D: GeCiM: A novel generalized approach to c-means clustering. CIARP 2008, La Habana (Cuba). LNCS vol. 5197, pp. 235-242, 2008.
  2. Szilágyi L, Benyó Z, Szilágyi SM, Adam HS: MR brain image segmentation using an enhanced fuzzy c-means algorithm. IEEE EMBC 2003 Cancún, pp. 724–726, 2003

 

Szabadalmak

  1. Haidegger T, Lehotsky Á, Nagy M, Szilágyi L: Method and apparatus for hand disinfection control quality. US Patent 9,424,735 B2, 23 August 2016.

 

Hírek
HÖK-elnökválasztás 2026
2026-09-29
Szociális ösztöndíj pályázat 2026/2027, I. félév
2026-09-29
Felhívás: jelentkezés az Erdélyi Politikai Iskola 10. évfolyamába
2026-09-29
Tájépítészeink a marosvásárhelyi egykori téglagyári tavat és tágabb környezetét vizsgálták az RNU keretében
2026-09-29
Sapientia.ro

Sapientia - Erdélyi Magyar Tudományegyetem

Sapientia EMTE

A Sapientia Erdélyi Magyar Tudományegyetem a romániai magyarság önálló egyeteme Európában, melynek célja nemzeti közösségünk oktatásának és tudományos életének elismert szakmai színvonalon való művelése.

Kapcsolat

Marosvásárhelyi Kar

Marosvásárhely/Koronka,  Calea Sighișoarei nr. 2.
Postacím: 540485 Târgu-Mureş, O.p. 9, C.p. 4


Tel: +40 265 206 210, fax: +40 265 206 211
E-mail: office@ms.sapientia.ro

btz webdesign