TY - JOUR AU - Ntampakis, N. AU - Diamantaras, K. AU - Goulianas, K. AU - Chouvarda, I. AU - Argyriou, V. AU - Sarigiannidis, P. TI - Optimizing Melanoma Prognosis Through Synergistic Preprocessing and Deep Learning Architecture for Dermoscopic Thickness Prediction JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14860 PY - 2024 SP - 323 EP - 335 PG - 13 SN - 0302-9743 DO - 10.1007/978-3-031-66958-3_24 UR - https://m2.mtmt.hu/api/publication/35260762 ID - 35260762 N1 - Conference code: 315959 Export Date: 12 September 2024 LA - English DB - MTMT ER - TY - JOUR AU - Mike, Nimród TI - Aligning AI Tool Classification with the EU AI Act. A Rule-Based Approach TS - A Rule-Based Approach JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14913 PY - 2024 SP - 21 EP - 26 PG - 6 SN - 0302-9743 DO - 10.1007/978-3-031-68211-7_2 UR - https://m2.mtmt.hu/api/publication/35257337 ID - 35257337 LA - English DB - MTMT ER - TY - JOUR AU - Klimkó, Gábor AU - Kiss, József Károly AU - Kiss, Péter József TI - Implementation Issues of a New Universal Personal Identifier. The Case of Hungarian Digital Citizenship TS - The Case of Hungarian Digital Citizenship JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14913 PY - 2024 SP - 59 EP - 72 PG - 14 SN - 0302-9743 DO - 10.1007/978-3-031-68211-7_6 UR - https://m2.mtmt.hu/api/publication/35257291 ID - 35257291 LA - English DB - MTMT ER - TY - JOUR AU - Asemi, Asefeh AU - Asemi, Adeleh AU - Kő, Andrea TI - ANFIS-Based Investment Recommendations for Government Bonds. Personalized Approach TS - Personalized Approach JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14913 PY - 2024 SP - 3 EP - 20 PG - 18 SN - 0302-9743 DO - 10.1007/978-3-031-68211-7_1 UR - https://m2.mtmt.hu/api/publication/35217156 ID - 35217156 LA - English DB - MTMT ER - TY - JOUR AU - Unyi, Dániel AU - Gyires-Tóth, Bálint Pál TI - Self-Supervised Pretraining for Cortical Surface Analysis JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14859 PY - 2024 SP - 96 EP - 108 PG - 13 SN - 0302-9743 DO - 10.1007/978-3-031-66955-2_7 UR - https://m2.mtmt.hu/api/publication/35172375 ID - 35172375 N1 - Conference code: 315959 Export Date: 16 August 2024 Correspondence Address: Unyi, D.; Department of Telecommunications and Media Informatics, Műegyetem rkp. 3, Hungary; email: unyi.daniel@tmit.bme.hu Funding details: European Geosciences Union, EGU Funding details: Consumer and Governmental Affairs Bureau Funding details: U.S. Embassy in Hungary Funding details: Ministry of Innovation, MOI Funding details: Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, TKP2021-NVA-02 Funding details: National Research, Development and Innovation Office, ÚNKP-23-3-II-BME-399 Funding text 1: The authors are grateful to Petar Veli\\u010Dkovi\\u0107 for supporting the project with his valuable insights. The work reported in this paper carried out at BME, has been supported by the European Union project RRF-2.3.1-21-2022-00004 within the framework of the Artificial Intelligence National Laboratory. Project no. TKP2021-NVA-02 has been implemented with the support provided by the Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund, financed under the TKP2021-NVA funding scheme. The presented work of D. Unyi was also supported by the \\u00DANKP-23-3-II-BME-399 New National Excellence Program of the Ministry for Culture and Innovation from the source of the National Research, Development and Innovation Fund. We thank the Governmental Agency for IT Development (KIF\\u00DC) for the opportunity provided by the Komondor supercomputer, which they operate, and where the computations were performed. AB - To advance our knowledge in neuroscience it is fundamental to understand the complexities of the human cerebral cortex. The cortex exhibits significant variability across individuals, presenting challenges in identifying patterns at the population level. While supervised learning methods excel at such tasks, they require a large amount of labeled samples to train. This is a serious limitation due to the costly and time-consuming annotation process requiring neuroscience experts. To address this challenge, self-supervised learning (SSL) was introduced in various other domains. By pretraining models on unlabeled data, SSL reduces the dependency on large labeled datasets, as labeled data is only used to fine-tune the models for downstream tasks. In this paper, we explore the effectiveness of self-supervised pretraining on a large number of cortical surfaces from the Human Connectome Project dataset. Leveraging a masked graph autoencoder, we develop a pretrained model suitable for various downstream tasks. The model’s performance in segmentation (node classification) and age prediction (graph regression) tasks are evaluated by using cortical surfaces from the manually labeled MindBoggle dataset. Our findings demonstrate that SSL with fine-tuning outperforms models trained from sratch across both tasks. Our research contributes to advancing the application of self-supervised learning in cortical surface analysis, with implications for neuroscience research and clinical practice. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. LA - English DB - MTMT ER - TY - JOUR AU - Millinghoffer, András Dániel AU - Antal, Mátyás AU - Marosi, Márk AU - Formanek, András AU - Antos, András AU - Antal, Péter TI - Boosting Multitask Decomposition: Directness, Sequentiality, Subsampling, Cross-Gradients JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14844 PY - 2024 SP - 17 EP - 35 PG - 19 SN - 0302-9743 DO - 10.1007/978-3-031-66538-7_3 UR - https://m2.mtmt.hu/api/publication/35172372 ID - 35172372 N1 - Department of Measurement and Information Systems, Budapest University of Technology and Economics, Magyar Tudósok Körútja 2., Budapest, 1117, Hungary Dynamical Systems, Signal Processing and Data Analytics (STADIUS), K.U.Leuven, Kasteelpark Arenberg 10, Leuven, 3001, Belgium Conference code: 316219 Export Date: 16 August 2024 Correspondence Address: Antal, P.; Department of Measurement and Information Systems, Magyar Tudósok Körútja 2., Hungary; email: marosi@mit.bme.hu Funding details: Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province Funding details: European Geosciences Union, EGU Funding details: National Research, Development and Innovation Office, K 139330, TKP2021-EGA-02, RRF-2.3.1–21-2022–00004 Funding details: National Research, Development and Innovation Office Funding details: SOLID JPND2021-650–233 Funding text 1: This study was supported by the Hungarian National Research, Development, and Innovation Office K 139330 grant; the European Union (EU) Joint Program on Neurodegenerative Disease (JPND) Grant SOLID JPND2021-650\\u2013233; the National Research, Development, and Innovation Fund of Hungary under Grant TKP2021-EGA-02, the European Union project RRF-2.3.1\\u201321-2022\\u201300004 within the framework of the Artificial Intelligence National Laboratory. AB - The exploration of transfer effects and selection of useful auxiliary tasks in multitask learning and foundation models with downstream tasks remain a largely empirical and computationally demanding process. To reduce the computational cost while maintaining statistical rigor, we investigate (1) the concept of direct transfer effect between tasks, (2) the use of sequential learning to minimize the number of test-train data splits, (3) the possibility of using partial data, and (4) the applicability of gradient-based cross-training task affinities in auxiliary task selection. We apply the methods to a drug-target interaction prediction problem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. LA - English DB - MTMT ER - TY - JOUR AU - Hao, Yue AU - Hoekstra, Alfons G. AU - Závodszky, Gábor TI - A Three-Dimensional Fluid-Structure Interaction Model for Platelet Aggregates Based on Porosity-Dependent Neo-Hookean Material JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14838 PY - 2024 SP - 48 EP - 62 PG - 15 SN - 0302-9743 DO - 10.1007/978-3-031-63783-4_5 UR - https://m2.mtmt.hu/api/publication/35162303 ID - 35162303 N1 - Computational Science Lab, Informatics Institute, Faculty of Science, University of Amsterdam, Amsterdam, Netherlands Department of Hydrodynamic Systems, Budapest University of Technology and Economics, Budapest, Hungary Conference code: 314659 Export Date: 7 August 2024 Correspondence Address: Hao, Y.; Computational Science Lab, Netherlands; email: y.hao@uva.nl AB - The stability of the initial platelet aggregates is relevant in both hemostasis and thrombosis. Understanding the structural stresses of such aggregates under different flow conditions is crucial to gaining insight into the role of platelet activation and binding in the more complex process of clot formation. In this work, a three-dimensional implicit partitioned fluid-structure interaction (FSI) model is presented to study the deformation and structural stress of platelet aggregates in specific blood flow environments. Platelet aggregates are considered as porous mediums in the model. The FSI model couples a fluid solver based on Navier-Stokes equations and a porosity-dependent compressible neo-Hookean material to capture the mechanical characteristics of the platelet aggregates. A parametric study is performed to explore the influence of porosity and applied body force on this material. Based on in vitro experimental data, the deformation and associated stress of a low shear aggregate and a high shear aggregate under different flow conditions are evaluated. This FSI framework offers a way to elucidate the complex interaction between blood flow and platelet aggregates and is applicable to a wider range of porous biomaterials in flow. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. LA - English DB - MTMT ER - TY - JOUR AU - Junaid, Muhammad AU - Ferretti, Maddalena AU - Garrone, Sabine AU - Gorokhov, Daniel TI - Exploring Mobility in Rural Areas. A Case Study in the Marche Region’s Central Apennine JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14819 PY - 2024 SP - 84 EP - 108 PG - 25 SN - 0302-9743 DO - 10.1007/978-3-031-65282-0_6 UR - https://m2.mtmt.hu/api/publication/35154668 ID - 35154668 LA - English DB - MTMT ER - TY - JOUR AU - D’Apuzzo, Mauro AU - Nardoianni, Sofia AU - Cappelli, Giuseppe AU - Furioso, Martina AU - Nicolosi, Vittorio TI - Leveraging e-Surveys for Investigating Sustainable Urban Mobility: A Case Study in Small Community JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14825 PY - 2024 SP - 20 EP - 38 PG - 19 SN - 0302-9743 DO - 10.1007/978-3-031-65343-8_2 UR - https://m2.mtmt.hu/api/publication/35153429 ID - 35153429 LA - English DB - MTMT ER - TY - JOUR AU - Mosonyi, J.M. AU - Hancock, G. AU - Miles, J.D. TI - Comparing Human Versus Avatar Instructors of Different Ethnicities: Effects on Student Learning Outcomes Using a Virtual Learning Platform JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 14691 PY - 2024 SP - 89 EP - 117 PG - 29 SN - 0302-9743 DO - 10.1007/978-3-031-60125-5_7 UR - https://m2.mtmt.hu/api/publication/35152290 ID - 35152290 LA - English DB - MTMT ER -