TY - JOUR AU - Kovács, Attila AU - Somogyiné Molnár, Judit AU - Jármai, Károly TI - A FESZÜLTSÉG ÉS ÁRAM HARMONIKUS TORZÍTÁSOK, AZ IEEE 519-2022 SZABVÁNY JF - GÉP J2 - GÉP VL - 75 PY - 2024 IS - 1 SP - 35 EP - 38 PG - 4 SN - 0016-8572 UR - https://m2.mtmt.hu/api/publication/34786234 ID - 34786234 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Kovács, László AU - Csépányi-Fürjes, László AU - Sewunetie, Walelign Tewabe ED - Gligor, Adrian ED - Moldovan, Liviu TI - Transformer Models in Natural Language Processing T2 - The 17th International Conference Interdisciplinarity in Engineering PB - Springer Nature Switzerland CY - Cham SN - 9783031546747 T3 - Lecture Notes in Networks and Systems, ISSN 2367-3370 ; 929. PY - 2024 SP - 180 EP - 193 PG - 14 DO - 10.1007/978-3-031-54674-7_14 UR - https://m2.mtmt.hu/api/publication/34770083 ID - 34770083 AB - The development of transformer-based language models brings a paradigm shift in the world of smart applications. The ChatGPT model opened new horizons in the field of natural language understanding and generation. This paper presents a survey on the history of transformer models, on the basic architecture and application areas. The last section is devoted to two use cases experiments on the application of ChatGPT. The first domain relates to Human-Level Programming and the second focuses on the semantic functional parsing of text sentences. The performed analysis demonstrates the big potential in the transformer language models. LA - English DB - MTMT ER - TY - THES AU - Göcs, László TI - Rendellenesség alapú behatolás érzékelő rendszerek gépi tanulási módszerrel történő tanítása PY - 2024 SP - 115 UR - https://m2.mtmt.hu/api/publication/34747185 ID - 34747185 LA - Hungarian DB - MTMT ER - TY - THES AU - Gavua, Ebenezer Komla TI - MapReduce Performance Analysis and Modelling of Auto-Scaling Applications Behaviours PY - 2024 SP - 198 UR - https://m2.mtmt.hu/api/publication/34726333 ID - 34726333 LA - English DB - MTMT ER - TY - JOUR AU - Sewunetie, Walelign Tewabe AU - Kovács, László TI - A Comparative Study of ChatGPT-Based and Hybrid Parser-based Sentence Parsing Methods for Semantic Graph-Based Induction JF - IEEE ACCESS J2 - IEEE ACCESS PY - 2024 SN - 2169-3536 DO - 10.1109/ACCESS.2024.3360480 UR - https://m2.mtmt.hu/api/publication/34721788 ID - 34721788 LA - English DB - MTMT ER - TY - JOUR AU - Al-Haboobi, Ali AU - Kecskeméti, Gábor TI - Structure-Aware Scheduling Algorithm for Deadline-Constrained Scientific Workflows in the Cloud JF - INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS J2 - IJACSA VL - 15 PY - 2024 IS - 2 SP - 792 EP - 802 PG - 11 SN - 2158-107X DO - 10.14569/IJACSA.2024.0150280 UR - https://m2.mtmt.hu/api/publication/34695021 ID - 34695021 AB - Cloud computing provides pay-per-use IT services through the Internet. Although cloud computing resources can help scientific workflow applications, several algorithms face the problem of meeting the user’s deadline while minimising the cost of workflow execution. In the cloud, selecting the appropriate type and the exact number of VMs is a major challenge for scheduling algorithms, as tasks in workflow applications are distributed very differently. Depending on workflow requirements, algorithms need to decide when to provision or de-provision VMs. Therefore, this paper presents an algorithm for effectively selecting and allocating resources. Based on the workflow structure, it decides the type and number of VMs to use and when to lease and release them. For some structures, our proposed algorithm uses the initial rented VMs to schedule all tasks of the same workflow to minimise data transfer costs. We evaluate the performance of our algorithm by simulating it with synthetic workflows derived from real scientific workflows with different structures. Our algorithm is compared with Dyna and CGA approaches in terms of meeting deadlines and execution costs. The experimental results show that the proposed algorithm met all the deadline factors of each workflow, while the CGA and Dyna algorithms met 25% and 50%, respectively, of all the deadline factors of all workflows. The results also show that the proposed algorithm provides more cost-efficient schedules than CGA and Dyna. LA - English DB - MTMT ER - TY - CONF AU - Akkad, Mohammad Zaher AU - Bányai, Tamás TI - Analyzing and Designing an Optimization System for In-Plant Complex Production Based on Industry 4.0 T2 - 9th International Conference on Advanced Engineering and Technology (ICAET) PB - Trans Tech Publications C1 - Zürich T3 - Advances in Science and Technology, ISSN 1662-0356 ; 140. PY - 2024 SP - 53 EP - 58 PG - 6 DO - 10.4028/p-Es6Xrb UR - https://m2.mtmt.hu/api/publication/34654257 ID - 34654257 AB - Industry 4.0 symbolizes various applications and technologies that have many possible positive effects within the industrial field. The complex production area contains longer product cycle times and multiple levels of subassemblies, and this reflects a higher need for raising production efficiency and optimizing the resources and time. Adopting developed Industry 4.0 technologies is considered a promising way for achieving this since they contribute directly to real-time data analysis, remote operation, and complete product life analysis next to further tools that allow more profound and inclusive analysis in the target complex production system. This article discusses the integration of Industry 4.0 technologies with in-plant complex production processes. A proposed system with an optimization purpose is designed and described that focuses on using multi-level integration processes effectively. LA - English DB - MTMT ER - TY - JOUR AU - Alshboul, Jawad AU - Baksáné Varga, Erika TI - A Hybrid Approach for Automatic Question Generation from Program Codes JF - INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS J2 - IJACSA VL - 15 PY - 2024 IS - 1 SP - 10 EP - 17 PG - 8 SN - 2158-107X DO - 10.14569/IJACSA.2024.0150102 UR - https://m2.mtmt.hu/api/publication/34550360 ID - 34550360 LA - English DB - MTMT ER - TY - JOUR AU - Sewunetie, Walelign Tewabe AU - Kovács, László TI - Automatic question generation using extended dependency parsing JF - INDONESIAN JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE J2 - IJEECS VL - 33 PY - 2024 IS - 2 SP - 1108 EP - 1115 PG - 8 SN - 2502-4752 DO - 10.11591/ijeecs.v33.i2.pp1108-1115 UR - https://m2.mtmt.hu/api/publication/34518995 ID - 34518995 AB - The importance of automatic question generation (AQG) systems in education is recognized for automating tasks and providing adaptive assessments. Recent research focuses on improving quality with advanced neural networks and machine learning techniques. However, selecting the appropriate target sentences and concepts remains challenging in AQG systems. To address this problem, the authors created a novel system that combined sentence structure analysis, dependency parsing approach, and named entity recognition techniques to select the relevant target words from the given sentence. The main goal of this paper is to develop an AQG system using syntactic and semantic sentence structure analysis. Evaluation using manual and automatic metrics shows good performance on simple and short sentences, with an overall score of 3.67 out of 5.0. As the field of AQG continues to evolve rapidly, future research should focus on developing more advanced models that can generate a wider range of questions, especially for complex sentence structures. LA - English DB - MTMT ER - TY - THES AU - Alnor Adam Khleel, Nasraldeen TI - Utilizing Data-Balancing Techniques to Improve AI-Based Prediction of Software Bugs and Code Smells PY - 2024 SP - 133 DO - 10.14750/ME.2024.012 UR - https://m2.mtmt.hu/api/publication/34498054 ID - 34498054 LA - English DB - MTMT ER -