TY - JOUR AU - Polcz, Péter AU - Tornai, Kálmán AU - Juhász, János AU - Cserey, György Gábor AU - Surján, György AU - Pándics, Tamás AU - Róka, Eszter AU - Vargha, Márta AU - Reguly, István Zoltán AU - Csikász-Nagy, Attila AU - Pongor, Sándor AU - Szederkényi, Gábor TI - Wastewater-based modeling, reconstruction, and prediction for COVID-19 outbreaks in Hungary caused by highly immune evasive variants JF - WATER RESEARCH J2 - WATER RES VL - 241 PY - 2023 PG - 18 SN - 0043-1354 DO - 10.1016/j.watres.2023.120098 UR - https://m2.mtmt.hu/api/publication/33864634 ID - 33864634 N1 - National Laboratory for Health Security, Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 85, Budapest, H-1083, Hungary Department of Public Health Laboratory, National Public Health Centre, Albert Flórián út 2-6, Budapest, H-1097, Hungary Institute of Medical Microbiology, Semmelweis University, Üllői út 26, Budapest, H-1085, Hungary Department of Digital Health Sciences, Semmelweis University, Üllői út 26, Budapest, H-1085, Hungary Department of Public Health Sciences, Faculty of Health Sciences, Semmelweis University, Vas utca 17, Budapest, H-1088, Hungary Export Date: 28 July 2023 CODEN: WATRA Correspondence Address: Polcz, P.; National Laboratory for Health Security, Práter utca 85, Hungary; email: polcz.peter@itk.ppke.hu LA - English DB - MTMT ER - TY - JOUR AU - Németh, Dániel AU - Tornai, Kálmán TI - Electrical Load Classification with Open-Set Recognition JF - ENERGIES J2 - ENERGIES VL - 16 PY - 2023 IS - 2 SN - 1996-1073 DO - 10.3390/en16020800 UR - https://m2.mtmt.hu/api/publication/33776658 ID - 33776658 AB - Full utilization of renewable energy resources is a difficult task due to the constantly changing demand-side load of the electrical grid. Demand-side management would solve this crucial problem. To enable demand-side management, knowledge about the composition of the grid load is required, as well as the ability to schedule individual loads. There are proposed Smart Plugs presented in the literature capable of such tasks. The problem, however, is that these methods lack the ability to detect if a previously unseen electrical load is connected. Misclassification of such loads presents a problem for load estimation and scheduling. Open-set recognition methods solve this problem by providing a way to detect samples not belonging to any class used during the training of the classifier. This paper evaluates the novel application of open-set recognition methods to the problem of load classification. Two approaches were examined, and both offer promising results. A Support Vector Machine based approach was first evaluated. The second, more robust method used a modified OpenMax-based algorithm to detect unseen loads. LA - English DB - MTMT ER - TY - JOUR AU - Halász, András Pál AU - Al Hemeary, Nawar AU - Daubner, Lóránt Szabolcs AU - Zsedrovits, Tamás AU - Tornai, Kálmán TI - Improving the Performance of Open-Set Recognition with Generated Fake Data JF - ELECTRONICS (SWITZ) VL - 12 PY - 2023 IS - 6 SP - 1311 EP - 6 PG - 14 SN - 2079-9292 DO - 10.3390/electronics12061311 UR - https://m2.mtmt.hu/api/publication/33697412 ID - 33697412 N1 - ISSN:2079-9292 AB - Open-set recognition models, in addition to generalizing to unseen instances of known categories, have to identify samples of unknown classes during the training phase. The main reason the latter is much more complicated is that there is very little or no information about the properties of these unknown classes. There are methodologies available to handle the unknowns. One possible method is to construct models for them by using generated inputs labeled as unknown. Generative adversarial networks are frequently deployed to generate synthetic samples representing unknown classes to create better models for known classes. In this paper, we introduce a novel approach to improve the accuracy of recognition methods while reducing the time complexity. Instead of generating synthetic input data to train neural networks, feature vectors are generated using the output of a hidden layer. This approach results in a less complex structure for the neural network representation of the classes. A distance-based classifier implemented by a convolutional neural network is used in our implementation. Our solution’s open-set detection performance reaches an AUC value of 0.839 on the CIFAR-10 dataset, while the closed-set accuracy is 91.4%, the highest among the open-set recognition methods. The generator and discriminator networks are much smaller when generating synthetic inner features. There is no need to run these samples through the first part of the classifier with the convolutional layers. Hence, this solution not only gives better performance than generating samples in the input space but also makes it less expensive in terms of computational complexity. LA - English DB - MTMT ER - TY - BOOK AU - Keömley-Horváth, Bence AU - Horváth, Gergely AU - Polcz, Péter AU - Siklósi, Bálint AU - Tornai, Kálmán AU - Juhász, János AU - Szederkényi, Gábor AU - Cserey, György Gábor AU - Csikász-Nagy, Attila AU - Reguly, István Zoltán TI - The Design and Utilisation of PanSim, a Portable Pandemic Simulator PB - IEEE CY - Piscataway (NJ) PY - 2022 SP - 1 EP - 9 SP - 9 DO - 10.1109/CIW-IUS56691.2022.00006 UR - https://m2.mtmt.hu/api/publication/33704221 ID - 33704221 LA - English DB - MTMT ER - TY - CHAP AU - Németh, Dániel AU - Tornai, Kálmán TI - Detecting Unknown Electrical Loads Using Open Set Recognition T2 - 2022 IEEE 10th International Conference on Smart Energy Grid Engineering (SEGE) PB - IEEE SN - 9781665499309 PY - 2022 SP - 7 EP - 11 PG - 5 DO - 10.1109/SEGE55279.2022.9889770 UR - https://m2.mtmt.hu/api/publication/33103187 ID - 33103187 LA - English DB - MTMT ER - TY - CHAP AU - Németh, Dániel AU - Tornai, Kálmán TI - SP4LC: A Method for Recognizing Power Consumers in a Smart Plug T2 - Proceedings of the 11th International Conference on Smart Cities and Green ICT Systems SN - 9789897585722 PY - 2022 SP - 69 EP - 77 PG - 9 DO - 10.5220/0010982800003203 UR - https://m2.mtmt.hu/api/publication/32803859 ID - 32803859 LA - English DB - MTMT ER - TY - JOUR AU - Badics, Tamás AU - Hajtó, Dániel AU - Tornai, Kálmán AU - Kiss, Levente AU - Reguly, István Zoltán AU - Pesti, István AU - Sváb, Péter AU - Cserey, György Gábor TI - Integral representation method based efficient rule optimizing framework for anti-money laundering JF - JOURNAL OF MONEY LAUNDERING CONTROL J2 - J MONEY LAUNDER CONT VL - 26 PY - 2022 IS - 2 SP - 290 EP - 308 PG - 19 SN - 1368-5201 DO - 10.1108/JMLC-12-2021-0137 UR - https://m2.mtmt.hu/api/publication/32784092 ID - 32784092 AB - Purpose This paper aims to introduce a framework for optimizing rule-based anti-money laundering systems with a clear economic interpretation, and the authors introduce the integral representation method. Design/methodology/approach By using a microeconomic model, the authors reformulate the threshold optimization problem as a decision problem to gain insights from economics regarding the main properties of the optimum. The authors used algorithmic considerations to find an efficient implementation by using a kind of weak mode estimate of the distribution and the authors extend this approach to classes of alerts or cases. Findings The method provides a new and efficient alternative for the sampling method or the multidimensional optimization technique described in the literature to decrease the bias emanating from multiple alerts by smoothing the number of alerts across classes in the optimum and decrease the overlapping between scenarios at the case level. Using the method for real bank data, the authors were able to decrease the number of false positives cases by about 18% while retaining almost 98% of the true-positive cases. Research limitations/implications The model assumes that alerts from different scenarios are indifferent to the bank. To include scenario-specific preferences or constraints demands further research. Originality/value The new framework presented in the paper is a flexible extension of the usual above-the-line method, which makes it possible to include bank preferences and use the parallelization capabilities of modern processors. LA - English DB - MTMT ER - TY - JOUR AU - Reguly, István Zoltán AU - Csercsik, Dávid AU - Juhász, János AU - Tornai, Kálmán AU - Bujtár, Zsófia AU - Horváth, Gergely AU - Keömley-Horváth, Bence AU - Kós, Tamás AU - Cserey, György Gábor AU - Iván, Kristóf AU - Pongor, Sándor AU - Szederkényi, Gábor AU - Röst, Gergely AU - Csikász-Nagy, Attila TI - Microsimulation based quantitative analysis of COVID-19 management strategies JF - PLOS COMPUTATIONAL BIOLOGY J2 - PLOS COMPUT BIOL VL - 18 PY - 2022 IS - 1 PG - 14 SN - 1553-734X DO - 10.1371/journal.pcbi.1009693 UR - https://m2.mtmt.hu/api/publication/32574366 ID - 32574366 N1 - Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Budapest, Hungary Cytocast Kft., Vecses, Hungary Institute of Medical Microbiology, Faculty of Medicine, Semmelweis University, Budapest, Hungary Bolyai Institute, University of Szeged, Szeged, Hungary Randall Centre for Cell and Molecular Biophysics, King’s College London, London, United Kingdom Cited By :1 Export Date: 16 June 2022 Correspondence Address: Reguly, I.Z.; Faculty of Information Technology and Bionics, Hungary; email: reguly.istvan.zoltan@itk.ppke.hu Correspondence Address: Csikász-Nagy, A.; Faculty of Information Technology and Bionics, Hungary; email: csikasz-nagy.attila@itk.ppke.hu LA - English DB - MTMT ER - TY - JOUR AU - Márkos, Zsolt AU - Tornai, Kálmán TI - Intelligent Sensor Data Analysis form Smart Systems JF - JEDLIK LABORATORIES REPORTS J2 - JEDLIK LABOR REP VL - 2020 PY - 2020 IS - 9 SP - 40 EP - 44 PG - 5 SN - 2064-3942 UR - https://m2.mtmt.hu/api/publication/31674480 ID - 31674480 LA - English DB - MTMT ER - TY - JOUR AU - Halász, András Pál AU - Tornai, Kálmán TI - Intelligent Sensor Data Analysis form Smart Systems JF - JEDLIK LABORATORIES REPORTS J2 - JEDLIK LABOR REP VL - 2020 PY - 2020 IS - 9 SP - 35 SN - 2064-3942 UR - https://m2.mtmt.hu/api/publication/31674479 ID - 31674479 LA - English DB - MTMT ER -