TY - JOUR AU - Üveges, Bálint Áron AU - Oláh, András TI - Enhanced reliability in hazardous event detection: A resilient multipath routing protocol for wireless sensor networks JF - IET WIRELESS SENSOR SYSTEMS J2 - IET WIREL SENS SYST VL - 14 PY - 2024 IS - 4 SP - 111 EP - 131 PG - 21 SN - 2043-6386 DO - 10.1049/wss2.12078 UR - https://m2.mtmt.hu/api/publication/34836445 ID - 34836445 AB - With the advance of climate change and the local effects of human activity, it has become of utmost importance to sense spatially extended natural and artificial physical phenomena to predict, monitor, and mitigate hazardous events. Wireless sensor networks are suitable for observing such phenomena, for example, wildfires, floods or landslides, without human supervision. This is due to affordable devices, independent power sources, wireless communication, and a broad range of sensors. During normal operation a few, while during the occurrence of an event a multitude of devices can fail. This leads to further disconnected devices, degrading the network's sensing capabilities. The communication requirements of such applications are difficult to fulfil with general routing protocols. The monitored event is rare compared to the network's lifetime, while its occurrence results in multiple, gradual node failures, still demanding the network to perform reliably. Available routing protocols fail to address every aspect of such application, thus the authors propose the Reliable Resilient Multipath Routing Protocol, designed to construct multiple disjoint paths from each device to a distinguished one, called the sink. The protocol employs proactive and reactive network management techniques to increase connection redundancy and maintain connectivity during failures. To verify the proposed protocol end‐to‐end, we evaluated the supported parameters, performed comparative simulations with routing algorithms known from the literature, and provided estimates of a realistic deployment. LA - English DB - MTMT ER - TY - JOUR AU - Üveges, Bálint Áron AU - Lőrincz, Máté AU - Oláh, András TI - Resilient Multipath Routing Protocol to Enable Hazardous event Monitoring with Wireless Sensor Network JF - TELFOR JOURNAL J2 - TELFOR J VL - 15 PY - 2023 IS - 1 SP - 20 EP - 25 PG - 6 SN - 1821-3251 DO - 10.5937/telfor2301020Q UR - https://m2.mtmt.hu/api/publication/34110809 ID - 34110809 AB - With the growing impact of climate change, the occurrence of hazardous spatial events increases. Wireless sensor networks are suitable to sense, monitor, and report such events in remote or inaccessible locations. Hazardous events are rare compared to the network's lifetime, thus maintaining its consistency must be realized energy efficiently. During the impact, the network must monitor the event with precision, and report the incidence, while mitigating the loss of perishing nodes. To fulfill these requirements, we propose the Self-healing Multipath Routing Protocol that is based on the Heterogeneous Disjoint Multipath Routing Protocol and introduces application-specific extensions to improve network stability, resiliency, and failover. To realize the monitoring of spatially extended hazardous events we introduce an event-based, application-level protocol. To evaluate the routing protocol, we perform simulations utilizing a cellular automaton-based wildfire model as the spatial event and provide measurement results including delivery ratio, consumed energy, and protocol-specific metrics. LA - English DB - MTMT ER - TY - CHAP AU - Üveges, Bálint Áron AU - Lőrincz, Máté AU - Oláh, András TI - Self-healing Multipath Routing Protocol to assist Wireless Sensor Network based Hazardous Event Monitoring T2 - 2022 30th Telecommunications Forum (TELFOR) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Belgrád SN - 9781665472739 PY - 2022 SP - 1 EP - 4 PG - 4 DO - 10.1109/TELFOR56187.2022.9983752 UR - https://m2.mtmt.hu/api/publication/33536003 ID - 33536003 LA - English DB - MTMT ER - TY - JOUR AU - Botos, Csaba AU - Hakkel, Tamás AU - Horváth, András AU - Oláh, András AU - Reguly, István Zoltán TI - PPCU Sam: Open-source face recognition framework JF - PROCEDIA COMPUTER SCIENCE J2 - PROC COMPUTER SCI VL - 159 PY - 2019 SP - 1947 EP - 1956 PG - 10 SN - 1877-0509 DO - 10.1016/j.procs.2019.09.367 UR - https://m2.mtmt.hu/api/publication/30866059 ID - 30866059 AB - In recent years by the popularization of AI, an increasing number of enterprises deployed machine learning algorithms in real life settings. This trend shed light on leaking spots of the Deep Learning bubble, namely the catastrophic decrease in quality when the distribution of the test data shifts from the training data. It is of utmost importance that we treat the promises of novel algorithms with caution and discourage reporting near perfect experimental results by fine-tuning on fixed test sets and finding metrics that hide weak points of the proposed methods. To support the wider acceptance of computer vision solutions we share our findings through a case-study in which we built a face-recognition system from scratch using consumer grade devices only, collected a database of 100k images from 150 subjects and carried out extensive validation of the most prominent approaches in single-frame face recognition literature. We show that the reported worst-case score, 74.3% true-positive ratio drops below 46.8% on real data. To overcome this barrier, after careful error analysis of the single-frame baselines we propose a low complexity solution to cover the failure cases of the single-frame recognition methods which yields an increased stability in multi-frame recognition during test time. We validate the effectiveness of the proposal by an extensive survey among our users which evaluates to 89.5% true-positive ratio. LA - English DB - MTMT ER - TY - JOUR AU - Levendovszky, János AU - Reguly, István Zoltán AU - Oláh, András AU - Ceffer, Attila TI - Low Complexity Algorithmic Trading by Feedforward Neural Networks JF - COMPUTATIONAL ECONOMICS J2 - COMPUT ECON VL - 54 PY - 2019 IS - 1 SP - 267 EP - 279 PG - 13 SN - 0927-7099 DO - 10.1007/s10614-017-9720-6 UR - https://m2.mtmt.hu/api/publication/3252486 ID - 3252486 LA - English DB - MTMT ER - TY - CHAP AU - Lőrincz, Máté AU - Oláh, András AU - Tornai, Kálmán TI - An effective neuron based method for process control in industrial environment T2 - 2018 IEEE International Conference on Industrial Technology (ICIT) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Piscataway (NJ) SN - 9781509059492 PY - 2018 SP - 69 EP - 74 PG - 6 DO - 10.1109/ICIT.2018.8352154 UR - https://m2.mtmt.hu/api/publication/3369208 ID - 3369208 LA - English DB - MTMT ER - TY - JOUR AU - Drenyovszki, Rajmund AU - Kovács, Lóránt AU - Tornai, Kálmán AU - Oláh, András AU - Pintér, István TI - Bottom-up modeling of domestic appliances with Markov chains and semi-Markov processes JF - KYBERNETIKA J2 - KYBERNETIKA VL - 53 PY - 2017 IS - 6 SP - 1100 EP - 1117 PG - 18 SN - 0023-5954 DO - 10.14736/kyb-2017-6-1100 UR - https://m2.mtmt.hu/api/publication/3320488 ID - 3320488 N1 - EFOP-3.6.1-16-2016-00006 Megjegyzés-27120507 EFOP-3.6.1-16-2016-00006 Megjegyzés-27120503 EFOP-3.6.1-16-2016-00006 LA - English DB - MTMT ER - TY - CHAP AU - Tornai, Kálmán AU - Oláh, András AU - Drenyovszki, Rajmund AU - Kovács, Lóránt AU - Pintér, István AU - J, Levendovszky TI - Recurrent neural network based user classification for smart grids T2 - 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - New York, New York SN - 9781538628904 T3 - IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), ISSN 2167-9665 PY - 2017 SP - 1 EP - 5 PG - 5 DO - 10.1109/ISGT.2017.8086043 UR - https://m2.mtmt.hu/api/publication/3314043 ID - 3314043 N1 - LA - English DB - MTMT ER - TY - CHAP AU - Tornai, Kálmán AU - Oláh, András AU - Drenyovszki, Rajmund AU - Kovács, Lóránt AU - Pintér, István AU - Levendovszky, J ED - Lau, E T ED - Chai, M K K ED - Chen, Y ED - Jung, O ED - Leung, V C M ED - Yang, K Bessler ED - S, Loo J ED - Nakayama, T TI - Deep learning based consumer classification for smart grid T2 - Smart grid inspired future technologies PB - Springer Netherlands CY - Cham (Németország) SN - 9783319618128 T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering (LNICST) PY - 2017 SP - 132 EP - 141 PG - 10 DO - 10.1007/978-3-319-61813-5_13 UR - https://m2.mtmt.hu/api/publication/3256354 ID - 3256354 LA - English DB - MTMT ER - TY - JOUR AU - Kovács, Lóránt AU - Drenyovszki, Rajmund AU - Oláh, András AU - Levendovszky, János AU - Tornai, Kálmán AU - Pintér, István TI - A probabilistic demand side management approach by consumption admission control JF - TEHNICKI VJESNIK-TECHNICAL GAZETTE J2 - TEH VJESN VL - 24 PY - 2017 IS - 1 SP - 199 EP - 207 PG - 9 SN - 1330-3651 DO - 10.17559/TV-20151021201400 UR - https://m2.mtmt.hu/api/publication/3183546 ID - 3183546 LA - English DB - MTMT ER -