TY - CONF AU - Bogdándy, Bence AU - Tóth, Zsolt ED - Fazekas, I. ED - Hajdu, A. ED - Tomacs, T. TI - Inversion of artificial neural networks for WiFi RSSI propagation modeling T2 - 1st Conference on Information Technology and Data Science, CITDS 2020 VL - 2874 PB - CEUR Workshop Proceedings T3 - CEUR Workshop Proceedings, ISSN 1613-0073 ; 2874. PY - 2021 SP - 67 EP - 76 PG - 10 UR - https://m2.mtmt.hu/api/publication/32840819 ID - 32840819 N1 - Conference code: 169351 Export Date: 6 December 2022 AB - Wireless communication via access points has rapidly become widespread in almost all aspects of human life. There is an abundance of Wi-Fi access points in almost every building. Wi-Fi positioning systems take advantage of the widespread use of the access points. Wi-Fi based indoor positioning techniques use Wi-Fi fingerprinting to record the propagated signal of individual access points. Recording the data of the propagation models can be used to build a fingerprinting radio map. The built fingerprinting radio maps consist of a set of coordinates, and an access point radio signal strength indication. Artificial Neural networks have proven to be one of the most useful prediction methods, given a big data set. Inversion of Artificial Neural Network models is the process of creating a model that is capable of predicting a set of possible inputs from a given output. The inversion of the neural network which has been trained on the fingerprinting data set can create a novel positioning method. Received signal strength indication can be inverted into a set of coordinates. This paper includes a description, and evaluation of possible metrics for calculating the error of indoor positioning in an evolutionary artificial neural network inversion system. Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). LA - English DB - MTMT ER - TY - CONF AU - Tóth, Zsolt ED - Fazekas, I. ED - Hajdu, A. ED - Tomacs, T. TI - Technical improvements of the ILONA system T2 - 1st Conference on Information Technology and Data Science, CITDS 2020 VL - 2874 PB - CEUR Workshop Proceedings T3 - CEUR Workshop Proceedings, ISSN 1613-0073 ; 2874. PY - 2021 SP - 240 EP - 245 PG - 6 UR - https://m2.mtmt.hu/api/publication/32840816 ID - 32840816 N1 - Conference code: 169351 Export Date: 6 December 2022 Correspondence Address: Tóth, Z.; Eszterházy Károly University, Hungary; email: toth.zsolt@uni-eszterhazy.hu AB - The Indoor Localization and Navigation (ILONA) System was designed and developed since 2015. During this period, the ILONA System was used to record data data sets, perform experiments and numerous students contributed to its development. Keeping the project up-to-date from the viewpoint of technology is a constant challenge which has both pitfalls and success stories. Collecting data with the ILONA System allowed us to get experience with its usage in real scenarios and set further directions of improvement. Testing different positioning algorithms showed the flexibility of the system. Modular decomposition of the monolithic first version of the ILONA System was successful with some overstatements. Development is an ongoing process with a couple of new features. Applications, experiences and further developments of the ILONA System are both detailed. Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). LA - English DB - MTMT ER - TY - CHAP AU - Adeyemo, Adedeji Charles AU - Bogdándy, Bence AU - Tóth, Zsolt ED - Szakál, Anikó TI - Machine Learning based Prediction of GDP using FAO Agricultural Data Set for Hungary T2 - 15th IEEE International Symposium on Applied Computational Intelligence and Informatics SACI 2021 PB - IEEE CY - Budapest CY - Piscataway (NJ) SN - 9781728195438 PY - 2021 SP - 473 EP - 477 PG - 5 DO - 10.1109/SACI51354.2021.9465608 UR - https://m2.mtmt.hu/api/publication/32189565 ID - 32189565 N1 - Conference code: 171067 Export Date: 6 December 2022 AB - Prediction of economical growth is a complex task which is essential for planning sustainable economy. The economy has a wide range of indicators that are monitored and recorded by governments and international organizations. Agriculture is one of the most essential factors to modern day economical sustainability. The Food and Agriculture Organization keeps essential agricultural data sets which consist of records on production of crops and other agricultural products whose production strongly relates to the Gross Domestic Product of many countries. Assuming that total crop production and agricultural economy growth are highly related, the production of crops and total value of income from agriculture can be learnt by machine learning models. As data is recorded along an axis of time, it can be interpreted as a time series of various factors. Recurrent Neural Network excel in learning time series and sequential data. This paper presents experimental results on training various recurrent neural networks for modeling the changes of Agricultural and Gross Domestic Products. The paper details the data transformation, model building and model validation steps. Our experimental results showed that the models could achieve 85% accuracy. LA - English DB - MTMT ER - TY - CHAP AU - Silabela, Mxolisi AU - Bogdándy, Bence AU - Tóth, Zsolt ED - Szakál, Anikó TI - Automatic Mask Detecion using Convolutional Neural Networks and Variational Autoencoder T2 - 15th IEEE International Symposium on Applied Computational Intelligence and Informatics SACI 2021 PB - IEEE CY - Budapest CY - Piscataway (NJ) SN - 9781728195438 PY - 2021 SP - 461 EP - 466 PG - 6 DO - 10.1109/SACI51354.2021.9465587 UR - https://m2.mtmt.hu/api/publication/32189564 ID - 32189564 N1 - Conference code: 171067 Export Date: 6 December 2022 AB - The importance of proper hygienical behaivour is essential in today's word especially during an ongoing pandemic. Wearing mask became mandatory in many countries during the COVID-19 Pandemic. Recognizing whether people are wearing masks is complicated image recognition task which could be facilitated and automated with machine learning techniques. Camera streams are widely available in indoor environments which can be used for object detection and image processing. Convolutional Neural Networks have been successfully applied in image classification and object recognition task in various application areas. There are already trained and openly available general purpose convolutional neural networks which can be used as an initial version for specific applications. A number of different image datasets are also available for research and industrial purposes. The InceptionV3 Neural Network architecture was used to tailored to determine whether a mask is being worn or not using transfer learning techniques, and convolutional neural networks. A variational autoencoder has also been trained to normalize the dataset with respect to skin colour, angle of the head and among other parameters. This paper describes the implementation of a mask recognition software using transfer learning, a convolutional neural network and a variational autoencoder. LA - English DB - MTMT ER - TY - CHAP AU - Kovács, Ádám AU - Bogdándy, Bence AU - Tóth, Zsolt ED - Szakál, Anikó TI - Predict Stock Market Prices with Recurrent Neural Networks using NASDAQ Data Stream T2 - 15th IEEE International Symposium on Applied Computational Intelligence and Informatics SACI 2021 PB - IEEE CY - Budapest CY - Piscataway (NJ) SN - 9781728195438 PY - 2021 SP - 449 EP - 453 PG - 5 DO - 10.1109/SACI51354.2021.9465634 UR - https://m2.mtmt.hu/api/publication/32189563 ID - 32189563 N1 - Conference code: 171067 Export Date: 6 December 2022 AB - Prediction and modeling of stock market changes attract not only economists and other scientific professionals, but the general public as well. With the rise of blockchain, and cryptocurrencies, the interest in stock trading has surged. Stock prices are precisely recorded in frequent fixed intervals, and this data is publicly available. Due to the outstanding performance of recurrent neural networks in sequential data modeling, recurrent networks can be applied to model the stock market. Although accurate prediction of the changes is not possible due to the stock market's highly stochastic stochastic nature, a recurrent neural network could give a good approximation of trends. National Association of Securities Dealers Automated Quotations publishes stock values every few minutes, which data stream was used to model and predict changes. This paper presents a proof of concept implementation of a stock market price prediction system using recurrent neural networks and a continuous data stream. LA - English DB - MTMT ER - TY - CONF AU - Tamás, Judit AU - Tóth, Zsolt ED - Fazekas, I. ED - Hajdu, A. ED - Tomacs, T. TI - Tuning of Category Hierarchy Enhanced Classification Based Indoor Positioning T2 - 1st Conference on Information Technology and Data Science, CITDS 2020 PB - CEUR Workshop Proceedings T3 - CEUR Workshop Proceedings, ISSN 1613-0073 ; 2874. PY - 2021 SP - 207 EP - 217 PG - 11 UR - https://m2.mtmt.hu/api/publication/32076574 ID - 32076574 AB - The tuning of classification refinement using hierarchical grouping of categories is presented in this paper. The refinement can improve the accuracy of classifiers in the case of low confidence level and it uses a classifier, a threshold and a dendrogram as parameters. For the examination, the k–NN and the Naive Bayes classifiers are used and the dendrogram will be generated by using linkage method and dissimilarity value of gravitational force-based approach on the topology information. The topology of the environment is described by IndoorGML (Indoor Geographic Markup Language) document. The data set for the classification is part of the Miskolc IIS (Institute of Information Science) Hybrid IPS (Indoor Positioning System) Data set recorded with the ILONA (Indoor Localization and Navigation) System. Three properties are examined of a setup, namely hitRate, confidence and abstraction, however, they are conflicting. A fitness function is introduced using these properties for the purpose of tuning. In this paper, the different weight tuples are examined in the given test environment. The goal of the paper is to examine the weighting possibilities of the hitRate, confidence, and abstraction level features for indoor positioning purposes. Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). LA - English DB - MTMT ER - TY - CONF AU - Bogdándy, Bence AU - Kovács, Ádám AU - Tóth, Zsolt ED - Kovásznai, Gergely ED - Fazekas, István ED - Tómács, Tibor TI - Persistent Storage of Data Sets in Apache Hive T2 - Proceedings of the 11th International Conference on Applied Informatics (ICAI 2020) PB - CEUR Workshop Proceedings C1 - Eger T3 - CEUR Workshop Proceedings, ISSN 1613-0073 ; 2650. PY - 2020 UR - https://m2.mtmt.hu/api/publication/32840140 ID - 32840140 LA - English DB - MTMT ER - TY - CONF AU - Bogdándy, Bence AU - Tóth, Zsolt TI - Overview of Artificial Neural Network Abduction and Inversion Methods T2 - The 12th Conference of PhD Students in Computer Science PB - Szegedi Tudományegyetem (SZTE) C1 - Szeged PY - 2020 SP - 32 EP - 35 PG - 4 UR - https://m2.mtmt.hu/api/publication/32036565 ID - 32036565 LA - English DB - MTMT ER - TY - CHAP AU - Bogdándy, Bence AU - Tamás, Judit AU - Tóth, Zsolt TI - Digital Transformation in Education during COVID–19: a Case Study T2 - 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom 2020) PB - IEEE CY - New York, New York SN - 9781728182148 T3 - International Conference on Cognitive Infocommunications, ISSN 2375-1312 PY - 2020 SP - 173 EP - 178 PG - 6 DO - 10.1109/CogInfoCom50765.2020.9237840 UR - https://m2.mtmt.hu/api/publication/31622604 ID - 31622604 N1 - IEEE Computational Intelligence Chapter; IEEE Finland Section; IEEE Hungary Section; IEEE IES and RAS Chapters; IEEE Systems, Man and Cybernetics Chapter Conference code: 164650 Cited By :43 Export Date: 4 October 2023 Funding text 1: This research was supported by the grant EFOP-3.6.1-16-2016-00001 (Complex improvement of research capacities and services at Eszterhazy Karoly University). LA - English DB - MTMT ER - TY - CHAP AU - Bogdándy, Bence AU - Kovács, Ádám AU - Tóth, Zsolt TI - Case Study of an On-premise Data Warehouse Configuration T2 - 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom 2020) PB - IEEE CY - New York, New York SN - 9781728182148 T3 - International Conference on Cognitive Infocommunications, ISSN 2375-1312 PY - 2020 SP - 179 EP - 184 PG - 6 DO - 10.1109/CogInfoCom50765.2020.9237814 UR - https://m2.mtmt.hu/api/publication/31617264 ID - 31617264 N1 - IEEE Computational Intelligence Chapter; IEEE Finland Section; IEEE Hungary Section; IEEE IES and RAS Chapters; IEEE Systems, Man and Cybernetics Chapter Institute of Computational Science, Eszterházy Károly University, Hungary Eszterházy Károly University, Hungary Conference code: 164650 Cited By :1 Export Date: 6 July 2023 LA - English DB - MTMT ER -