{"title":"Propagation Constant in Tapered Segment of Slotted Rectangular Waveguide","authors":"R. Abdullin, Rodion Narudinov","doi":"10.1109/TELFOR52709.2021.9653384","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653384","url":null,"abstract":"The paper investigates the propagation constant inside the rectangular waveguide, which has a narrow longitudinal slot on its broad face, while the width of waveguide linearly changes. The propagation constant is the result of solving the dispersion equation composed by means of Galerkin method for the tangential components of magnetic field, which is obtained on the basis of dyadic Green's functions. For the description of internal region the cylindrical coordinates system is introduced so that the faces of tapered segment of waveguide coincided with the coordinate surfaces. The dependencies of the propagation constant are obtained for various values of slot length and the waveguide expansion coefficient. The results of theoretical calculations are confirmed by the results of electrodynamic modeling in ANSYS Electronics Desktop.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125035542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comparison of Machine Learning algorithms for venue presence with inclusion of neighbours","authors":"Wiqar Khan, Asif Raza, H. Kuusniemi, M. Elmusrati","doi":"10.1109/TELFOR52709.2021.9653230","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653230","url":null,"abstract":"User presence determination for being inside a venue, such that the user is provided with possible value-added services, is of high significance. It will get more prominent as we move to 5G and 6G networks’ rollout as we’ll get further means to have better aids. In this paper, machine learning (ML) algorithms computation results are obtained and analysed. Such algorithms would be candidate to be deployed for finding the confidence in decision making for a user’s location with respect to a venue. Number of UEs (User Equipment) are simultaneously placed inside and outside a venue and kept over a longer duration. Data such as received reference signal received power for serving cells and neighbour candidate cells etc. data is collected by each UE. The different available neighbours’ level in each data set is analysed. k-Nearest Neighbour (KNN), Logistic Regression (LR), Decision Tree (DT) and Random Forest (RF) algorithms are used to find the accuracy based on neighbours’ depth among the available info. Very convincing results are observed over different level of neighbours being included in each Machine Learning (ML) algorithms.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"403 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123361079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tijana Đurkić, Aleksandra Lojaničić, S. Suzic, B. Popović, M. Secujski, Tijana V. Nosek
{"title":"Emotion recognition from speech based on ML algorithms applied on two Serbian datasets","authors":"Tijana Đurkić, Aleksandra Lojaničić, S. Suzic, B. Popović, M. Secujski, Tijana V. Nosek","doi":"10.1109/TELFOR52709.2021.9653287","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653287","url":null,"abstract":"As machines play an increasing role in people's daily lives, human-machine communication needs to become more similar to communication between two people. For this reason, the need for automatic emotion recognition from speech has arisen. The aim of this paper is to compare the performance of different machine learning algorithms in automatic emotion recognition on two corpora of expressive speech in the Serbian language, one containing speech samples delivered by professional actors, and the other one produced by amateurs. In both cases acoustic features were extracted using the OpenSmile toolkit. The machine learning algorithms under investigation include: k-nearest neighbours, support vector machines and decision trees. The best performance was achieved by support vector machines with dimensionality reduced by principal component analysis. This support was shown to achieve the accuracy of more than 80% for each of 5 analyzed emotions (joy, sadness, fear, anger and neutral) on the amateur speech corpus.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129655734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Marinković-Nedelicki, J. Radivojević, P. Petrovic, A. Lebl
{"title":"Radio Spectrum Monitoring and Surveillance System in the VHF/UHF Frequency Band","authors":"V. Marinković-Nedelicki, J. Radivojević, P. Petrovic, A. Lebl","doi":"10.1109/TELFOR52709.2021.9653314","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653314","url":null,"abstract":"The radio system for very/ultra high frequency (VHF/UHF) spectrum monitoring and signal processing used in direction finding is presented in this paper. This main system function is based on the implementation of 6-channel VHF/UHF radio signal receiver. The multicoupler unit allows selection of the desired signal frequency band for the analysis in the receiver. The system implementation is verified according to the user requirements. Several measured electrical characteristics of multicoupler unit and receiver are presented just to illustrate their possibilities for the full application.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129962295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Applicability of single- and two-hidden-layer neural networks in decoding linear block codes","authors":"Srdan Brkic, P. Ivaniš, B. Vasic","doi":"10.1109/TELFOR52709.2021.9653357","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653357","url":null,"abstract":"In this paper, we analyze applicability of single- and two-hidden-layer feed-forward artificial neural networks, SLFNs and TLFNs, respectively, in decoding linear block codes. Based on the provable capability of SLFNs and TLFNs to approximate discrete functions, we discuss sizes of the network capable to perform maximum likelihood decoding. Furthermore, we propose a decoding scheme, which use artificial neural networks (ANNs) to lower the error-floors of low-density parity-check (LDPC) codes. By learning a small number of error patterns, uncorrectable with typical decoders of LDPC codes, ANN can lower the error-floor by an order of magnitude, with only marginal average complexity incense.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116329003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ivana S. Vasiljević, M. Krstić, J. Crnjanski, Mladen Ž. Banović, D. Gvozdić
{"title":"Generation of dual optical frequency combs by pulse modulation of a single semiconductor laser using a step recovery diode","authors":"Ivana S. Vasiljević, M. Krstić, J. Crnjanski, Mladen Ž. Banović, D. Gvozdić","doi":"10.1109/TELFOR52709.2021.9653267","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653267","url":null,"abstract":"In this paper we present and theoretically investigate a simple scheme for dual optical frequency comb generation residing on a pulse modulation of a semiconductor laser. The modulation current is composed of two superimposed waveforms, generated by two independent step recovery diodes, driven by two sine generators. Our model of the modulated laser estimates dual-combs comprising 300 teeth pairs within 10 dB margin spanning up to 60 GHz with total optical power of 0.4 mW.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115735989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design and Implementation of a Hybrid Power for Telecommunication and Measuring Remote Station of the Surveillance, Alert and Warning System","authors":"Z. Despotovic, Marko Tajdić","doi":"10.1109/TELFOR52709.2021.9653255","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653255","url":null,"abstract":"The paper present the realization of a hybrid power supply of telecommunication and measuring equipment of remote measuring stations, which are an integral part of the Serbian Surveillance, Alert & Warning System (SAWS). The power supply system is based on the use of solar energy in combination with the mains power supply 230V, 50Hz. Solar power is the primary source of power during the day, while in night conditions the secondary power supply is a distribution power grid. The hybrid power system is realized with two controlled MPPT chargers (mains and solar), battery bank 12V/110Ah and the corresponding system for its monitoring. In the paper the key results obtained during the realization of a specifically implemented remote station on the river Ub, municipality of Ub, will be presented.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125585443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Electromagnetic Modelling of Micro-Doppler Signatures of Commercial Airborne Drones","authors":"Pavle Z. Petrović, S. Savić, M. Ilić","doi":"10.1109/TELFOR52709.2021.9653308","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653308","url":null,"abstract":"We analyze the micro-Doppler spectrum of a drone by studying the radar cross sections (RCSs) of a commercial drone with respect to position of its propellers. Major differences in the RCS of the original drone, compared to a model of a drone without the propellers are presented. These differences, originating from electromagnetic field scattered from propellers, will be Doppler-shifted and will thus result in a micro-Doppler signature of a drone, which, in turn, can be used to facilitate target detection, classification, and tracking. Method for calculating the spectrum of the micro-Doppler signature of a drone is also presented.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131176516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hybrid ensemble neural network approach for photovoltaic production forecast","authors":"Dea Pujić, Nikola M. Tomasevic","doi":"10.1109/TELFOR52709.2021.9653369","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653369","url":null,"abstract":"With the main goal of saving the environment and reducing the amount of burnt fossil fuels, the penetration of renewable energy sources as a share of the electrical energy production is constantly increasing. However, this growth significantly jeopardizes electrical grid stability, since renewable sources highly depend on the meteorological conditions, which are stochastic by their nature. Therefore, careful planning of energy use is necessary, which is why a photovoltaic production forecaster model has been presented within this paper. The main focus was presenting a hybrid ensemble neural network approach which combines ensembling method with complex LSTM + CNN networks with the aim of improving forecasting performance. The approach has been tested using real-world year-long data from the town of Adeje in Tenerife and the results show an improvement in forecasting precision in comparison with the conventional ensemble model and with the hybrid approach on the test data, both state-of-the-art solutions.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133473398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analiza izazova i definisanje preporuka za uspješnu implementaciju 5G mreža","authors":"Milica Pejanović Đurišić, Zoran Veljović","doi":"10.1109/TELFOR52709.2021.9653351","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653351","url":null,"abstract":"As a cohesive platform for innovative applications that adapts to specific user requirements, 5G networks have an important role in the overall development of the economy and society, representing a cornerstone segment of the overall digital transformation. Taking into consideration architecture characteristics of the 5G systems, their functionalities, as well as the components of the associated eco-system, it is clear that their effective implementation depends on a number of factors that may be limitations, if not identified properly and in a timely manner. As the region of Western Balkans is lacking behind the rest of Europe when deployment of 5G is considered, this paper aims at identifying challenges that might have an impact on that process and on that basis, recommendations and suggestions for further actions of different relevant stakeholders, are presented.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132350404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}