M. Mokhtari, J. Bajčetić, Boban Sazdic-Jotic, B. Pavlović
{"title":"RF-based drone detection and classification system using convolutional neural network","authors":"M. Mokhtari, J. Bajčetić, Boban Sazdic-Jotic, B. Pavlović","doi":"10.1109/TELFOR52709.2021.9653332","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653332","url":null,"abstract":"This paper presents an effort towards developing a detection and classification information system based on the RF signature of several commercial drones. The developed application implements a Convolutional Neural Network which was trained and tested using data from a publically accessible database. The tested neural network reached an accuracy of almost 100% (4-classes), which is considered as a significant contribution to the development of a functional drone detection system. Moreover, the developed interface allows the user to supervise the spectral activity in the 2.4 GHz ISM band, notifies him about the presence and the nature of a potential threat, and stores the event log in a database for later exploitation.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"5 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":"128184249","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":"Ergodic Capacity Analysis of Cognitive System with Self-Sustainable Relay and Statistical CSI","authors":"N. Kozic, Vesna Blagojevic, P. Ivaniš","doi":"10.1109/TELFOR52709.2021.9653387","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653387","url":null,"abstract":"The cooperative cognitive wireless system based on underlay paradigm with available statistical channel state information (CSI) is considered in this paper. The primary and the cognitive network share the same spectrum band, under the constraint of interference threshold and maximal tolerable outage permitted by the primary user. The communication in the cognitive decode-and-forward (DF) relaying system is established via energy constrained relay, which harvests energy from both cognitive and primary transmitters. The ergodic capacity analysis is provided and the results are corroborated by an independent simulation method.","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":"129989394","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":"Technoeconomic Analysis of Photovoltaic Systems Integration in Power Grid and Off-Grid Telecom Stations in Cyprus","authors":"M. Chrysostomou, N. Christofides, K. Efstathiou","doi":"10.1109/TELFOR52709.2021.9653293","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653293","url":null,"abstract":"The enormous growth of telecom network technologies of this decade and the ever-growing data needs, will unavoidably increase the energy consumption of telecom base stations and datacenters. The energy demand increase tend to become a serious issue for both power grid operators and telecom network owners in the upcoming years. Having in mind that adding the 5G layer can consume more than double of a typical 3-cell system (consisting of 2G, 3G and 4G bands), the telecoms industry will need to find solutions to mitigate the increase in energy demand. In this work the energy/load profiles of different telecom stations are analyzed and correlated in discrete steps with the expected PV power generated profile taking into consideration the inherent presence of storage that telecom stations have. The work is validated through a technoeconomic feasibility study.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"53 6 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":"133929475","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}
Stojancho Tudjarski, Tomislav Ignjatov, Marjan Gusev
{"title":"A New ML-based AFIB Detector","authors":"Stojancho Tudjarski, Tomislav Ignjatov, Marjan Gusev","doi":"10.1109/TELFOR52709.2021.9653409","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653409","url":null,"abstract":"Objectives: This paper aims to develop a model for detecting Atrial Fibrillation (AFIB) in a single-channel electrocardiogram.Methodology: The applied Machine Learning methods are XGBoost and Random Forest. Training and testing split was realized by splitting the patients 70% for training and 30% for testing. Features included annotations for heartbeats, intervals between neighboring heartbeats, Shannon entropy, and Fluctuation index by designing a moving window with predefined length.Data: Standard ECG benchmarks were used for training and testing from MIT-BIH Arrhythmia [1] and MIT-BIH Atrial Fibrillation[2] datasets.Conclusion: Experiments were done with different window sizes and different hyperparameters. The best results were achieved from the 41 Beat window, with XGBoost achieving the best performance of 99% with an F1 score of 99%.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"9 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":"131235154","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":"Software Architecture for an Open-Source Tool to Test DVB-T2 Networks Based on Linux TV, Kaffeine, and RTL-SDR","authors":"S. Staroletov","doi":"10.1109/TELFOR52709.2021.9653329","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653329","url":null,"abstract":"Digital terrestrial television of the European DVB-T2 standard is now replacing analog signals in households everywhere. Moreover, such television is usually available in most places where people live due to the developed network of ground stations. However, both in modern cities, due to buildings, and in the countryside, due to the terrain, there are areas with an uncertain signal. At the same time, setting up a household receiver is further complicated by the fact that the orientation of the antenna in the room is necessary. Hence, testing tools for assessing the signal level and quality are relevant for both professionals and consumers. In this paper, we present the architecture of our open-source solution and methods for solving the problem of assessing the signal quality in DVB-T2 networks using open source software running under Linux. We implement our solution based on the Kaffeine tool, which provides the necessary abstractions for working with a DVB card and transponders. We show how to programmatically monitor a signal, build a spectrum diagram, mark the signal level on a map, and analyze its quality in the form of constellation diagrams. To work with a raw signal, in the latter case, we use RTL-SDR. The architectural modeling was done using UML.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"77 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":"131111352","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":"Pre-build optimization of Android operating system for running inside container","authors":"N. Stanojev, Bogdan Pavković, Pavle Stanojevic","doi":"10.1109/TELFOR52709.2021.9653322","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653322","url":null,"abstract":"Android, being the most widely used operating system, created a motive to run its applications on as many platforms, which can even have a different operating system. For Android applications to be used in such environments, Android needs to be present on the platform as well. To make this possible, we decreased Android's memory usage and used lightweight virtualization technology in order to have two coexisting operating systems properly running. This paper aims to provide the solution for the above-mentioned problem using pre-built optimization of the Android operating system and running it inside a Linux container.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"264 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":"132780873","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":"Sim-to-Real Autonomous Vehicle Lane Keeping using Vision","authors":"Jelena Kocic, Nenad Jovičić","doi":"10.1109/TELFOR52709.2021.9653302","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653302","url":null,"abstract":"This paper presents the analysis of the J-Net deep neural network used for autonomous vehicle lane keeping, and its verification in simulated and real conditions. The transition from the simulated world on the personal computer to the real world in laboratory conditions is tackled. In the presented solution, autonomous lane keeping is achieved by analyzing information from visual sensors using a deep neural network. J-Net was developed with an aim to be implemented on an autonomous vehicle platform with limited hardware performance in terms of computing power and memory capacity. Verification of autonomous driving using J-Net was achieved in simulated conditions, using an open-source simulator for autonomous driving, and in real-world conditions. For the verification in real-world conditions, an autonomous driving system was designed and implemented in the Laboratory of Electronics at the School of Electrical Engineering, University of Belgrade.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"32 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":"124302434","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}
A. Petrovic, I. Strumberger, Timea Bezdan, Hothefa Shaker Jassim, Said Suleiman Nassor
{"title":"Cryptocurrency Price Prediction by Using Hybrid Machine Learning and Beetle Antennae Search Approach","authors":"A. Petrovic, I. Strumberger, Timea Bezdan, Hothefa Shaker Jassim, Said Suleiman Nassor","doi":"10.1109/TELFOR52709.2021.9653305","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653305","url":null,"abstract":"Cryptocurrencies are defined as digital mediums of exchange, that use strong cryptography for securing the transactions and verifying the ownership of the coins. Blockchain operates in the background to guarantee the security, transparency and traceability of the transactions. Consequently, cryptocurrencies became more and more popular and established their considerable presence in financial sector. However, one of the major drawbacks in the cryptocurrency market is the unreliability and unpredictability of their values, that poses a major risk for any kind of investment. Predicting the price of cryptocurrencies is therefore a hot research domain today. This paper proposes a novel method to predict the prices, that is based on a hybrid machine learning and swarm intelligence approach. The results of the conducted experiments suggest that the proposed model obtains higher accuracy than other recent similar approaches, and that it can be successfully applied for this important task.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"31 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":"123538073","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}
Milica M. Badža, Milica Lazić, Jana Živanović, Dimitrije Popović, Ivan A. Vajs, M. Janković
{"title":"How piano training affects manual dexterity and finger synergy?","authors":"Milica M. Badža, Milica Lazić, Jana Živanović, Dimitrije Popović, Ivan A. Vajs, M. Janković","doi":"10.1109/TELFOR52709.2021.9653227","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653227","url":null,"abstract":"Piano training generally improves motor control of hands and fingers in individuals. The assessment of fine motor control implies manual dexterity quantification as well as finger synergy analysis. In this paper we present a modification of the previously developed strain-gauge based system for hand dexterity assessment. The upgraded system was used to compare the strategy of fingers’ control between pianists and non-pianists. During the experiment, the examinee had to track the predefined trapezoidal force pattern in real-time. Two tests were performed: in the first one fingers were positioned directly above the force sensors, and during the second test, the fingers were fastened to the force sensors to analyze the finger synergy as well. The experiment was performed on ten healthy subjects, of which five declared to play the piano actively. We have determined that there is a statistically significant difference between the pianists and non-pianist for both tests.","PeriodicalId":330449,"journal":{"name":"2021 29th Telecommunications Forum (TELFOR)","volume":"97 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":"124036418","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":"Analysis of virtio GPU in a containerized environment","authors":"Dejan Bogdanović, M. Popovic, Srdjan Usorac","doi":"10.1109/TELFOR52709.2021.9653366","DOIUrl":"https://doi.org/10.1109/TELFOR52709.2021.9653366","url":null,"abstract":"Virtio technology is a widely spread technology for emulating IO devices in virtualized environments. These environments are then called paravirtualized, because the guest system cooperates with the host system when performing IO tasks to achieve better performance. Virtio GPU is an emulated device for graphics, used for rendering and displaying. One of the benefits of Virtio devices is that most operating systems provide drivers and libraries for them. Despite the popularity of paravirtualization technology, its performance still falls short to those of containers. Containers offer near native speed because the guest and the host share the same kernel. This raises the question whether Virtio GPU device (and driver) should be utilized inside the container. This paper exposes the concept of how Virtio GPU can be integrated with a container, and what the main disadvantages of that solution are. An important lesson learned from this research is that Virtio GPU should not be used inside the container.","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":"128501518","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}