Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900553
Bruno Mendes, D. Martins, Raul Barbosa, Marco Araújo
with the advent of Software Defined Networks (SDN) that allow for the near real-time topological change of the telecommunications infrastructure, aided by Network Function Virtualization (NFV) techniques, critical services that demand Ultra Reliable Low Latency Communications (URLLC) can be enforced into an edge Mobile Edge Center (MEC) in order to be processed near the User Equipment (UE). The problem arises when a specific service requires ubiquitous mobility, which is the case of autonomous driving. This paper provides a follow-me cloud solution based on a popular SDN controller, with practical applications.
{"title":"Follow-me Cloud: an OpenDayLight Implementation for 5G automotive","authors":"Bruno Mendes, D. Martins, Raul Barbosa, Marco Araújo","doi":"10.1109/BalkanCom55633.2022.9900553","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900553","url":null,"abstract":"with the advent of Software Defined Networks (SDN) that allow for the near real-time topological change of the telecommunications infrastructure, aided by Network Function Virtualization (NFV) techniques, critical services that demand Ultra Reliable Low Latency Communications (URLLC) can be enforced into an edge Mobile Edge Center (MEC) in order to be processed near the User Equipment (UE). The problem arises when a specific service requires ubiquitous mobility, which is the case of autonomous driving. This paper provides a follow-me cloud solution based on a popular SDN controller, with practical applications.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126804710","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900819
Mikail Erdem, O. Gurbuz
In this work, we propose integrated linear and nonlinear digital self-interference cancellation (DSIC) for full duplex (FD) multiple-input multiple-output (MIMO) radios, where nonlinear DSIC is applied to the residual of the linear DSIC over all streams in the MIMO system. As nonlinear DSIC techniques, random Fourier features transformation with least mean squares algorithm and memory polynomial model are considered. Our FD MIMO set-up consists only of two identical monostatic FD antennas, a WARP v3 board, and an add-on transceiver board. Experimental results show that, with the proposed integrated solution, the total cancellation performance of the FD MIMO system is enhanced by up to 6 dB per stream as compared to linear only DSIC.
{"title":"Integrated Digital Self-interference Cancellation for Full Duplex MIMO Radios","authors":"Mikail Erdem, O. Gurbuz","doi":"10.1109/BalkanCom55633.2022.9900819","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900819","url":null,"abstract":"In this work, we propose integrated linear and nonlinear digital self-interference cancellation (DSIC) for full duplex (FD) multiple-input multiple-output (MIMO) radios, where nonlinear DSIC is applied to the residual of the linear DSIC over all streams in the MIMO system. As nonlinear DSIC techniques, random Fourier features transformation with least mean squares algorithm and memory polynomial model are considered. Our FD MIMO set-up consists only of two identical monostatic FD antennas, a WARP v3 board, and an add-on transceiver board. Experimental results show that, with the proposed integrated solution, the total cancellation performance of the FD MIMO system is enhanced by up to 6 dB per stream as compared to linear only DSIC.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115874082","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900709
Stefan Kalabakov, A. Švigelj, T. Javornik
In light of events such as the recent pandemic and many potential applications in fields such as the social sciences, healthcare, and architecture, the detection of interactions or proximity between people has become increasingly important. In this context, this paper investigates the limitations of a machine learning-based approach that detects the proximity of two devices based on the WiFi and BLE fingerprints of their radio environments. More specifically, (i) we compare the use of a rudimentary set of two features and an extended, more complex set of features, (ii) we investigate the use of separate classifiers that treat WiFi and BLE features separately, and (iii) we investigate whether using only one of the two communication technologies for detection could provide better results. In addition, we also try to use techniques such as undersampling and oversampling or their combination to deal with the highly imbalanced set of examples. Our results show that the use of a more complex set of features that can be subjected to further feature selection procedures can provide a performance benefit of about 4.6 percentage points. In terms of the communication technologies used, our results also show that using BLE alone always gives significantly worse results than using WiFi alone or WiFi and BLE together. On the other hand, there is no clear winner between using WiFi alone or combining WiFi and BLE, as both provide comparable results. Finally, our results also show that using under/oversampling helps in scenarios where the classification task is somewhat more complex, but not in those where the diversity between instances is low; thus, the classification problem is simpler.
{"title":"Smartphone Proximity Detection Using WiFi and BLE Fingerprinting","authors":"Stefan Kalabakov, A. Švigelj, T. Javornik","doi":"10.1109/BalkanCom55633.2022.9900709","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900709","url":null,"abstract":"In light of events such as the recent pandemic and many potential applications in fields such as the social sciences, healthcare, and architecture, the detection of interactions or proximity between people has become increasingly important. In this context, this paper investigates the limitations of a machine learning-based approach that detects the proximity of two devices based on the WiFi and BLE fingerprints of their radio environments. More specifically, (i) we compare the use of a rudimentary set of two features and an extended, more complex set of features, (ii) we investigate the use of separate classifiers that treat WiFi and BLE features separately, and (iii) we investigate whether using only one of the two communication technologies for detection could provide better results. In addition, we also try to use techniques such as undersampling and oversampling or their combination to deal with the highly imbalanced set of examples. Our results show that the use of a more complex set of features that can be subjected to further feature selection procedures can provide a performance benefit of about 4.6 percentage points. In terms of the communication technologies used, our results also show that using BLE alone always gives significantly worse results than using WiFi alone or WiFi and BLE together. On the other hand, there is no clear winner between using WiFi alone or combining WiFi and BLE, as both provide comparable results. Finally, our results also show that using under/oversampling helps in scenarios where the classification task is somewhat more complex, but not in those where the diversity between instances is low; thus, the classification problem is simpler.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115715273","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900817
Djamel Djenour, Roufaida Laidi, Y. Djenouri
The aim of this work is to develop a deep learning model that uses spatial correlation to enable turning turn off a subset of sensors while predicting their readings. This considerably saves the energy that would be consumed by those sensors both for sensing and communications (reporting the reading to the central station), which prolongs sensors’ lifetime and opens sky for a plethora of Internet of Things (IoT) applications. Subject of this research, event-based sensing is more challenging than periodic sensing and is uncovered in the literature. We explore advanced learning approaches including Graph Convolutional Network (GCN) and Generative Adversarial Networks (GANs) and comb them in a novel way to derive a solution that uses both spatial correlation and the readings of the active sensors to accurately generate the missing readings from inactive sensors. The proposed solution is holistic and does not rely on any duty-cycling scheduling policy. A generic random pattern is used in this paper in which every sensor is duty-cycled randomly. The structure of the network is plugged into the GCN through a graph derived using the sensing range, as well as the euclidean distance between the sensors that determines the wights on the edges. Moreover, the accuracy of the GCN is enhanced by optmizing the weights of its deep neural network with a GANs and a game theory based model, which adversarially trains the GCN’s generator by estimating the generator’s performance and calculating the Wasserstein distance between the real and the generated data. The proposed solution is evaluated in comparison with the most relevant state-of-the-art approaches in terms of accuracy, energy consumption. The results show that the proposed solution provides high performance and is clearly superior to all the compared solutions in terms of reducing energy consumption and improving accuracy.
{"title":"Deep Learning for Estimating Sleeping Sensor’s Values in Sustainable IoT Applications","authors":"Djamel Djenour, Roufaida Laidi, Y. Djenouri","doi":"10.1109/BalkanCom55633.2022.9900817","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900817","url":null,"abstract":"The aim of this work is to develop a deep learning model that uses spatial correlation to enable turning turn off a subset of sensors while predicting their readings. This considerably saves the energy that would be consumed by those sensors both for sensing and communications (reporting the reading to the central station), which prolongs sensors’ lifetime and opens sky for a plethora of Internet of Things (IoT) applications. Subject of this research, event-based sensing is more challenging than periodic sensing and is uncovered in the literature. We explore advanced learning approaches including Graph Convolutional Network (GCN) and Generative Adversarial Networks (GANs) and comb them in a novel way to derive a solution that uses both spatial correlation and the readings of the active sensors to accurately generate the missing readings from inactive sensors. The proposed solution is holistic and does not rely on any duty-cycling scheduling policy. A generic random pattern is used in this paper in which every sensor is duty-cycled randomly. The structure of the network is plugged into the GCN through a graph derived using the sensing range, as well as the euclidean distance between the sensors that determines the wights on the edges. Moreover, the accuracy of the GCN is enhanced by optmizing the weights of its deep neural network with a GANs and a game theory based model, which adversarially trains the GCN’s generator by estimating the generator’s performance and calculating the Wasserstein distance between the real and the generated data. The proposed solution is evaluated in comparison with the most relevant state-of-the-art approaches in terms of accuracy, energy consumption. The results show that the proposed solution provides high performance and is clearly superior to all the compared solutions in terms of reducing energy consumption and improving accuracy.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129609984","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900741
Nada Elsokkary, Muhammad Habib ur Rehman, S. Suhail, H. Kaindl, D. Svetinovic
Despite a recent increase in popularity, most individuals remain hesitant to use cryptocurrencies due to concerns about their volatility, general lack of understanding of blockchain technology, and various trust issues. Therefore, it is of high priority for the community to better understand such systems, and what increases or decreases trust in them. In this paper, we explore the current trust-related requirements on blockchain systems, focusing on the use of the dedicated requirements elicitation method TrUStAPIS. We evaluate Bitcoin and Diem trust issues and requirements. Based on the evaluation, we present a cryptocurrency trust model.
{"title":"Trust Evaluation of Blockchain-Based Cryptocurrencies: The Cases of Bitcoin and Diem","authors":"Nada Elsokkary, Muhammad Habib ur Rehman, S. Suhail, H. Kaindl, D. Svetinovic","doi":"10.1109/BalkanCom55633.2022.9900741","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900741","url":null,"abstract":"Despite a recent increase in popularity, most individuals remain hesitant to use cryptocurrencies due to concerns about their volatility, general lack of understanding of blockchain technology, and various trust issues. Therefore, it is of high priority for the community to better understand such systems, and what increases or decreases trust in them. In this paper, we explore the current trust-related requirements on blockchain systems, focusing on the use of the dedicated requirements elicitation method TrUStAPIS. We evaluate Bitcoin and Diem trust issues and requirements. Based on the evaluation, we present a cryptocurrency trust model.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128314715","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900680
Belma Ramic-Brkic, B. Mijatovic, Faik Ćatibušić, Emina Mekic
Research has shown that technology promotes learning environments that stimulate improved learning performance, learners satisfaction and completion rates. Virtual reality (VR) is a computer-generated environment with scenes and objects that look and feel real, making the user feel immersed in that world. This immersion provides learning and training opportunities in a variety of areas. This paper aims to investigate the perceived usefulness, ease of use and impression of the presented solution and whether it can improve the safety and effectiveness of field demining missions. A focus group study was conducted. The findings of the study are very positive, and show an affirmative attitude towards the use of the presented application for the purpose of educating and training new deminers.
{"title":"Developing a Virtual Reality (VR) Lab for Improving the Safety of Pyrotechnicians","authors":"Belma Ramic-Brkic, B. Mijatovic, Faik Ćatibušić, Emina Mekic","doi":"10.1109/BalkanCom55633.2022.9900680","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900680","url":null,"abstract":"Research has shown that technology promotes learning environments that stimulate improved learning performance, learners satisfaction and completion rates. Virtual reality (VR) is a computer-generated environment with scenes and objects that look and feel real, making the user feel immersed in that world. This immersion provides learning and training opportunities in a variety of areas. This paper aims to investigate the perceived usefulness, ease of use and impression of the presented solution and whether it can improve the safety and effectiveness of field demining missions. A focus group study was conducted. The findings of the study are very positive, and show an affirmative attitude towards the use of the presented application for the purpose of educating and training new deminers.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125769217","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900820
Halil Said Cankurtaran, Serhan Yarkan, M. Hasna, K. Qaraqe
Propagation characteristics of electromagnetic (EM) waves such as amplitude, wavelength, and polarization can be altered by the medium that they travel. Such changes can decrease performance, and even lead to complete failures in communication networks. Hence, studies focusing on the propagation of EM waves under different atmospheric conditions such as rain, fog and snow have attracted researchers for decades. However, it is evident in both literature and standards that effects of sand and dust storms (SDS) on EM waves have not been understood well. Although proposed models consider randomness in the estimation of parameters, they end up with a deterministic solution without any uncertainty. However, uncertainty in the measurements makes the use of statistical models obligatory. In this study, a statistical model of attenuation is proposed solely based on frequency, and visibility. Moreover, in the proposed model, a region of uncertainty in estimations is provided by considering randomness in visibility measurements, whose characteristics are determined by the World Meteorological Organization and off-the-shelf measurement devices. Additionally, visibility and SDS statistics of Gulf area has been obtained by the analysis of NASA Hourly Global – Integrated Surface Database (ISD). Also, SDS attenuation is compared with rain and gaseous attenuation according to ITU recommendations.
{"title":"Statistical Modeling of Sand and Dust Storm Attenuation","authors":"Halil Said Cankurtaran, Serhan Yarkan, M. Hasna, K. Qaraqe","doi":"10.1109/BalkanCom55633.2022.9900820","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900820","url":null,"abstract":"Propagation characteristics of electromagnetic (EM) waves such as amplitude, wavelength, and polarization can be altered by the medium that they travel. Such changes can decrease performance, and even lead to complete failures in communication networks. Hence, studies focusing on the propagation of EM waves under different atmospheric conditions such as rain, fog and snow have attracted researchers for decades. However, it is evident in both literature and standards that effects of sand and dust storms (SDS) on EM waves have not been understood well. Although proposed models consider randomness in the estimation of parameters, they end up with a deterministic solution without any uncertainty. However, uncertainty in the measurements makes the use of statistical models obligatory. In this study, a statistical model of attenuation is proposed solely based on frequency, and visibility. Moreover, in the proposed model, a region of uncertainty in estimations is provided by considering randomness in visibility measurements, whose characteristics are determined by the World Meteorological Organization and off-the-shelf measurement devices. Additionally, visibility and SDS statistics of Gulf area has been obtained by the analysis of NASA Hourly Global – Integrated Surface Database (ISD). Also, SDS attenuation is compared with rain and gaseous attenuation according to ITU recommendations.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114412887","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900672
Abdullateef Almohamad, F. Yilmaz, M. Hasna, K. Qaraqe
As user applications become more diverse and data rate-hungry, networks emerge into heterogeneous and flexible forms. Unmanned aerial vehicles (UAV) play a prominent role in achieving a next level of flexibility thanks to their rapid deployment, low cost and favorable propagation conditions. One of the most important aspects of UAV-assisted heterogeneous networks (HetNets) is the user association strategy. In this regard, we propose an instantaneous-sense association strategy, as opposed to the widely adopted average-sense one. We study the association performance in a two tiers mmWave HetNet, where a terrestrial network is supported by a tier of UAV BSs (UBS). In specific, using tools from stochastic geometry we provide tractable expressions for the association probability with each tier in addition to expression for coverage hole probability taking into account the users’ reception sensitivity. Monte Carlo simulations are provided to validate the accuracy of analytical formulas, and it is shown that the average-sense association strategy is a special case of the proposed method.
{"title":"UAV-Assisted HetNets: Association Probability With Instantaneous Received Power","authors":"Abdullateef Almohamad, F. Yilmaz, M. Hasna, K. Qaraqe","doi":"10.1109/BalkanCom55633.2022.9900672","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900672","url":null,"abstract":"As user applications become more diverse and data rate-hungry, networks emerge into heterogeneous and flexible forms. Unmanned aerial vehicles (UAV) play a prominent role in achieving a next level of flexibility thanks to their rapid deployment, low cost and favorable propagation conditions. One of the most important aspects of UAV-assisted heterogeneous networks (HetNets) is the user association strategy. In this regard, we propose an instantaneous-sense association strategy, as opposed to the widely adopted average-sense one. We study the association performance in a two tiers mmWave HetNet, where a terrestrial network is supported by a tier of UAV BSs (UBS). In specific, using tools from stochastic geometry we provide tractable expressions for the association probability with each tier in addition to expression for coverage hole probability taking into account the users’ reception sensitivity. Monte Carlo simulations are provided to validate the accuracy of analytical formulas, and it is shown that the average-sense association strategy is a special case of the proposed method.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126775094","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900784
Meltem Civas, O. Akan
In this study, we investigate the nanomaterial-based approach for developing practical molecular communication transmitters (MC-Txs) for the Internet of Bio-Nano Things (IoBNT) applications, which are expected to be unconventional in many aspects. In particular, we focus on the most pressing challenges for MC-Tx architectures, namely controlling information molecule release and molecule replenishment, together with other aspects, selective molecule release and molecule leakage mitigation. We discuss promising nanomaterials and also identify potential challenges and research directions.
{"title":"Molecular Communication Transmitter Architectures for the Internet of Bio-Nano Things","authors":"Meltem Civas, O. Akan","doi":"10.1109/BalkanCom55633.2022.9900784","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900784","url":null,"abstract":"In this study, we investigate the nanomaterial-based approach for developing practical molecular communication transmitters (MC-Txs) for the Internet of Bio-Nano Things (IoBNT) applications, which are expected to be unconventional in many aspects. In particular, we focus on the most pressing challenges for MC-Tx architectures, namely controlling information molecule release and molecule replenishment, together with other aspects, selective molecule release and molecule leakage mitigation. We discuss promising nanomaterials and also identify potential challenges and research directions.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"38 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114100939","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}
Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900607
Blaž Bertalanič, G. Morano, Gregor Cerar
While the Global Positioning System (GPS) provides high accuracy it places a significant strain on the device’s battery. In search of alternative techniques for outdoor localization, several approaches have been explored and recently Bluetooth Low Energy (BLE) is becoming a viable alternative to GPS for outdoor localization. Despite its popularity, access to open-source datasets for outdoor localization is limited. In this paper, we present a new openly available BLE fingerprint-based localization dataset that has been collected on LOG-a-TEC testedbed at the Jožef Stefan Institute, Ljubljana, Slovenia. The presented dataset was also used to develop a machine learning model that is capable of correctly classifying fingerprints with an average F1-score of 96.1%. We also provide insight into the importance of each node to the performance of the model. Although fingerprint-based localization is proving to be a robust alternative to GPS, we also show how changes in the environment can negatively impact the localization performance.
{"title":"LOG-a-TEC Testbed outdoor localization using BLE beacons","authors":"Blaž Bertalanič, G. Morano, Gregor Cerar","doi":"10.1109/BalkanCom55633.2022.9900607","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900607","url":null,"abstract":"While the Global Positioning System (GPS) provides high accuracy it places a significant strain on the device’s battery. In search of alternative techniques for outdoor localization, several approaches have been explored and recently Bluetooth Low Energy (BLE) is becoming a viable alternative to GPS for outdoor localization. Despite its popularity, access to open-source datasets for outdoor localization is limited. In this paper, we present a new openly available BLE fingerprint-based localization dataset that has been collected on LOG-a-TEC testedbed at the Jožef Stefan Institute, Ljubljana, Slovenia. The presented dataset was also used to develop a machine learning model that is capable of correctly classifying fingerprints with an average F1-score of 96.1%. We also provide insight into the importance of each node to the performance of the model. Although fingerprint-based localization is proving to be a robust alternative to GPS, we also show how changes in the environment can negatively impact the localization performance.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123912877","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：