Pub Date : 2019-06-04DOI: 10.1109/ICL-GNSS.2019.8752942
R. Imam, M. Pini, G. Marucco, F. Dominici, F. Dovis
Signals transmitted by Global Navigation Satellite Systems can be exploited as signals of opportunity for remote sensing applications. Satellites can be seen as spread sources of electromagnetic radiation, whose signals reflected back from ground can be processed to detect and monitor geophysical properties of the Earths surface. In the past years, several experiments of GNSS-based passive radars have been demonstrated successfully, mainly from piloted aircraft. Then, the proliferation of small UAVs enabled new applications where GNSS-based passive radars can provide useful geospatial information for environmental monitoring. Thanks to the availability of commercial Radio Frequency front ends and the enhanced processing capabilities of embedded platforms, it is possible to develop GNSS-based passive radars at moderated cost. These can be mounted on Unmanned Aerial Vehicles, and be used to support the sensing of environmental parameters. This paper presents the results of an experimental campaign based on the use of a UAV for GNSS reflectometry, tailored to the detection of the presence of water on ground after floods. The work is part of wider project, which intends to develop solutions to support rescuers and decision makers to manage operations after natural disasters, through the integration and modelling of geospatial data coming from multiple sources.
{"title":"Data from GNSS-Based Passive Radar to Support Flood Monitoring Operations","authors":"R. Imam, M. Pini, G. Marucco, F. Dominici, F. Dovis","doi":"10.1109/ICL-GNSS.2019.8752942","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752942","url":null,"abstract":"Signals transmitted by Global Navigation Satellite Systems can be exploited as signals of opportunity for remote sensing applications. Satellites can be seen as spread sources of electromagnetic radiation, whose signals reflected back from ground can be processed to detect and monitor geophysical properties of the Earths surface. In the past years, several experiments of GNSS-based passive radars have been demonstrated successfully, mainly from piloted aircraft. Then, the proliferation of small UAVs enabled new applications where GNSS-based passive radars can provide useful geospatial information for environmental monitoring. Thanks to the availability of commercial Radio Frequency front ends and the enhanced processing capabilities of embedded platforms, it is possible to develop GNSS-based passive radars at moderated cost. These can be mounted on Unmanned Aerial Vehicles, and be used to support the sensing of environmental parameters. This paper presents the results of an experimental campaign based on the use of a UAV for GNSS reflectometry, tailored to the detection of the presence of water on ground after floods. The work is part of wider project, which intends to develop solutions to support rescuers and decision makers to manage operations after natural disasters, through the integration and modelling of geospatial data coming from multiple sources.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116523083","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 : 2019-06-04DOI: 10.1109/ICL-GNSS.2019.8752853
Maximilian Stahlke, Sebastian Kram, Thorbjoern Mumme, J. Seitz
Automatic recognition of production tasks is a key aspect of an industrial Internet-of-things (IOT)environment. Often, the positions the tasks are executed at are of additional importance for process supervision and quality assurance. The complex structure of typical industrial environments including equipment, furniture and production objects leads to problems in obtaining the line-of-sight (LOS)connection necessary for precise localization with many RF-based systems. In this contribution, a method to obtain position estimates at a restricted set of points-of-interest via a machine-learning approach is proposed. The method is based on feature extraction on channel impulse responses (CIRs)of a Ultra-Wideband (UWB)radio system. It produces promising results in realistic scenarios, while the amount of data needed is small enough to enable retraining the database in a small amount of time. Additionally, the approach does not require calibration or synchronization of the UWB system and therefore could also be deployed in an existing system without additional configuration.
{"title":"Discrete Positioning Using UWB Channel Impulse Responses and Machine Learning","authors":"Maximilian Stahlke, Sebastian Kram, Thorbjoern Mumme, J. Seitz","doi":"10.1109/ICL-GNSS.2019.8752853","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752853","url":null,"abstract":"Automatic recognition of production tasks is a key aspect of an industrial Internet-of-things (IOT)environment. Often, the positions the tasks are executed at are of additional importance for process supervision and quality assurance. The complex structure of typical industrial environments including equipment, furniture and production objects leads to problems in obtaining the line-of-sight (LOS)connection necessary for precise localization with many RF-based systems. In this contribution, a method to obtain position estimates at a restricted set of points-of-interest via a machine-learning approach is proposed. The method is based on feature extraction on channel impulse responses (CIRs)of a Ultra-Wideband (UWB)radio system. It produces promising results in realistic scenarios, while the amount of data needed is small enough to enable retraining the database in a small amount of time. Additionally, the approach does not require calibration or synchronization of the UWB system and therefore could also be deployed in an existing system without additional configuration.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122271121","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752794
M. Schmidhammer, C. Gentner, B. Siebler
This paper presents a localization approach which aims to detect and localize discrete mobile scatterers. Therefore, a network of spatially distributed transmitting and receiving nodes is used. The localization problem is formulated as a non-linear optimization problem and corresponding performance bounds for the positioning error are provided. To solve the optimization problem, an iterative non-linear least squares approach is used, following the algorithm of Levenberg and Marquard. The proposed localization approach is evaluated based on wideband measurement data. It is shown, that the localization of mobile scatterers can be achieved. A further evaluation reveals a strong dependence of the localization performance on the preceding link level parameter estimation. Particularly sparse networks are shown to be sensitive to rich multipath environments.
{"title":"Localization of Discrete Mobile Scatterers in Vehicular Environments Using Delay Estimates","authors":"M. Schmidhammer, C. Gentner, B. Siebler","doi":"10.1109/ICL-GNSS.2019.8752794","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752794","url":null,"abstract":"This paper presents a localization approach which aims to detect and localize discrete mobile scatterers. Therefore, a network of spatially distributed transmitting and receiving nodes is used. The localization problem is formulated as a non-linear optimization problem and corresponding performance bounds for the positioning error are provided. To solve the optimization problem, an iterative non-linear least squares approach is used, following the algorithm of Levenberg and Marquard. The proposed localization approach is evaluated based on wideband measurement data. It is shown, that the localization of mobile scatterers can be achieved. A further evaluation reveals a strong dependence of the localization performance on the preceding link level parameter estimation. Particularly sparse networks are shown to be sensitive to rich multipath environments.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122956142","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752725
Jaakko Pihlajasalo, H. Leppäkoski, Saara Kuismanen, S. Ali-Löytty, R. Piché
Clock offset predictions along with satellite orbit predictions are used in self-assisted GNSS to reduce the Time-to-First-Fix of a satellite positioning device. This paper compares three methods for predicting GNSS satellite clock offsets: polynomial regression, Kalman filtering and support vector machines (SVM). The regression polynomial and support vector machine model are trained from past offsets. The Kalman filter uses past offsets to estimate the clock offset coefficients. In tests with GPS and GLONASS data, it is found that all three methods significantly improve the clock predictions relative to extrapolation with the basic clock model of the last obtained broadcast ephemeris (BE). In particular, the 68% quantile of 7 day clock offset errors of GPS satellites was reduced by 66% with polynomial regression, 69% with Kalman filtering and 56% with SVM on average.
{"title":"Methods for Long-Term GNSS Clock Offset Prediction","authors":"Jaakko Pihlajasalo, H. Leppäkoski, Saara Kuismanen, S. Ali-Löytty, R. Piché","doi":"10.1109/ICL-GNSS.2019.8752725","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752725","url":null,"abstract":"Clock offset predictions along with satellite orbit predictions are used in self-assisted GNSS to reduce the Time-to-First-Fix of a satellite positioning device. This paper compares three methods for predicting GNSS satellite clock offsets: polynomial regression, Kalman filtering and support vector machines (SVM). The regression polynomial and support vector machine model are trained from past offsets. The Kalman filter uses past offsets to estimate the clock offset coefficients. In tests with GPS and GLONASS data, it is found that all three methods significantly improve the clock predictions relative to extrapolation with the basic clock model of the last obtained broadcast ephemeris (BE). In particular, the 68% quantile of 7 day clock offset errors of GPS satellites was reduced by 66% with polynomial regression, 69% with Kalman filtering and 56% with SVM on average.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131159497","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752751
M. Gamba, E. Falletti
Adaptive notch filters in general, and frequency lock loop-equivalent adaptive notch filters in particular, have been shown to be an effective solution to counteract jamming signals. Much effort has been spent at analyzing their adaptive capability, while detection approaches in charge of activating/deactivating the filter have not been properly addressed. This paper presents two new detection strategies, namely discriminator-based and output-input power ratio-based, suitable to be applied to FLL-equivalent ANFs. The performance evaluation for several interference-to-noise ratio conditions demostrates their suitability to be combined with such kind of filters and their effectiveness in mitigating jamming signals.
{"title":"Performance Comparison of FLL Adaptive Notch Filters to Counter GNSS Jamming","authors":"M. Gamba, E. Falletti","doi":"10.1109/ICL-GNSS.2019.8752751","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752751","url":null,"abstract":"Adaptive notch filters in general, and frequency lock loop-equivalent adaptive notch filters in particular, have been shown to be an effective solution to counteract jamming signals. Much effort has been spent at analyzing their adaptive capability, while detection approaches in charge of activating/deactivating the filter have not been properly addressed. This paper presents two new detection strategies, namely discriminator-based and output-input power ratio-based, suitable to be applied to FLL-equivalent ANFs. The performance evaluation for several interference-to-noise ratio conditions demostrates their suitability to be combined with such kind of filters and their effectiveness in mitigating jamming signals.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123739686","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752840
J. R. V. D. Merwe, A. Rügamer, Alejandro Fernández-Dans Goicoechea, W. Felber
Spatial processing methods that utilize an array of antennas can be used to detect spoofing signals e.g. due to their typical, common spatial origin. A multi-antenna snapshot receiver that utilizes multi-channel processing is used to estimate the beamforming steering vector to each acquired satellite in a constellation. A detector based on steering vector correlation is presented, analyzed and tested. The detection performance is evaluated using a laboratory setup for spoofing, whereas the false detection rate is evaluated using an open-sky recording with an antenna array. The detector has shown good performance to detect spoofing signals in these controlled spoofing scenarios.
{"title":"Blind Spoofing Detection Using a Multi-Antenna Snapshot Receiver","authors":"J. R. V. D. Merwe, A. Rügamer, Alejandro Fernández-Dans Goicoechea, W. Felber","doi":"10.1109/ICL-GNSS.2019.8752840","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752840","url":null,"abstract":"Spatial processing methods that utilize an array of antennas can be used to detect spoofing signals e.g. due to their typical, common spatial origin. A multi-antenna snapshot receiver that utilizes multi-channel processing is used to estimate the beamforming steering vector to each acquired satellite in a constellation. A detector based on steering vector correlation is presented, analyzed and tested. The detection performance is evaluated using a laboratory setup for spoofing, whereas the false detection rate is evaluated using an open-sky recording with an antenna array. The detector has shown good performance to detect spoofing signals in these controlled spoofing scenarios.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121803496","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752944
Ruben Morales Ferre, Philipp Richter, A. Fuente, E. Lohan
Our paper focuses on the detection and direction finding of jamming signals in Global Navigation Satellite System (GNSS)bands. A methodology for in-lab validation for three selected jammer detection algorithms and two selected jammer direction finding algorithms is presented and measurement-based results, for nine combinations of GNSS and jamming signals, are shown. Both chirp jammers and amplitude-modulated single-tone jammers are considered in our in-lab validation process. The algorithm selection was done based on literature studies. Power-based detectors and direction finding algorithms are considered in this paper. It is shown that the considered detectors have similar performance and good detection probabilities for Jammer-to-Signal ratio (JSR)above −10 dB and that the Minimum Variance Distortionless Response (MVDR)beamformer can estimate quite accurately the jammer's Angle of Arrival (AoA)with JSR above 10 dB.
{"title":"In-lab validation of jammer detection and direction finding algorithms for GNSS","authors":"Ruben Morales Ferre, Philipp Richter, A. Fuente, E. Lohan","doi":"10.1109/ICL-GNSS.2019.8752944","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752944","url":null,"abstract":"Our paper focuses on the detection and direction finding of jamming signals in Global Navigation Satellite System (GNSS)bands. A methodology for in-lab validation for three selected jammer detection algorithms and two selected jammer direction finding algorithms is presented and measurement-based results, for nine combinations of GNSS and jamming signals, are shown. Both chirp jammers and amplitude-modulated single-tone jammers are considered in our in-lab validation process. The algorithm selection was done based on literature studies. Power-based detectors and direction finding algorithms are considered in this paper. It is shown that the considered detectors have similar performance and good detection probabilities for Jammer-to-Signal ratio (JSR)above −10 dB and that the Minimum Variance Distortionless Response (MVDR)beamformer can estimate quite accurately the jammer's Angle of Arrival (AoA)with JSR above 10 dB.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122684252","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752948
A. Hashemi, S. Thombre, G. Ferrara, M. Z. H. Bhuiyan, M. Pattinson
One of the major use cases of GNSS signals is precise time keeping but introduction of interference signals has threatened the reliability of such a functionality. Therefore, it is necessary to identify signal types most threatening to GNSS and adopt solutions as they evolve. We studied the performance of a timing-grade GNSS receiver in presence of interference signals. We tested the robustness of the receiver against different classes of signals which were captured in real world and identified as most threatening interference to GNSS by the EU Horizon 2020 research project STRIKE3. We showed that the quality of the time solution provided by the receiver degrades in their presence. Through statistical analysis we characterized the degradation of the solution in case of different classes of interference signals.
{"title":"STRIKE3-Case Study for Standardized Testing of Timing-Grade GNSS Receivers Against Real-World Interference Threats","authors":"A. Hashemi, S. Thombre, G. Ferrara, M. Z. H. Bhuiyan, M. Pattinson","doi":"10.1109/ICL-GNSS.2019.8752948","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752948","url":null,"abstract":"One of the major use cases of GNSS signals is precise time keeping but introduction of interference signals has threatened the reliability of such a functionality. Therefore, it is necessary to identify signal types most threatening to GNSS and adopt solutions as they evolve. We studied the performance of a timing-grade GNSS receiver in presence of interference signals. We tested the robustness of the receiver against different classes of signals which were captured in real world and identified as most threatening interference to GNSS by the EU Horizon 2020 research project STRIKE3. We showed that the quality of the time solution provided by the receiver degrades in their presence. Through statistical analysis we characterized the degradation of the solution in case of different classes of interference signals.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127209697","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752764
S. Bezzateev, N. Voloshina, K. Zhidanov, A. Ometov
Worldwide changes in climate and increasing pollution level are tremendously affecting the need for environmental monitoring solutions. Recent activities in wireless sensor networks (WSNs) together with Cloud computing paradigm brought an entirely new perspective on monitoring as part of the Industrial Internet of Things (IIoT). However, most of the systems developed today are still facing lack of flexibility and security. This work presents the results of prototyping the IIoT wireless environmental monitoring system from both hardware and software sides. The developed mechanisms enable connectivity in infrastructure and mesh-like modes, where each sensor could act as relay allowing for improved node-failure resistance and scalability. Next, the authentication mechanism is proposed to enable transparent migration of any node between different network segments while keeping the overall operation secure. Finally, proof of the concept prototype deployment in real-life conditions shows the potential of metropolitan-scale utilization of the developed system.
{"title":"Secure Environmental Monitoring for Industrial Internet of Things: from Framework to Live Implementation","authors":"S. Bezzateev, N. Voloshina, K. Zhidanov, A. Ometov","doi":"10.1109/ICL-GNSS.2019.8752764","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752764","url":null,"abstract":"Worldwide changes in climate and increasing pollution level are tremendously affecting the need for environmental monitoring solutions. Recent activities in wireless sensor networks (WSNs) together with Cloud computing paradigm brought an entirely new perspective on monitoring as part of the Industrial Internet of Things (IIoT). However, most of the systems developed today are still facing lack of flexibility and security. This work presents the results of prototyping the IIoT wireless environmental monitoring system from both hardware and software sides. The developed mechanisms enable connectivity in infrastructure and mesh-like modes, where each sensor could act as relay allowing for improved node-failure resistance and scalability. Next, the authentication mechanism is proposed to enable transparent migration of any node between different network segments while keeping the overall operation secure. Finally, proof of the concept prototype deployment in real-life conditions shows the potential of metropolitan-scale utilization of the developed system.","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127225405","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 : 2019-06-01DOI: 10.1109/ICL-GNSS.2019.8752635
Caner Savas, F. Dovis
The aim of this paper is to analyze the design of support vector machine (SVM)algorithm that belongs to the class of supervised machine learning algorithms for phase scintillation detection and to discuss the performance comparison of linear and Gaussian kernel implementations by considering the design parameter's effects. The algorithm processes the phase scintillation indices computed for GPS L1 signals through the designed linear and Gaussian kernel SVM models. The study is based on the real GNSS signals which are affected by phase scintillations, collected at South African Antarctic research base (SANAE IV).
{"title":"Comparative Performance Study of Linear and Gaussian Kernel SVM Implementations for Phase Scintillation Detection","authors":"Caner Savas, F. Dovis","doi":"10.1109/ICL-GNSS.2019.8752635","DOIUrl":"https://doi.org/10.1109/ICL-GNSS.2019.8752635","url":null,"abstract":"The aim of this paper is to analyze the design of support vector machine (SVM)algorithm that belongs to the class of supervised machine learning algorithms for phase scintillation detection and to discuss the performance comparison of linear and Gaussian kernel implementations by considering the design parameter's effects. The algorithm processes the phase scintillation indices computed for GPS L1 signals through the designed linear and Gaussian kernel SVM models. The study is based on the real GNSS signals which are affected by phase scintillations, collected at South African Antarctic research base (SANAE IV).","PeriodicalId":119581,"journal":{"name":"2019 International Conference on Localization and GNSS (ICL-GNSS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126966165","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：