Pub Date : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495978
Pavle Skocir, Katarina Mandaric, I. Kralj, Ivana Podnar Žarko, G. Jezic
Precision agriculture uses new technologies to improve crop yields and increase profitability for farmers while reducing the inputs required to grow crops, such as land, water, fertilizers, pesticides, etc. Environmental microclimate data (e.g., air and soil temperature or moisture) are needed as inputs to precision agriculture applications so that adequate decisions and agrotechnical measures can be applied in the fields. Most of the existing precision agriculture solutions for environmental and crop monitoring use locally deployed sensors as the main data source. Since the deployment and maintenance of physical sensors in the fields potentially involves significant costs and human effort, open-access data sources may be an effective complement to environmental data from deployed sensors, but the question remains whether open-access data sources are comparable to locally deployed sensors in terms of accuracy. This paper analyzes the correlation between open environmental data sources provided by the Copernicus ERA5-Land and Agri4Cast data sets, and data collected by locally deployed sensors to determine the extent to which open data sources can be used in precision agriculture.
{"title":"Analysis of Open Access Data Sources for Application in Precision Agriculture","authors":"Pavle Skocir, Katarina Mandaric, I. Kralj, Ivana Podnar Žarko, G. Jezic","doi":"10.23919/ConTEL52528.2021.9495978","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495978","url":null,"abstract":"Precision agriculture uses new technologies to improve crop yields and increase profitability for farmers while reducing the inputs required to grow crops, such as land, water, fertilizers, pesticides, etc. Environmental microclimate data (e.g., air and soil temperature or moisture) are needed as inputs to precision agriculture applications so that adequate decisions and agrotechnical measures can be applied in the fields. Most of the existing precision agriculture solutions for environmental and crop monitoring use locally deployed sensors as the main data source. Since the deployment and maintenance of physical sensors in the fields potentially involves significant costs and human effort, open-access data sources may be an effective complement to environmental data from deployed sensors, but the question remains whether open-access data sources are comparable to locally deployed sensors in terms of accuracy. This paper analyzes the correlation between open environmental data sources provided by the Copernicus ERA5-Land and Agri4Cast data sets, and data collected by locally deployed sensors to determine the extent to which open data sources can be used in precision agriculture.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"49 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123567029","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495973
Tim Jeršič, Žana Juvan, Klemen Pecnik
This paper includes a quick overview of different distance learning solutions, learning management systems, videoconferencing platforms with emphasis on bundles of equipment for video production and videoconferencing usage. Different types of integration between learning management systems and videoconferencing platforms are presented, backed up with solutions used at the University of Ljubljana. Additionally, several types of equipment bundles are proposed as suitable solutions to fulfil as many scenarios as possible with special emphasis on flexibility and compatibility. At the end automation aspects and further development and usage are discussed.
{"title":"Video production systems for videoconferencing and distance learning solutions","authors":"Tim Jeršič, Žana Juvan, Klemen Pecnik","doi":"10.23919/ConTEL52528.2021.9495973","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495973","url":null,"abstract":"This paper includes a quick overview of different distance learning solutions, learning management systems, videoconferencing platforms with emphasis on bundles of equipment for video production and videoconferencing usage. Different types of integration between learning management systems and videoconferencing platforms are presented, backed up with solutions used at the University of Ljubljana. Additionally, several types of equipment bundles are proposed as suitable solutions to fulfil as many scenarios as possible with special emphasis on flexibility and compatibility. At the end automation aspects and further development and usage are discussed.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116285547","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495993
Tomislav Stefanec, M. Kusek
Different IoT application layer protocols offer different benefits, but they also have their set of drawbacks. Energy consumption has become an extremely important factor as more and more battery-powered and resource-constrained IoT devices are deployed worldwide. In this paper, measurements of energy consumption and network traffic profiles of the most commonly used IoT application layer protocols (HTTP, HTTP2, CoAP, MQTT, and AMQP) are presented. The measurements of all these protocols are performed on real hardware, for different packet sizes and different QoS levels, depending on what the protocols support.
{"title":"Comparing energy consumption of application layer protocols on IoT devices","authors":"Tomislav Stefanec, M. Kusek","doi":"10.23919/ConTEL52528.2021.9495993","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495993","url":null,"abstract":"Different IoT application layer protocols offer different benefits, but they also have their set of drawbacks. Energy consumption has become an extremely important factor as more and more battery-powered and resource-constrained IoT devices are deployed worldwide. In this paper, measurements of energy consumption and network traffic profiles of the most commonly used IoT application layer protocols (HTTP, HTTP2, CoAP, MQTT, and AMQP) are presented. The measurements of all these protocols are performed on real hardware, for different packet sizes and different QoS levels, depending on what the protocols support.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"15 Suppl 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114859539","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 : 2021-06-30DOI: 10.23919/contel52528.2021.9495958
{"title":"Keynote 3: Quality of Experience in the Era of Immersive Networked Multimedia Services","authors":"","doi":"10.23919/contel52528.2021.9495958","DOIUrl":"https://doi.org/10.23919/contel52528.2021.9495958","url":null,"abstract":"","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127194561","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495969
Jurica Goricanec, Nadir Kapetanović, Ivo Vatavuk, Ivan Hrabar, Goran Vasiljević, G. Gledec, Dario Stuhne, S. Bogdan, M. Orsag, T. Petrović, N. Mišković, Z. Kovačić, Antonia Kurtela, J. Bolotin, V. Kozul, N. Glavic, N. Antolovic, M. Anić, B. Kozina, Marko Cukon
This paper presents the overview and preliminary results of the HEKTOR - Heterogeneous Autonomous Robotic System in Viticulture and Mariculture project. HEKTOR is divided into two main parts, each dealing with specific scenarios in viticulture and mariculture. The robots used in the project and each specific scenario considered are presented. In viticulture, this includes vineyard surveillance, spraying and bud rubbing using an all-terrain mobile manipulator and unmanned aerial vehicle (UAV). In mariculture, scenarios include coordinated monitoring of fish net cages from below the surface and from the air, using the UAV, an unmanned surface vehicle (USV) and a remotely operated underwater vehicle (ROV).
{"title":"Heterogeneous autonomous robotic system in viticulture and mariculture - project overview","authors":"Jurica Goricanec, Nadir Kapetanović, Ivo Vatavuk, Ivan Hrabar, Goran Vasiljević, G. Gledec, Dario Stuhne, S. Bogdan, M. Orsag, T. Petrović, N. Mišković, Z. Kovačić, Antonia Kurtela, J. Bolotin, V. Kozul, N. Glavic, N. Antolovic, M. Anić, B. Kozina, Marko Cukon","doi":"10.23919/ConTEL52528.2021.9495969","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495969","url":null,"abstract":"This paper presents the overview and preliminary results of the HEKTOR - Heterogeneous Autonomous Robotic System in Viticulture and Mariculture project. HEKTOR is divided into two main parts, each dealing with specific scenarios in viticulture and mariculture. The robots used in the project and each specific scenario considered are presented. In viticulture, this includes vineyard surveillance, spraying and bud rubbing using an all-terrain mobile manipulator and unmanned aerial vehicle (UAV). In mariculture, scenarios include coordinated monitoring of fish net cages from below the surface and from the air, using the UAV, an unmanned surface vehicle (USV) and a remotely operated underwater vehicle (ROV).","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128911461","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495976
Matko Zrnic, Josip Spisic, Anita Pejković, K. Grgic, J. Balen, D. Zagar
Measuring temperature and humidity is probably the most interesting parameter set for smart agriculture. Using simple hardware and low-power long-range communication is a great way to archive weather monitoring and collecting data from the field. In this paper, a low-cost weather station based on IoT LoRa communication is proposed. This simple solution for monitoring the two weather parameters - temperature and humidity of a particular location continuously and uploading the data to the web server using the commercially available gateway.
{"title":"Low-Cost Wireless Sensor Node for Smart Agriculture Applications","authors":"Matko Zrnic, Josip Spisic, Anita Pejković, K. Grgic, J. Balen, D. Zagar","doi":"10.23919/ConTEL52528.2021.9495976","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495976","url":null,"abstract":"Measuring temperature and humidity is probably the most interesting parameter set for smart agriculture. Using simple hardware and low-power long-range communication is a great way to archive weather monitoring and collecting data from the field. In this paper, a low-cost weather station based on IoT LoRa communication is proposed. This simple solution for monitoring the two weather parameters - temperature and humidity of a particular location continuously and uploading the data to the web server using the commercially available gateway.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123102850","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495968
Moritz Tockner, H. Brachtendorf, M. Steiger
This paper presents a method for the design of lattice wave digital filters (LWDFs) with an approximately linear phase response. A recently developed algorithm for the design of approximately linear phase allpass filters was utilized in combination with the LWDF structure, to synthesize frequency selective filters with a high phase response flatness. An iterative optimization method to generate such an LWDF for a given set of frequency response constraints was implemented and integrated into an open source LWDF design toolbox to allow an outreach to a broader audience. Additionally, the generated floating point LWDF coefficients can be quantized as multiplier-free signed digits by solving a nonlinear optimization problem. The design toolbox finds the coefficient representation requiring the minimum number of additions and/or subtractions, while still satisfying a given set of frequency response constraints. The results show the effectiveness of the filter design method compared to standard designs such as Butterworth, Tschebyscheff or Cauer and they highlight the differences to another existing linear phase method of the toolbox. A significant improvement can be seen in a comparison between the signed digit quantization compared to simple coefficient rounding.
{"title":"Design of Wave Digital Filters with the TU Delft Toolbox","authors":"Moritz Tockner, H. Brachtendorf, M. Steiger","doi":"10.23919/ConTEL52528.2021.9495968","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495968","url":null,"abstract":"This paper presents a method for the design of lattice wave digital filters (LWDFs) with an approximately linear phase response. A recently developed algorithm for the design of approximately linear phase allpass filters was utilized in combination with the LWDF structure, to synthesize frequency selective filters with a high phase response flatness. An iterative optimization method to generate such an LWDF for a given set of frequency response constraints was implemented and integrated into an open source LWDF design toolbox to allow an outreach to a broader audience. Additionally, the generated floating point LWDF coefficients can be quantized as multiplier-free signed digits by solving a nonlinear optimization problem. The design toolbox finds the coefficient representation requiring the minimum number of additions and/or subtractions, while still satisfying a given set of frequency response constraints. The results show the effectiveness of the filter design method compared to standard designs such as Butterworth, Tschebyscheff or Cauer and they highlight the differences to another existing linear phase method of the toolbox. A significant improvement can be seen in a comparison between the signed digit quantization compared to simple coefficient rounding.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125502285","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495964
Hrvoje Vdovic, Jurica Babic, V. Podobnik
The amount of data generated by vehicles has increased in recent years. Automotive manufacturers employ data processing and analysis to gain insights from the data they collect from vehicles. Contextually enriching vehicle-generated data with information describing location, weather and traffic is a way to generate even more insights into driver behaviour profiling and transportation sustainability. As the contextually enriched automotive data is usually stored in big data storage platforms, a middleware solution is needed to provide an abstraction layer for the stored data. Application programming interfaces (APIs) are commonly used as a bridge between the data consumers and the collected data. This paper describes one such API for advanced analytics of contextually enriched automotive data. The collection, contextual enrichment and data model of the data offered by the API is shown, along with the APIs architecture and available functionalities. To show the usability of the API, two use cases from the automotive domain are demonstrated: (i) contextually enriched automotive data visualization; and (ii) eco-efficient driving pattern evaluation.
{"title":"An Application Programming Interface for Advanced Analytics of Contextually Enriched Automotive Data","authors":"Hrvoje Vdovic, Jurica Babic, V. Podobnik","doi":"10.23919/ConTEL52528.2021.9495964","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495964","url":null,"abstract":"The amount of data generated by vehicles has increased in recent years. Automotive manufacturers employ data processing and analysis to gain insights from the data they collect from vehicles. Contextually enriching vehicle-generated data with information describing location, weather and traffic is a way to generate even more insights into driver behaviour profiling and transportation sustainability. As the contextually enriched automotive data is usually stored in big data storage platforms, a middleware solution is needed to provide an abstraction layer for the stored data. Application programming interfaces (APIs) are commonly used as a bridge between the data consumers and the collected data. This paper describes one such API for advanced analytics of contextually enriched automotive data. The collection, contextual enrichment and data model of the data offered by the API is shown, along with the APIs architecture and available functionalities. To show the usability of the API, two use cases from the automotive domain are demonstrated: (i) contextually enriched automotive data visualization; and (ii) eco-efficient driving pattern evaluation.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134171675","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495971
Irena Orsolic, Michael Seufert
With Over-The-Top traffic being extensively encrypted end-to-end, network operators typically lack insight into the performance of these services, as perceived by the end users. Yet, such an insight is essential for employing QoE-aware network management and potential alleviation of problems that may originate in the network. There is a clear interest from network operators to find ways to estimate service performance in terms of Key Performance Indicators (KPIs) and Quality of Experience (QoE). Over the last years, machine-learning–based (ML) models have proven to be capable of inferring QoE/KPIs from patterns in encrypted network traffic. The particular focus has mostly been on adaptive video streaming services, considering their share of the global network traffic. Those ML–based models have typically been trained and tested on a single dataset collected under specific conditions only. Going beyond related work on the topic of QoE/KPI estimation, we collected two large datasets related to YouTube streaming using the same setup at two different locations in Europe and analyzed the extent to which the differences in network characteristics and location specifics influence the performance of such models. This is of interest, as applicability of the models across diverse networks would significantly reduce the needed extensiveness of data collection typically required for ML–based approaches. In this paper, we compare models trained and tested on a single dataset/location (network-specific), models trained on the merged dataset (general), and models trained on one dataset and tested on the other dataset (cross-tested). The results show that the performance of general models is comparable to that of network-specific models, but cross-tests exhibit a considerable reduction in performance. With the aim to understand and improve cross-network applicability of the models in the future, the paper also provides an investigation of underlying reasons for the performance degradation.
{"title":"On Machine Learning Based Video QoE Estimation Across Different Networks","authors":"Irena Orsolic, Michael Seufert","doi":"10.23919/ConTEL52528.2021.9495971","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495971","url":null,"abstract":"With Over-The-Top traffic being extensively encrypted end-to-end, network operators typically lack insight into the performance of these services, as perceived by the end users. Yet, such an insight is essential for employing QoE-aware network management and potential alleviation of problems that may originate in the network. There is a clear interest from network operators to find ways to estimate service performance in terms of Key Performance Indicators (KPIs) and Quality of Experience (QoE). Over the last years, machine-learning–based (ML) models have proven to be capable of inferring QoE/KPIs from patterns in encrypted network traffic. The particular focus has mostly been on adaptive video streaming services, considering their share of the global network traffic. Those ML–based models have typically been trained and tested on a single dataset collected under specific conditions only. Going beyond related work on the topic of QoE/KPI estimation, we collected two large datasets related to YouTube streaming using the same setup at two different locations in Europe and analyzed the extent to which the differences in network characteristics and location specifics influence the performance of such models. This is of interest, as applicability of the models across diverse networks would significantly reduce the needed extensiveness of data collection typically required for ML–based approaches. In this paper, we compare models trained and tested on a single dataset/location (network-specific), models trained on the merged dataset (general), and models trained on one dataset and tested on the other dataset (cross-tested). The results show that the performance of general models is comparable to that of network-specific models, but cross-tests exhibit a considerable reduction in performance. With the aim to understand and improve cross-network applicability of the models in the future, the paper also provides an investigation of underlying reasons for the performance degradation.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114994411","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 : 2021-06-30DOI: 10.23919/ConTEL52528.2021.9495981
Denis Pejić, Visnja Krizanovic, K. Grgic
Predictive maintenance is used to predict system failures using deep learning algorithms and IoT sensors. However, IoT sensors and deep learning algorithms are susceptible to attacks, which at the same time poses a serious threat as far as car engine IoT sensors are concerned. This paper tends to research the consequence of false data injection on IoT automotive engine sensors, which can result in disastrous results. Also, the following deep learning algorithms are used in this paper to detect attacks and intrusions on automotive engine IoT sensors: RNN (Recurrent Neural Networks), LSTM (Long Short Term Memory Networks), GAN (Generative Adversarial Networks) and a new developed algorithm SPNN (Sequential Probability Neural Networks). The new SPNN algorithm was the fastest in detecting and preventing attacks/intrusions on automotive engine IoT sensors when it came to continuous attack, but the GAN algorithm was the fastest in detecting and preventing attacks/intrusions on automotive engine IoT sensors when it came to temporary attack.
{"title":"Detection of attacks and intrusions on automotive engine IoT sensors","authors":"Denis Pejić, Visnja Krizanovic, K. Grgic","doi":"10.23919/ConTEL52528.2021.9495981","DOIUrl":"https://doi.org/10.23919/ConTEL52528.2021.9495981","url":null,"abstract":"Predictive maintenance is used to predict system failures using deep learning algorithms and IoT sensors. However, IoT sensors and deep learning algorithms are susceptible to attacks, which at the same time poses a serious threat as far as car engine IoT sensors are concerned. This paper tends to research the consequence of false data injection on IoT automotive engine sensors, which can result in disastrous results. Also, the following deep learning algorithms are used in this paper to detect attacks and intrusions on automotive engine IoT sensors: RNN (Recurrent Neural Networks), LSTM (Long Short Term Memory Networks), GAN (Generative Adversarial Networks) and a new developed algorithm SPNN (Sequential Probability Neural Networks). The new SPNN algorithm was the fastest in detecting and preventing attacks/intrusions on automotive engine IoT sensors when it came to continuous attack, but the GAN algorithm was the fastest in detecting and preventing attacks/intrusions on automotive engine IoT sensors when it came to temporary attack.","PeriodicalId":269755,"journal":{"name":"2021 16th International Conference on Telecommunications (ConTEL)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129478652","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：