Pub Date : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9021084
Yujung Roh, Seungjae Jung, Joonhyuk Kang
An unmanned aerial vehicle (UAV)-aided network is becoming a promising application for the future wireless communication due to the flexible deployment and dominant line-of-sight channel. In this paper, we consider the UAV is operated as a cooperative jammer to enhance the physical layer security of the ground legitimated nodes in the presence of an eavesdropper (Eve). Furthermore, we assume that the UAV has imperfect information on the locations of the receiver and Eve due to GPS jamming and covert operation of Eve, respectively. With these uncertainties of the nodes' locations, we formulate a robust joint optimization problem of the UAV's jamming power and trajectory to maximize the average secrecy rate. To handle the non-convexity of the optimization problem, we propose an iterative suboptimal algorithm based on the block coordinate descent method. Simulation results present that the proposed algorithm has outstanding performance in terms of physical layer security compared to other benchmark methods.
{"title":"Cooperative UAV Jammer for Enhancing Physical Layer Security: Robust Design for Jamming Power and Trajectory","authors":"Yujung Roh, Seungjae Jung, Joonhyuk Kang","doi":"10.1109/MILCOM47813.2019.9021084","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9021084","url":null,"abstract":"An unmanned aerial vehicle (UAV)-aided network is becoming a promising application for the future wireless communication due to the flexible deployment and dominant line-of-sight channel. In this paper, we consider the UAV is operated as a cooperative jammer to enhance the physical layer security of the ground legitimated nodes in the presence of an eavesdropper (Eve). Furthermore, we assume that the UAV has imperfect information on the locations of the receiver and Eve due to GPS jamming and covert operation of Eve, respectively. With these uncertainties of the nodes' locations, we formulate a robust joint optimization problem of the UAV's jamming power and trajectory to maximize the average secrecy rate. To handle the non-convexity of the optimization problem, we propose an iterative suboptimal algorithm based on the block coordinate descent method. Simulation results present that the proposed algorithm has outstanding performance in terms of physical layer security compared to other benchmark methods.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127228598","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020807
D. Adesina, J. Bassey, Lijun Qian
In future wireless systems, intelligent capabilities are of utmost importance. To efficiently utilize resources, communication systems require knowledge of the prevalent situation in a frequency band through learning. To learn appropriately, it is critical for practitioners to select the right parameters in building learning models, use the appropriate algorithms and performance evaluation methods. In this paper, we evaluate the performance of some deep learning models compared to other machine learning methods, explore the different scenarios in which deep learning can be used for radio frequency (RF) monitoring, and evaluate performance in the various scenarios. Our work looks at the best practices and procedures for developing intelligent RF Learning. Specifically, we analysed over-the-air RF dataset collected from a USRP-based testbed to identify the number of interfering devices as a case study. From the obtained results, we discuss how Signal-to-Noise Ratio (SNR) selection for training affects the model performance as it relates to practical implementation of Deep Learning in communications systems.
{"title":"Practical Radio Frequency Learning for Future Wireless Communication Systems","authors":"D. Adesina, J. Bassey, Lijun Qian","doi":"10.1109/MILCOM47813.2019.9020807","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020807","url":null,"abstract":"In future wireless systems, intelligent capabilities are of utmost importance. To efficiently utilize resources, communication systems require knowledge of the prevalent situation in a frequency band through learning. To learn appropriately, it is critical for practitioners to select the right parameters in building learning models, use the appropriate algorithms and performance evaluation methods. In this paper, we evaluate the performance of some deep learning models compared to other machine learning methods, explore the different scenarios in which deep learning can be used for radio frequency (RF) monitoring, and evaluate performance in the various scenarios. Our work looks at the best practices and procedures for developing intelligent RF Learning. Specifically, we analysed over-the-air RF dataset collected from a USRP-based testbed to identify the number of interfering devices as a case study. From the obtained results, we discuss how Signal-to-Noise Ratio (SNR) selection for training affects the model performance as it relates to practical implementation of Deep Learning in communications systems.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130386886","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020774
Ioannis Agadakos, Gabriela F. Cretu-Ciocarlie, Bogdan Copos, M. Emmi, Jemin George, Nandi O. Leslie, James R. Michaelis
Continued advances in IoT technology have prompted new investigation into its usage for military operations, both to augment and complement existing military sensing assets and support next-generation artificial intelligence and machine learning systems. Under the emerging Internet of Battlefield Things (IoBT) paradigm, current operational conditions necessitate the development of novel security techniques, centered on establishment of trust for individual assets and supporting resilience of broader systems. To advance current IoBT efforts, a collection of prior-developed cybersecurity techniques is reviewed for applicability to conditions presented by IoBT operational environments (e.g., diverse asset ownership, degraded networking infrastructure, adversary activities) through use of supporting case study examples. The research techniques covered focus on two themes: (1) Supporting trust assessment for known/unknown IoT assets; (2) ensuring continued trust of known IoT assets and IoBT systems.
{"title":"Application of Trust Assessment Techniques to IoBT Systems","authors":"Ioannis Agadakos, Gabriela F. Cretu-Ciocarlie, Bogdan Copos, M. Emmi, Jemin George, Nandi O. Leslie, James R. Michaelis","doi":"10.1109/MILCOM47813.2019.9020774","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020774","url":null,"abstract":"Continued advances in IoT technology have prompted new investigation into its usage for military operations, both to augment and complement existing military sensing assets and support next-generation artificial intelligence and machine learning systems. Under the emerging Internet of Battlefield Things (IoBT) paradigm, current operational conditions necessitate the development of novel security techniques, centered on establishment of trust for individual assets and supporting resilience of broader systems. To advance current IoBT efforts, a collection of prior-developed cybersecurity techniques is reviewed for applicability to conditions presented by IoBT operational environments (e.g., diverse asset ownership, degraded networking infrastructure, adversary activities) through use of supporting case study examples. The research techniques covered focus on two themes: (1) Supporting trust assessment for known/unknown IoT assets; (2) ensuring continued trust of known IoT assets and IoBT systems.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128026837","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020777
Jongdeog Lee, Suk Min Hwang, T. Abdelzaher, K. Marcus, K. Chan
In an age of data overload and scenarios that require fast-distributed situational understanding, we envision that content summarization services will become a critical capability of underlying networked systems. Previous work, called InfoMax, proposed such a service in the transport layer to minimize semantic redundancy of transmitted content and maximize information coverage. Here, we extended this work in three ways. First, we adapted summarization to the needs of streaming content and developed a corresponding publish-subscribe protocol (called Pub/Sub-Sum) with on-the-fly extractive summarization of continuous content streams (as opposed to extractive summarization of fixed data sets). Next, we supported many-to-many communication between publishers and subscribers, as opposed to InfoMax, which was designed to disseminate data from one producer to multiple consumers. Lastly, we introduce a new type of congestion handling mechanism that adaptively controls the level of summarization by considering available network bandwidth. We conducted experiments for functionality and performance on Mininet (a network emulator) and on a real device testbed. Evaluation results indicated that the new protocol summarizes data appropriately to available network resources, offering an improved compromise between received data quality and resource consumption.
{"title":"Pub/Sub-Sum: A Content Summarization Pub/Sub Protocol for Information-Centric Networks","authors":"Jongdeog Lee, Suk Min Hwang, T. Abdelzaher, K. Marcus, K. Chan","doi":"10.1109/MILCOM47813.2019.9020777","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020777","url":null,"abstract":"In an age of data overload and scenarios that require fast-distributed situational understanding, we envision that content summarization services will become a critical capability of underlying networked systems. Previous work, called InfoMax, proposed such a service in the transport layer to minimize semantic redundancy of transmitted content and maximize information coverage. Here, we extended this work in three ways. First, we adapted summarization to the needs of streaming content and developed a corresponding publish-subscribe protocol (called Pub/Sub-Sum) with on-the-fly extractive summarization of continuous content streams (as opposed to extractive summarization of fixed data sets). Next, we supported many-to-many communication between publishers and subscribers, as opposed to InfoMax, which was designed to disseminate data from one producer to multiple consumers. Lastly, we introduce a new type of congestion handling mechanism that adaptively controls the level of summarization by considering available network bandwidth. We conducted experiments for functionality and performance on Mininet (a network emulator) and on a real device testbed. Evaluation results indicated that the new protocol summarizes data appropriately to available network resources, offering an improved compromise between received data quality and resource consumption.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133700100","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020863
R. Lopes, Pooja Hanavadi Balaraju, Adrián Toribio Silva, Paulo H. L. Rettore, P. Sevenich
In this paper, we discuss experimental results testing a hierarchy of queues controlling the user data-flow over a VHF network with ever-changing data rates (up to 9.6 kbps). We challenged our solution creating three patterns of ever-changing data rates using a stochastic model to include the element of chance (randomness) that can be reproduced for quantitative comparisons. We discuss numbers showing that our queuing mechanism adapts its behavior (i.e. shaping the user data-flow) to the network conditions using feedback from the radio buffer (reactive) and from the routing protocol (proactive). Thus, our hybrid solution monitors the radio buffer occupancy to pause the transmission when a threshold is crossed, and proactively adds an inter-packet interval (IPI). The IPI varies as a function of the link data rate (computed by a tactical router), current network usage, packet loss and latency. The experimental results show three queues (for messages, IP packets and the radio buffer) complementing each other to handle different network conditions while transmitting a message that surely overflows the radio buffer (four times the buffer size).
{"title":"Experiments with a Queuing Mechanism over Ever-Changing Data Rates in a VHF Network","authors":"R. Lopes, Pooja Hanavadi Balaraju, Adrián Toribio Silva, Paulo H. L. Rettore, P. Sevenich","doi":"10.1109/MILCOM47813.2019.9020863","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020863","url":null,"abstract":"In this paper, we discuss experimental results testing a hierarchy of queues controlling the user data-flow over a VHF network with ever-changing data rates (up to 9.6 kbps). We challenged our solution creating three patterns of ever-changing data rates using a stochastic model to include the element of chance (randomness) that can be reproduced for quantitative comparisons. We discuss numbers showing that our queuing mechanism adapts its behavior (i.e. shaping the user data-flow) to the network conditions using feedback from the radio buffer (reactive) and from the routing protocol (proactive). Thus, our hybrid solution monitors the radio buffer occupancy to pause the transmission when a threshold is crossed, and proactively adds an inter-packet interval (IPI). The IPI varies as a function of the link data rate (computed by a tactical router), current network usage, packet loss and latency. The experimental results show three queues (for messages, IP packets and the radio buffer) complementing each other to handle different network conditions while transmitting a message that surely overflows the radio buffer (four times the buffer size).","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134352252","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020935
Srijita Mukherjee, K. Namuduri
Flocking and deconfliction are two important functional aspects of swarms. Flocking in Unmanned Aerial Vehicle (UAV) swarms refers to UAVs flying in a pattern whereas deconfliction refers to collision avoidance. Flocking enables communications and information sharing among neighbors. This paper presents a distributed model and establishes the necessary control laws for joint flocking and deconfliction. The proposed model and control laws are developed based on the principles of consensus-building and social potential functions. Experiments with promising results are presented to support the derived model.
{"title":"Joint Flocking and Deconfliction in Unmanned Aerial Vehicle Swarms","authors":"Srijita Mukherjee, K. Namuduri","doi":"10.1109/MILCOM47813.2019.9020935","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020935","url":null,"abstract":"Flocking and deconfliction are two important functional aspects of swarms. Flocking in Unmanned Aerial Vehicle (UAV) swarms refers to UAVs flying in a pattern whereas deconfliction refers to collision avoidance. Flocking enables communications and information sharing among neighbors. This paper presents a distributed model and establishes the necessary control laws for joint flocking and deconfliction. The proposed model and control laws are developed based on the principles of consensus-building and social potential functions. Experiments with promising results are presented to support the derived model.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133104536","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020977
Liangdong Deng, Yuzhou Feng, Dong Chen, N. Rishe
The Internet of Things (IoT) has been erupting the world widely over the decade. Smart home owners and smart building managers are increasingly deploying IoT devices to monitor and control their environments due to the rapid decline in the price of IoT devices. The network traffic data produced by these IoT devices are collected by Internet Service Providers (ISPs) and telecom providers, and often shared with third-parties to maintain and promote user services. Such network traffic data is considered “anonymous” if it is not associated with identifying device information, e.g., MAC address and DHCP negotiation. Extensive prior work has shown that IoT devices are vulnerable to multiple cyber attacks. However, people do not believe that these attacks can be launched successfully without the knowledge of what IoT devices are deployed in their houses. Our key insight is that the network traffic data is not anonymous: IoT devices have unique network traffic patterns, and they embedded detailed device information. To explore the severity and extent of this privacy threat, we design IoTSpot to identify the IoT devices using their “anonymous” network traffic data. We evaluate IoTSpot on publicly-available network traffic data from 3 homes. We find that IoTSpot is able to identify 19 IoT devices with F1 accuracy of 0.984. More importantly, our approach only requires very limited data for training, as few as 40 minutes. IoTSpot paves the way for operators of smart homes and smart buildings to monitor the functionality, security and privacy threat without requiring any additional devices.
{"title":"IoTSpot: Identifying the IoT Devices Using their Anonymous Network Traffic Data","authors":"Liangdong Deng, Yuzhou Feng, Dong Chen, N. Rishe","doi":"10.1109/MILCOM47813.2019.9020977","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020977","url":null,"abstract":"The Internet of Things (IoT) has been erupting the world widely over the decade. Smart home owners and smart building managers are increasingly deploying IoT devices to monitor and control their environments due to the rapid decline in the price of IoT devices. The network traffic data produced by these IoT devices are collected by Internet Service Providers (ISPs) and telecom providers, and often shared with third-parties to maintain and promote user services. Such network traffic data is considered “anonymous” if it is not associated with identifying device information, e.g., MAC address and DHCP negotiation. Extensive prior work has shown that IoT devices are vulnerable to multiple cyber attacks. However, people do not believe that these attacks can be launched successfully without the knowledge of what IoT devices are deployed in their houses. Our key insight is that the network traffic data is not anonymous: IoT devices have unique network traffic patterns, and they embedded detailed device information. To explore the severity and extent of this privacy threat, we design IoTSpot to identify the IoT devices using their “anonymous” network traffic data. We evaluate IoTSpot on publicly-available network traffic data from 3 homes. We find that IoTSpot is able to identify 19 IoT devices with F1 accuracy of 0.984. More importantly, our approach only requires very limited data for training, as few as 40 minutes. IoTSpot paves the way for operators of smart homes and smart buildings to monitor the functionality, security and privacy threat without requiring any additional devices.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131035577","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020736
Erick D. Buenrostro, Abel O. Gomez Rivera, Deepak K. Tosh, Jaime C. Acosta, L. Njilla
Military technology is ever-evolving to increase the safety and security of soldiers on the field while integrating Internet-of-Things solutions to improve operational efficiency in mission oriented tasks in the battlefield. Centralized communication technology is the traditional network model used for battlefields and is vulnerable to denial of service attacks, therefore suffers performance hazards. They also lead to a central point of failure, due to which, a flexible model that is mobile, resilient, and effective for different scenarios must be proposed. Blockchain offers a distributed platform that allows multiple nodes to update a distributed ledger in a tamper-resistant manner. The decentralized nature of this system suggests that it can be an effective tool for battlefields in securing data communication among Internet-of-Battlefield Things (IoBT). In this paper, we integrate a permissioned blockchain, namely Hyperledger Sawtooth, in IoBT context and evaluate its performance with the goal of determining whether it has the potential to serve the performance needs of IoBT environment. Using different testing parameters, the metric data would help in suggesting the best parameter set, network configuration and blockchain usability views in IoBT context. We show that a blockchain-integrated IoBT platform has heavy dependency on the characteristics of the underlying network such as topology, link bandwidth, jitter, and other communication configurations, that can be tuned up to achieve optimal performance.
{"title":"Evaluating Usability of Permissioned Blockchain for Internet-of-Battlefield Things Security","authors":"Erick D. Buenrostro, Abel O. Gomez Rivera, Deepak K. Tosh, Jaime C. Acosta, L. Njilla","doi":"10.1109/MILCOM47813.2019.9020736","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020736","url":null,"abstract":"Military technology is ever-evolving to increase the safety and security of soldiers on the field while integrating Internet-of-Things solutions to improve operational efficiency in mission oriented tasks in the battlefield. Centralized communication technology is the traditional network model used for battlefields and is vulnerable to denial of service attacks, therefore suffers performance hazards. They also lead to a central point of failure, due to which, a flexible model that is mobile, resilient, and effective for different scenarios must be proposed. Blockchain offers a distributed platform that allows multiple nodes to update a distributed ledger in a tamper-resistant manner. The decentralized nature of this system suggests that it can be an effective tool for battlefields in securing data communication among Internet-of-Battlefield Things (IoBT). In this paper, we integrate a permissioned blockchain, namely Hyperledger Sawtooth, in IoBT context and evaluate its performance with the goal of determining whether it has the potential to serve the performance needs of IoBT environment. Using different testing parameters, the metric data would help in suggesting the best parameter set, network configuration and blockchain usability views in IoBT context. We show that a blockchain-integrated IoBT platform has heavy dependency on the characteristics of the underlying network such as topology, link bandwidth, jitter, and other communication configurations, that can be tuned up to achieve optimal performance.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115086299","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020735
Inna Valieva, M. Björkman, J. Åkerberg, Mikael Ekström, I. Voitenko
In this paper the potential of improving channel utilization by signal modulation type classification based on machine learning algorithms has been studied. The classification has been performed between two popular digital modulations: BPSK and FSK in target application. Classification was based on three features available on a popular software defined radio transceiver AD9361: In-phase and quadrature components of the digital time domain signal and signal-to-noise ratio (SNR), measured as RSSI value. Data used for network training, validation and testing was generated by the Simulink model consisting mainly of modulator, transceiver AD9361 and AWGN to generate the signal with SNR ranging from 1 to 30 dB. Twenty-three supervised machine learning algorithms including K-nearest neighbor, Support Vector Machines, Decision Trees and Ensembles have been studied, evaluated and verified against the target application's requirements in terms of classification accuracy and speed. The highest average classification accuracy of 86.9% was achieved by Support Vector Machines with Fine Gaussian kernel, however with demonstrated classification speed of 790 objects per second it was considered unable to meet target application's real-time operation requirement of 2000 objects per second. Fine Decision Trees and Ensemble Boosted Trees have shown optimal performance in terms of both reaching classification speed of 1200000 objects per second and average classification accuracy of 86.0% and 86.3% respectively. Classification accuracy has been also studied as a function of SNR to determine the most accurate classifier for each SNR level. At the target application's demodulation threshold of 12 dB 87.0% classification accuracy has been observed for the Fine Decision Trees, 87.5% for both Fine Gaussian SVM and Coarse KNN. At SNR higher than 27 dB Fine Trees, Coarse KNN have reached 97.5% classification accuracy. The effects of data set size and number of classification features on classification speed and accuracy have been studied too.
本文研究了基于机器学习算法的信号调制类型分类提高信道利用率的潜力。分类之间进行了两种流行的数字调制:BPSK和FSK在目标应用。分类基于流行的软件定义无线电收发器AD9361的三个特征:数字时域信号的同相分量和正交分量以及以RSSI值测量的信噪比(SNR)。用于网络训练、验证和测试的数据由Simulink模型生成，该模型主要由调制器、收发器AD9361和AWGN组成，产生信噪比为1 ~ 30db的信号。针对目标应用在分类精度和速度方面的要求，研究、评估和验证了23种监督机器学习算法，包括k近邻、支持向量机、决策树和集成。采用细高斯核的支持向量机的平均分类准确率最高，达到86.9%，但其显示的分类速度为每秒790个对象，被认为无法满足目标应用每秒2000个对象的实时运行要求。Fine Decision Trees和Ensemble boosting Trees在分类速度达到每秒120万个对象、平均分类准确率分别达到86.0%和86.3%方面表现出了最优的性能。分类精度也作为信噪比的函数进行了研究，以确定每个信噪比水平下最准确的分类器。在目标应用程序的解调阈值为12 dB时，精细决策树的分类准确率为87.0%，精细高斯支持向量机和粗KNN的分类准确率均为87.5%。在信噪比高于27 dB Fine Trees的情况下，粗KNN的分类准确率达到97.5%。研究了数据集大小和分类特征数量对分类速度和准确率的影响。
{"title":"Multiple Machine Learning Algorithms Comparison for Modulation Type Classification for Efficient Cognitive Radio","authors":"Inna Valieva, M. Björkman, J. Åkerberg, Mikael Ekström, I. Voitenko","doi":"10.1109/MILCOM47813.2019.9020735","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020735","url":null,"abstract":"In this paper the potential of improving channel utilization by signal modulation type classification based on machine learning algorithms has been studied. The classification has been performed between two popular digital modulations: BPSK and FSK in target application. Classification was based on three features available on a popular software defined radio transceiver AD9361: In-phase and quadrature components of the digital time domain signal and signal-to-noise ratio (SNR), measured as RSSI value. Data used for network training, validation and testing was generated by the Simulink model consisting mainly of modulator, transceiver AD9361 and AWGN to generate the signal with SNR ranging from 1 to 30 dB. Twenty-three supervised machine learning algorithms including K-nearest neighbor, Support Vector Machines, Decision Trees and Ensembles have been studied, evaluated and verified against the target application's requirements in terms of classification accuracy and speed. The highest average classification accuracy of 86.9% was achieved by Support Vector Machines with Fine Gaussian kernel, however with demonstrated classification speed of 790 objects per second it was considered unable to meet target application's real-time operation requirement of 2000 objects per second. Fine Decision Trees and Ensemble Boosted Trees have shown optimal performance in terms of both reaching classification speed of 1200000 objects per second and average classification accuracy of 86.0% and 86.3% respectively. Classification accuracy has been also studied as a function of SNR to determine the most accurate classifier for each SNR level. At the target application's demodulation threshold of 12 dB 87.0% classification accuracy has been observed for the Fine Decision Trees, 87.5% for both Fine Gaussian SVM and Coarse KNN. At SNR higher than 27 dB Fine Trees, Coarse KNN have reached 97.5% classification accuracy. The effects of data set size and number of classification features on classification speed and accuracy have been studied too.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122960316","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 : 2019-11-01DOI: 10.1109/MILCOM47813.2019.9020814
Sarah Brown, Tamsin Moye, Rob Hubertse, Cezar Glăvan
For the past decade, cyber security teams around the world have recognized the growing importance of sharing cyber security information. Data regarding recently discovered vulnerabilities, cyber threats, and cyber incident information has been recognized as vital for cyber security teams to stay resilient in the face of the ever-changing threat landscape. This paper introduces federated cyber incident management and cyber information sharing requirements for NATO and Nations and highlights the Cyber Information and Incident Coordination System (CIICS), developed in the Multinational Cyber Defence Capability Development (MN CD2) Smart Defence program, designed specifically to address such requirements.
{"title":"Towards Mature Federated Cyber Incident Management and Information Sharing Capabilities in NATO and NATO Nations","authors":"Sarah Brown, Tamsin Moye, Rob Hubertse, Cezar Glăvan","doi":"10.1109/MILCOM47813.2019.9020814","DOIUrl":"https://doi.org/10.1109/MILCOM47813.2019.9020814","url":null,"abstract":"For the past decade, cyber security teams around the world have recognized the growing importance of sharing cyber security information. Data regarding recently discovered vulnerabilities, cyber threats, and cyber incident information has been recognized as vital for cyber security teams to stay resilient in the face of the ever-changing threat landscape. This paper introduces federated cyber incident management and cyber information sharing requirements for NATO and Nations and highlights the Cyber Information and Incident Coordination System (CIICS), developed in the Multinational Cyber Defence Capability Development (MN CD2) Smart Defence program, designed specifically to address such requirements.","PeriodicalId":371812,"journal":{"name":"MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121932474","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：