Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012990
Peng Lin, Omer Haliloglu
The Distributed Multiple Input Multiple Output (D-MIMO) network comprises a very large number of distributed Radio Units (RUs), which simultaneously serve multiple User Equipments (UEs) over the same time/frequency resources based on directly measured channel characteristics. Existing research had shown that Coherent Joint Transmission (CJT) in D-MIMO networks could obtain better performance compared to the traditional small cell and cellular massive MIMO network through multiple RUs. Nonetheless, reliable access links become more important at high frequency bands and mobility scenarios that needs robust precoding schemes to utilize the full performance of a D-MIMO network. In this paper, Physical layer (L1) mobility is incorporated in D-MIMO network operating at mmWave. Then centralized and distributed precoding methods are considered to evaluate the spectral efficiencies of mobile UEs with different serving RU subset update periodicities. Moreover, Non-Coherent Joint Transmission (NCJT) among multiple RUs is explored. Through the simulation results, it is shown that serving RU subset (cluster) update and NCJT substantially impact the performance. During UE mobility, frequent serving subset update is necessary for CJT, however, not critical for NCJT.
{"title":"Layer-1 Mobility in Distributed MIMO with Non-Coherent Joint Transmission","authors":"Peng Lin, Omer Haliloglu","doi":"10.1109/VTC2022-Fall57202.2022.10012990","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012990","url":null,"abstract":"The Distributed Multiple Input Multiple Output (D-MIMO) network comprises a very large number of distributed Radio Units (RUs), which simultaneously serve multiple User Equipments (UEs) over the same time/frequency resources based on directly measured channel characteristics. Existing research had shown that Coherent Joint Transmission (CJT) in D-MIMO networks could obtain better performance compared to the traditional small cell and cellular massive MIMO network through multiple RUs. Nonetheless, reliable access links become more important at high frequency bands and mobility scenarios that needs robust precoding schemes to utilize the full performance of a D-MIMO network. In this paper, Physical layer (L1) mobility is incorporated in D-MIMO network operating at mmWave. Then centralized and distributed precoding methods are considered to evaluate the spectral efficiencies of mobile UEs with different serving RU subset update periodicities. Moreover, Non-Coherent Joint Transmission (NCJT) among multiple RUs is explored. Through the simulation results, it is shown that serving RU subset (cluster) update and NCJT substantially impact the performance. During UE mobility, frequent serving subset update is necessary for CJT, however, not critical for NCJT.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124440383","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}
Terahertz (THz) communication with ultra-wide available spectrum is a promising technique that can achieve the stringent requirement of high data rate in the next-generation wireless networks, yet its severe propagation attenuation significantly hinders its implementation in practice. Finding beam directions for a large-scale antenna array to effectively overcome severe propagation attenuation of THz signals is a pressing need. This paper proposes a novel approach of federated deep reinforcement learning (FDRL) to swiftly perform THz-beam search for multiple base stations (BSs) coordinated by an edge server in a cellular network. All the BSs conduct deep deterministic policy gradient (DDPG)-based DRL to obtain THz beamforming policy with limited channel state information (CSI). They update their DDPG models with hidden information in order to mitigate inter-cell interference. We demonstrate that the cell network can achieve higher throughput as more THz CSI and hidden neurons of DDPG are adopted. We also show that FDRL with partial model update is able to nearly achieve the same performance of FDRL with full model update, which indicates an effective means to reduce communication load between the edge server and the BSs by partial model uploading. Moreover, the proposed FDRL outperforms conventional non-learning-based and existing non-FDRL benchmark optimization methods.
{"title":"Federated Deep Reinforcement Learning for THz-Beam Search with Limited CSI","authors":"Po-chun Hsu, Li-Hsiang Shen, Chun-Hung Liu, Kai-Ten Feng","doi":"10.1109/VTC2022-Fall57202.2022.10012887","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012887","url":null,"abstract":"Terahertz (THz) communication with ultra-wide available spectrum is a promising technique that can achieve the stringent requirement of high data rate in the next-generation wireless networks, yet its severe propagation attenuation significantly hinders its implementation in practice. Finding beam directions for a large-scale antenna array to effectively overcome severe propagation attenuation of THz signals is a pressing need. This paper proposes a novel approach of federated deep reinforcement learning (FDRL) to swiftly perform THz-beam search for multiple base stations (BSs) coordinated by an edge server in a cellular network. All the BSs conduct deep deterministic policy gradient (DDPG)-based DRL to obtain THz beamforming policy with limited channel state information (CSI). They update their DDPG models with hidden information in order to mitigate inter-cell interference. We demonstrate that the cell network can achieve higher throughput as more THz CSI and hidden neurons of DDPG are adopted. We also show that FDRL with partial model update is able to nearly achieve the same performance of FDRL with full model update, which indicates an effective means to reduce communication load between the edge server and the BSs by partial model uploading. Moreover, the proposed FDRL outperforms conventional non-learning-based and existing non-FDRL benchmark optimization methods.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125087967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012974
Sandesh Rao Mattu, A. Chockalingam
Traditionally, channel estimation in orthogonal time frequency space (OTFS) is carried out in the delay-Doppler (DD) domain by placing pilot symbols surrounded by guard bins in the DD grid. This results in reduced spectral efficiency as the guard bins do not carry information. In the absence of guard bins, there is leakage from pilot symbols to data symbols and vice versa. Therefore, in this paper, we consider an interleaved pilot (IP) placement scheme with a lattice-type arrangement (which does not have guard bins) and propose a deep learning architecture using recurrent neural networks (referred to as IPNet) for efficient estimation of DD domain channel state information. The proposed IPNet is trained to overcome the effects of leakage from data symbols and provide channel estimates with good accuracy (e.g., the proposed scheme achieves a normalized mean square error of about 0.01 at a pilot SNR of 25 dB). Our simulation results also show that the proposed IPNet architecture achieves good bit error performance while being spectrally efficient. For example, the proposed scheme uses 12 overhead bins (12 pilot bins and no guard bins) for channel estimation in a considered frame while the embedded pilot scheme uses 25 overhead bins (1 pilot bin and 24 guard bins).
{"title":"Learning based Delay-Doppler Channel Estimation with Interleaved Pilots in OTFS","authors":"Sandesh Rao Mattu, A. Chockalingam","doi":"10.1109/VTC2022-Fall57202.2022.10012974","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012974","url":null,"abstract":"Traditionally, channel estimation in orthogonal time frequency space (OTFS) is carried out in the delay-Doppler (DD) domain by placing pilot symbols surrounded by guard bins in the DD grid. This results in reduced spectral efficiency as the guard bins do not carry information. In the absence of guard bins, there is leakage from pilot symbols to data symbols and vice versa. Therefore, in this paper, we consider an interleaved pilot (IP) placement scheme with a lattice-type arrangement (which does not have guard bins) and propose a deep learning architecture using recurrent neural networks (referred to as IPNet) for efficient estimation of DD domain channel state information. The proposed IPNet is trained to overcome the effects of leakage from data symbols and provide channel estimates with good accuracy (e.g., the proposed scheme achieves a normalized mean square error of about 0.01 at a pilot SNR of 25 dB). Our simulation results also show that the proposed IPNet architecture achieves good bit error performance while being spectrally efficient. For example, the proposed scheme uses 12 overhead bins (12 pilot bins and no guard bins) for channel estimation in a considered frame while the embedded pilot scheme uses 25 overhead bins (1 pilot bin and 24 guard bins).","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117023494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012805
K. K. Tiwari, G. Caire
We present mean communication rate loss (MCRL) values due to the beam cusping phenomenon inherent to grid of beams based wireless systems, which are widely used/proposed in millimeter-wave and sub-THz bands. We consider array antenna elements with non-zero aperture and axisymmetric radiation pattern with a certain directivity, unlike the ideal isotropic antenna elements widely considered in theoretical papers on array processing and RF beamforming. The array antenna elements have a half power beam width of ninety degrees in this work which is typical of commonly used microstrip patch antenna elements. We perform Monte Carlo numerical experiments to obtain MCRL values for different spatial dimensions of multiple input multiple output (MIMO) systems, different angular fields of view, and different beamforming codebook sizes. We show that increasing the beam grid density beyond a certain threshold does not help and therefore a certain cusping loss is unavoidable even for continuous beam steering with directive antenna elements. Further, we also show the quantitative impact on the MCRL values as the axisymmetric radiation pattern directivity of the modelled antenna element is increased.
{"title":"Rate Loss due to Beam Cusping in Grid of Beams","authors":"K. K. Tiwari, G. Caire","doi":"10.1109/VTC2022-Fall57202.2022.10012805","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012805","url":null,"abstract":"We present mean communication rate loss (MCRL) values due to the beam cusping phenomenon inherent to grid of beams based wireless systems, which are widely used/proposed in millimeter-wave and sub-THz bands. We consider array antenna elements with non-zero aperture and axisymmetric radiation pattern with a certain directivity, unlike the ideal isotropic antenna elements widely considered in theoretical papers on array processing and RF beamforming. The array antenna elements have a half power beam width of ninety degrees in this work which is typical of commonly used microstrip patch antenna elements. We perform Monte Carlo numerical experiments to obtain MCRL values for different spatial dimensions of multiple input multiple output (MIMO) systems, different angular fields of view, and different beamforming codebook sizes. We show that increasing the beam grid density beyond a certain threshold does not help and therefore a certain cusping loss is unavoidable even for continuous beam steering with directive antenna elements. Further, we also show the quantitative impact on the MCRL values as the axisymmetric radiation pattern directivity of the modelled antenna element is increased.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129565023","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}
Satellite communication is one primary structure of the future wireless systems. Many corporations and academic institutions are committed to this research, e.g., StarLink. Their aim is to construct a constellation of satellite networks covering the whole world. Thanks to this design, our mobile devices can connect to the Internet anywhere in the world without being restricted by the coverage area of base stations. However, given that the constellation of satellites around the Earth is a system that varies in time, algorithms must adapt to the dynamic topology. To solve the problem, in this paper we investigate how to send data from the base station to the target satellite with minimal delay. We systematically formulate the transmission limitations, uplink, and downlink transmission delay. With well defined limits and delays on space-terrestrial transmissions, we can set rewards and punishments by mathematical analysis to simulate the agent in deep reinforcement learning (DRL), which can explore all choices in the system and optimize the routing algorithm. Finally, the simulation results corroborate a fully functional space-terrestrial network constellation to simulate the actual situation.
{"title":"Deep Reinforcement Learning-Based Routing for Space-Terrestrial Networks","authors":"Kai-Chu Tsai, Ting-Jui Yao, Pingmu Huang, Cheng-Sen Huang, Zhu Han, Li-Chun Wang","doi":"10.1109/VTC2022-Fall57202.2022.10013028","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10013028","url":null,"abstract":"Satellite communication is one primary structure of the future wireless systems. Many corporations and academic institutions are committed to this research, e.g., StarLink. Their aim is to construct a constellation of satellite networks covering the whole world. Thanks to this design, our mobile devices can connect to the Internet anywhere in the world without being restricted by the coverage area of base stations. However, given that the constellation of satellites around the Earth is a system that varies in time, algorithms must adapt to the dynamic topology. To solve the problem, in this paper we investigate how to send data from the base station to the target satellite with minimal delay. We systematically formulate the transmission limitations, uplink, and downlink transmission delay. With well defined limits and delays on space-terrestrial transmissions, we can set rewards and punishments by mathematical analysis to simulate the agent in deep reinforcement learning (DRL), which can explore all choices in the system and optimize the routing algorithm. Finally, the simulation results corroborate a fully functional space-terrestrial network constellation to simulate the actual situation.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128351670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012870
Kazuya Inoue, Keita Imaizumi, K. Ichige, Tatsuya Nagao, Takahiro Hayashi
We propose a novel path loss estimation method based on deep learning with some newly defined system parameters and images. Estimating the radio wave propagation environment is one of the key techniques for indoor/outdoor high-speed wireless communication. The radio wave propagation environment is basically a multipath environment, and path loss characteristics should be estimated under various environments. The authors have already proposed path loss estimation methods based on machine learning and spatial image data. The purpose of this paper is to further enhance the path loss estimation accuracy by appropriately selecting the input parameters and the CNN/FNN model structure.
{"title":"Learning-Based Path Loss Estimation Using Multiple Spatial Data and System Parameters","authors":"Kazuya Inoue, Keita Imaizumi, K. Ichige, Tatsuya Nagao, Takahiro Hayashi","doi":"10.1109/VTC2022-Fall57202.2022.10012870","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012870","url":null,"abstract":"We propose a novel path loss estimation method based on deep learning with some newly defined system parameters and images. Estimating the radio wave propagation environment is one of the key techniques for indoor/outdoor high-speed wireless communication. The radio wave propagation environment is basically a multipath environment, and path loss characteristics should be estimated under various environments. The authors have already proposed path loss estimation methods based on machine learning and spatial image data. The purpose of this paper is to further enhance the path loss estimation accuracy by appropriately selecting the input parameters and the CNN/FNN model structure.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128675025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012773
Dajiang Suo, S. Sarma
A roadside adversary who holds compromised vehicle-to-everything (V2X) credentials can easily spoof vehicle identities and broadcast fabricated messages that jeopardize the maneuvers of surrounding vehicles. Previous work on the security of ad hoc networks suggests the use of a side channel for two parties to exchange digital certificates to prevent impersonation and man-in-the-middle attacks on the main wireless channel. This paper presents a two-factor authentication scheme by leveraging line-of-sight (LOS) communication as the side channel to impede roadside adversaries who try to impersonate legitimate moving vehicles in the non-line-of-sight (NLOS) channel. To gain the trust of other traffic participants, a vehicle that has received a challenge message broadcast by infrastructure through the main (NLOS) wireless channel must send back its response through the LOS channel to demonstrate it is indeed a vehicle in traffic. The directional property and visual confirmation of the LOS channel and the fact that vehicle movement is ascertained based on physics make it extremely difficult for the roadside adversary to finish the response-challenge process without being detected. Experimental results demonstrate the feasibility of using the proposed scheme for authenticating low-speed vehicles. However, for authenticating vehicles traveling at high speed, transmitting the response message containing certificates through the LOS channel can create a communication bottleneck for the authentication process, although implicit certificates can be adopted to reduce the total authentication time. Future work will explore the alternative format of the challenge-response protocol and the potential technologies for realizing LOS communication to reduce the communication bottleneck.
{"title":"A Two-Factor Authentication Scheme for Moving Connected Vehicles","authors":"Dajiang Suo, S. Sarma","doi":"10.1109/VTC2022-Fall57202.2022.10012773","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012773","url":null,"abstract":"A roadside adversary who holds compromised vehicle-to-everything (V2X) credentials can easily spoof vehicle identities and broadcast fabricated messages that jeopardize the maneuvers of surrounding vehicles. Previous work on the security of ad hoc networks suggests the use of a side channel for two parties to exchange digital certificates to prevent impersonation and man-in-the-middle attacks on the main wireless channel. This paper presents a two-factor authentication scheme by leveraging line-of-sight (LOS) communication as the side channel to impede roadside adversaries who try to impersonate legitimate moving vehicles in the non-line-of-sight (NLOS) channel. To gain the trust of other traffic participants, a vehicle that has received a challenge message broadcast by infrastructure through the main (NLOS) wireless channel must send back its response through the LOS channel to demonstrate it is indeed a vehicle in traffic. The directional property and visual confirmation of the LOS channel and the fact that vehicle movement is ascertained based on physics make it extremely difficult for the roadside adversary to finish the response-challenge process without being detected. Experimental results demonstrate the feasibility of using the proposed scheme for authenticating low-speed vehicles. However, for authenticating vehicles traveling at high speed, transmitting the response message containing certificates through the LOS channel can create a communication bottleneck for the authentication process, although implicit certificates can be adopted to reduce the total authentication time. Future work will explore the alternative format of the challenge-response protocol and the potential technologies for realizing LOS communication to reduce the communication bottleneck.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128733803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012979
Jin-Ling Hu, Li Zhao, Yuan Feng, Yinghao Liu, Mingjun Gao
C-V2X (Cellular Vehicle-to-Everything) is the vital enabling technology of Intelligent Connected Vehicle (ICV) and Intelligent Transportation System (ITS). Standardization of LTE (Long Term Evolution)-V2X has been completed in Third Generation Partnership Project (3GPP), but the congestion control mechanism is not specified and up to implementation. This paper mainly focuses on the congestion control mechanism in LTE-V2X. The measurements and adjustable transmitting parameters related to the congestion control mechanism is introduced. Then the implementation of congestion control mechanism in LTE-V2X is proposed. The field test results are presented to verify the effectiveness with system performance metrics.
C-V2X (Cellular Vehicle-to- everything)是智能网联汽车(ICV)和智能交通系统(ITS)的重要使能技术。在第三代合作伙伴计划(3GPP)中，LTE (Long Term Evolution)-V2X的标准化已经完成，但拥塞控制机制尚未明确，有待实施。本文主要研究LTE-V2X中的拥塞控制机制。介绍了与拥塞控制机制相关的测量和可调传输参数。然后提出了LTE-V2X中拥塞控制机制的实现。给出了现场测试结果，以验证系统性能指标的有效性。
{"title":"Research, Implementation and Practice of Congestion Control Mechanism in LTE-V2X","authors":"Jin-Ling Hu, Li Zhao, Yuan Feng, Yinghao Liu, Mingjun Gao","doi":"10.1109/VTC2022-Fall57202.2022.10012979","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012979","url":null,"abstract":"C-V2X (Cellular Vehicle-to-Everything) is the vital enabling technology of Intelligent Connected Vehicle (ICV) and Intelligent Transportation System (ITS). Standardization of LTE (Long Term Evolution)-V2X has been completed in Third Generation Partnership Project (3GPP), but the congestion control mechanism is not specified and up to implementation. This paper mainly focuses on the congestion control mechanism in LTE-V2X. The measurements and adjustable transmitting parameters related to the congestion control mechanism is introduced. Then the implementation of congestion control mechanism in LTE-V2X is proposed. The field test results are presented to verify the effectiveness with system performance metrics.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129158525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012703
Jie Zhou, Yang Peng, Guan Gui, Yun Lin, B. Adebisi, H. Gačanin, H. Sari
Radio frequency fingerprint (RFF) is regarded as a key technology in physical layer security in various wireless communications systems. Deep learning (DL) has achieved great success in the field of signal identification, particularly in improving performance and eliminating manual feature extraction. However, the training cost of these DL-based methods is usually large. It is unwise to retrain the network with whole data when it comes to new data. Therefore, we propose a novel RFF identification method based on incremental learning (IL), which uses continuous data stream to update the identification model, constantly. Experimental results show that with the increase of increment times, the accuracy of the proposed IL-based method gradually approaches the performance of joint training, and finally reaches 96.79%, which is only 1.9% lower than the performance upper bound.
{"title":"A Novel Radio Frequency Fingerprint Identification Method Using Incremental Learning","authors":"Jie Zhou, Yang Peng, Guan Gui, Yun Lin, B. Adebisi, H. Gačanin, H. Sari","doi":"10.1109/VTC2022-Fall57202.2022.10012703","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012703","url":null,"abstract":"Radio frequency fingerprint (RFF) is regarded as a key technology in physical layer security in various wireless communications systems. Deep learning (DL) has achieved great success in the field of signal identification, particularly in improving performance and eliminating manual feature extraction. However, the training cost of these DL-based methods is usually large. It is unwise to retrain the network with whole data when it comes to new data. Therefore, we propose a novel RFF identification method based on incremental learning (IL), which uses continuous data stream to update the identification model, constantly. Experimental results show that with the increase of increment times, the accuracy of the proposed IL-based method gradually approaches the performance of joint training, and finally reaches 96.79%, which is only 1.9% lower than the performance upper bound.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"242 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124665928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012794
Hongzhi Liu, Chengyao Hao, Yang Peng, Yu Wang, T. Ohtsuki, Guan Gui
With the increasing popularity of Internet of things (IoT), the emergence of many IoT devices has led to security vulnerabilities. The classification of wireless signals is very important for secure communications. Most of existing signal classification tasks only focus on single signal classification task, while ignoring the relationship between radio frequency fingerprinting identification (RFFI) and automatic modulation classification (AMC). To solve the multi-task classification problem, this paper designs a multi-task learning convolutional neural networks (MTL-CNN). Real-radio datasets are generated by Signal Hound VSG60A and collected by Signal Hound BB60C to solve the lack of RFF samples with numerous modulation types. Experimental results confirm that the MTL-CNN method can work well by using the generated dataset. The MTL network designed in this paper improves the accuracy of RFFI by 1xs% relative to the single-task learning (STL) network. The keras code is released at https://github.comLiuK1288/1hw-000.
{"title":"An Effective Radio Frequency Signal Classification Method Based on Multi-Task Learning Mechanism","authors":"Hongzhi Liu, Chengyao Hao, Yang Peng, Yu Wang, T. Ohtsuki, Guan Gui","doi":"10.1109/VTC2022-Fall57202.2022.10012794","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012794","url":null,"abstract":"With the increasing popularity of Internet of things (IoT), the emergence of many IoT devices has led to security vulnerabilities. The classification of wireless signals is very important for secure communications. Most of existing signal classification tasks only focus on single signal classification task, while ignoring the relationship between radio frequency fingerprinting identification (RFFI) and automatic modulation classification (AMC). To solve the multi-task classification problem, this paper designs a multi-task learning convolutional neural networks (MTL-CNN). Real-radio datasets are generated by Signal Hound VSG60A and collected by Signal Hound BB60C to solve the lack of RFF samples with numerous modulation types. Experimental results confirm that the MTL-CNN method can work well by using the generated dataset. The MTL network designed in this paper improves the accuracy of RFFI by 1xs% relative to the single-task learning (STL) network. The keras code is released at https://github.comLiuK1288/1hw-000.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124965490","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：