Pub Date : 2022-09-01DOI: 10.1109/VTC2022-Fall57202.2022.10012716
Chao Liu, Xue Fu, Yunlu Ge, Yu Wang, Yun Lin, Guan Gui, H. Sari
Specific emitter identification (SEI) is a promising physical layer authentication technique based on unintentionally hardware impairments of transmitters. These impairments are independent of the data’s content, so they are difficult to forge and analyze. Recently, most deep learning (DL) based SEI methods have been proposed, and have shown their great performance. However, these methods are big data-driven which means they have poor performance with limited training samples, and the vulnerability of neural networks to adversarial attacks is also a problem worth considering. In this paper, we propose an innovative few-shot SEI method based on class-reconstruction classification network and adversarial training (CRCN-AT) without the support of auxiliary dataset. Simulation results show that the proposed method achieves better identification performance and robustness in few-shot scenarios compared to traditional methods. The Pytorch code is released at https://github.comLIUC-000/CRCN-AT.
{"title":"A Robust Few-Shot SEI Method Using Class-Reconstruction and Adversarial Training","authors":"Chao Liu, Xue Fu, Yunlu Ge, Yu Wang, Yun Lin, Guan Gui, H. Sari","doi":"10.1109/VTC2022-Fall57202.2022.10012716","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012716","url":null,"abstract":"Specific emitter identification (SEI) is a promising physical layer authentication technique based on unintentionally hardware impairments of transmitters. These impairments are independent of the data’s content, so they are difficult to forge and analyze. Recently, most deep learning (DL) based SEI methods have been proposed, and have shown their great performance. However, these methods are big data-driven which means they have poor performance with limited training samples, and the vulnerability of neural networks to adversarial attacks is also a problem worth considering. In this paper, we propose an innovative few-shot SEI method based on class-reconstruction classification network and adversarial training (CRCN-AT) without the support of auxiliary dataset. Simulation results show that the proposed method achieves better identification performance and robustness in few-shot scenarios compared to traditional methods. The Pytorch code is released at https://github.comLIUC-000/CRCN-AT.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"51 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":"132417037","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-Fall57202.2022.10012949
Sreelakshmi Pazhoor, Jesy Pachat, Nujoom Sageer Karat, V. Joseph, P. Deepthi, B. Rajan
Vehicular ad hoc network (VANET), is a developing platform with massive data demands for infotainment services in recent years. Index Coded NOMA (IC-NOMA) is a spectral efficient transmission method that can be used in VANETs. IC-NOMA applies the concepts of non-orthogonal multiple access (NOMA) over the index coded data to increase spectrum and power efficiency. In NOMA, far user does not get access to the near user data, while near user can successfully decode far user data. Therefore, the IC-NOMA demands a novel design of index code for improved bandwidth efficiency. This work considers the design of index code for NOMA when the user demands in VANET follows the data distribution of one-sided symmetric neighboring consecutive side information single unicast index coding problem (SNC-SUICP). For this setup, we develop an optimal closed form index coding (IC) solution which can bring in additional bandwidth savings through NOMA. The improved performance of the proposed IC-NOMA transmission scheme when compared with one-sided SNC-SUICP in terms of bandwidth efficiency is demonstrated.
车载自组网(Vehicular ad hoc network, VANET)是近年来发展起来的具有海量数据需求的信息娱乐服务平台。索引编码NOMA (IC-NOMA)是一种适用于VANETs的高效光谱传输方法。IC-NOMA在索引编码数据上应用了非正交多址(NOMA)的概念，以提高频谱和功率效率。在NOMA中，远用户无法访问近用户数据，而近用户可以成功解码远用户数据。因此，IC-NOMA需要一种新的索引码设计来提高带宽效率。本文考虑了VANET中用户需求遵循单侧对称相邻连续侧信息数据分布的NOMA索引编码设计问题(SNC-SUICP)。对于这种设置，我们开发了一个最佳的封闭形式索引编码(IC)解决方案，它可以通过NOMA带来额外的带宽节省。与单侧SNC-SUICP相比，所提出的IC-NOMA传输方案在带宽效率方面有所提高。
{"title":"Optimal Index Code Design for IC-NOMA Transmission in VANETs","authors":"Sreelakshmi Pazhoor, Jesy Pachat, Nujoom Sageer Karat, V. Joseph, P. Deepthi, B. Rajan","doi":"10.1109/VTC2022-Fall57202.2022.10012949","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012949","url":null,"abstract":"Vehicular ad hoc network (VANET), is a developing platform with massive data demands for infotainment services in recent years. Index Coded NOMA (IC-NOMA) is a spectral efficient transmission method that can be used in VANETs. IC-NOMA applies the concepts of non-orthogonal multiple access (NOMA) over the index coded data to increase spectrum and power efficiency. In NOMA, far user does not get access to the near user data, while near user can successfully decode far user data. Therefore, the IC-NOMA demands a novel design of index code for improved bandwidth efficiency. This work considers the design of index code for NOMA when the user demands in VANET follows the data distribution of one-sided symmetric neighboring consecutive side information single unicast index coding problem (SNC-SUICP). For this setup, we develop an optimal closed form index coding (IC) solution which can bring in additional bandwidth savings through NOMA. The improved performance of the proposed IC-NOMA transmission scheme when compared with one-sided SNC-SUICP in terms of bandwidth efficiency is demonstrated.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"68 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":"132495228","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-Fall57202.2022.10012891
M. Javidsharifi, Hamoun Pourroshanfekr Arabani, T. Kerekes, D. Sera, J. Guerrero
Recently, the application of unmanned aerial vehicles (UAVs) to support the base stations in cellular telecommunication networks attracts attentions. UAV-assisted base stations can provide the extra users’ demand in extreme and/ or unpredictable situations such as Olympic Games to avoid extra cost of installing ground base stations. In this paper, a PV-battery power system is presented to supply UAV-assisted base stations in cellular telecommunication networks in urban areas to prevent environmental issues as well as to reduce the cost of fulfilling the energy demand. First, the energy consumption profile of the batteries of UAVs is estimated. Afterwards, the impact of the PV system sizing and battery capacity are studied based on sensitivity analysis.
{"title":"PV-Powered Base Stations Equipped by UAVs in Urban Areas","authors":"M. Javidsharifi, Hamoun Pourroshanfekr Arabani, T. Kerekes, D. Sera, J. Guerrero","doi":"10.1109/VTC2022-Fall57202.2022.10012891","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012891","url":null,"abstract":"Recently, the application of unmanned aerial vehicles (UAVs) to support the base stations in cellular telecommunication networks attracts attentions. UAV-assisted base stations can provide the extra users’ demand in extreme and/ or unpredictable situations such as Olympic Games to avoid extra cost of installing ground base stations. In this paper, a PV-battery power system is presented to supply UAV-assisted base stations in cellular telecommunication networks in urban areas to prevent environmental issues as well as to reduce the cost of fulfilling the energy demand. First, the energy consumption profile of the batteries of UAVs is estimated. Afterwards, the impact of the PV system sizing and battery capacity are studied based on sensitivity analysis.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"5 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":"133962509","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-Fall57202.2022.10012765
Liza Afeef, H. Arslan
In multicarrier wideband millimeter-wave (mmWave) communications, as the size of antenna array increases, as in massive multiple-input multiple-output (MIMO), an additional propagation delay of the electromagnetic wave at each antenna element is introduced comparable to (or greater than) the symbol duration, resulting in producing a displacement in beam direction at each subcarrier frequency or as it calls beam squinting. With multi-beam transmission in massive MIMO systems, due to beam squinting effect, an additional inter-beam interference (IBI) can be introduced to the system which significantly decreases the overall system capacity. Therefore, in this paper, IBI under beam squint effect is modeled for different subcarrier frequencies and beam angles in a multi-beam mmWave massive MIMO system. In addition, the impact of this IBI model on the system capacity is evaluated. The analysis results show that beam squinting causes a significant increase in IBI level, even when transmitting with orthogonal beams. Moreover, the results provide the optimal number of beams for a given antenna array size to maximize the system’s capacity considering beam squinting phenomena.
{"title":"Beam Squint Effect in Multi-Beam mmWave Massive MIMO Systems","authors":"Liza Afeef, H. Arslan","doi":"10.1109/VTC2022-Fall57202.2022.10012765","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012765","url":null,"abstract":"In multicarrier wideband millimeter-wave (mmWave) communications, as the size of antenna array increases, as in massive multiple-input multiple-output (MIMO), an additional propagation delay of the electromagnetic wave at each antenna element is introduced comparable to (or greater than) the symbol duration, resulting in producing a displacement in beam direction at each subcarrier frequency or as it calls beam squinting. With multi-beam transmission in massive MIMO systems, due to beam squinting effect, an additional inter-beam interference (IBI) can be introduced to the system which significantly decreases the overall system capacity. Therefore, in this paper, IBI under beam squint effect is modeled for different subcarrier frequencies and beam angles in a multi-beam mmWave massive MIMO system. In addition, the impact of this IBI model on the system capacity is evaluated. The analysis results show that beam squinting causes a significant increase in IBI level, even when transmitting with orthogonal beams. Moreover, the results provide the optimal number of beams for a given antenna array size to maximize the system’s capacity considering beam squinting phenomena.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"51 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":"132168080","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-Fall57202.2022.10012702
Xinran Zhang, Hui Tian, Wanli Ni, Mengying Sun
As a distributed machine learning paradigm, federated learning (FL) has been regarded as a promising candidate to preserve user privacy in Internet of Things (IoT) networks. Leveraging the waveform superposition property of wireless channels, over-the-air FL (AirFL) achieves fast model aggregation by integrating communication and computation via concurrent analog transmissions. To support sustainable AirFL among energy-constrained IoT devices, we consider that the base station (BS) adopts simultaneous wireless information and power transfer (SWIPT) to distribute global model and charge local devices in each communication round. To maximize the long-term energy efficiency (EE) of AirFL, we investigate a resource allocation problem by jointly optimizing the time division, transceiver beamforming, and power splitting in SWIPT-enabled IoT networks. Considering such multiple closely-coupled continuous valuables, we propose a deep reinforcement learning (DRL) algorithm based on twin delayed deep deterministic (TD3) policy to smartly make downlink and uplink communication strategies with the coordination between the BS and devices. Simulation results show that the proposed TD3 algorithm obtains about 41% EE improvement compared to traditional optimization method and other DRL algorithms.
{"title":"Deep Reinforcement Learning for Over-the-Air Federated Learning in SWIPT-Enabled IoT Networks","authors":"Xinran Zhang, Hui Tian, Wanli Ni, Mengying Sun","doi":"10.1109/VTC2022-Fall57202.2022.10012702","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012702","url":null,"abstract":"As a distributed machine learning paradigm, federated learning (FL) has been regarded as a promising candidate to preserve user privacy in Internet of Things (IoT) networks. Leveraging the waveform superposition property of wireless channels, over-the-air FL (AirFL) achieves fast model aggregation by integrating communication and computation via concurrent analog transmissions. To support sustainable AirFL among energy-constrained IoT devices, we consider that the base station (BS) adopts simultaneous wireless information and power transfer (SWIPT) to distribute global model and charge local devices in each communication round. To maximize the long-term energy efficiency (EE) of AirFL, we investigate a resource allocation problem by jointly optimizing the time division, transceiver beamforming, and power splitting in SWIPT-enabled IoT networks. Considering such multiple closely-coupled continuous valuables, we propose a deep reinforcement learning (DRL) algorithm based on twin delayed deep deterministic (TD3) policy to smartly make downlink and uplink communication strategies with the coordination between the BS and devices. Simulation results show that the proposed TD3 algorithm obtains about 41% EE improvement compared to traditional optimization method and other DRL algorithms.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"26 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":"131832345","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-Fall57202.2022.10012904
Yunda Li, Xiaolei Shang
We consider the problem of angle estimation and ghost target identification for automotive multiple-input multiple-output (MIMO) radar in multipath scenarios. Firstly, we establish the multipath propagation model for the case of horizental MIMO arrays, and divide the multipath into two categories, i.e., Type 1: multipath with direction-of-arrival (DOA) $neq$ direction-of-departure (DOD); Type 2: multipath with DOA$=$DOD. In the presence of multipath, the different DOA and DOD angles corrupt the notion of virtual array for MIMO radar, making angle estimation a major challenge. To jointly estimate the DOA and DOD of the target reflections, including both the direct path and multipath scenarios, we introduce a multipath iterative adaptive approach (MP-IAA), which possesses the super resolution, low sidelobe level, and robust properties for DOA and DOD estimation. Then, the Type 1 multipath with DOA$neq$DOD can be directly identified based on the MP-IAA’s DOA and DOD estimates. Regarding to the Type 2 multipath with DOA$=$DOD, we solve the triangle relationships to identify the corresponding ghost targets. Numerical examples are provided to demonstrate the effectiveness of the proposed algorithm for angle estimation and ghost target identification using automotive MIMO radar.
{"title":"Multipath Ghost Target Identification for Automotive MIMO Radar","authors":"Yunda Li, Xiaolei Shang","doi":"10.1109/VTC2022-Fall57202.2022.10012904","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012904","url":null,"abstract":"We consider the problem of angle estimation and ghost target identification for automotive multiple-input multiple-output (MIMO) radar in multipath scenarios. Firstly, we establish the multipath propagation model for the case of horizental MIMO arrays, and divide the multipath into two categories, i.e., Type 1: multipath with direction-of-arrival (DOA) $neq$ direction-of-departure (DOD); Type 2: multipath with DOA$=$DOD. In the presence of multipath, the different DOA and DOD angles corrupt the notion of virtual array for MIMO radar, making angle estimation a major challenge. To jointly estimate the DOA and DOD of the target reflections, including both the direct path and multipath scenarios, we introduce a multipath iterative adaptive approach (MP-IAA), which possesses the super resolution, low sidelobe level, and robust properties for DOA and DOD estimation. Then, the Type 1 multipath with DOA$neq$DOD can be directly identified based on the MP-IAA’s DOA and DOD estimates. Regarding to the Type 2 multipath with DOA$=$DOD, we solve the triangle relationships to identify the corresponding ghost targets. Numerical examples are provided to demonstrate the effectiveness of the proposed algorithm for angle estimation and ghost target identification using automotive MIMO radar.","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":"133371660","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-Fall57202.2022.10012980
Praveen Sai Bere, Mohammed Zafar Ali Khan
As Cyclic Redundancy Check (CRC) codes offer the advantages of low power transmission and variable payload length, they have found applications in IoT standards like IEEE 802.15.4 and Bluetooth low energy (BLE). Despite having redundant bits, CRC codes are merely used as error-detecting codes due to the unavailability of a suitable decoder. Several efforts have been made to design a decoder for CRC to use as error-correcting code. The recently proposed GRAND algorithm serves as an error-correcting algorithm for CRC but has huge complexity. In this paper, a low complexity hard decision decoder is proposed for CRC with $g(x)=1+x^{5}+x^{12}+x^{16}$ which is used in IEEE 802.15.4 for IoT applications. The proposed decoder utilizes channel state information (CSI) for decoding in a Rayleigh fading channel and attained fourth-order diversity with very low complexity. The proposed decoder is especially effective at short block lengths; hence it serves as a sound decoder catering to IoT and URLLC services.
{"title":"Low complexity, diversity preserving hard decision decoder for CRC codes with IoT applications","authors":"Praveen Sai Bere, Mohammed Zafar Ali Khan","doi":"10.1109/VTC2022-Fall57202.2022.10012980","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012980","url":null,"abstract":"As Cyclic Redundancy Check (CRC) codes offer the advantages of low power transmission and variable payload length, they have found applications in IoT standards like IEEE 802.15.4 and Bluetooth low energy (BLE). Despite having redundant bits, CRC codes are merely used as error-detecting codes due to the unavailability of a suitable decoder. Several efforts have been made to design a decoder for CRC to use as error-correcting code. The recently proposed GRAND algorithm serves as an error-correcting algorithm for CRC but has huge complexity. In this paper, a low complexity hard decision decoder is proposed for CRC with $g(x)=1+x^{5}+x^{12}+x^{16}$ which is used in IEEE 802.15.4 for IoT applications. The proposed decoder utilizes channel state information (CSI) for decoding in a Rayleigh fading channel and attained fourth-order diversity with very low complexity. The proposed decoder is especially effective at short block lengths; hence it serves as a sound decoder catering to IoT and URLLC services.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"58 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":"133846283","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-Fall57202.2022.10012865
T. Chen, Hong Shen, A. Hu, Weihang He, Jie Xu, Hong-Mei Hu
The vehicle-to-everything (V2X) technology has recently drawn attention from both academic and industrial areas. However, the openness of the wireless communication system makes it more vulnerable to identity impersonation and information tampering. How to employ the powerful radio frequency fingerprint (RFF) identification technology in V2X systems turns out to be a vital and challenging task. In this paper, we propose a novel RFF extraction method for Long Term Evolution-V2X (LTE-V2X) systems. In order to conquer the difficulty of extracting transmitter RFF in the presence of wireless channel and receiver noise, we first estimate the wireless channel which excludes the RFF. Then, we remove the impact of the wireless channel based on the channel estimate and obtain initial RFF features. Finally, we conduct RFF denoising to enhance the quality of the initial RFF. Simulation and experiment results both demonstrate that our proposed RFF extraction scheme achieves a high identification accuracy. Furthermore, the performance is also robust to the vehicle speed.
{"title":"Radio Frequency Fingerprints Extraction for LTE-V2X: A Channel Estimation Based Methodology","authors":"T. Chen, Hong Shen, A. Hu, Weihang He, Jie Xu, Hong-Mei Hu","doi":"10.1109/VTC2022-Fall57202.2022.10012865","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012865","url":null,"abstract":"The vehicle-to-everything (V2X) technology has recently drawn attention from both academic and industrial areas. However, the openness of the wireless communication system makes it more vulnerable to identity impersonation and information tampering. How to employ the powerful radio frequency fingerprint (RFF) identification technology in V2X systems turns out to be a vital and challenging task. In this paper, we propose a novel RFF extraction method for Long Term Evolution-V2X (LTE-V2X) systems. In order to conquer the difficulty of extracting transmitter RFF in the presence of wireless channel and receiver noise, we first estimate the wireless channel which excludes the RFF. Then, we remove the impact of the wireless channel based on the channel estimate and obtain initial RFF features. Finally, we conduct RFF denoising to enhance the quality of the initial RFF. Simulation and experiment results both demonstrate that our proposed RFF extraction scheme achieves a high identification accuracy. Furthermore, the performance is also robust to the vehicle speed.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"56 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":"132735591","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-Fall57202.2022.10012863
Y. Shi, Xixi Zhang, Zhengran He, Jie Yang
The application of deep learning (DL) in the field of network intrusion detection (NID) has yielded remarkable results in recent years. As for malicious traffic classification tasks, numerous DL methods have proved robust and effective with self-designed model architecture. However, the design of model architecture requires substantial professional knowledge and effort of human experts. Neural architecture search (NAS) can automatically search the architecture of the model under the premise of a given optimization goal, which is a subdomain of automatic machine learning (AutoML). After that, Differentiable Architecture Search (DARTS) has been proposed by formulating architecture search in a differentiable manner, which greatly improves the search efficiency. In this paper, we introduce a model which performs DARTS in the field of malicious traffic classification and search for optimal architecture based on network traffic datasets. In addition, we compare the DARTS method with several common models, including convolutional neural network (CNN), full connect neural network (FC), support vector machine (SVM), and multi-layer Perception (MLP). Simulation results show that the proposed method can achieve the optimal classification accuracy at lower parameters without manual architecture engineering.
{"title":"A Novel Malware Traffic Classification Method Based on Differentiable Architecture Search","authors":"Y. Shi, Xixi Zhang, Zhengran He, Jie Yang","doi":"10.1109/VTC2022-Fall57202.2022.10012863","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10012863","url":null,"abstract":"The application of deep learning (DL) in the field of network intrusion detection (NID) has yielded remarkable results in recent years. As for malicious traffic classification tasks, numerous DL methods have proved robust and effective with self-designed model architecture. However, the design of model architecture requires substantial professional knowledge and effort of human experts. Neural architecture search (NAS) can automatically search the architecture of the model under the premise of a given optimization goal, which is a subdomain of automatic machine learning (AutoML). After that, Differentiable Architecture Search (DARTS) has been proposed by formulating architecture search in a differentiable manner, which greatly improves the search efficiency. In this paper, we introduce a model which performs DARTS in the field of malicious traffic classification and search for optimal architecture based on network traffic datasets. In addition, we compare the DARTS method with several common models, including convolutional neural network (CNN), full connect neural network (FC), support vector machine (SVM), and multi-layer Perception (MLP). Simulation results show that the proposed method can achieve the optimal classification accuracy at lower parameters without manual architecture engineering.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"58 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":"117253262","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-Fall57202.2022.10013071
Weixuan Xiao, G. D. Sousa, N. Rachkidy, A. Guitton
LoRa (Long Range) is a physical layer designed for low-power wide area networks. It is widely used to provide long range connectivity to Internet of Things devices. In order to improve the limited throughput of LoRa, researchers have proposed several collision resolution algorithms. However, a common software framework to compare these algorithms is lacking. In this paper, we propose an open-source framework using GNU Radio, mainly designed to test and compare collision resolution algorithms, as well as physical layer algorithms. Our framework can help optimizing the parameters of algorithms according to channel conditions such as very low signal to noise ratio for instance. We also discuss technical implementation issues of existing collision resolution algorithms. Finally, we show how our framework can be used for either real experiments on USRPs, or for simulations with a large number of nodes.
{"title":"An Open-Source GNU Radio Framework for LoRa Physical Layer and Collision Resolution","authors":"Weixuan Xiao, G. D. Sousa, N. Rachkidy, A. Guitton","doi":"10.1109/VTC2022-Fall57202.2022.10013071","DOIUrl":"https://doi.org/10.1109/VTC2022-Fall57202.2022.10013071","url":null,"abstract":"LoRa (Long Range) is a physical layer designed for low-power wide area networks. It is widely used to provide long range connectivity to Internet of Things devices. In order to improve the limited throughput of LoRa, researchers have proposed several collision resolution algorithms. However, a common software framework to compare these algorithms is lacking. In this paper, we propose an open-source framework using GNU Radio, mainly designed to test and compare collision resolution algorithms, as well as physical layer algorithms. Our framework can help optimizing the parameters of algorithms according to channel conditions such as very low signal to noise ratio for instance. We also discuss technical implementation issues of existing collision resolution algorithms. Finally, we show how our framework can be used for either real experiments on USRPs, or for simulations with a large number of nodes.","PeriodicalId":326047,"journal":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","volume":"19 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":"116035960","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：