Pub Date : 2022-10-07DOI: 10.3389/frcmn.2022.995135
Piergiuseppe Di Marco, Roberto Valentini , Fortunato Santucci , Giuseppe Pettanice, Giulio Antonini
Smart metasurfaces have recently emerged as a promising paradigm for next-generation wireless communication systems, providing a reconfigurable radio propagation environment for a wide range of services and applications. In this paper, we discuss how to include and exploit smart metasurfaces into a 6G environment employing non-orthogonal multiple access (NOMA) communications. We identify the key challenges in the characterization of NOMA systems assisted by metasurfaces, which encompass the mutual coupling between electromagnetic fields in the scattering surfaces and its impact on the signal-to-interference-plus-noise ratio at the receiver. Furthermore, we describe opportunities and limitations for fully integrated systems: in this frame we envisage and outline a “deep” cross-layer approach, that encompasses full-wave electromagnetic analysis, circuit analysis, signal processing, and communication, then providing a model with affordable computational complexity for solving challenging configuration tasks in 6G wireless scenarios.
{"title":"Boosting NOMA systems through smart metasurfaces","authors":"Piergiuseppe Di Marco, Roberto Valentini , Fortunato Santucci , Giuseppe Pettanice, Giulio Antonini","doi":"10.3389/frcmn.2022.995135","DOIUrl":"https://doi.org/10.3389/frcmn.2022.995135","url":null,"abstract":"Smart metasurfaces have recently emerged as a promising paradigm for next-generation wireless communication systems, providing a reconfigurable radio propagation environment for a wide range of services and applications. In this paper, we discuss how to include and exploit smart metasurfaces into a 6G environment employing non-orthogonal multiple access (NOMA) communications. We identify the key challenges in the characterization of NOMA systems assisted by metasurfaces, which encompass the mutual coupling between electromagnetic fields in the scattering surfaces and its impact on the signal-to-interference-plus-noise ratio at the receiver. Furthermore, we describe opportunities and limitations for fully integrated systems: in this frame we envisage and outline a “deep” cross-layer approach, that encompasses full-wave electromagnetic analysis, circuit analysis, signal processing, and communication, then providing a model with affordable computational complexity for solving challenging configuration tasks in 6G wireless scenarios.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132499102","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 : 2022-09-21DOI: 10.3389/frcmn.2022.1010228
L. Lubna, Hira Hameed, Shuja Ansari, A. Zahid, Abubakar Sharif, Hassan Abbas, Fehaid Alqahtani, N. Mufti, S. Ullah, Muhammad Imran, Q. Abbasi
Recent advancements in radio frequency (RF) sensing technology can be attributed to the development of the Internet of Things (IoT), healthcare, RF-identification, and communication applications. RF sensing is a multidisciplinary research field that requires expertise in computing, electronics, and electromagnetics to cover all system features, including protocol development, antenna design, sensor integration, algorithm formulation, interconnection, data, and analytics. The overarching aim of this work is to present detailed information about RF technologies and their innovations and application diversity from the novel work carried out at CSI Lab 1, together in one platform with an extensive survey. This study presents state-of-the art applications and RF sensing that include W-Fi, radar, and SDR and RFID-based sensing. A comprehensive survey and study of the advantages and limitations of each non-contact technology is discussed. Additionally, open research gaps have been identified as well. Decades of knowledge and experience have been put to use to meet new challenges and demands. The development and study of RF systems, IoT, RFID sensing, and research and deployment activities, are briefly discussed. The emerging research projects with industry, institutional research centers, and academic studies are also addressed. Finally, an outline of identified potential future research areas is provided, emphasizing opportunities and challenges.
{"title":"Radio frequency sensing and its innovative applications in diverse sectors: A comprehensive study","authors":"L. Lubna, Hira Hameed, Shuja Ansari, A. Zahid, Abubakar Sharif, Hassan Abbas, Fehaid Alqahtani, N. Mufti, S. Ullah, Muhammad Imran, Q. Abbasi","doi":"10.3389/frcmn.2022.1010228","DOIUrl":"https://doi.org/10.3389/frcmn.2022.1010228","url":null,"abstract":"Recent advancements in radio frequency (RF) sensing technology can be attributed to the development of the Internet of Things (IoT), healthcare, RF-identification, and communication applications. RF sensing is a multidisciplinary research field that requires expertise in computing, electronics, and electromagnetics to cover all system features, including protocol development, antenna design, sensor integration, algorithm formulation, interconnection, data, and analytics. The overarching aim of this work is to present detailed information about RF technologies and their innovations and application diversity from the novel work carried out at CSI Lab 1, together in one platform with an extensive survey. This study presents state-of-the art applications and RF sensing that include W-Fi, radar, and SDR and RFID-based sensing. A comprehensive survey and study of the advantages and limitations of each non-contact technology is discussed. Additionally, open research gaps have been identified as well. Decades of knowledge and experience have been put to use to meet new challenges and demands. The development and study of RF systems, IoT, RFID sensing, and research and deployment activities, are briefly discussed. The emerging research projects with industry, institutional research centers, and academic studies are also addressed. Finally, an outline of identified potential future research areas is provided, emphasizing opportunities and challenges.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132762782","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 : 2022-09-08DOI: 10.3389/frcmn.2022.1011754
David Owens, Shuja Ansari, H. Cruickshank, R. Tafazolli, M. Imran
One of the most significant applications of Internet of Things are smart meters with wireless capabilities. Smart gas and electricity meters can capture half-hourly pricing and consumption data and send automated meter readings to your energy provider, in contrast to regular meters that can only register a running total of energy used. However, the legacy regular meters were not installed with wireless connectivity in mind and are usually found in hard-to-reach places for wireless radio coverage. To understand these scenarios, this paper provides signal strength measurements conducted at the Building Research Establishment determining building penetration losses in both 900 and 2,100 MHz band. We then present a building penetration loss model using these measurements that is practical and cost effective when compared to traditional statistical propagation loss models.
{"title":"Building penetration loss measurements and modelling in the 900 and 2100 MHz band for smart meter installation","authors":"David Owens, Shuja Ansari, H. Cruickshank, R. Tafazolli, M. Imran","doi":"10.3389/frcmn.2022.1011754","DOIUrl":"https://doi.org/10.3389/frcmn.2022.1011754","url":null,"abstract":"One of the most significant applications of Internet of Things are smart meters with wireless capabilities. Smart gas and electricity meters can capture half-hourly pricing and consumption data and send automated meter readings to your energy provider, in contrast to regular meters that can only register a running total of energy used. However, the legacy regular meters were not installed with wireless connectivity in mind and are usually found in hard-to-reach places for wireless radio coverage. To understand these scenarios, this paper provides signal strength measurements conducted at the Building Research Establishment determining building penetration losses in both 900 and 2,100 MHz band. We then present a building penetration loss model using these measurements that is practical and cost effective when compared to traditional statistical propagation loss models.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130312434","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 : 2022-08-31DOI: 10.3389/frcmn.2022.933047
Zhihui Han, Jie Gong
With the development of the Internet of Things, more and more sensors are deployed to monitor the environmental status. To reduce deployment costs, a large number of sensors need to be deployed without a stable grid power supply. Therefore, on the one hand, the wireless sensors need to save as much energy as possible to extend their lifetime. On the other hand, they need to sense and transmit timely and accurate information for real-time monitoring. In this study, based on the spatiotemporal correlation of the environmental status monitored by the sensors, status information estimation is considered to effectively reduce the information collection frequency of the sensors, thereby reducing the energy cost. Under an ideal communication model with unlimited and perfect channels, a status update scheduling mechanism based on a Q-learning algorithm is proposed. With a nonideal channel model, a status update scheduling mechanism based on deep reinforcement learning is proposed. In this scenario, all sensors share a limited number of channels, and channel fading is considered. A finite state Markov chain is adopted to model the channel state transition process. The simulation results based on a real dataset show that compared with several baseline methods, the proposed mechanisms can well balance the energy cost and information errors and significantly reduce the update frequency while ensuring information accuracy.
{"title":"Status update control based on reinforcement learning in energy harvesting sensor networks","authors":"Zhihui Han, Jie Gong","doi":"10.3389/frcmn.2022.933047","DOIUrl":"https://doi.org/10.3389/frcmn.2022.933047","url":null,"abstract":"With the development of the Internet of Things, more and more sensors are deployed to monitor the environmental status. To reduce deployment costs, a large number of sensors need to be deployed without a stable grid power supply. Therefore, on the one hand, the wireless sensors need to save as much energy as possible to extend their lifetime. On the other hand, they need to sense and transmit timely and accurate information for real-time monitoring. In this study, based on the spatiotemporal correlation of the environmental status monitored by the sensors, status information estimation is considered to effectively reduce the information collection frequency of the sensors, thereby reducing the energy cost. Under an ideal communication model with unlimited and perfect channels, a status update scheduling mechanism based on a Q-learning algorithm is proposed. With a nonideal channel model, a status update scheduling mechanism based on deep reinforcement learning is proposed. In this scenario, all sensors share a limited number of channels, and channel fading is considered. A finite state Markov chain is adopted to model the channel state transition process. The simulation results based on a real dataset show that compared with several baseline methods, the proposed mechanisms can well balance the energy cost and information errors and significantly reduce the update frequency while ensuring information accuracy.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"454 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123367086","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 : 2022-08-25DOI: 10.3389/frcmn.2022.965336
Giorgos Stratidakis, S. Droulias, A. Alexiou
Millimeter wave (mmWave) and terahertz (THz) frequencies are attractive for increased bandwidth applications, however are vulnerable to blockage and suffer from high pathloss. While the use of directional antennas can potentially mitigate these effects, the need for careful alignment becomes crucial, especially when the user moves. In this context, to ensure a reliable link, several parameters must be taken into account, such as the type of user’s motion, the location of the access point (AP), the shape of the area, the beamwidth, etc. In this work, the link reliability is divided into two main categories, the trajectory tracking resolution and the angular resolution. To address the challenges of both categories, a beam-tracking algorithm that promises high tracking reliability and low pilot overhead is proposed. The algorithm employs multiple cooperating APs and a hierarchical codebook and the performance of the proposed tracking method is evaluated through Monte-Carlo simulations with the probability of success, the average number of pilots per timeslot and the mean square error (MSE) as metrics, for different tracking estimation frequencies and different number of blocked links.
{"title":"A beam-tracking framework for THz networks","authors":"Giorgos Stratidakis, S. Droulias, A. Alexiou","doi":"10.3389/frcmn.2022.965336","DOIUrl":"https://doi.org/10.3389/frcmn.2022.965336","url":null,"abstract":"Millimeter wave (mmWave) and terahertz (THz) frequencies are attractive for increased bandwidth applications, however are vulnerable to blockage and suffer from high pathloss. While the use of directional antennas can potentially mitigate these effects, the need for careful alignment becomes crucial, especially when the user moves. In this context, to ensure a reliable link, several parameters must be taken into account, such as the type of user’s motion, the location of the access point (AP), the shape of the area, the beamwidth, etc. In this work, the link reliability is divided into two main categories, the trajectory tracking resolution and the angular resolution. To address the challenges of both categories, a beam-tracking algorithm that promises high tracking reliability and low pilot overhead is proposed. The algorithm employs multiple cooperating APs and a hierarchical codebook and the performance of the proposed tracking method is evaluated through Monte-Carlo simulations with the probability of success, the average number of pilots per timeslot and the mean square error (MSE) as metrics, for different tracking estimation frequencies and different number of blocked links.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121492604","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 : 2022-08-14DOI: 10.3389/frcmn.2022.1016270
Zehra Yigit, E. Başar, I. Altunbas
Reconfigurable intelligent surface (RIS)-empowered communication is a revolutionary technology that enables to manipulate wireless propagation environment via smartly controllable low-cost reflecting surfaces. However, in order to outperform conventional communication systems, an RIS-aided system with solely passive reflection requires an extremely large surface. To meet this challenge, the concept of active RIS, which performs simultaneous amplification and reflection on the incident signal at the expense of additional power consumption, has been recently introduced. In this paper, deploying an active RIS, we propose a novel beamforming concept, over-the-air beamforming, for RIS-aided multi-user multiple-input single-output (MISO) transmission schemes without requiring any pre/post signal processing hardware designs at the transmitter and receiver sides. In the proposed over-the-air beamforming-based transmission scheme, the reflection coefficients of the active RIS elements are customized to maximize the sum-rate gain. To tackle this issue, first, a non-convex quadratically constrained quadratic programming (QCQP) problem is formulated. Then, using semidefinite relaxation (SDR) approach, this optimization problem is converted to a convex feasibility problem, which is efficiently solved using the CVX optimization toolbox. Moreover, taking inspiration from this beamforming technique, a novel high-rate receive index modulation (IM) scheme with a low-complexity sub-optimal detector is developed. Through comprehensive simulation results, the sum-rate and bit error rate (BER) performance of the proposed designs are investigated.
{"title":"Over-the-air beamforming with reconfigurable intelligent surfaces","authors":"Zehra Yigit, E. Başar, I. Altunbas","doi":"10.3389/frcmn.2022.1016270","DOIUrl":"https://doi.org/10.3389/frcmn.2022.1016270","url":null,"abstract":"Reconfigurable intelligent surface (RIS)-empowered communication is a revolutionary technology that enables to manipulate wireless propagation environment via smartly controllable low-cost reflecting surfaces. However, in order to outperform conventional communication systems, an RIS-aided system with solely passive reflection requires an extremely large surface. To meet this challenge, the concept of active RIS, which performs simultaneous amplification and reflection on the incident signal at the expense of additional power consumption, has been recently introduced. In this paper, deploying an active RIS, we propose a novel beamforming concept, over-the-air beamforming, for RIS-aided multi-user multiple-input single-output (MISO) transmission schemes without requiring any pre/post signal processing hardware designs at the transmitter and receiver sides. In the proposed over-the-air beamforming-based transmission scheme, the reflection coefficients of the active RIS elements are customized to maximize the sum-rate gain. To tackle this issue, first, a non-convex quadratically constrained quadratic programming (QCQP) problem is formulated. Then, using semidefinite relaxation (SDR) approach, this optimization problem is converted to a convex feasibility problem, which is efficiently solved using the CVX optimization toolbox. Moreover, taking inspiration from this beamforming technique, a novel high-rate receive index modulation (IM) scheme with a low-complexity sub-optimal detector is developed. Through comprehensive simulation results, the sum-rate and bit error rate (BER) performance of the proposed designs are investigated.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116294430","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 : 2022-07-07DOI: 10.3389/frcmn.2022.959303
A. Zoha, Junaid Qadir, Q. Abbasi
AI-powered IoT for Intelligent Systems and together different contributions that highlight innovative uses of arti fi cial intelligence (AI) for monitoring, next-generation transportation systems, and social pulse monitoring. Using design-driven innovation, the proposed various solutions to the challenges involved in implementing AI-driven systems. These include addressing the quality-of-service requirements (latency, bandwidth, and delay), hybrid mechanisms to provide reliable estimation of healthcare conditions, as well as mechanisms to support improved textual analysis. the state-of-the-art of atrial (AF) techniques that emerging AI models for proactive and automatic detection of AF in of conductance responses regarding the relationship between hydration between and hydration levels in the the of dysfunction. advantages of for hydration an on the relationship between skin hydration level and
{"title":"Editorial: AI-Powered IoT for Intelligent Systems and Smart Applications","authors":"A. Zoha, Junaid Qadir, Q. Abbasi","doi":"10.3389/frcmn.2022.959303","DOIUrl":"https://doi.org/10.3389/frcmn.2022.959303","url":null,"abstract":"AI-powered IoT for Intelligent Systems and together different contributions that highlight innovative uses of arti fi cial intelligence (AI) for monitoring, next-generation transportation systems, and social pulse monitoring. Using design-driven innovation, the proposed various solutions to the challenges involved in implementing AI-driven systems. These include addressing the quality-of-service requirements (latency, bandwidth, and delay), hybrid mechanisms to provide reliable estimation of healthcare conditions, as well as mechanisms to support improved textual analysis. the state-of-the-art of atrial (AF) techniques that emerging AI models for proactive and automatic detection of AF in of conductance responses regarding the relationship between hydration between and hydration levels in the the of dysfunction. advantages of for hydration an on the relationship between skin hydration level and","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130813246","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 : 2022-06-27DOI: 10.3389/frcmn.2022.907388
Songshan Liu, H. Yang, Yiqi Tao, Yang Feng, Jinxiang Hao, Zuozhu Liu
Semantic segmentation over three-dimensional (3D) intra-oral mesh scans (IOS) is an essential step in modern digital dentistry. Many existing methods usually rely on a limited number of labeled samples as annotating IOS scans is time consuming, while a large-scale dataset of IOS is not yet publicly available due to privacy and regulatory concerns. Moreover, the local data heterogeneity would cause serious performance degradation if we follow the conventional learning paradigms to train local models in individual institutions. In this study, we propose the FedTSeg framework, a federated 3D tooth segmentation framework with a deep graph convolutional neural network, to resolve the 3D tooth segmentation task while alleviating data privacy issues. Moreover, we adopt a general privacy-preserving mechanism with homomorphic encryption to prevent information leakage during parameter exchange between the central server and local clients. Extensive experiments demonstrate that both the local and global models trained with the FedTSeg framework can significantly outperform models trained with the conventional paradigm in terms of the mean intersection over union, dice coefficient, and accuracy metrics. The FedTSeg framework can achieve better performance under imbalanced data distributions with different numbers of clients, and its overall performance is on par with the central model trained with the full dataset aggregated from all distributed clients. The data privacy during parameter exchange of FedTSeg is further enhanced with a homomorphic encryption process. Our work presents the first attempts of federated learning for 3D tooth segmentation, demonstrating its strong potential in challenging federated 3D medical image analysis in multi-centric settings.
{"title":"Privacy-Preserved Federated Learning for 3D Tooth Segmentation in Intra-Oral Mesh Scans","authors":"Songshan Liu, H. Yang, Yiqi Tao, Yang Feng, Jinxiang Hao, Zuozhu Liu","doi":"10.3389/frcmn.2022.907388","DOIUrl":"https://doi.org/10.3389/frcmn.2022.907388","url":null,"abstract":"Semantic segmentation over three-dimensional (3D) intra-oral mesh scans (IOS) is an essential step in modern digital dentistry. Many existing methods usually rely on a limited number of labeled samples as annotating IOS scans is time consuming, while a large-scale dataset of IOS is not yet publicly available due to privacy and regulatory concerns. Moreover, the local data heterogeneity would cause serious performance degradation if we follow the conventional learning paradigms to train local models in individual institutions. In this study, we propose the FedTSeg framework, a federated 3D tooth segmentation framework with a deep graph convolutional neural network, to resolve the 3D tooth segmentation task while alleviating data privacy issues. Moreover, we adopt a general privacy-preserving mechanism with homomorphic encryption to prevent information leakage during parameter exchange between the central server and local clients. Extensive experiments demonstrate that both the local and global models trained with the FedTSeg framework can significantly outperform models trained with the conventional paradigm in terms of the mean intersection over union, dice coefficient, and accuracy metrics. The FedTSeg framework can achieve better performance under imbalanced data distributions with different numbers of clients, and its overall performance is on par with the central model trained with the full dataset aggregated from all distributed clients. The data privacy during parameter exchange of FedTSeg is further enhanced with a homomorphic encryption process. Our work presents the first attempts of federated learning for 3D tooth segmentation, demonstrating its strong potential in challenging federated 3D medical image analysis in multi-centric settings.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127518023","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 : 2022-06-23DOI: 10.3389/frcmn.2022.878170
Bo Che, Xinyi Li, Zhi Chen, Qi He
End-to-end learning of the communication system regards the transmitter, channel, and receiver as a neural network-based autoencoder. This approach enables joint optimization of both the transmitter and receiver and can learn to communicate more efficiently than model-based ones. Despite the achieved success, high complexity is the major disadvantage that hinders its further development, while low-precision compression such as one-bit quantization is an effective solution. This study proposed an autoencoder communication system composed of binary neural networks (BNNs), which is based on bit operations and has a great potential to be applied to hardware platforms with very limited computing resources such as FPGAs. Several modifications are explored to further improve the performance. Experiments showed that the proposed BNN-based system can achieve a performance similar to that of the existing neural network-based autoencoder systems while largely reducing the storage and computation complexities.
{"title":"Trainable Communication Systems Based on the Binary Neural Network","authors":"Bo Che, Xinyi Li, Zhi Chen, Qi He","doi":"10.3389/frcmn.2022.878170","DOIUrl":"https://doi.org/10.3389/frcmn.2022.878170","url":null,"abstract":"End-to-end learning of the communication system regards the transmitter, channel, and receiver as a neural network-based autoencoder. This approach enables joint optimization of both the transmitter and receiver and can learn to communicate more efficiently than model-based ones. Despite the achieved success, high complexity is the major disadvantage that hinders its further development, while low-precision compression such as one-bit quantization is an effective solution. This study proposed an autoencoder communication system composed of binary neural networks (BNNs), which is based on bit operations and has a great potential to be applied to hardware platforms with very limited computing resources such as FPGAs. Several modifications are explored to further improve the performance. Experiments showed that the proposed BNN-based system can achieve a performance similar to that of the existing neural network-based autoencoder systems while largely reducing the storage and computation complexities.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123063243","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 : 2022-06-02DOI: 10.3389/frcmn.2022.921186
Pavlos S. Bouzinis, P. Diamantoulakis, G. Karagiannidis
In the original article there is an error in the Funding statement, pg 12. The correct number for European Union’s Horizon 2020 research and innovation programme is No 957406. Therefore, the following correction is needed at the beginning of the Funding statement: “Part of the research leading to these results has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 957406.” The authors apologize for this error and state that this does not change the scientific conclusions of the article in any way. The original article has been updated.
{"title":"Corrigendum: Incentive-Based Delay Minimization for 6G-Enabled Wireless Federated Learning","authors":"Pavlos S. Bouzinis, P. Diamantoulakis, G. Karagiannidis","doi":"10.3389/frcmn.2022.921186","DOIUrl":"https://doi.org/10.3389/frcmn.2022.921186","url":null,"abstract":"In the original article there is an error in the Funding statement, pg 12. The correct number for European Union’s Horizon 2020 research and innovation programme is No 957406. Therefore, the following correction is needed at the beginning of the Funding statement: “Part of the research leading to these results has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 957406.” The authors apologize for this error and state that this does not change the scientific conclusions of the article in any way. The original article has been updated.","PeriodicalId":106247,"journal":{"name":"Frontiers in Communications and Networks","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123232751","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：