Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538890
Yue Su, Yuzhi Zhang, R. Bai, Yang Liu, Bin Wang, Yanjing Sun
As underwater acoustic (UWA) channels usually experience temporally variation, link disconnection usually occurs during long time deployment of UWA networks. In the UWA data collection network, one destination needs to collect data from multiple underwater nodes. With the thought of node cooperation, one node can be selected as a potential relay to forward data for another failure node in the retransmission phase. One of the key points is that the selection schedule depends on the channel state information. Whereas, the channel usually varies during the information collection time which will make the decision schedule not accurate. In this paper, a Q-Learning based cooperation scheme has been proposed for node selection in time varying UWA channels, with the setup of proper states, action and rewards. The state is a combination of channel state information (CSI) and mutual information, and the rewards updating functions have been given. With the proposed method, the cooperative forwarding relay nodes can be chosen by the rewards which has been updated with channel variation information. Simulation results indicate that proposed Q-Learning based cooperative scheme can achieve better system capacity compared to random schemes. And with predicted CSI, the performance is close to the bench mark with ideal CSI.
{"title":"Q-Learning based Dynamic Cooperative Communication in Time Varying Underwater Acoustic Channels","authors":"Yue Su, Yuzhi Zhang, R. Bai, Yang Liu, Bin Wang, Yanjing Sun","doi":"10.1109/ICCCWorkshops52231.2021.9538890","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538890","url":null,"abstract":"As underwater acoustic (UWA) channels usually experience temporally variation, link disconnection usually occurs during long time deployment of UWA networks. In the UWA data collection network, one destination needs to collect data from multiple underwater nodes. With the thought of node cooperation, one node can be selected as a potential relay to forward data for another failure node in the retransmission phase. One of the key points is that the selection schedule depends on the channel state information. Whereas, the channel usually varies during the information collection time which will make the decision schedule not accurate. In this paper, a Q-Learning based cooperation scheme has been proposed for node selection in time varying UWA channels, with the setup of proper states, action and rewards. The state is a combination of channel state information (CSI) and mutual information, and the rewards updating functions have been given. With the proposed method, the cooperative forwarding relay nodes can be chosen by the rewards which has been updated with channel variation information. Simulation results indicate that proposed Q-Learning based cooperative scheme can achieve better system capacity compared to random schemes. And with predicted CSI, the performance is close to the bench mark with ideal CSI.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131108148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538912
Jinjin Chu, Rang Liu, Yang Liu, Ming Li, Qian Liu
Dual-functional radar-communication (DFRC) systems can utilize the same hardware platforms and spectrum resources to simultaneously realize radar sensing and communication functionalities. This paper focuses on the secure beamforming design for multi-input multi-output (MIMO) DFRC systems, in which the target of interest is considered as a vicious eavesdropper who attempts to eavesdrop the information transmissions from the DFRC base station (BS) to the multiple legitimate users. In order to ensure the confidential information transmissions, artificial noise (AN) is generated at the BS to disrupt the receptions of the eavesdropper. While satisfying the communication quality-of-service (QoS) requirements of the legitimate users, the constant-modulus power constraints, and the beampattern similarity constraint, the maximum eavesdropping signal-to-interference-plus-noise ratio (SINR) of the target is minimized by jointly optimizing the transmit beamforming and the AN. A semi-definite relaxation (SDR) and fractional programming (FP) based algorithm is proposed to solve for the non-convex AN-aided secure beamforming design. Simulation results verify the effectiveness of the proposed scheme and associated beamforming design algorithm in ensuring the secure transmissions for the DFRC systems.
{"title":"AN-aided Secure Beamforming Design for Dual-Functional Radar-Communication Systems","authors":"Jinjin Chu, Rang Liu, Yang Liu, Ming Li, Qian Liu","doi":"10.1109/ICCCWorkshops52231.2021.9538912","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538912","url":null,"abstract":"Dual-functional radar-communication (DFRC) systems can utilize the same hardware platforms and spectrum resources to simultaneously realize radar sensing and communication functionalities. This paper focuses on the secure beamforming design for multi-input multi-output (MIMO) DFRC systems, in which the target of interest is considered as a vicious eavesdropper who attempts to eavesdrop the information transmissions from the DFRC base station (BS) to the multiple legitimate users. In order to ensure the confidential information transmissions, artificial noise (AN) is generated at the BS to disrupt the receptions of the eavesdropper. While satisfying the communication quality-of-service (QoS) requirements of the legitimate users, the constant-modulus power constraints, and the beampattern similarity constraint, the maximum eavesdropping signal-to-interference-plus-noise ratio (SINR) of the target is minimized by jointly optimizing the transmit beamforming and the AN. A semi-definite relaxation (SDR) and fractional programming (FP) based algorithm is proposed to solve for the non-convex AN-aided secure beamforming design. Simulation results verify the effectiveness of the proposed scheme and associated beamforming design algorithm in ensuring the secure transmissions for the DFRC systems.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132093016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538853
Aichen Li, Yang Liu, Ming Li, Qingqing Wu, Jun Zhao
Internet of things (IoT) technology is critical to realize universal connections of everything and pervasive intelligence for the future world. The forthcoming IoT technology will be characterized by two predominant features: energy self-sustainability, which is fueled by the recent thrilling wireless power transfer (WPT) technology, and sufficient computation power capability, which will be empowered by the mobile edge computing (MEC) networking. Very recently a promising technology named reconfigurable intelligent surfaces (RIS) has attracted much attention due to its effective beamforming capability and viable potentials to enhance wireless communication system. In this paper we consider exploiting RIS to enhance the WPT-based MEC IoT networks via boosting its energy transferring and communication efficiency. Specifically, we consider the scheduling design through jointly optimizing the WPT-time allocation, dynamic RIS phase control and all IoT mobile devices’ offloading decisions to improve the entire MEC network’s computation capability. This problem is very challenging due to its high dimension discrete variable space. Here we adopt a reinforcement learning (RL) based online method, which utilizes a novel double deep Q-network (DDQN) structure to effectively overcome the overestimation issue and outperforms the conventional deep Q-network (DQN) learning methods. Numerical results verify the effectiveness of our proposed algorithm and demonstrate the benefits of introducing RIS to assist the WPT-based MEC network.
{"title":"Joint Scheduling Design in Wireless Powered MEC IoT Networks Aided by Reconfigurable Intelligent Surface","authors":"Aichen Li, Yang Liu, Ming Li, Qingqing Wu, Jun Zhao","doi":"10.1109/ICCCWorkshops52231.2021.9538853","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538853","url":null,"abstract":"Internet of things (IoT) technology is critical to realize universal connections of everything and pervasive intelligence for the future world. The forthcoming IoT technology will be characterized by two predominant features: energy self-sustainability, which is fueled by the recent thrilling wireless power transfer (WPT) technology, and sufficient computation power capability, which will be empowered by the mobile edge computing (MEC) networking. Very recently a promising technology named reconfigurable intelligent surfaces (RIS) has attracted much attention due to its effective beamforming capability and viable potentials to enhance wireless communication system. In this paper we consider exploiting RIS to enhance the WPT-based MEC IoT networks via boosting its energy transferring and communication efficiency. Specifically, we consider the scheduling design through jointly optimizing the WPT-time allocation, dynamic RIS phase control and all IoT mobile devices’ offloading decisions to improve the entire MEC network’s computation capability. This problem is very challenging due to its high dimension discrete variable space. Here we adopt a reinforcement learning (RL) based online method, which utilizes a novel double deep Q-network (DDQN) structure to effectively overcome the overestimation issue and outperforms the conventional deep Q-network (DQN) learning methods. Numerical results verify the effectiveness of our proposed algorithm and demonstrate the benefits of introducing RIS to assist the WPT-based MEC network.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129625880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538932
Junliang Lin, Gongpu Wang, R. Xu, Huahua Xiao
In this paper, we suggest a new framework for wireless communications on railways aided by transmissive metasurfaces (TMs) and investigate the channel and phase shift estimation when orthogonal time frequency space (OTFS) is used. Specifically, we first establish the OTFS transmitter, end-to-end channel, and OTFS receiver models, and then define the input-output signal relation in vector form. Based on signal relation, we develop a channel and phase shift estimator that initially adopts the linear minimum mean squared error method to obtain the end-to-end channel and iteratively optimize the phase shift using the majorization-minimization (MM) method. Finally, numerical results are provided to show both convergence and performance of our MM-based estimation algorithm.
{"title":"Channel and Phase Shift Estimation for TM-aided OTFS Railway Communications","authors":"Junliang Lin, Gongpu Wang, R. Xu, Huahua Xiao","doi":"10.1109/ICCCWorkshops52231.2021.9538932","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538932","url":null,"abstract":"In this paper, we suggest a new framework for wireless communications on railways aided by transmissive metasurfaces (TMs) and investigate the channel and phase shift estimation when orthogonal time frequency space (OTFS) is used. Specifically, we first establish the OTFS transmitter, end-to-end channel, and OTFS receiver models, and then define the input-output signal relation in vector form. Based on signal relation, we develop a channel and phase shift estimator that initially adopts the linear minimum mean squared error method to obtain the end-to-end channel and iteratively optimize the phase shift using the majorization-minimization (MM) method. Finally, numerical results are provided to show both convergence and performance of our MM-based estimation algorithm.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132249334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538869
Aifei Liu, Shengguo Shi, Xinyi Wang
The ambient noise covariance matrix for the array of underwater acoustic vector-sensors (AVSs) is not equal to an identity matrix with a constant. This fact contradicts the requirement of subspace-based DOA estimation methods such as the conventional MUSIC method, leading to the performance degradation of DOA estimation. In order to overcome this problem, we propose an efficient DOA estimation method with Ambient Noise Elimination (Named as ANE method). In particular, the ANE method first transforms the array covariance matrix to a new one of which the imaginary part eliminates ambient noises. Afterwards, based on the imaginary part of the new covariance matrix, the ANE method completes DOA estimation. The ANE method involves the real-valued Singular Value Decomposition(SVD) and thus it is computationally more efficient than the conventional MUSIC method with the complex-valued Eigenvalue Decomposition(EVD). Simulation and experimental results demonstrate the ANE method is superior to the other methods, especially in a low signal-to-noise ratio (SNR).
{"title":"Efficient DOA Estimation Method with Ambient Noise Elimination for Array of Underwater Acoustic Vector Sensors","authors":"Aifei Liu, Shengguo Shi, Xinyi Wang","doi":"10.1109/ICCCWorkshops52231.2021.9538869","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538869","url":null,"abstract":"The ambient noise covariance matrix for the array of underwater acoustic vector-sensors (AVSs) is not equal to an identity matrix with a constant. This fact contradicts the requirement of subspace-based DOA estimation methods such as the conventional MUSIC method, leading to the performance degradation of DOA estimation. In order to overcome this problem, we propose an efficient DOA estimation method with Ambient Noise Elimination (Named as ANE method). In particular, the ANE method first transforms the array covariance matrix to a new one of which the imaginary part eliminates ambient noises. Afterwards, based on the imaginary part of the new covariance matrix, the ANE method completes DOA estimation. The ANE method involves the real-valued Singular Value Decomposition(SVD) and thus it is computationally more efficient than the conventional MUSIC method with the complex-valued Eigenvalue Decomposition(EVD). Simulation and experimental results demonstrate the ANE method is superior to the other methods, especially in a low signal-to-noise ratio (SNR).","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133436889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538887
Xiaoting Wang, Weijun Cheng, Chenshan Ren
With the development of the commercial scale of 5G, the explosive growth of smart mobile devices has promoted the emergence of new applications. How to reasonably design and allocate computing resources and improve users’ experience quality with the limited computing and storage capabilities of mobile devices is a challenging problem. The existing work about joint optimization either minimizes the execution delay or the energy consumption of communication, computation, and caching resources of all the devices. However, the single-objective optimization may not be a practical solution given the heterogeneous capabilities and service requirements of mobile devices. This paper proposes a multi-objective joint optimization of communication-computation-caching resources to satisfy the various devices’ requirements for execution delay and energy consumption. We reformulate to optimize the tradeoff between energy consumption and latency with the limited computing and storage resources. Then, the problem is transferred to a multi-objective problem and solved by the multi optimization method of non-dominated sorting genetic algorithm II (NSGA-II). Simulation results demonstrate that the proposed approach can achieve the tradeoff between energy consumption and latency with different practical scenarios.
{"title":"Multi-objective Joint Optimization of Communication-Computation-Caching Resources in Mobile Edge Computing","authors":"Xiaoting Wang, Weijun Cheng, Chenshan Ren","doi":"10.1109/ICCCWorkshops52231.2021.9538887","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538887","url":null,"abstract":"With the development of the commercial scale of 5G, the explosive growth of smart mobile devices has promoted the emergence of new applications. How to reasonably design and allocate computing resources and improve users’ experience quality with the limited computing and storage capabilities of mobile devices is a challenging problem. The existing work about joint optimization either minimizes the execution delay or the energy consumption of communication, computation, and caching resources of all the devices. However, the single-objective optimization may not be a practical solution given the heterogeneous capabilities and service requirements of mobile devices. This paper proposes a multi-objective joint optimization of communication-computation-caching resources to satisfy the various devices’ requirements for execution delay and energy consumption. We reformulate to optimize the tradeoff between energy consumption and latency with the limited computing and storage resources. Then, the problem is transferred to a multi-objective problem and solved by the multi optimization method of non-dominated sorting genetic algorithm II (NSGA-II). Simulation results demonstrate that the proposed approach can achieve the tradeoff between energy consumption and latency with different practical scenarios.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131342421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538882
Lan Zhang, W. Feng, Jianlong Li, Huijie Zhu
Channel modeling and the prediction of the reliability of acoustic link is the key to a successful deployment of underwater acoustic networks (UAN). In this paper, we build a Bellhop-based simulation framework driven by the environmental data to assess and predict the quality of the long-range and low-frequency communication links between the unmanned platforms in the deep ocean. The environmental data is measured in the South China Sea Experiment 2020 (SCSEx20). Results of channel modeling and link reliability prediction are reported in terms of the estimated channel impulse response (CIR), signal-to-noise ratio (SNR), and bit rate error (BER). The analysis shows how the communication performance of the physical level is dominated by the environmental data, aiming at evaluating the communication performance, and correlating the variation of the environmental conditions to the reliability of the entire communication link.
{"title":"Link Reliability Prediction for Long-range Underwater Acoustic Communications between Gliders","authors":"Lan Zhang, W. Feng, Jianlong Li, Huijie Zhu","doi":"10.1109/ICCCWorkshops52231.2021.9538882","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538882","url":null,"abstract":"Channel modeling and the prediction of the reliability of acoustic link is the key to a successful deployment of underwater acoustic networks (UAN). In this paper, we build a Bellhop-based simulation framework driven by the environmental data to assess and predict the quality of the long-range and low-frequency communication links between the unmanned platforms in the deep ocean. The environmental data is measured in the South China Sea Experiment 2020 (SCSEx20). Results of channel modeling and link reliability prediction are reported in terms of the estimated channel impulse response (CIR), signal-to-noise ratio (SNR), and bit rate error (BER). The analysis shows how the communication performance of the physical level is dominated by the environmental data, aiming at evaluating the communication performance, and correlating the variation of the environmental conditions to the reliability of the entire communication link.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114608468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538897
Chengzhuo Han, Tingting Yang
Federated learning is a machine learning model based on distributed data sets, which builds a global model under the premise of ensuring the privacy and data security of participants. Because of this characteristic, federated learning is very suitable for maritime communication systems with large amounts of distributed data. However, the data set of maritime multi-agent communication system is different from the general data set, and the data distribution is not uniform, which increases the deviation of the model. In this paper, we propose a Part-Federated Learning (PFL) method which combines the advantages of split learning to improve the classical federated learning. This method, only uploading some parameters in the local model to the cloud server as shared parameters, reduces the communication cost of distributed learning, improves the privacy of the algorithm to the data, and has better performance in processing non-IDD distributed data. We optimize the proportion of shared parameters of PFL by considering the convergence of the algorithm and the communication cost. Finally, we verify the advantages of the algorithm in processing non-IID data through experiments, simulate the process of parameter optimization, and prove the feasibility of the algorithm.
{"title":"Privacy Protection Technology of Maritime Multi-agent Communication Based on Part-Federated Learning","authors":"Chengzhuo Han, Tingting Yang","doi":"10.1109/ICCCWorkshops52231.2021.9538897","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538897","url":null,"abstract":"Federated learning is a machine learning model based on distributed data sets, which builds a global model under the premise of ensuring the privacy and data security of participants. Because of this characteristic, federated learning is very suitable for maritime communication systems with large amounts of distributed data. However, the data set of maritime multi-agent communication system is different from the general data set, and the data distribution is not uniform, which increases the deviation of the model. In this paper, we propose a Part-Federated Learning (PFL) method which combines the advantages of split learning to improve the classical federated learning. This method, only uploading some parameters in the local model to the cloud server as shared parameters, reduces the communication cost of distributed learning, improves the privacy of the algorithm to the data, and has better performance in processing non-IDD distributed data. We optimize the proportion of shared parameters of PFL by considering the convergence of the algorithm and the communication cost. Finally, we verify the advantages of the algorithm in processing non-IID data through experiments, simulate the process of parameter optimization, and prove the feasibility of the algorithm.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134038926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538900
Ronghui Zhang, Jiaen Zhou, Sheng Wu, Xiaojun Jing
Gesture recognition has enabled IoT applications such as human-computer interaction and virtual reality. In this work, we propose a cross-domain device-free gesture recognition (DFGR) model, that exploits 3D-CNN to obtain spatiotemporal features in Wi-Fi sensing. To adapt the sensing data to the 3D model, we carry out 3D data segment and supplement in addition to signal denoising and time-frequency transformation. We demonstrate that our proposed model outperforms the state-of-the-art method in the application of DFGR even cross 3 domain factors simultaneously, and is easy to converge and convenient for training with a less complicated hierarchical structure.
{"title":"Cross-Domain Gesture Recognition via Learning Spatiotemporal Features in Wi-Fi Sensing","authors":"Ronghui Zhang, Jiaen Zhou, Sheng Wu, Xiaojun Jing","doi":"10.1109/ICCCWorkshops52231.2021.9538900","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538900","url":null,"abstract":"Gesture recognition has enabled IoT applications such as human-computer interaction and virtual reality. In this work, we propose a cross-domain device-free gesture recognition (DFGR) model, that exploits 3D-CNN to obtain spatiotemporal features in Wi-Fi sensing. To adapt the sensing data to the 3D model, we carry out 3D data segment and supplement in addition to signal denoising and time-frequency transformation. We demonstrate that our proposed model outperforms the state-of-the-art method in the application of DFGR even cross 3 domain factors simultaneously, and is easy to converge and convenient for training with a less complicated hierarchical structure.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133259693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-28DOI: 10.1109/ICCCWorkshops52231.2021.9538933
Hua He, Yanxia Liang, Shulei Li
In order to resolve the massive access in future generation, NOMA (non-orthogonal multiple access) is exploited in the Massive MIMO communication system at the mmWave (millimeter wave) frequency to gain a very high capacity and access a very large number of users. The user clustering is key issue, which give impact to the performance of the system. Due to the directional transmission at mmWave frequency and space multiplexing of Massive MIMO, we propose k-means clustering algorithm based on azimuth, which takes use of the user’s azimuth to group users with the similar azimuths into the same cluster, while users with distinct azimuths into the different clusters. It cannot only increase the access number from spatial aspect, and also reduce the inter-cluster interference. The simulation results show that the proposed algorithms can realize directional clustering, which well achieves the desired goal.
{"title":"Clustering Algorithm based on Azimuth in MmWave Massive MIMO-NOMA System","authors":"Hua He, Yanxia Liang, Shulei Li","doi":"10.1109/ICCCWorkshops52231.2021.9538933","DOIUrl":"https://doi.org/10.1109/ICCCWorkshops52231.2021.9538933","url":null,"abstract":"In order to resolve the massive access in future generation, NOMA (non-orthogonal multiple access) is exploited in the Massive MIMO communication system at the mmWave (millimeter wave) frequency to gain a very high capacity and access a very large number of users. The user clustering is key issue, which give impact to the performance of the system. Due to the directional transmission at mmWave frequency and space multiplexing of Massive MIMO, we propose k-means clustering algorithm based on azimuth, which takes use of the user’s azimuth to group users with the similar azimuths into the same cluster, while users with distinct azimuths into the different clusters. It cannot only increase the access number from spatial aspect, and also reduce the inter-cluster interference. The simulation results show that the proposed algorithms can realize directional clustering, which well achieves the desired goal.","PeriodicalId":335240,"journal":{"name":"2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121907248","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：