Zhe Chen, Tianyue Zheng, Chao Hu, Hangcheng Cao, Yanbing Yang, Hongbo Jiang, Jun Luo
The intention of leveraging Radio-Frequency (RF) resources for diverse sensing purposes has grown increasingly keen, thanks to the ever-expanding deployment of IoT devices using RF communications to maintain connectivity. To this end, we propose ISACoT as the framework for enabling Integrated Sensing and Communication (ISAC) over IoT devices. ISACoT extends over existing devices via four aspects, namely time, frequency, space, and protocol. We argue that, as the multistatic communication infrastructure of IoT is adverse to device-free sensing (e.g., lack of precise time synchronization), the keystone of ISACoT should be to operate sensing in a monostatic mode (like radar). We tackle the fundamental time aspect based on Wi-Fi first, then explore the other three aspects with both preliminary proposals made and potential challenges raised for future extensions.
{"title":"Integrating monostatic sensing with communication for IoT","authors":"Zhe Chen, Tianyue Zheng, Chao Hu, Hangcheng Cao, Yanbing Yang, Hongbo Jiang, Jun Luo","doi":"10.1145/3556562.3558571","DOIUrl":"https://doi.org/10.1145/3556562.3558571","url":null,"abstract":"The intention of leveraging Radio-Frequency (RF) resources for diverse sensing purposes has grown increasingly keen, thanks to the ever-expanding deployment of IoT devices using RF communications to maintain connectivity. To this end, we propose ISACoT as the framework for enabling Integrated Sensing and Communication (ISAC) over IoT devices. ISACoT extends over existing devices via four aspects, namely time, frequency, space, and protocol. We argue that, as the multistatic communication infrastructure of IoT is adverse to device-free sensing (e.g., lack of precise time synchronization), the keystone of ISACoT should be to operate sensing in a monostatic mode (like radar). We tackle the fundamental time aspect based on Wi-Fi first, then explore the other three aspects with both preliminary proposals made and potential challenges raised for future extensions.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"2 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128781412","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}
The constant modulus (CM) waveform design, for Multiple-Input-Multiple-Output (MIMO) Integrated Sensing and Communication (ISAC) systems, is a key technology. The existing methods mainly include waveform design without Reconfigurable Intelligent Surface (RIS) or the sensing-based waveform design with RIS, which usually degrade the comprehensive performance. To address this issue, the comprehensive waveform design with RIS is proposed, where we jointly maximizing the Signal-to-Interference-and-Noise-Ratio (SINR) for radar and minimizing the RIS-aided Multiple User Interference (MUI). Due to the coupling effect between the phase shifts and waveform, the problem is difficult to solve. Additionally, the CM constraint on both the phase shifts and waveform along with the fractional SINR expression further aggravate the difficulty. To address these issues, a Decoupled Online Learning Network (DOL-Net) method is proposed using the characteristic of multiple input to multiple output mapping, which includes trainable network parameters module, loss calculation module and back-propagation module. Given fixed network parameters, the cost function can be calculated in the loss calculation module. Then, the network parameters are trained by the deep learning optimizer to minimize the loss function. Compared with the existing methods, the proposed method obtains 0.69 dB radar SINR enhancement and 138.8 % communication sum rate improvement.
{"title":"DOL-net: a decoupled online learning network method for RIS-assisted ISAC waveform design","authors":"Kai Zhong, Jinfeng Hu, Yaya Pei, Cunhua Pan","doi":"10.1145/3556562.3558574","DOIUrl":"https://doi.org/10.1145/3556562.3558574","url":null,"abstract":"The constant modulus (CM) waveform design, for Multiple-Input-Multiple-Output (MIMO) Integrated Sensing and Communication (ISAC) systems, is a key technology. The existing methods mainly include waveform design without Reconfigurable Intelligent Surface (RIS) or the sensing-based waveform design with RIS, which usually degrade the comprehensive performance. To address this issue, the comprehensive waveform design with RIS is proposed, where we jointly maximizing the Signal-to-Interference-and-Noise-Ratio (SINR) for radar and minimizing the RIS-aided Multiple User Interference (MUI). Due to the coupling effect between the phase shifts and waveform, the problem is difficult to solve. Additionally, the CM constraint on both the phase shifts and waveform along with the fractional SINR expression further aggravate the difficulty. To address these issues, a Decoupled Online Learning Network (DOL-Net) method is proposed using the characteristic of multiple input to multiple output mapping, which includes trainable network parameters module, loss calculation module and back-propagation module. Given fixed network parameters, the cost function can be calculated in the loss calculation module. Then, the network parameters are trained by the deep learning optimizer to minimize the loss function. Compared with the existing methods, the proposed method obtains 0.69 dB radar SINR enhancement and 138.8 % communication sum rate improvement.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132985392","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}
Shuaishuai Guo, Dingyan Cong, Jia Ye, Shuping Dang, N. Saeed
This paper proposes a non-uniform beam pattern modulation (NUBPM) scheme for integrated sensing and communication (ISAC) systems, where the beam pattern indices are adopted to carry additional information, increasing the spectral efficiency. We analyze the sensing performance and spectral efficiency of the proposed NUBPM scheme, which depends on the beam patterns and their activation probabilities. Furthermore, to improve the performance of the NUBPM-enabled ISAC systems, we investigate the beam pattern set design and activation probability optimization. Simulation results show that the proposed scheme considerably outperforms existing ISAC designs in spectral efficiency while keeping the same sensing performance. The gained spectral efficiency through the proposed scheme can also be traded off for novel equilibria between communication and sensing performance for ISAC systems.
{"title":"Non-uniform beam pattern modulation for joint sensing and communication in 6G networks","authors":"Shuaishuai Guo, Dingyan Cong, Jia Ye, Shuping Dang, N. Saeed","doi":"10.1145/3556562.3558569","DOIUrl":"https://doi.org/10.1145/3556562.3558569","url":null,"abstract":"This paper proposes a non-uniform beam pattern modulation (NUBPM) scheme for integrated sensing and communication (ISAC) systems, where the beam pattern indices are adopted to carry additional information, increasing the spectral efficiency. We analyze the sensing performance and spectral efficiency of the proposed NUBPM scheme, which depends on the beam patterns and their activation probabilities. Furthermore, to improve the performance of the NUBPM-enabled ISAC systems, we investigate the beam pattern set design and activation probability optimization. Simulation results show that the proposed scheme considerably outperforms existing ISAC designs in spectral efficiency while keeping the same sensing performance. The gained spectral efficiency through the proposed scheme can also be traded off for novel equilibria between communication and sensing performance for ISAC systems.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116524905","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}
Jiaqi Zou, Yuanhao Cui, Z. Zou, Yuyang Liu, Guanyu Zhang, Songlin Sun, W. Yuan
This paper focuses on the beamforming algorithm for UAV-to-vehicle communications. To deal with high communication overhead caused by beam tracking in high mobility communication scenarios, we utilize the inherent vision functionality of UAV platforms and propose a vision-assisted beamforming framework. We propose to use a deep-learning-based network for vehicle detection. Based on the predicted positions of vehicles, we propose a lightweight beamforming algorithm to save beam tracking overhead. Experiments and simulations are implemented on the UAV detection and tracking (UAVDT) dataset, which shows that the proposed algorithm gains a significant performance on received signal-to-interference-plus-noise ratio (SINR).
{"title":"Computer vision assisted mmWave beamforming for UAV-to-vehicle links","authors":"Jiaqi Zou, Yuanhao Cui, Z. Zou, Yuyang Liu, Guanyu Zhang, Songlin Sun, W. Yuan","doi":"10.1145/3556562.3558565","DOIUrl":"https://doi.org/10.1145/3556562.3558565","url":null,"abstract":"This paper focuses on the beamforming algorithm for UAV-to-vehicle communications. To deal with high communication overhead caused by beam tracking in high mobility communication scenarios, we utilize the inherent vision functionality of UAV platforms and propose a vision-assisted beamforming framework. We propose to use a deep-learning-based network for vehicle detection. Based on the predicted positions of vehicles, we propose a lightweight beamforming algorithm to save beam tracking overhead. Experiments and simulations are implemented on the UAV detection and tracking (UAVDT) dataset, which shows that the proposed algorithm gains a significant performance on received signal-to-interference-plus-noise ratio (SINR).","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"19 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114029099","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}
Changfeng Ding, Cheng Zeng, Chuanwen Chang, Jun-Bo Wang, Min Lin
Integrated sensing and communication (ISAC) is an emerging technology for next generation communication networks. In this paper, we propose to design the ISAC system by jointly considering radar sensing and ultra-reliable low-latency communication (URLLC), which needs a joint precoding design for radar and URLLC. Then, we formulate a transmit power minimization problem by jointly considering the performance requirements of radar sensing and latency in URLLC. By using approximation method and quadratic transform based fractional programming method, the optimization problem can be efficiently solved. Simulation results verify that our proposed design can minimize the transmit power consumption while guaranteeing the requirements of radar sensing and URLLC.
{"title":"Joint precoding for MIMO radar and URLLC in ISAC systems","authors":"Changfeng Ding, Cheng Zeng, Chuanwen Chang, Jun-Bo Wang, Min Lin","doi":"10.1145/3556562.3558566","DOIUrl":"https://doi.org/10.1145/3556562.3558566","url":null,"abstract":"Integrated sensing and communication (ISAC) is an emerging technology for next generation communication networks. In this paper, we propose to design the ISAC system by jointly considering radar sensing and ultra-reliable low-latency communication (URLLC), which needs a joint precoding design for radar and URLLC. Then, we formulate a transmit power minimization problem by jointly considering the performance requirements of radar sensing and latency in URLLC. By using approximation method and quadratic transform based fractional programming method, the optimization problem can be efficiently solved. Simulation results verify that our proposed design can minimize the transmit power consumption while guaranteeing the requirements of radar sensing and URLLC.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123058826","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}
Xiaoyang Li, Zidong Han, Ziqin Zhou, Qinyu Zhang, Kaibin Huang, Yi Gong
To facilitate the data collection process in 6G radio access network, the advanced integrated sensing and communication (ISAC) technology has been proposed by sharing the radio resource for both data transmission and radar sensing. Despite the promising performance of ISAC, the power supply of million of radar sensors distributed in remote or even dangerous areas has not been resolved yet. To tackle this problem, wireless power transfer (WPT) is expected to enable the wirelessly powered ISAC, where the edge nodes equipped with multiple antennas are powered by the beacon and then perform ISAC. To improve the sensing accuracy while guaranteeing the communication throughput, the power control, WPT energy beamforming, and ISAC beamforming are jointly optimized, which results in a non-convex problem. To derive a practical solution, the semi-definite relaxation together with the properties for achieving the optimum are exploited. Simulations and experiments are further conducted to verify the effectiveness of the proposed design.
{"title":"Wirelessly powered integrated sensing and communication","authors":"Xiaoyang Li, Zidong Han, Ziqin Zhou, Qinyu Zhang, Kaibin Huang, Yi Gong","doi":"10.1145/3556562.3558564","DOIUrl":"https://doi.org/10.1145/3556562.3558564","url":null,"abstract":"To facilitate the data collection process in 6G radio access network, the advanced integrated sensing and communication (ISAC) technology has been proposed by sharing the radio resource for both data transmission and radar sensing. Despite the promising performance of ISAC, the power supply of million of radar sensors distributed in remote or even dangerous areas has not been resolved yet. To tackle this problem, wireless power transfer (WPT) is expected to enable the wirelessly powered ISAC, where the edge nodes equipped with multiple antennas are powered by the beacon and then perform ISAC. To improve the sensing accuracy while guaranteeing the communication throughput, the power control, WPT energy beamforming, and ISAC beamforming are jointly optimized, which results in a non-convex problem. To derive a practical solution, the semi-definite relaxation together with the properties for achieving the optimum are exploited. Simulations and experiments are further conducted to verify the effectiveness of the proposed design.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123955122","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}
In order to solve the problem of mass raw data sharing among automated vehicles, millimeter wave (mmWave) communication is considered as an efficient technology to ensure the communication requirements of low-latency and high data rate between vehicles and roadside facilities. However, in the autonomous driving scenario, a fast and robust beam tracking algorithm is needed to ensure the quality of communication. We propose a sensing information assisted mmWave beam tracking algorithm combining both camera and light detection and ranging (LiDAR). The beam misalignment problem of the camera in the case of insufficient ambient light is solved and the robustness of the beam tracking algorithm is enhanced. The proposed algorithm in this paper is validated by the joint sensing and communication hardware platform in the mmWave frequency band, which can guarantee the high data rate communication performance regardless of sufficient and insufficient ambient light under the mobility scenarios.
{"title":"Research and verification of sensing information assisted millimeter wave beam tracking algorithm for automated vehicles","authors":"Qixun Zhang, B. Yu, Zhiyong Feng","doi":"10.1145/3556562.3558570","DOIUrl":"https://doi.org/10.1145/3556562.3558570","url":null,"abstract":"In order to solve the problem of mass raw data sharing among automated vehicles, millimeter wave (mmWave) communication is considered as an efficient technology to ensure the communication requirements of low-latency and high data rate between vehicles and roadside facilities. However, in the autonomous driving scenario, a fast and robust beam tracking algorithm is needed to ensure the quality of communication. We propose a sensing information assisted mmWave beam tracking algorithm combining both camera and light detection and ranging (LiDAR). The beam misalignment problem of the camera in the case of insufficient ambient light is solved and the robustness of the beam tracking algorithm is enhanced. The proposed algorithm in this paper is validated by the joint sensing and communication hardware platform in the mmWave frequency band, which can guarantee the high data rate communication performance regardless of sufficient and insufficient ambient light under the mobility scenarios.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116223040","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}
This paper investigates the design of hybrid beamforming transmitter, radar receiver, and communication receiver in an orthogonal frequency division multiplexing (OFDM) dual-function radar-communication (DFRC) system. Specifically, we formulate the joint design problem as optimizing the spectrum efficiency (SE) of communication and the signal-to-interference noise ratio (SINR) of radar sensing. Due to the coupling between the digital and analog beamformers in the hybrid beamforming structure, the resultant problem is NP-hard. Towards this end, a consensus alternating direction method of multipliers (CADMM) approach is developed, by decoupling the digital precoder and the analog precoder with auxiliary variables. In each iteration, the digital precoder can be analytically obtained, while the analog precoder is designed via a phase-only beamforming method. Both the communication and radar receivers are optimized through the generalized eigenvalue decomposition. Numerical simulations are provided to demonstrate the effectiveness of the proposed design approach.
{"title":"Joint design of hybrid transmitter and receiver in multi-user OFDM dual-function radar-communication system","authors":"Junjie Zeng, Bin Liao","doi":"10.1145/3556562.3558572","DOIUrl":"https://doi.org/10.1145/3556562.3558572","url":null,"abstract":"This paper investigates the design of hybrid beamforming transmitter, radar receiver, and communication receiver in an orthogonal frequency division multiplexing (OFDM) dual-function radar-communication (DFRC) system. Specifically, we formulate the joint design problem as optimizing the spectrum efficiency (SE) of communication and the signal-to-interference noise ratio (SINR) of radar sensing. Due to the coupling between the digital and analog beamformers in the hybrid beamforming structure, the resultant problem is NP-hard. Towards this end, a consensus alternating direction method of multipliers (CADMM) approach is developed, by decoupling the digital precoder and the analog precoder with auxiliary variables. In each iteration, the digital precoder can be analytically obtained, while the analog precoder is designed via a phase-only beamforming method. Both the communication and radar receivers are optimized through the generalized eigenvalue decomposition. Numerical simulations are provided to demonstrate the effectiveness of the proposed design approach.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130579040","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}
We design and test over-the-air for the first time, a joint dual-functional radar communication waveform for an integrated radar sensing and multi-user multiple input multiple output (MIMO) based orthogonal frequency division multiplexing (OFDM) communication system. Unlike existing work, the prototyping testbed in this paper can realize radar sensing and communication using the same time, frequency and spatial resources. The designed dual-functional integrated sensing and communication (ISAC) waveform in this work can be easily incorporated into existing communication standards where OFDM is used. The experiment observes a graceful trade-off between radar sensing and communication after comprehensive measurement on communication constellation diagrams and radar beampattern quality. This experiment also reveals the mutual impacts between communication signals using different modulation schemes and radar beampattern performance.
{"title":"Proof of concept experiments of joint waveform design for integrated sensing and communications","authors":"T. Xu, F. Liu, C. Masouros, I. Darwazeh","doi":"10.1145/3556562.3558568","DOIUrl":"https://doi.org/10.1145/3556562.3558568","url":null,"abstract":"We design and test over-the-air for the first time, a joint dual-functional radar communication waveform for an integrated radar sensing and multi-user multiple input multiple output (MIMO) based orthogonal frequency division multiplexing (OFDM) communication system. Unlike existing work, the prototyping testbed in this paper can realize radar sensing and communication using the same time, frequency and spatial resources. The designed dual-functional integrated sensing and communication (ISAC) waveform in this work can be easily incorporated into existing communication standards where OFDM is used. The experiment observes a graceful trade-off between radar sensing and communication after comprehensive measurement on communication constellation diagrams and radar beampattern quality. This experiment also reveals the mutual impacts between communication signals using different modulation schemes and radar beampattern performance.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133487602","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}
Emerging device-free sensing technologies and applications promote the development of indoor ubiquitous sensing. Device-free sensing with machine learning mechanisms enable detection, recognition automatically, without required explicit programming. Because of concern of indoor sensing privacy and ubiquitous sensing ability, it is really necessary to conduct an in-depth survey on device-free sensing security training and cross-domain sensing issues. Existing surveys have two important problems: weak robustness and low efficiency. To address them, this article put forward to learn domain independent features, model training and inference localization based on federated transfer learning. Moreover, several efficient methods are proposed to provide a distributed edge device-free sensing mechanism with sensing data privacy protection, low time cost, communication, computing and energy resources. We implement the proposed mechanism and carry out experiments with Widar3.0 datasets to evaluate its performance. The results demonstrate that our mechanism performs better for cross-domain device-free sensing while preserving user data privacy and saving resources.
{"title":"An efficient cross-domain device-free gesture recognition method for ISAC with federated transfer learning","authors":"Wanbin Qi, Yanxi Xie, Hao Zhang, Jiaen Zhou, Ronghui Zhang, Xiaojun Jing","doi":"10.1145/3556562.3558575","DOIUrl":"https://doi.org/10.1145/3556562.3558575","url":null,"abstract":"Emerging device-free sensing technologies and applications promote the development of indoor ubiquitous sensing. Device-free sensing with machine learning mechanisms enable detection, recognition automatically, without required explicit programming. Because of concern of indoor sensing privacy and ubiquitous sensing ability, it is really necessary to conduct an in-depth survey on device-free sensing security training and cross-domain sensing issues. Existing surveys have two important problems: weak robustness and low efficiency. To address them, this article put forward to learn domain independent features, model training and inference localization based on federated transfer learning. Moreover, several efficient methods are proposed to provide a distributed edge device-free sensing mechanism with sensing data privacy protection, low time cost, communication, computing and energy resources. We implement the proposed mechanism and carry out experiments with Widar3.0 datasets to evaluate its performance. The results demonstrate that our mechanism performs better for cross-domain device-free sensing while preserving user data privacy and saving resources.","PeriodicalId":203933,"journal":{"name":"Proceedings of the 1st ACM MobiCom Workshop on Integrated Sensing and Communications Systems","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127654763","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：