Intelligent compression and feedback technology for multi-node collaborative ISAC

CHEN Lu; LOU Xingliang; XIA wenchao; SHEN Luyao

您当前的位置：

首页 >

文章列表页 >

Intelligent compression and feedback technology for multi-node collaborative ISAC

更新时间：2026-03-03

- Intelligent compression and feedback technology for multi-node collaborative ISAC
- Chinese Journal on Internet of Things (2026)
- 作者机构：
  
  1.南京邮电大学教育部泛在网络健康服务系统工程研究中心，江苏南京 210003
  2.南京邮电大学江苏省无线通信与物联网重点实验室，江苏南京 210003
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China (NSFC) Young Scientists Fund(62201285)
- DOI：
  CLC： TN92
- Received：26 March 2025，
  
  Revised：2025-06-13，
  
  Accepted：20 June 2025，
- 稿件说明：
移动端阅览
CHEN Lu, LOU Xingliang, XIA wenchao, et al. Intelligent compression and feedback technology for multi-node collaborative ISAC[J/OL]. Chinese Journal on Internet of Things, 2026.
DOI：

CHEN Lu, LOU Xingliang, XIA wenchao, et al. Intelligent compression and feedback technology for multi-node collaborative ISAC[J/OL]. Chinese Journal on Internet of Things, 2026. DOI：

摘要

在通感一体化（ISAC

integrated sensing and communication）系统中，基站、无线接入点（AP

access point）等各类节点相互协作可以增强感知的广度和精度。然而，节点与融合中心之间的回传链路容量有限且存在异构性，导致感知信号无法直接上传融合。针对该问题，提出了一种基于自编码器技术的感知信号智能压缩反馈方法。具体来说，编码器在AP处利用深度神经网络从感知信号中提取特征，并通过回传链路上传至融合中心。融合中心利用解码器进行感知信号重构，并基于重构信号和广义似然比（GLRT

generalized likelihood ratio test）检测器进行目标检测。此外，考虑到不同节点的回传链路容量不同，提出了基于迁移学习的自适应压缩反馈方法，在预训练模型基础上，冻结该模型的大部分层（这些层已充分学习信号特征），利用少量样本对模型结构进行微调以适应不同压缩比。最后，仿真结果表明，与决策融合方案相比，所提方法在压缩比为1/2时的平均检测概率提升了33.92%，能够在感知性能和反馈开销之间取得较好的平衡。

Abstract

In ISAC systems

the collaboration between various nodes

such as base stations and radio AP

can enhance sensing scope and accuracy. However

capacity-constrained and heterogeneous backhaul links between nodes and the fusion center impede the direct uploading and fusion of sensing signals. To address this issue

an intelligent compressed feedback method for sensing signals based on autoencoder techniques was proposed. Specifically

features were extracted from the signals at the AP by an encoder using deep neural networks and uploaded to the fusion center via backhaul links. The fusion center used a decoder to reconstruct signals

and then performed target detection via the GLRT detector. Moreover

considering heterogeneous backhaul capacities

an adaptive compression feedback method based on transfer learning was proposed. Based on the pre-trained model

most layers which had already sufficiently learned signal features

were frozen. The model structure was then fine-tuned with few samples to adapt to varying compression ratios. Finally

simulation results validate the proposed method achieves a 33.92% improvement in average detection probability over the decision-fusion method at a 1/2 compression ratio

showing a favorable balance between sensing performance and feedback overhead.

关键词

Keywords

references

潘成康 . 通信感知一体化技术思考 [J ] . 中兴通讯技术 , 2022 , 28 ( 5 ): 53 - 56 .

PAN C K . Reflections on Integrated Sensing and Communication Technology [J ] . ZTE Technology Journal , 2022 , 28 ( 5 ): 53 - 56 .

LIU X , HUANG T Y , SHLEZINGER N , et al . Joint Transmit Beamforming for Multiuser MIMO Communications and MIMO Radar [J ] . IEEE Transactions on Signal Processing , 2020 , 68 : 3929 - 3944 .

LIU F , LIU Y F , LI A , et al . Cramér-Rao Bound Optimization for Joint Radar-Communication Beamforming [J ] . IEEE Transactions on Signal Processing , 2022 , 70 : 240 - 253 .

ATTIAH K M , YU W . Active beamforming for integrated sensing and communication [C ] // 2023 IEEE International Conference on Communications Workshops (ICC Workshops) . Rome, Italy : IEEE Press , 2023 : 1469 - 1474 .

王为栋 , 高晖 , 粟欣 , 等 . 面向车联网的感知辅助通信的大规模 MIMO-OTFS 鲁棒传输方案 [J ] . 物联网学报 , 2023 , 7 ( 4 ): 39 - 51 .

WANG W D , GAO H , SU X , et al . A massive MIMO-OTFS robust transmission scheme for vehicular networks using sensing-assisted communication [J ] . Chinese Journal on Internet of Things , 2023 , 7 ( 4 ): 39 - 51 .

LIYANAARACHCHI S D , BAQUERO BARNETO C , RIIHONEN T , et al . Joint Multi-User Communication and MIMO Radar Through Full-Duplex Hybrid Beamforming [C ] // 2021 1st IEEE International Online Symposium on Joint Communications & Sensing (JC&S) . Dresden, Germany : IEEE Press , 2021 : 1 - 5 .

WANG X Y , FEI Z S , ZHANG J A , et al . Constrained Utility Maximization in Dual-Functional Radar-Communication Multi-UAV Networks [J ] . IEEE Transactions on Communications , 2021 , 69 ( 4 ): 2660 - 2672 .

HUANG Y , FANG Y , LI X M , et al . Coordinated Power Control for Network Integrated Sensing and Communication [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 12 ): 13361 - 13365 .

BEHDAD Z , DEMIR Ö T , SUNG K W , et al . Power Allocation for Joint Communication and Sensing in Cell-Free Massive MIMO [C ] // GLOBECOM 2022 - 2022 IEEE Global Communications Conference . Rio de Janeiro, Brazil : IEEE Press , 2022 : 4081 - 4086 .

LOU X Y , XIA W C , WONG K K , et al . Power Optimization for Integrated Active and Passive Sensing in DFRC Systems [J ] . IEEE Transactions on Communications , 2024 , 72 ( 6 ): 3365 - 3377 .

DONG Y Y , WANG H , YANG Z H , et al . Cell-free ISAC massive MIMO systems with capacity-constrained fronthaul links [J ] . Digital Signal Processing , 2024 , 145 : 104341 .

WEN C K , SHIH W T , JIN S . Deep Learning for Massive MIMO CSI Feedback [J ] . IEEE Wireless Communications Letters , 2018 , 7 ( 5 ): 748 - 751 .

HE H T , WEN C K , JIN S , et al . Deep learning-based channel estimation for beamspace mmWave massive MIMO systems [J ] . IEEE Wireless Communications Letters , 2018 , 7 ( 5 ): 852 - 855 .

HE C F , HU Y , CHEN Y , et al . Joint Power Allocation and Channel Assignment for NOMA With Deep Reinforcement Learning [J ] . IEEE Journal on Selected Areas in Communications , 2019 , 37 ( 10 ): 2200 - 2210 .

HUANG H J , SONG Y S , YANG J , et al . Deep-Learning-Based Millimeter-Wave Massive MIMO for Hybrid Precoding [J ] . IEEE Transactions on Vehicular Technology , 2019 , 68 ( 3 ): 3027 - 3032 .

BJÖRNSON E , HOYDIS J , SANGUINETTI L . Massive mimo networks: Spectral, energy, and hardware efficiency [J ] . Foundations and Trends in Signal Processing , 2017 , 11 ( 3-4 ): 154 - 655 .

ZHAO N , WANG Y L , ZHANG Z , et al . Joint Transmit and Receive Beamforming Design for Integrated Sensing and Communication [J ] . IEEE Communications Letters , 2022 , 26 ( 3 ): 662 - 666 .

DEMIR Ö T , BJÖRNSON E , SANGUINETTI L . Foundations of user-centric cell-free massive MIMO [J ] . Foundations and Trends in Signal Processing , 2021 , 14 ( 3-4 ): 162 - 472 .

ZENG J , SUN J L , GUI G , et al . Downlink CSI Feedback Algorithm With Deep Transfer Learning for FDD Massive MIMO Systems [J ] . IEEE Transactions on Cognitive Communications and Networking , 2021 , 7 ( 4 ): 1253 - 1265 .

KHAWAR A , ABDELHADI A , CLANCY C . Target Detection Performance of Spectrum Sharing MIMO Radars [J ] . IEEE Sensors Journal , 2015 , 15 ( 9 ): 4928 - 4940 .

KAI S , HALL P . Fundamentals of Statistical Signal Processing,Volume II:Detection Theory [M ] . Englewood Cliffs, NJ : Prentice-Hall , 1993 .

BEKKERMAN I , TABRIKIAN J . Target Detection and Localization Using MIMO Radars and Sonars [J ] . IEEE Transactions on Signal Processing , 2006 , 54 ( 10 ) : 3873 - 3883 .

LOU X L , XIA W C , CHEN S Y , et al . Precoding for Multi-Static ISAC System With Integrated Active and Passive Sensing [J ] . IEEE Communications Letters , 2024 , 28 ( 9 ) : 2036 - 2040 .

XIA W C , ZHENG G , ZHU Y X , et al . A Deep Learning Framework for Optimization of MISO Downlink Beamforming [J ] . IEEE Transactions on Communications , 2020 , 68 ( 3 ): 1866 - 1880 .

CUI Y M , GUO J J , WEN C K , et al . Communication-Efficient Personalized Federated Edge Learning for Massive MIMO CSI Feedback [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 7 ): 7362 - 7375 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Implicit smartphone authentication via multimodal data and transfer autoencoders

Siamese GCN empowered fingerprinting indoor localization using few-shot transfer learning

A transfer reinforcement learning-based approach for cross-domain charging station recommendation in the Internet of vehicles

Related Author

XU Zi’ang

SHI Zheng

GU Hao

HUANG Hao

WANG Yu

XIA Wenchao

ZHAO Haitao

ZHU Hongbo

Related Institution

Brunel London School, North China University of Technology

School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications

School of Integrated Circuits, Southeast University

Jiangsu Province Key Laboratory of Wireless Communication and Internet of Things

School of Internet of Things, Nanjing University of Posts and Telecommunications

⁰