基于人工智能的无线通信数据标注技术研究进展

张瀚文; 白崧言; 李凡; 高琳; 罗亚梅

doi:10.11959/j.issn.1000-0801.DXKX260053

您当前的位置：

首页 >

文章列表页 >

基于人工智能的无线通信数据标注技术研究进展

更新时间：2026-05-11

- 基于人工智能的无线通信数据标注技术研究进展
- Recent Advances in AI-Based Data Annotation for Wireless Communications
- 电信科学 2026年
- 作者机构：
  
  1).成都信息工程大学人工智能学院 , 成都中国 610225
  2).成都市武侯区数字健康与医学智能产业研究院医学智能研究所, 成都中国 610041
  3).西南医科大学医学信息与工程学院, 泸州中国 646000
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.DXKX260053
  中图分类号：
- 收稿：2026-01-18，
  
  修回：2026-04-02，
  
  录用：2026-05-11，
- 稿件说明：
移动端阅览
张瀚文, 白崧言, 李凡, 等. 基于人工智能的无线通信数据标注技术研究进展[J/OL]. 电信科学, 2026.

Hanwen Zhang, Songyan Bai, Fan Li, et al. Recent Advances in AI-Based Data Annotation for Wireless Communications[J/OL]. Telecommunications Science, 2026.
张瀚文, 白崧言, 李凡, 等. 基于人工智能的无线通信数据标注技术研究进展[J/OL]. 电信科学, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260053.

Hanwen Zhang, Songyan Bai, Fan Li, et al. Recent Advances in AI-Based Data Annotation for Wireless Communications[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260053.

摘要

随着无线通信系统向 5G-A 与 6G 演进，网络环境的复杂性和动态性不断增强，数据驱动方法在无线系统中的应用日益广泛。然而，无线通信数据具有连续流、强时变和场景依赖等特点，高质量标注数据的获取与长期维护成本高昂，已成为制约电信智能化发展的关键瓶颈。围绕无线通信中的数据标注问题，本文系统梳理了无线数据的主要模态、标签形态及真值来源，并分析了标注噪声与数据分布漂移的形成机制。进一步结合频谱监测、干扰识别、调制识别和 Wi-Fi 感知等典型场景，综述主动学习、弱监督、半监督、自监督、噪声鲁棒学习、生成式模型、大模型等技术路线，并比较其在降低标注成本与提升标注质量方面的优势与局限。最后，面向未来 6G 与 AI-RAN 场景，探讨了基础模型、持续学习与隐私约束下标注优化等潜在研究方向，为无线通信智能化标注体系的构建提供参考。

Abstract

With the evolution of wireless communication systems toward 5G-Advanced and 6G

network environments are becoming increasingly complex and dynamic

making data-driven approaches and artificial intelligence essential for intelligent wireless systems. However

wireless communication data exhibit continuous streams

strong temporal variations

and high scenario dependency

resulting in high costs for acquiring and maintaining high-quality labeled data

which has become a critical bottleneck for practical deployment. Focusing on the problem of data annotation in wireless communications

this paper systematically reviews the main data modalities

label forms

and ground-truth acquisition mechanisms

and analyzes the sources of annotation noise and data distribution drift. We further survey several representative learning paradigms

including active learning

weak supervision

semi-supervised learning

self-supervised learning

noise-robust learning

generative models

and large-model-based approaches

and discuss their advantages and limitations in reducing annotation cost and improving label quality across typical applications such as spectrum monitoring

interference identification

modulation recognition

and Wi-Fi sensing. Finally

future research directions are outlined toward 6G and AI-RAN

including foundation models

continual learning

and privacy-aware annotation

aiming to provide insights for building low-cost and reliable annotation pipelines for intelligent wireless systems.

关键词

Keywords

references

O’SHEA T , HOYDIS J . An introduction to deep learning for the physical layer [J ] . IEEE Transactions on Cognitive Communications and Networking , 2017 , 3 ( 4 ): 563 - 75 .

谷志群 , 张佳玮 , 纪越峰 , et al . 数据与模型协同驱动的智能光网络架构与关键技术 [J ] . 电信科学 , 2024 , 38 ( 7 ): 18 - 30 .

O’SHEA T J , ROY T , CLANCY T C . Over-the-air deep learning based radio signal classification [J ] . IEEE Journal of Selected Topics in Signal Processing , 2018 , 12 ( 1 ): 168 - 79 .

SOLTANI N , ZHANG J , SALEHI B , et al . Learning from the best: Active learning for wireless communications [J ] . IEEE Wireless Communications , 2024 , 31 ( 4 ): 177 - 83 .

章坚武 , 王路鑫 , 孙玲芬 , et al . 人工智能在 5G 系统中的应用综述 [J ] . 电信科学 , 2024 , 37 ( 5 ): 14 - 31 .

李攀攀 , 谢正霞 , 乐光学 , et al . 基于深度学习的无线通信接收方法研究进展与趋势 [J ] . 电信科学 , 2024 , 38 ( 2 ): 1 - 17 .

GEBRU T , MORGENSTERN J , VECCHIONE B , et al . Datasheets for datasets [J ] . Communications of the ACM , 2021 , 64 ( 12 ): 86 - 92 .

HILBURN B , WEST N , O'SHEA T , et al . SigMF: The signal metadata format; proceedings of the Proceedings of the GNU Radio Conference, F, 2018 [C ] .

O’SHEA T J , CORGAN J , CLANCY T C . Convolutional radio modulation recognition networks; proceedings of the International conference on engineering applications of neural networks, F, 2016 [C ] . Springer .

O'SHEA T J , WEST N . Radio machine learning dataset generation with gnu radio; proceedings of the Proceedings of the GNU radio conference, F, 2016 [C ] .

VAN DEN BERGH B , GIUSTINIANO D , CORDOBéS H , et al . Electrosense: Crowdsourcing spectrum monitoring; proceedings of the 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), F, 2017 [C ] . IEEE .

YANG J , CHEN X , ZOU H , et al . SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing [J ] . Patterns , 2023 , 4 ( 3 ).

ZHANG Y , ZHENG Y , QIAN K , et al . Widar3. 0: Zero-effort cross-domain gesture recognition with Wi-Fi [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021 , 44 ( 11 ): 8671 - 88 .

ALKHATEEB A . DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications [J ] . arXiv preprint arXiv: 190206435 , 2019 .

RAPPAPORT T S , MACCARTNEY G R , SAMIMI M K , et al . Wideband millimeter-wave propagation measurements and channel models for future wireless communication system design [J ] . IEEE transactions on Communications , 2015 , 63 ( 9 ): 3029 - 56 .

CALVO-PALOMINO R , CORDOBéS H , ENGEL M , et al . Electrosense+: Crowdsourcing radio spectrum decoding using IoT receivers [J ] . Computer Networks , 2020 , 174 : 107231 .

WELINDER P , BRANSON S , PERONA P , et al . The multidimensional wisdom of crowds [J ] . Advances in neural information processing systems , 2010 , 23 .

王金强 , 孙闽红 , 唐向宏 , et al . 小样本下雷达复合干扰半监督迁移学习识别方法 [J ] . 电信科学 , 2024 , 39 ( 10 ): 15 - 28 .

HAO C , WAN X , FENG D , et al . Satellite-based radio spectrum monitoring: Architecture, applications, and challenges [J ] . IEEE Network , 2021 , 35 ( 4 ): 20 - 7 .

PFAMMATTER D , GIUSTINIANO D , LENDERS V . A software-defined sensor architecture for large-scale wideband spectrum monitoring; proceedings of the Proceedings of the 14th International Conference on Information Processing in Sensor Networks, F, 2015 [C ] .

LIU W , CHWALISZ M , FORTUNA C , et al . Heterogeneous spectrum sensing: challenges and methodologies [J ] . EURASIP Journal on Wireless Communications and Networking , 2015 , 2015 ( 1 ): 70 .

SETTLES B . Active learning literature survey [J ] . 2009 .

BOEGNER L , GULATI M , VANHOY G , et al . Large scale radio frequency signal classification [J ] . arXiv preprint arXiv: 220709918 , 2022 .

SENER O , SAVARESE S . Active learning for convolutional neural networks: A core-set approach [J ] . arXiv preprint arXiv: 170800489 , 2017 .

NORTHCUTT C , JIANG L , CHUANG I . Confident learning: Estimating uncertainty in dataset labels [J ] . Journal of Artificial Intelligence Research , 2021 , 70 : 1373 - 411 .

ZHU G , HU Y , GAO W , et al . CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing [J ] . arXiv preprint arXiv: 250521866 , 2025 .

HUANG S , LI K , YOU D , et al . Wimans: A benchmark dataset for wifi-based multi-user activity sensing; proceedings of the European Conference on Computer Vision, F, 2024 [C ] . Springer .

ZHOU Z-H . A brief introduction to weakly supervised learning [J ] . National science review , 2018 , 5 ( 1 ): 44 - 53 .

FERRAND P , GUILLAUD M , STUDER C , et al . Wireless channel charting: Theory, practice, and applications [J ] . IEEE Communications Magazine , 2023 , 61 ( 6 ): 124 - 30 .

ALHUSSEIN O , ZHANG N , MUHAIDAT S , et al . Active ML for 6G: Towards Efficient Data Generation, Acquisition, and Annotation [J ] . arXiv preprint arXiv: 240603630 , 2024 .

RATNER A J , DE SA C M , WU S , et al . Data programming: Creating large training sets, quickly [J ] . Advances in neural information processing systems , 2016 , 29 .

TARVAINEN A , VALPOLA H . Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results [J ] . Advances in neural information processing systems , 2017 , 30 .

SOHN K , BERTHELOT D , CARLINI N , et al . Fixmatch: Simplifying semi-supervised learning with consistency and confidence [J ] . Advances in neural information processing systems , 2020 , 33 : 596 - 608 .

BERTHELOT D , CARLINI N , GOODFELLOW I , et al . Mixmatch: A holistic approach to semi-supervised learning [J ] . Advances in neural information processing systems , 2019 , 32 .

ERICSSON L , GOUK H , HOSPEDALES T M . How well do self-supervised models transfer?; proceedings of the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, F, 2021 [C ] .

LI M , LI O , LIU G , et al . Generative adversarial networks-based semi-supervised automatic modulation recognition for cognitive radio networks [J ] . Sensors , 2018 , 18 ( 11 ): 3913 .

BALEVI E , ANDREWS J G . Wideband channel estimation with a generative adversarial network [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 5 ): 3049 - 60 .

CHI G , YANG Z , WU C , et al . RF-diffusion: Radio signal generation via time-frequency diffusion; proceedings of the Proceedings of the 30th Annual International Conference on Mobile Computing and Networking, F, 2024 [C ] .

FOOLADGAR F , TO M N N , MOUSAVI P , et al . Manifold DivideMix: A semi-supervised contrastive learning framework for severe label noise; proceedings of the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, F, 2024 [C ] .

LIU B , GAO S , LIU X , et al . WiFo: Wireless foundation model for channel prediction [J ] . Science China Information Sciences , 2025 , 68 ( 6 ): 162302 .

BUFFELLI D , DAS S , LIN Y-W , et al . Towards a Foundation Model for Communication Systems [J ] . arXiv preprint arXiv: 250514603 , 2025 .

BOATENG G O , SAMI H , ALAGHA A , et al . A survey on large language models for communication, network, and service management: Application insights, challenges, and future directions [J ] . IEEE Communications Surveys & Tutorials , 2025 .

SIINO M , GIULIANO F , TINNIRELLO I . Integrating Large Language Models into Network Testbeds: A Novel Approach for Automated Experimentation and Optimization [J ] . Available at SSRN 5187143 .

ASH J T , ZHANG C , KRISHNAMURTHY A , et al . Deep batch active learning by diverse, uncertain gradient lower bounds [J ] . arXiv preprint arXiv: 190603671 , 2019 .

SHI Y , DAVASLIOGLU K , SAGDUYU Y E , et al . Deep learning for RF signal classification in unknown and dynamic spectrum environments; proceedings of the 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), F, 2019 [C ] . IEEE .

RATNER A , BACH S H , EHRENBERG H , et al . Snorkel: rapid training data creation with weak supervision [J ] . The VLDB Journal , 2020 , 29 ( 2 ): 709 - 30 .

BACH S H , RODRIGUEZ D , LIU Y , et al . Snorkel drybell: A case study in deploying weak supervision at industrial scale; proceedings of the Proceedings of the 2019 International Conference on Management of Data, F, 2019 [C ] .

STUDER C , MEDJKOUH S , GONULTAş E , et al . Channel charting: Locating users within the radio environment using channel state information [J ] . IEEE Access , 2018 , 6 : 47682 - 98 .

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [J ] . Communications of the ACM , 2020 , 63 ( 11 ): 139 - 44 .

YANG L , ZHANG Z , SONG Y , et al . Diffusion models: A comprehensive survey of methods and applications [J ] . ACM computing surveys , 2023 , 56 ( 4 ): 1 - 39 .

ROY T , O'SHEA T , WEST N . Generative adversarial radio spectrum networks; proceedings of the Proceedings of the ACM Workshop on Wireless Security and Machine Learning, F, 2019 [C ] .

CHEN Y , SHEN X , HU S X , et al . Boosting co-teaching with compression regularization for label noise; proceedings of the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, F, 2021 [C ] .

BOMMASANI R , HUDSON D A , ADELI E , et al . On the opportunities and risks of foundation models [J ] . arXiv preprint arXiv: 210807258 , 2021 .

BROWN T , MANN B , RYDER N , et al . Language models are few-shot learners [J ] . Advances in neural information processing systems , 2020 , 33 : 1877 - 901 .

LEE D-H . Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks; proceedings of the Workshop on challenges in representation learning, ICML, F, 2013 [C ] . Atlanta .

NGUYEN D N , HOANG D T , DOBRE O A , et al . Generative AI for Communications Systems: Fundamentals, Applications, and Prospects [M ] . John Wiley & Sons , 2026 .

KAYA O , KARABULUT M A , SHAH A S , et al . Modulation Classifier Based on Deep Learning for Beyond 5G Communications; proceedings of the 2024 47th International Conference on Telecommunications and Signal Processing (TSP), F, 2024 [C ] . IEEE .

ELEZI I , YU Z , ANANDKUMAR A , et al . Not all labels are equal: Rationalizing the labeling costs for training object detection; proceedings of the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, F, 2022 [C ] .

SCULLEY D , HOLT G , GOLOVIN D , et al . Hidden technical debt in machine learning systems [J ] . Advances in neural information processing systems , 2015 , 28 .

BRECK E , CAI S , NIELSEN E , et al . The ML test score: A rubric for ML production readiness and technical debt reduction; proceedings of the 2017 IEEE international conference on big data (big data), F, 2017 [C ] . IEEE .

TZIOUVARAS A , FORTUNA C , FLOROS G , et al . Towards Reliable AI in 6G: Detecting Concept Drift in Wireless Network [J ] . arXiv preprint arXiv: 250800042 , 2025 .

MOHSIN M A , UMER M , BILAL A , et al . Continual Learning for Wireless Channel Prediction [J ] . arXiv preprint arXiv: 250622471 , 2025 .

GUO S , ZHONG Y , FENG Z , et al . Towards Transparent 6G AI-RAN: A Survey on Explainable Deep Reinforcement Learning for Intelligent Network Slicing [J ] . Journal of Information and Intelligence , 2025 .

QU Y , ZHANG Y , WANG Y , et al . Secure and privacy-preserving issues in integrated sensing and communication-enabled wireless networks: a survey [J ] . EURASIP Journal on Advances in Signal Processing , 2025 .

ROY K , HASAN T F , WU C , et al . FedWiLoc: Federated Learning for Privacy-Preserving WiFi Indoor Localization [J ] . arXiv preprint arXiv: 251218207 , 2025 .

YASUNAGA M , LIANG P . Graph-based, Self-Supervised Program Repair from Diagnostic Feedback [Z ] //HAL D, III, AARTI S. Proceedings of the 37th International Conference on Machine Learning . Proceedings of Machine Learning Research; PMLR. 2020 : 10799--808

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向5G-Advanced与6G的智能无线电接入网：关键标准技术与未来演进

数字孪生技术赋能6G网络

OSI-RM视角下的移动通信网络AI技术应用综述

超越同质性假设的双通道属性图聚类

云化的智算中心万卡集群创新与实践