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

SHI Zheng; GU Hao; HUANG Hao; WANG Yu; XIA Wenchao; ZHAO Haitao; ZHU Hongbo

doi:10.11959/j.issn.2096-3750.2025.00540

您当前的位置：

首页 >

文章列表页 >

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

Theory and Technology | 更新时间：2026-01-04

- Siamese GCN empowered fingerprinting indoor localization using few-shot transfer learning
- Chinese Journal on Internet of Things Vol. 9, Issue 4, Pages: 62-76(2025)
- 作者机构：
  
  1.南京邮电大学通信与信息工程学院，江苏南京 210003
  2.东南大学集成电路学院，江苏南京 211189
  3.江苏省无线通信与物联网重点实验室，江苏南京 210003
  4.南京邮电大学物联网学院，江苏南京 210003
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62274096);Natural Science Foundation of Jiangsu Province(BK20240621)
- DOI：10.11959/j.issn.2096-3750.2025.00540
  CLC：
- Received：28 September 2025，
  
  Revised：2025-11-17，
  
  Published：10 December 2025
- 稿件说明：
移动端阅览
施政,顾浩,黄浩等.基于孪生图卷积神经网络的小样本迁移学习室内指纹定位[J].物联网学报,2025,09(04):62-76.

SHI Zheng,GU Hao,HUANG Hao,et al.Siamese GCN empowered fingerprinting indoor localization using few-shot transfer learning[J].Chinese Journal on Internet of Things,2025,09(04):62-76.
施政,顾浩,黄浩等.基于孪生图卷积神经网络的小样本迁移学习室内指纹定位[J].物联网学报,2025,09(04):62-76. DOI： 10.11959/j.issn.2096-3750.2025.00540.

SHI Zheng,GU Hao,HUANG Hao,et al.Siamese GCN empowered fingerprinting indoor localization using few-shot transfer learning[J].Chinese Journal on Internet of Things,2025,09(04):62-76. DOI： 10.11959/j.issn.2096-3750.2025.00540.

摘要

基于射频信号的室内定位技术是第六代无线通信系统中的重要研究方向之一。随着人工智能的发展，基于深度学习的室内指纹定位方法在定位性能上得到了显著提升。然而，这类方法仍面临以下挑战，包括射频数据采集时间长、标注成本高，导致现有深度学习算法在不同场景下的环境泛化能力差。针对该问题，提出了一种基于孪生图卷积神经网络（Siamese GCN

siamese graph convolutional network）的小样本迁移学习室内指纹定位方法。该技术结合Siamese GCN模型与基于最大均值差异的领域自适应方法，仅需在当前环境中采集少量信道状态信息样本，即可复用其他环境中已训练好的模型权重，从而显著降低新环境下的数据采集与标注成本。为验证所提方法的有效性，在实验室和走廊两个典型的室内场景下采集了真实的环境数据。实验结果表明，所提的迁移学习方法在仅使用30%的标注样本的情况下，仍能实现较好的定位性能。

Abstract

Radio frequency (RF)-based indoor positioning technology is recognized as one of the important research directions in the sixth generation wireless communication (6G) systems. With the advancement of artificial intelligence (AI)

deep learning-based indoor fingerprint localization methods have achieved significant improvements in positioning performance. However

these methods still face the following challenges

including lengthy RF data collection periods and high annotation costs

which lead to poor environmental generalization capability of existing deep learning algorithms across different scenarios. To address this issue

a few-shot transfer learning indoor fingerprint localization method based on a Siamese graph convolutional network (Siamese GCN) was proposed. The Siamese GCN model was combined with a maximum mean discrepancy-based domain adaptation approach

requiring only a small number of channel state information samples to be collected in the current environment. Pre-trained network weights from other environments were reused

significantly reducing data collection and annotation costs in new environments. To validate the effectiveness of the proposed method

real environmental data were collected in two typical indoor scenarios: a laboratory and a corridor. Experimental results demonstrated that the proposed transfer learning method achieved satisfactory localization performance using only 30% of the labeled samples.

关键词

Keywords

references

闫大禹 , 宋伟 , 王旭丹 , 等 . 国内室内定位技术发展现状综述 [J ] . 导航定位学报 , 2019 , 7 ( 4 ): 5 - 12 .

YAN D Y , SONG W , WANG X D , et al . Review of development status of indoor location technology in China [J ] . Journal of Navigation and Positioning , 2019 , 7 ( 4 ): 5 - 12 .

ZHANG L , CHEN Z H , CUI W , et al . WiFi-based indoor robot positioning using deep fuzzy forests [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 11 ): 10773 - 10781 .

SHAO W H , LUO H Y , ZHAO F , et al . Accurate indoor positioning using temporal-spatial constraints based on Wi-Fi fine time measurements [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 11 ): 11006 - 11019 .

WANG Z , GUO B , YU Z W , et al . Wi-Fi CSI-based behavior recognition: from signals and actions to activities [J ] . IEEE Communications Magazine , 2018 , 56 ( 5 ): 109 - 115 .

陈斌涛 , 刘任任 , 陈益强 , 等 . 动态环境中的WiFi指纹自适应室内定位方法 [J ] . 传感技术学报 , 2015 , 28 ( 5 ): 729 - 738 .

CHEN B T , LIU R R , CHEN Y Q , et al . WiFi fingerprint based self-adaptive indoor localization in the dynamic environment [J ] . Chinese Journal of Sensors and Actuators , 2015 , 28 ( 5 ): 729 - 738 .

朱正伟 , 蒋威 , 张贵玲 , 等 . 基于RSSI的室内WiFi定位算法 [J ] . 计算机工程与设计 , 2020 , 41 ( 10 ): 2958 - 2962 .

ZHU Z W , JIANG W , ZHANG G L , et al . Indoor WiFi location algorithm based on RSSI [J ] . Computer Engineering and Design , 2020 , 41 ( 10 ): 2958 - 2962 .

GÖNÜLTAŞ E , LEI E , LANGERMAN J , et al . CSI-based multi-antenna and multi-point indoor positioning using probability fusion [J ] . IEEE Transactions on Wireless Communications , 2022 , 21 ( 4 ): 2162 - 2176 .

宁夏薇 , 夏林元 , 祝宏宇 , 等 . 基于增强指纹特征的WiFi室内定位方法 [J ] . 地理空间信息 , 2024 , 22 ( 8 ): 102 - 106 .

NING X W , XIA L Y , ZHU H Y , et al . WiFi indoor location method based on enhanced fingerprint feature [J ] . Geospatial Information , 2024 , 22 ( 8 ): 102 - 106 .

WANG X Y , WANG X Y , MAO S W . Indoor fingerprinting with bimodal CSI tensors: a deep residual sharing learning approach [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 6 ): 4498 - 4513 .

KO C H , WU S H . A framework for proactive indoor positioning in densely deployed WiFi networks [J ] . IEEE Transactions on Mobile Computing , 2022 , 21 ( 1 ): 1 - 15 .

PAN S J , YANG Q . A survey on transfer learning [J ] . IEEE Transactions on Knowledge and Data Engineering , 2010 , 22 ( 10 ): 1345 - 1359 .

LI L , GUO X S , ZHAO M X , et al . TransLoc: a heterogeneous knowledge transfer framework for fingerprint-based indoor localization [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 6 ): 3628 - 3642 .

ZHANG Y , WU C B , CHEN Y . A low-overhead indoor positioning system using CSI fingerprint based on transfer learning [J ] . IEEE Sensors Journal , 2021 , 21 ( 16 ): 18156 - 18165 .

LIU K , ZHANG H , NG J K , et al . Toward low-overhead fingerprint-based indoor localization via transfer learning: de sign, implementation, and evaluation [J ] . IEEE Transactions on Industrial Informatics , 2018 , 14 ( 3 ): 898 - 908 .

SHEN W X , ZHANG H X , GUO S S , et al . Time-wise attention aided convolutional neural network for data-driven cellular traffic prediction [J ] . IEEE Wireless Communications Letters , 2021 , 10 ( 8 ): 1747 - 1751 .

CHIOU M J , LIU Z G , YIN Y F , et al . Zero-shot multi-view indoor localization via graph location networks [C ] // Proceedings of the 28th ACM International Conference on Multimedia . New York : ACM , 2020 : 3431 - 3440 .

LIANG C , ZHANG H X , YUAN D F , et al . Location property of convolutional neural networks for image classification [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2021 , 32 ( 9 ): 3831 - 3845 .

LI Q , LIAO X W , LIU M M , et al . Indoor localization based on CSI fingerprint by Siamese convolution neural network [J ] . IEEE Transactions on Vehicular Technology , 2021 , 70 ( 11 ): 12168 - 12173 .

LI J J , LU K , HUANG Z , et al . Transfer independently together: a generalized framework for domain adaptation [J ] . IEEE Transactions on Cybernetics , 2019 , 49 ( 6 ): 2144 - 2155 .

LIU F , LIU J , YIN Y Q , et al . Survey on WiFi-based indoor positioning techniques [J ] . IET Communications , 2020 , 14 ( 9 ): 1372 - 1383 .

QIU T , LIU J , SI W S , et al . Robustness optimization scheme with multi-population co-evolution for scale-free wireless sensor networks [J ] . IEEE/ACM Transactions on Networking , 2019 , 27 ( 3 ): 1028 - 1042 .

朱海 , 肖甫 , 孙力娟 , 等 . 基于信道状态信息的WiFi环境感知技术 [J ] . 南京邮电大学学报(自然科学版) , 2016 , 36 ( 1 ): 94 - 103, 110 .

ZHU H , XIAO F , SUN L J , et al . CSI-based WiFi environment sensing [J ] . Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition) , 2016 , 36 ( 1 ): 94 - 103, 110 .

GHARAT V , COLIN E , BAUDOIN G , et al . Indoor performance analysis of LF-RFID based positioning system: Comparison with UHF-RFID and UWB [C ] // Proceedings of the 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN) . Piscataway : IEEE Press , 2017 : 1 - 8 .

BAHL P , PADMANABHAN V N . RADAR: an in-building RF-based user location and tracking system [C ] // Proceedings IEEE INFOCOM 2000 . Conference on Computer Communications Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat No 00CH37064). Piscataway: IEEE Press , 2000: 775 - 784 .

吴泽泰 , 蔡仁钦 , 徐书燕 , 等 . 基于K近邻法的WiFi定位研究与改进 [J ] . 计算机工程 , 2017 , 43 ( 3 ): 289 - 293 .

WU Z T , CAI R Q , XU S Y , et al . Research and improvement of WiFi positioning based on K nearest neighbor method [J ] . Computer Engineering , 2017 , 43 ( 3 ): 289 - 293 .

YOUSSEF M , AGRAWALA A . The Horus WLAN location determination system [C ] // Proceedings of the 3rd International Conference on Mobile Systems, Applications, and Services . New York : ACM , 2005 : 205 - 218 .

WANG X Y , WANG X Y , MAO S W , et al . Indoor radio map construction and localization with deep Gaussian processes [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 11 ): 11238 - 11249 .

LI D , ZHANG B X , YAO Z , et al . A feature scaling based k-nearest neighbor algorithm for indoor positioning system [C ] // Proceedings of the 2014 IEEE Global Communications Conference . Piscataway : IEEE Press , 2015 : 436 - 441 .

WU K S , XIAO J , YI Y W , et al . CSI-based indoor localization [J ] . IEEE Transactions on Parallel and Distributed Systems , 2013 , 24 ( 7 ): 1300 - 1309 .

WU G S , TSENG P H . A deep neural network-based indoor positioning method using channel state information [C ] // Proceedings of the 2018 International Conference on Computing, Networking and Communications (ICNC) . Piscataway : IEEE Press , 2018 : 290 - 294 .

XIAO J , WU K S , YI Y W , et al . FIFS: fine-grained indoor fingerprinting system [C ] // Proceedings of the 2012 21st International Conference on Computer Communications and Networks (ICCCN) . Piscataway : IEEE Press , 2012 : 1 - 7 .

WANG J , XIONG J , JIANG H B , et al . Low human-effort, device-free localization with fine-grained subcarrier information [C ] // Proceedings of the IEEE Transactions on Mobile Computing . Piscataway : IEEE Press , 2018 : 2550 - 2563 .

HARSHANAND B A , SANGAIAH A K . Comprehensive analysis of deep learning methodology in classification of leukocytes and enhancement using swish activation units [J ] . Mobile Networks and Applications , 2020 , 25 ( 6 ): 2302 - 2320 .

SANGAIAH A K , GOLI A , TIRKOLAEE E B , et al . Big data-driven cognitive computing system for optimization of social media analytics [J ] . IEEE Access , 2020 , 8 : 82215 - 82226 .

WANG X Y , GAO L J , MAO S W , et al . DeepFi: Deep learning for indoor fingerprinting using channel state information [C ] // Proceedings of the 2015 IEEE Wireless Communications and Networking Conference (WCNC) . Piscataway : IEEE Press , 2015 : 1666 - 1671 .

WANG X Y , GAO L J , MAO S W . CSI phase fingerprinting for indoor localization with a deep learning approach [J ] . IEEE Internet of Things Journal , 2016 , 3 ( 6 ): 1113 - 1123 .

CHEN X , MA C , ALLEGUE M , et al . Taming the inconsistency of Wi-Fi fingerprints for device-free passive indoor localization [C ] // Proceedings of the IEEE INFOCOM 2017 - IEEE Conference on Computer Communications . Piscataway : IEEE Press , 2017 : 1 - 9 .

WANG J , ZHANG X , GAO Q H , et al . Device-free wireless localization and activity recognition: a deep learning approach [J ] . IEEE Transactions on Vehicular Technology , 2017 , 66 ( 7 ): 6258 - 6267 .

WANG X Y , WANG X Y , MAO S W . Deep convolutional neural networks for indoor localization with CSI images [J ] . IEEE Transactions on Network Science and Engineering , 2020 , 7 ( 1 ): 316 - 327 .

ZHANG L Y , WU S H , ZHANG T T , et al . Automatic radio map adaptation for robust indoor localization with dynamic adversarial learning [J ] . IEEE Transactions on Industrial Informatics , 2025 , 21 ( 2 ): 1615 - 1624 .

ZHANG L Y , QIU Y F , WU S H , et al . GraphLoc: enhancing fingerprint-based localization with graph representation learning [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 12 ): 21593 - 21603 .

SHOKRY A , TORKI M , YOUSSEF M . DeepLoc: a ubiquitous accurate and low-overhead outdoor cellular localization system [C ] // Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems . New York : ACM , 2018 : 339 - 348 .

CHEN B J , CHANG R Y . Few-shot transfer learning for device-free fingerprinting indoor localization [C ] // Proceedings of the ICC 2022 - IEEE International Conference on Communications . Piscataway : IEEE Press , 2022 : 4631 - 4636 .

LI X N , GUO Y , LI F F . Few-shot indoor localization model based on simplified graph convolution and adversarial Gaussian process regression [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 13 ): 24490 - 24502 .

PAN S J , TSANG I W , KWOK J T , et al . Domain adaptation via transfer component analysis [J ] . IEEE Transactions on Neural Networks , 2011 , 22 ( 2 ): 199 - 210 .

LONG M S , WANG J M , DING G G , et al . Transfer feature learning with joint distribution adaptation [C ] // Proceedings of the 2013 IEEE International Conference on Computer Vision . Piscataway : IEEE Press , 2014 : 2200 - 2207 .

LIU K , ZHANG H , NG J K , et al . Toward low-overhead fingerprint-based indoor localization via transfer learning: design, implementation, and evaluation [J ] . IEEE Transactions on Industrial Informatics , 2018 , 14 ( 3 ): 898 - 908 .

WANG L , SHAO Y , GUO X S . An adaptive localization approach based on deep adaptation networks [C ] // Proceedings of the 2019 International Conference on Control, Automation and Information Sciences (ICCAIS) . Piscataway : IEEE Press , 2019 : 1 - 5 .

HALPERIN D , HU W J , SHETH A , et al . Tool release: gathering 802.11n traces with channel state information [J ] . ACM SIGCOMM Computer Communication Review , 2011 , 41 ( 1 ): 53 .

BERTINETTO L , VALMADRE J , HENRIQUES J F , et al . Fully-convolutional Siamese networks for object tracking [C ] // Computer Vision - ECCV 2016 Workshops . Cham : Springer , 2016 : 850 - 865 .

LIU B , YU X C , ZHANG P Q , et al . Supervised deep feature extraction for hyperspectral image classification [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2018 , 56 ( 4 ): 1909 - 1921 .

LUNGU I A , AIMAR A , HU Y H , et al . Siamese networks for few-shot learning on edge embedded devices [J ] . IEEE Journal on Emerging and Selected Topics in Circuits and Systems , 2020 , 10 ( 4 ): 488 - 497 .

WANG X Y , GAO L J , MAO S W , et al . CSI-based fingerprinting for indoor localization: a deep learning approach [J ] . IEEE Transactions on Vehicular Technology , 2017 , 66 ( 1 ): 763 - 776 .

WEI W , YAN J , WU X F , et al . A meta-learning approach for device-free indoor localization [C ] // Proceedings of the IEEE Communications Letters . Piscataway : IEEE Press , 2023 : 846 - 850 .

JIAO J Y , WANG X J , HAN C P , et al . Few-shot meta-learning for dynamic indoor fingerprinting localization based on CSI images [C ] // Proceedings of the 2025 IEEE Wireless Communications and Networking Conference (WCNC) . Piscataway : IEEE Press , 2025 : 1 - 6 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Indoor localization method based on CSI in complex environment

Indoor autonomous parking via UWB fusion positioning: system design and domestic chip validation

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

Implicit smartphone authentication via multimodal data and transfer autoencoders

Related Author

Xiaochao DANG

Xiong SI

Zhanjun HAO

Yaning HUANG

Yili HEI

Chen Yun

Wu Qiong

Wu Yiang

Related Institution

Gansu Province Internet of Things Engineering Research Center

College of Computer Science and Engineering, Northwest Normal University

Zhuhai Fudan Innovation Institute

Beijing National Research Center for Information Science and Technology, Tsinghua University

School of Internet of Things Engineering, Jiangnan University

⁰