A Lightweight Fingerprinting Localization Model based on Smartphone CSI

YANG Runze; HUANG Baoqi; JIA Bing

doi:XXX

您当前的位置：

首页 >

文章列表页 >

A Lightweight Fingerprinting Localization Model based on Smartphone CSI

更新时间：2026-03-03

- A Lightweight Fingerprinting Localization Model based on Smartphone CSI
- Chinese Journal on Internet of Things (2026)
- 作者机构：
  
  1.内蒙古大学计算机学院呼和浩特 010021
  2.生态大数据教育部工程研究中心呼和浩特 010021
  3.内蒙古电子科技有限责任公司鄂尔多斯 017000
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62262046;42161070);Inner Mongolia Science and Technology Program(2022YFSJ0027);Ordos Science and Technology Program(YF20240029);Hohhot Basic and Applied Basic Research Program
- DOI：XXX
  CLC： TP393
- Received：14 June 2025，
  
  Revised：2025-08-08，
  
  Accepted：01 September 2025，
- 稿件说明：
移动端阅览
YANG Runze, HUANG Baoqi, JIA Bing. A Lightweight Fingerprinting Localization Model based on Smartphone CSI[J/OL]. Chinese Journal on Internet of Things, 2026.
DOI：

YANG Runze, HUANG Baoqi, JIA Bing. A Lightweight Fingerprinting Localization Model based on Smartphone CSI[J/OL]. Chinese Journal on Internet of Things, 2026. DOI： XXX.

摘要

近年来，深度学习技术被广泛地应用于基于信道状态信息(Channel State Information，CSI)的指纹定位领域，并展现出高可靠的定位精度。然而，基于深度学习的指纹定位方法大多依赖于多层次的网络模型结构来提取具有判别性的位置特征，此过程伴随着大量的模型参数和密集的计算操作，对设备的硬件资源占用较高。特别是对于资源有限的智能手机而言，这会为其带来不容忽视的负担。为此，本文提出一种新颖的智能手机CSI轻量级指纹定位模型，（1）通过设计简洁高效的特征提取模块，仅用少量参数的线性层与卷积层结合特征融合机制，兼顾模型轻量化与特征提取能力；（2）引入数据增强模块，通过生成非参考点CSI数据，扩充训练样本空间，显著提升模型对未经训练位置的鉴别能力。本文在两种典型的室内场景下开展实验，与最优的基准模型相比，本文提出的定位模型在两种场景下的平均RMSE降低了12.5%，并且单次定位的推理时间仅为0.08秒。实验结果表明，本文提出的定位模型不仅能够有效提高定位精度，还明显缩短了定位所需时间。

Abstract

In recent years

deep learning technologies have been widely adopted to the Channel State Information (CSI)-based fingerprinting localization field

demonstrating reliable localization accuracy. However

deep learning-based fingerprinting localization models typically rely on multi-layered network structures to extract distinctive location features

the process accompanied by a large number of model parameters and intensive computational operations

which occupy substantial physical resources on devices. This can be a significant burden

especially for resource-limited smartphones. To this end

this paper proposes a novel lightweight fingerprinting localization model based on smartphone CSI，(1) a concise and efficient feature extraction module is designed

employing linear and convolutional layers with a minimal number of parameters and incorporating a feature fusion mechanism to achieve both lightweight deployment and strong discriminative capability in feature extraction; (2) a data augmentation module is introduced to generate CSI data for unknown points

thereby expanding the training sample space and significantly enhancing the model’s recognition ability for untrained locations. Experiments were conducted in two typical indoor scenarios. The results show that compared to the most advanced benchmark models

the proposed localization model has reduced the average RMSE by 12.5% in two indoor scenarios

and the inference time for a single localization is only 0.08 seconds. The proposed localization model not only effectively improves positioning accuracy but also significantly reduces the required positioning time.

关键词

Keywords

references

Farahsari P S , Farahzadi A , Rezazadeh J , et al . A survey on indoor positioning systems for iot-based applications . IEEE Internet of Things Journal , 2022 , 9 ( 10 ): 7680 – 7699 .

Chen X , Li H , Zhou C , et al . Fidora: Robust wifi-based indoor localization via unsupervised domain adaptation . IEEE Internet of Things Journal , 2022 , 9 ( 12 ): 9872 – 9888 .

Zheng S , Zhou Z , Zhang Q , et al . A factor graph based indoor localization approach for healthcare // Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Istanbul and Turkey , 2023 : 3257 – 3264 .

Zhou Y , Huang H , Yuan S , et al . Metafi+: wifi-enabled transformer-based human pose estimation for metaverse avatar simulation . IEEE Internet of Things Journal , 2023 , 10 ( 16 ): 14128 - 14136 .

Zhu X , Qu W , Qiu T , et al . Indoor intelligent fingerprint-based localization: Principles, approaches and challenges . IEEE Communications Surveys & Tutorials , 2020 , 22 ( 4 ): 2634 – 2657 .

He S and Chan S H G . Wifi fingerprint-based indoor positioning: recent advances and comparisons . IEEE Communications Surveys & Tutorials , 2016 , 18 ( 1 ): 466 - 490 .

Wu K , Xiao J , Yi Y , et al . FILA: Fine-grained indoor localization [C ] // 2012 Proceedings IEEE INFOCOM . IEEE , 2012 : 2210 - 2218 .

Kotaru M , Joshi K , Bharadia D , et al . Spotfi: Decimeter level localization using wifi // Proceedings of the 2015 ACM conference on special interest group on data communication . London, UK , 2015 : 269 - 282 .

Soltanaghaei E , Kalyanaraman A , Whitehouse K . Multipath triangulation: Decimeter-level wifi localization and orientation with a single unaided receiver // Proceedings of the 16th annual international conference on mobile systems, applications, and services . Munich, Germany 2018 : 376 - 388 .

Xie Y , Xiong J , Li M , et al . mD-Track: Leveraging multi-dimensionality for passive indoor Wi-Fi tracking [C ] // The 25th Annual International Conference on Mobile Computing and Networking . 2019 : 1 - 16 .

Li Y , Yan K . Indoor localization based on radio and sensor measurements . IEEE Sensors Journal , 2021 , 21 ( 22 ): 25090 - 25097 .

Sobehy A , Renault É and Mühlethaler P . Csi-mimo: k-nearest neighbor applied to indoor localization // Proceedings of the 2020 IEEE International Conference on Communications (ICC) , Dublin, Ireland , 2020 : 1 - 6 .

Dang X , Si X , Hao Z , et al . A novel passive indoor localization method by fusion CSI amplitude and phase information [J ] . Sensors , 2019 , 19 ( 4 ): 875 .

Xiao J , Wu K , Yi Y , et al . Pilot: Passive device-free indoor localization using channel state information [C ] // 2013 IEEE 33rd International Conference on Distributed Computing Systems . IEEE , 2013 : 236 - 245 .

Song X , Fan X , He X , et al . Cnnloc: deep-learning based indoor localization with wifi fingerprinting // Proceedings of the 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation , Paris , 2019 : 589 – 595 .

Wang X , Wang X , and Mao S . Deep convolutional neural networks for indoor localization with csi images . IEEE Transactions on Network Science and Engineering , 2020 , 7 ( 1 ): 316 – 327 .

Choi J S , Lee W H , Lee J H , et al . Deep learning based NLOS identification with commodity WLAN devices . IEEE Transactions on Vehicular Technology , 2017 , 67 ( 4 ): 3295 - 3303 .

Chen C , Chen Y , Han Y , et al . Achieving centimeter-accuracy indoor localization on WiFi platforms: A frequency hopping approach [J ] . IEEE Internet of Things Journal , 2016 , 4 ( 1 ): 111 - 121 .

Song Q , Guo S , Liu X , et al . Csi amplitude fingerprinting-based nb-iot indoor localization . IEEE Internet of Things Journal , 2018 , 5 ( 3 ): 1494 – 1504 .

Sanam T F and Godrich H . Fuseloc: A cca based information fusion for indoor localization using csi phase and amplitude of wifi signals // Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing . London, UK , 2019 : 7565 – 7569 .

Zhou R , Lu X , Zhao P , et al . Device-free presence detection and localization with svm and csi fingerprinting . IEEE Sensors Journal , 2017 , 17 ( 23 ): 7990 – 7999 .

Wang Y , Xiu C , Zhang X , et al . Wifi indoor localization with csi fingerprinting-based random forest . Sensors , 2018 , 18 ( 9 ): 1 - 23 .

Wang X , Gao L , Mao S , et al . Csi-based fingerprinting for indoor localization: A deep learning approach . IEEE Transactions on Vehicular Technology , 2017 , 66 ( 1 ): 763 – 776 .

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

Wang X , Gao L , Mao S . BiLoc: Bi-modal deep learning for indoor localization with commodity 5GHz WiFi [J ] . IEEE access , 2017 , 5 : 4209 - 4220 .

Hoang M T , Yuen B , Ren K , et al . A cnn-lstm quantifier for single access point csi indoor localization . ArXiv e-prints , 2020 : 1 – 10 .

M. Liu , X. Liao , Z. Gao , et al . FT-Loc: A Fine-Grained Temporal Features-Based Fusion Network for Indoor Localization [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 3 ): 4324 - 4334 .

Fan S , Wu Y , Han C , et al . A structured bidirectional lstm deep learning method for 3d terahertz indoor localization // Proceedings of the 2020 IEEE Conference on Computer Communications . Virtual Conference , 2020 : 2381 – 2390 .

Xu X , Zhu F , Han S , et al . Swin-loc: transformer-based csi fingerprinting indoor localization with mimo isac system [J ] . IEEE Transactions on Vehicular Technology , 2024 : 1 - 16 .

Liu Z , Lin Y , Cao Y , et al . Swin transformer: Hierarchical vision transformer using shifted windows // Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Virtual Conference , 2021 : 10012 - 10022 .

Wang J , Li F , Ma X , et al . Lightweight device-free wireless sensing using information-for-complexity strategy [J ] . IEEE Transactions on Industrial Informatics , 2022 , 19 ( 4 ): 6117 - 6126 .

Yousefi S , Narui H , Dayal S , et al . A survey on behavior recognition using WiFi channel state information . IEEE Communications Magazine , 2017 , 55 ( 10 ): 98 - 104 .

Sohn K , Lee H , Yan X . Learning structured output representation using deep conditional generative models // Proceedings of Advances in neural information processing systems . Montreal, Canada , 2015 : 1 - 9 .

Rasmussen C E . Gaussian processes in machine learning // Advanced Lectures on Machine Learning . Berlin, Germany , 2003 : 63 - 71 .

Li X , Li T , Ma J . Gaussian process mixture model for flexible prediction of coal mine gas concentration under noisy input prediction strategy . Signal Processing , 2021 , 37 ( 11 ): 2031 – 2040 .

李晓燕 , 李弢 , 马尽文 . 高斯过程混合模型在含噪输入预测策略下的煤矿瓦斯浓度柔性预测 . 信号处理 , 2021 , 37 ( 11 ): 2031 − 2040 .

Ioffe S , Szegedy C . Batch normalization: Accelerating deep network training by reducing internal covariate shift // International conference on machine learning . Lille, France , 2015 : 448 - 456 .

Maas A L , Hannun A Y , Ng A Y . Rectifier nonlinearities improve neural network acoustic models // International conference on machine learning . Atlanta, USA , 2013 : 1 - 6 .

Gao Z , Gao Y , Wang S , et al . CRISLoc: Reconstructable CSI fingerprinting for indoor smartphone localization . IEEE Internet of Things Journal , 2020 , 8 ( 5 ): 3422 - 3437 .

Zeng A , Chen M , Zhang L , et al . Are transformers effective for time series forecasting // Proceedings of the AAAI conference on artificial intelligence . Washington, USA , 2023 , 37 ( 9 ): 11121 - 11128 .

He K , Zhang X , Ren S , et al . Deep residual learning for image recogni tion // Proceedings of the IEEE conference on computer vision and pattern recognition . Las Vegas, USA , 2016 : 770 - 778 .

Yang J , Yang J , Zhang D , et al . Feature fusion: parallel strategy vs . serial strategy. Pattern recognition , 2003 , 36 ( 6 ): 1369 - 1381 .

Han K , Wang Y , Tian Q , et al . Ghostnet: More features from cheap operations [C ] // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition . 2020 : 1580 - 1589 .

Liu G , Wang J . Dendrite net: A white-box module for classification, re gression, and system identification . IEEE Transactions on Cybernetics , 2021 , 52 ( 12 ): 13774 - 13787 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

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

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

Feature fusion method for UWB angle of arrival estimation under non-line-of-sight conditions

Lightweight parallel denoising network-based OTFS channel estimation algorithm

Related Author

Wu Qiong

Wu Yiang

Qin Dong

Fan Pingyi

Song Shulin

Chen Yun

SHI Zheng

GU Hao

Related Institution

Zhuhai Fudan Innovation Institute

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

School of Internet of Things Engineering, Jiangnan University

Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications, Nanchang University

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

⁰