Few-Shot Transfer Learning for Device-Free Fingerprinting Indoor Localization

被引:12
作者
Chen, Bing-Jia [1 ]
Chang, Ronald Y. [1 ]
机构
[1] Acad Sinica, Res Ctr Informat Technol Innovat, Taipei, Taiwan
来源
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022) | 2022年
关键词
Indoor localization; fingerprinting; channel state information (CSI); transfer learning; few-shot learning; graph neural network (GNN);
D O I
10.1109/ICC45855.2022.9839217
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Device-free wireless indoor localization is an essential technology for the Internet of Things (IoT), and fingerprintbased methods are widely used. A common challenge to fingerprint-based methods is data collection and labeling. This paper proposes a few-shot transfer learning system that uses only a small amount of labeled data from the current environment and reuses a large amount of existing labeled data previously collected in other environments, thereby significantly reducing the data collection and labeling cost for localization in each new environment. The core method lies in graph neural network (GNN) based few-shot transfer learning and its modifications. Experimental results conducted on real-world environments show that the proposed system achieves comparable performance to a convolutional neural network (CNN) model, with 40 times fewer labeled data.
引用
收藏
页码:4631 / 4636
页数:6
相关论文
共 22 条
[1]   Internet of Things in agriculture: A survey [J].
Abbasi, Mahmoud ;
Yaghmaee, Mohammad Hossein ;
Rahnama, Fereshteh .
PROCEEDINGS OF 2019 3RD INTERNATIONAL CONFERENCE ON INTERNET OF THINGS AND APPLICATIONS (IOT), 2019, :17-28
[2]  
Chandra Rohitash, 2018, PROC IEEE GLOBAL COM, P1, DOI DOI 10.1109/GLOCOM.2018.8647261
[3]  
Chen K., 2020, ADV MATER SCI ENG, V12, P1
[4]   A Comparative Study of Deep-Learning-Based Semi-Supervised Device-Free Indoor Localization [J].
Chen, Kevin M. ;
Chang, Ronald Y. .
2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
[5]  
Cheng H, 2020, ARXIV200706878
[6]  
Chidlovskii B, 2019, INT C INDOOR POSIT
[7]  
Defferrard M., 2016, ADV NEURAL INFORM PR
[8]   Tool Release: Gathering 802.11n Traces with Channel State Information [J].
Halperin, Daniel ;
Hu, Wenjun ;
Sheth, Anmol ;
Wetherall, David .
ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2011, 41 (01) :53-53
[9]   Deep Learning-Based Indoor Localization Using Received Signal Strength and Channel State Information [J].
Hsieh, Chaur-Heh ;
Chen, Jen-Yang ;
Nien, Bo-Hong .
IEEE ACCESS, 2019, 7 :33256-33267
[10]   Edge-Labeling Graph Neural Network for Few-shot Learning [J].
Kim, Jongmin ;
Kim, Taesup ;
Kim, Sungwoong ;
Yoo, Chang D. .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :11-20