The Adaptive Fingerprint Localization in Dynamic Environment

被引:8
作者
Long, Keliu [1 ,2 ]
Zheng, Chongwei [3 ]
Zhang, Kun [4 ]
Tian, Chuan [5 ]
Shen, Chong [1 ,2 ]
机构
[1] Hainan Univ, State Key Lab Marine Resource Utilizat South Chin, Haikou 570228, Hainan, Peoples R China
[2] Hainan Univ, Sch Informat & Commun Engn, Haikou 570228, Hainan, Peoples R China
[3] Dalian Naval Acad, Dalian 116018, Peoples R China
[4] Hainan Trop Ocean Univ, Educ Ctr MTA, Sanya 572022, Peoples R China
[5] Chinese Acad Sci, Inst Deep Sea Sci & Engn, Sanya 572000, Peoples R China
基金
中国国家自然科学基金;
关键词
Fingerprint recognition; Location awareness; Heuristic algorithms; Wireless fidelity; Feature extraction; Convolutional neural networks; Databases; Feature extracting; fingerprint localization; generalized policy iteration; indoor localization; transfer learning; WI-FI LOCALIZATION; NETWORKS; CSI;
D O I
10.1109/JSEN.2022.3175742
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Indoor localization service is an indispensable part of modern intelligent life, among which Wi-Fi based fingerprint localization system is popular in indoor positioning researches due to its advantages of low cost and widely deployment. However, Wi-Fi based localization system is susceptible to dynamic environment, and fingerprint collection and updating are time-consuming and labor-intensive. To address this problem, we propose a novel positioning framework based on multiple transfer learning fusion using Generalized Policy Iteration (GPI). Firstly, a 1-Dimension Convolutional Autoencoder (1-D CAE) is designed to extract features from one-dimensional fingerprint data; similar to Convolutional Neural Network (CNN), it can not only pay more attention to the information of different dimensions of fingerprints, but also compress redundant information and reduce noise. After that, Domain Adversarial Neural Network (DANN) and Passive Aggressive (PA) algorithm are fused to train localization model based on unlabeled fingerprint of target domain using the theory of GPI in offline stage. Finally, the model is fine-tuned with unlabeled fingerprints and few labeled fingerprints in daily online predictions to improve the performance of the localization system. Various evaluations in five typical scenarios validate the effectiveness of proposed algorithm in dynamic environment, with low tendency, easy recalibration, long-term stabilization high accuracy and so on.
引用
收藏
页码:13562 / 13580
页数:19
相关论文
共 50 条
[21]   TransLoc: A Heterogeneous Knowledge Transfer Framework for Fingerprint-Based Indoor Localization [J].
Li, Lin ;
Guo, Xiansheng ;
Zhao, Mengxue ;
Li, Huiyong ;
Ansari, Nirwan .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2021, 20 (06) :3628-3642
[22]   Semi-Supervised Deep Adversarial Forest for Cross-Environment Localization [J].
Cui, Wei ;
Zhang, Le ;
Li, Bing ;
Chen, Zhenghua ;
Wu, Min ;
Li, Xiaoli ;
Kang, Jiawen .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (09) :10215-10219
[23]   Fingerprint and Assistant Nodes Based Wi-Fi Localization in Complex Indoor Environment [J].
Li, Qiyue ;
Li, Wei ;
Sun, Wei ;
Li, Jie ;
Liu, Zhi .
IEEE ACCESS, 2016, 4 :2993-3004
[24]   MuSpel-Fi: Multipath Subspace Projection and ELM-Based Fingerprint Localization [J].
Fan, Jiancun ;
Sun, Hao ;
Su, Yanzhao ;
Huang, Jin .
IEEE SIGNAL PROCESSING LETTERS, 2022, 29 :329-333
[25]   Exploiting Fingerprint Correlation for Fingerprint-Based Indoor Localization: A Deep Learning Based Approach [J].
Zhou, Chengyi ;
Liu, Junyu ;
Sheng, Min ;
Zheng, Yang ;
Li, Jiandong .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (06) :5762-5774
[26]   Indoor Localization With Adaptive Signal Sequence Representations [J].
Liu, Ning ;
He, Tao ;
He, Suining ;
Niu, Qun .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (11) :11678-11694
[27]   Privacy-Preserving WiFi Localization Based on Inner Product Encryption in a Cloud Environment [J].
Wang, Zhiheng ;
Xu, Yanyan ;
Yan, Yuejing ;
Ouyang, Xue ;
Zhang, Bo .
IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (10) :17264-17282
[28]   Localization With Cellular Signal RSRP Fingerprint of Multiband and Multicell [J].
Hu, Zhinan ;
Chen, Xin ;
Zhou, Zhenyu ;
Mumtaz, Shahid .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2024, 42 (09) :2380-2394
[29]   Adaptive Weighted Access Point Technique for Robust Dynamic Indoor Positioning [J].
Mazlan, Aqilah Binti ;
Ng, Yin Hoe .
IEEE ACCESS, 2024, 12 :179726-179747
[30]   Learning to Locate: Adaptive Fingerprint-Based Localization With Few-Shot Relation Learning in Dynamic Indoor Environments [J].
Zhang, Lingyan ;
Wu, Shaohua ;
Zhang, Tingting ;
Zhang, Qinyu .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2023, 22 (08) :5253-5264