WiFi Indoor Positioning Based on EGA-PF and Fernet Algorithm
With the massive popularity of WiFi in public places, using WiFi for indoor positioning has become a viable and popular technique. In this article, a method for WiFi indoor positioning utilizing EGA-PF and Fernet is proposed. Firstly, in response to the challenge of balancing positioning time and ac...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10848063/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576741352144896 |
|---|---|
| author | Yanchun Wang Shaoye Sun Fengjuan Miao Ying Xia |
| author_facet | Yanchun Wang Shaoye Sun Fengjuan Miao Ying Xia |
| author_sort | Yanchun Wang |
| collection | DOAJ |
| description | With the massive popularity of WiFi in public places, using WiFi for indoor positioning has become a viable and popular technique. In this article, a method for WiFi indoor positioning utilizing EGA-PF and Fernet is proposed. Firstly, in response to the challenge of balancing positioning time and accuracy, the extreme learning machine (ELM) does not require iterative adjustment of the weights of the hidden layer, allowing it to achieve high positioning accuracy in a short time, but the difficulty in adjusting the parameters restricts the development of the ELM, with each partial parameter of the ELM as an individual, the genetic algorithm (GA) uses operations such as crossover, compilation and selection to optimize until the system performance is met continuously. Secondly, the above algorithms reflect the problem of large system variance and unstable results when dealing with too much noise or incomplete data. In this regard, the random sampling and resampling techniques of the particle filtering (PF) algorithm are utilized for secondary optimization of the selection of the GA. Finally, to ensure the offline fingerprint database’s security, encrypting fingerprint database using the Fernet algorithm, and database is decrypted when the positioning request is received in the online phase. The suggested method is validated using UJIIndoorLoc dataset, and the research findings indicate that the average positioning error of the system is 0.95 m, 90% of the positioning errors are below 2 m, the variance is 0.0031, and the positioning time is 13.253 s. |
| format | Article |
| id | doaj-art-225220b270df4ddba28c5b374accd384 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-225220b270df4ddba28c5b374accd3842025-01-31T00:01:11ZengIEEEIEEE Access2169-35362025-01-0113166831669610.1109/ACCESS.2025.353233110848063WiFi Indoor Positioning Based on EGA-PF and Fernet AlgorithmYanchun Wang0https://orcid.org/0009-0000-5474-5655Shaoye Sun1Fengjuan Miao2https://orcid.org/0000-0003-4489-2322Ying Xia3College of Communications and Electronics Engineering, Qiqihar University, Qiqihar, Heilongjiang, ChinaCollege of Communications and Electronics Engineering, Qiqihar University, Qiqihar, Heilongjiang, ChinaCollege of Communications and Electronics Engineering, Qiqihar University, Qiqihar, Heilongjiang, ChinaCollege of Communications and Electronics Engineering, Qiqihar University, Qiqihar, Heilongjiang, ChinaWith the massive popularity of WiFi in public places, using WiFi for indoor positioning has become a viable and popular technique. In this article, a method for WiFi indoor positioning utilizing EGA-PF and Fernet is proposed. Firstly, in response to the challenge of balancing positioning time and accuracy, the extreme learning machine (ELM) does not require iterative adjustment of the weights of the hidden layer, allowing it to achieve high positioning accuracy in a short time, but the difficulty in adjusting the parameters restricts the development of the ELM, with each partial parameter of the ELM as an individual, the genetic algorithm (GA) uses operations such as crossover, compilation and selection to optimize until the system performance is met continuously. Secondly, the above algorithms reflect the problem of large system variance and unstable results when dealing with too much noise or incomplete data. In this regard, the random sampling and resampling techniques of the particle filtering (PF) algorithm are utilized for secondary optimization of the selection of the GA. Finally, to ensure the offline fingerprint database’s security, encrypting fingerprint database using the Fernet algorithm, and database is decrypted when the positioning request is received in the online phase. The suggested method is validated using UJIIndoorLoc dataset, and the research findings indicate that the average positioning error of the system is 0.95 m, 90% of the positioning errors are below 2 m, the variance is 0.0031, and the positioning time is 13.253 s.https://ieeexplore.ieee.org/document/10848063/Extreme learning machine (ELM)fingerprint databasegenetic algorithm (GA)particle filtering (PF)WiFi indoor positioning |
| spellingShingle | Yanchun Wang Shaoye Sun Fengjuan Miao Ying Xia WiFi Indoor Positioning Based on EGA-PF and Fernet Algorithm IEEE Access Extreme learning machine (ELM) fingerprint database genetic algorithm (GA) particle filtering (PF) WiFi indoor positioning |
| title | WiFi Indoor Positioning Based on EGA-PF and Fernet Algorithm |
| title_full | WiFi Indoor Positioning Based on EGA-PF and Fernet Algorithm |
| title_fullStr | WiFi Indoor Positioning Based on EGA-PF and Fernet Algorithm |
| title_full_unstemmed | WiFi Indoor Positioning Based on EGA-PF and Fernet Algorithm |
| title_short | WiFi Indoor Positioning Based on EGA-PF and Fernet Algorithm |
| title_sort | wifi indoor positioning based on ega pf and fernet algorithm |
| topic | Extreme learning machine (ELM) fingerprint database genetic algorithm (GA) particle filtering (PF) WiFi indoor positioning |
| url | https://ieeexplore.ieee.org/document/10848063/ |
| work_keys_str_mv | AT yanchunwang wifiindoorpositioningbasedonegapfandfernetalgorithm AT shaoyesun wifiindoorpositioningbasedonegapfandfernetalgorithm AT fengjuanmiao wifiindoorpositioningbasedonegapfandfernetalgorithm AT yingxia wifiindoorpositioningbasedonegapfandfernetalgorithm |