Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots
The ever-expanding scale of WiFi deployments in metropolitan areas has made accurate GPS-free outdoor localization possible by relying solely on the WiFi infrastructure. Nevertheless, neither academic researches nor existing industrial practices seem to provide a satisfactory solution or implementat...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/151323 |
| _version_ | 1826120260071194624 |
|---|---|
| author | Wang, Jin Luo, Jun Pan, Sinno Jialin Sun, Aixin |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Wang, Jin Luo, Jun Pan, Sinno Jialin Sun, Aixin |
| author_sort | Wang, Jin |
| collection | NTU |
| description | The ever-expanding scale of WiFi deployments in metropolitan areas has made accurate GPS-free outdoor localization possible by relying solely on the WiFi infrastructure. Nevertheless, neither academic researches nor existing industrial practices seem to provide a satisfactory solution or implementation. In this paper, we propose WOLoc (WiFi-only Outdoor Localization) as a learning-based outdoor localization solution using only WiFi hotspots labeled by crowdsensing. On one hand, we do not take these labels as fingerprints as it is almost impossible to extend indoor localization mechanisms by fingerprinting metropolitan areas. On the other hand, we avoid the over-simplified local synthesis methods (e.g., centroid) that significantly lose the information contained in the labels. Instead, WOLoc adopts a semi-supervised manifold learning approach that accommodates all the labeled and unlabeled data for a given area, and the output concerning the unlabeled part will become the estimated locations for both unknown users and unknown WiFi hotspots. Moreover, WOLoc applies text mining techniques to analyze the SSIDs of hotspots, so as to derive more accurate input to its manifold learning. We conduct extensive experiments in several outdoor areas, and the results have strongly indicated the efficacy of our solution in achieving a meter-level localization accuracy. |
| first_indexed | 2024-10-01T05:13:36Z |
| format | Journal Article |
| id | ntu-10356/151323 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:13:36Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1513232021-06-16T02:31:42Z Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots Wang, Jin Luo, Jun Pan, Sinno Jialin Sun, Aixin School of Computer Science and Engineering Engineering::Computer science and engineering WiFi-based Localization Manifold Learning The ever-expanding scale of WiFi deployments in metropolitan areas has made accurate GPS-free outdoor localization possible by relying solely on the WiFi infrastructure. Nevertheless, neither academic researches nor existing industrial practices seem to provide a satisfactory solution or implementation. In this paper, we propose WOLoc (WiFi-only Outdoor Localization) as a learning-based outdoor localization solution using only WiFi hotspots labeled by crowdsensing. On one hand, we do not take these labels as fingerprints as it is almost impossible to extend indoor localization mechanisms by fingerprinting metropolitan areas. On the other hand, we avoid the over-simplified local synthesis methods (e.g., centroid) that significantly lose the information contained in the labels. Instead, WOLoc adopts a semi-supervised manifold learning approach that accommodates all the labeled and unlabeled data for a given area, and the output concerning the unlabeled part will become the estimated locations for both unknown users and unknown WiFi hotspots. Moreover, WOLoc applies text mining techniques to analyze the SSIDs of hotspots, so as to derive more accurate input to its manifold learning. We conduct extensive experiments in several outdoor areas, and the results have strongly indicated the efficacy of our solution in achieving a meter-level localization accuracy. Ministry of Education (MOE) National Research Foundation (NRF) This work is supported in part by the National Research Foundation of Singapore and AcRF Tier 2 Grant MOE2016- T2-2-022. 2021-06-16T02:31:42Z 2021-06-16T02:31:42Z 2018 Journal Article Wang, J., Luo, J., Pan, S. J. & Sun, A. (2018). Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots. IEEE Transactions On Mobile Computing, 18(4), 896-909. https://dx.doi.org/10.1109/TMC.2018.2849416 1536-1233 0000-0002-0629-1617 0000-0002-7036-5158 0000-0003-0764-4258 https://hdl.handle.net/10356/151323 10.1109/TMC.2018.2849416 2-s2.0-85048900694 4 18 896 909 en MOE2016-T2-2-022 IEEE Transactions on Mobile Computing © 2018 IEEE. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering WiFi-based Localization Manifold Learning Wang, Jin Luo, Jun Pan, Sinno Jialin Sun, Aixin Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots |
| title | Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots |
| title_full | Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots |
| title_fullStr | Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots |
| title_full_unstemmed | Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots |
| title_short | Learning-based outdoor localization exploiting crowd-labeled WiFi hotspots |
| title_sort | learning based outdoor localization exploiting crowd labeled wifi hotspots |
| topic | Engineering::Computer science and engineering WiFi-based Localization Manifold Learning |
| url | https://hdl.handle.net/10356/151323 |
| work_keys_str_mv | AT wangjin learningbasedoutdoorlocalizationexploitingcrowdlabeledwifihotspots AT luojun learningbasedoutdoorlocalizationexploitingcrowdlabeledwifihotspots AT pansinnojialin learningbasedoutdoorlocalizationexploitingcrowdlabeledwifihotspots AT sunaixin learningbasedoutdoorlocalizationexploitingcrowdlabeledwifihotspots |