A universal Wi-Fi fingerprint localization method based on machine learning and sample differences
Abstract Wi-Fi technology has become an important candidate for localization due to its low cost and no need of additional installation. The Wi-Fi fingerprint-based positioning is widely used because of its ready hardware and acceptable accuracy, especially with the current fingerprint localization...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-12-01
|
| Series: | Satellite Navigation |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s43020-021-00058-8 |
| _version_ | 1818402164766146560 |
|---|---|
| author | Xiaoxiang Cao Yuan Zhuang Xiansheng Yang Xiao Sun Xuan Wang |
| author_facet | Xiaoxiang Cao Yuan Zhuang Xiansheng Yang Xiao Sun Xuan Wang |
| author_sort | Xiaoxiang Cao |
| collection | DOAJ |
| description | Abstract Wi-Fi technology has become an important candidate for localization due to its low cost and no need of additional installation. The Wi-Fi fingerprint-based positioning is widely used because of its ready hardware and acceptable accuracy, especially with the current fingerprint localization algorithms based on Machine Learning (ML) and Deep Learning (DL). However, there exists two challenges. Firstly, the traditional ML methods train a specific classification model for each scene; therefore, it is hard to deploy and manage it on the cloud. Secondly, it is difficult to train an effective multi-classification model by using a small number of fingerprint samples. To solve these two problems, a novel binary classification model based on the samples’ differences is proposed in this paper. We divide the raw fingerprint pairs into positive and negative samples based on each pair’s distance. New relative features (e.g., sort features) are introduced to replace the traditional pair features which use the Media Access Control (MAC) address and Received Signal Strength (RSS). Finally, the boosting algorithm is used to train the classification model. The UJIndoorLoc dataset including the data from three different buildings is used to evaluate our proposed method. The preliminary results show that the floor success detection rate of the proposed method can reach 99.54% (eXtreme Gradient Boosting, XGBoost) and 99.22% (Gradient Boosting Decision Tree, GBDT), and the positioning error can reach 3.460 m (XGBoost) and 4.022 m (GBDT). Another important advantage of the proposed algorithm is that the model trained by one building’s data can be well applied to another building, which shows strong generalizable ability. |
| first_indexed | 2024-12-14T08:04:01Z |
| format | Article |
| id | doaj.art-046c2590ccd04cf8b06c0b78c756c987 |
| institution | Directory Open Access Journal |
| issn | 2662-1363 |
| language | English |
| last_indexed | 2024-12-14T08:04:01Z |
| publishDate | 2021-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Satellite Navigation |
| spelling | doaj.art-046c2590ccd04cf8b06c0b78c756c9872022-12-21T23:10:16ZengSpringerOpenSatellite Navigation2662-13632021-12-012111510.1186/s43020-021-00058-8A universal Wi-Fi fingerprint localization method based on machine learning and sample differencesXiaoxiang Cao0Yuan Zhuang1Xiansheng Yang2Xiao Sun3Xuan Wang4State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan UniversityState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan UniversityState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan UniversityState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan UniversityState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan UniversityAbstract Wi-Fi technology has become an important candidate for localization due to its low cost and no need of additional installation. The Wi-Fi fingerprint-based positioning is widely used because of its ready hardware and acceptable accuracy, especially with the current fingerprint localization algorithms based on Machine Learning (ML) and Deep Learning (DL). However, there exists two challenges. Firstly, the traditional ML methods train a specific classification model for each scene; therefore, it is hard to deploy and manage it on the cloud. Secondly, it is difficult to train an effective multi-classification model by using a small number of fingerprint samples. To solve these two problems, a novel binary classification model based on the samples’ differences is proposed in this paper. We divide the raw fingerprint pairs into positive and negative samples based on each pair’s distance. New relative features (e.g., sort features) are introduced to replace the traditional pair features which use the Media Access Control (MAC) address and Received Signal Strength (RSS). Finally, the boosting algorithm is used to train the classification model. The UJIndoorLoc dataset including the data from three different buildings is used to evaluate our proposed method. The preliminary results show that the floor success detection rate of the proposed method can reach 99.54% (eXtreme Gradient Boosting, XGBoost) and 99.22% (Gradient Boosting Decision Tree, GBDT), and the positioning error can reach 3.460 m (XGBoost) and 4.022 m (GBDT). Another important advantage of the proposed algorithm is that the model trained by one building’s data can be well applied to another building, which shows strong generalizable ability.https://doi.org/10.1186/s43020-021-00058-8Fingerprint-based positioningSample differenceBinary-classificationBoostingMachine learningWi-Fi positioning |
| spellingShingle | Xiaoxiang Cao Yuan Zhuang Xiansheng Yang Xiao Sun Xuan Wang A universal Wi-Fi fingerprint localization method based on machine learning and sample differences Satellite Navigation Fingerprint-based positioning Sample difference Binary-classification Boosting Machine learning Wi-Fi positioning |
| title | A universal Wi-Fi fingerprint localization method based on machine learning and sample differences |
| title_full | A universal Wi-Fi fingerprint localization method based on machine learning and sample differences |
| title_fullStr | A universal Wi-Fi fingerprint localization method based on machine learning and sample differences |
| title_full_unstemmed | A universal Wi-Fi fingerprint localization method based on machine learning and sample differences |
| title_short | A universal Wi-Fi fingerprint localization method based on machine learning and sample differences |
| title_sort | universal wi fi fingerprint localization method based on machine learning and sample differences |
| topic | Fingerprint-based positioning Sample difference Binary-classification Boosting Machine learning Wi-Fi positioning |
| url | https://doi.org/10.1186/s43020-021-00058-8 |
| work_keys_str_mv | AT xiaoxiangcao auniversalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT yuanzhuang auniversalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT xianshengyang auniversalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT xiaosun auniversalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT xuanwang auniversalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT xiaoxiangcao universalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT yuanzhuang universalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT xianshengyang universalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT xiaosun universalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences AT xuanwang universalwififingerprintlocalizationmethodbasedonmachinelearningandsampledifferences |