On-Device Learning of Indoor Location for WiFi Fingerprint Approach
Indoor positioning is a recent technology that has gained interest in industry and academia thanks to the promising results of locating objects, people or robots accurately in indoor environments. One of the utilized technologies is based on algorithms that process the Received Signal Strength Indic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/7/2202 |
| _version_ | 1798025402299449344 |
|---|---|
| author | Marco Aurelio Nuño-Maganda Hiram Herrera-Rivas Cesar Torres-Huitzil Heidy Marisol Marín-Castro Yuriria Coronado-Pérez |
| author_facet | Marco Aurelio Nuño-Maganda Hiram Herrera-Rivas Cesar Torres-Huitzil Heidy Marisol Marín-Castro Yuriria Coronado-Pérez |
| author_sort | Marco Aurelio Nuño-Maganda |
| collection | DOAJ |
| description | Indoor positioning is a recent technology that has gained interest in industry and academia thanks to the promising results of locating objects, people or robots accurately in indoor environments. One of the utilized technologies is based on algorithms that process the Received Signal Strength Indicator (RSSI) in order to infer location information without previous knowledge of the distribution of the Access Points (APs) in the area of interest. This paper presents the design and implementation of an indoor positioning mobile application, which allows users to capture and build their own RSSI maps by off-line training of a set of selected classifiers and using the models generated to obtain the current indoor location of the target device. In an early experimental and design stage, 59 classifiers were evaluated, using data from proposed indoor scenarios. Then, from the tested classifiers in the early stage, only the top-five classifiers were integrated with the proposed mobile indoor positioning, based on the accuracy obtained for the test scenarios. The proposed indoor application achieves high classification rates, above 89%, for at least 10 different locations in indoor environments, where each location has a minimum separation of 0.5 m. |
| first_indexed | 2024-04-11T18:18:17Z |
| format | Article |
| id | doaj.art-fbd0b882d65f47629e72c244bb58e111 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T18:18:17Z |
| publishDate | 2018-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fbd0b882d65f47629e72c244bb58e1112022-12-22T04:09:50ZengMDPI AGSensors1424-82202018-07-01187220210.3390/s18072202s18072202On-Device Learning of Indoor Location for WiFi Fingerprint ApproachMarco Aurelio Nuño-Maganda0Hiram Herrera-Rivas1Cesar Torres-Huitzil2Heidy Marisol Marín-Castro3Yuriria Coronado-Pérez4Information Technology Department, Universidad Politécnica de Victoria, Ciudad Victoria 87130, MexicoInformation Technology Department, Universidad Politécnica de Victoria, Ciudad Victoria 87130, MexicoInformation Technology Laboratory, Cinvestav-Tamaulipas, Ciudad Victoria 87130, MexicoCátedras CONACYT, Autonomous University of Tamaulipas, Ciudad Victoria 87000, MexicoInformation Technology Department, Universidad Politécnica de Victoria, Ciudad Victoria 87130, MexicoIndoor positioning is a recent technology that has gained interest in industry and academia thanks to the promising results of locating objects, people or robots accurately in indoor environments. One of the utilized technologies is based on algorithms that process the Received Signal Strength Indicator (RSSI) in order to infer location information without previous knowledge of the distribution of the Access Points (APs) in the area of interest. This paper presents the design and implementation of an indoor positioning mobile application, which allows users to capture and build their own RSSI maps by off-line training of a set of selected classifiers and using the models generated to obtain the current indoor location of the target device. In an early experimental and design stage, 59 classifiers were evaluated, using data from proposed indoor scenarios. Then, from the tested classifiers in the early stage, only the top-five classifiers were integrated with the proposed mobile indoor positioning, based on the accuracy obtained for the test scenarios. The proposed indoor application achieves high classification rates, above 89%, for at least 10 different locations in indoor environments, where each location has a minimum separation of 0.5 m.http://www.mdpi.com/1424-8220/18/7/2202mobile applicationclassifierWiFi fingerprintindoor localization |
| spellingShingle | Marco Aurelio Nuño-Maganda Hiram Herrera-Rivas Cesar Torres-Huitzil Heidy Marisol Marín-Castro Yuriria Coronado-Pérez On-Device Learning of Indoor Location for WiFi Fingerprint Approach Sensors mobile application classifier WiFi fingerprint indoor localization |
| title | On-Device Learning of Indoor Location for WiFi Fingerprint Approach |
| title_full | On-Device Learning of Indoor Location for WiFi Fingerprint Approach |
| title_fullStr | On-Device Learning of Indoor Location for WiFi Fingerprint Approach |
| title_full_unstemmed | On-Device Learning of Indoor Location for WiFi Fingerprint Approach |
| title_short | On-Device Learning of Indoor Location for WiFi Fingerprint Approach |
| title_sort | on device learning of indoor location for wifi fingerprint approach |
| topic | mobile application classifier WiFi fingerprint indoor localization |
| url | http://www.mdpi.com/1424-8220/18/7/2202 |
| work_keys_str_mv | AT marcoaurelionunomaganda ondevicelearningofindoorlocationforwififingerprintapproach AT hiramherrerarivas ondevicelearningofindoorlocationforwififingerprintapproach AT cesartorreshuitzil ondevicelearningofindoorlocationforwififingerprintapproach AT heidymarisolmarincastro ondevicelearningofindoorlocationforwififingerprintapproach AT yuririacoronadoperez ondevicelearningofindoorlocationforwififingerprintapproach |