Presentation | 2018-06-20 A Study on Indoor Localization based on Unified Fingerprint of Wi-Fi and Bluetooth Low Energy using Machine Learning Shunsuke Tsuchida, Shinsuke Ibi, Seiivhi Sampei, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper deals with an indoor localization by fingerprint estimation with the aid of machine learning on the basis of both Wi-Fi (Wireless-Fidelity) and BLE (Bluetooth Low Energy) Received Power Strength Indication (RSSI) observations of beacon signals. Wi-Fi and BLE localizations have been individually studied so far. For estimating the indoor position, the position of the beacon transmitter can be often estimated by using three-point positioning. However, the accurate position cannot be estimated by calculating the observed RSSI in the indoor environments. This is because the principle of the three-point positioning relies on ideal free space propagation loss. Unfortunately, the RSSI does not obey the ideal case. The other approach is to consider the stochastical behavior of RSSI distribution. However, the analytical distribution does not capture the practical environments, resulting in low estimation quality. Instead of considering the accuracy of the distribution, machine learning is capable of estimating the position form RSSI data itself. In the machine learning regime, big data, which is integrating Wi-Fi and BLE RSSI, helps to improve the accuracy of the localization. This paper confirms the validity of the unified Wi-Fi and BLE localization through empirical results. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Machine Learning / Wi-Fi / BLE / Fingerprint / Indoor Localization |
Paper # | RCS2018-35 |
Date of Issue | 2018-06-13 (RCS) |
Conference Information | |
Committee | RCS |
---|---|
Conference Date | 2018/6/20(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Nagasaki University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | First Presentation in IEICE Technical Committee, Railroad Communications, Inter-Vehicle Communications, Road to Vehicle Communications, Resource Control, Scheduling, Wireless Communication Systems, etc. |
Chair | Tomoaki Otsuki(Keio Univ.) |
Vice Chair | Eisuke Fukuda(Fujitsu Labs.) / Satoshi Suyama(NTT DoCoMo) / Fumiaki Maehara(Waseda Univ.) |
Secretary | Eisuke Fukuda(Hokkaido Univ.) / Satoshi Suyama(NTT) / Fumiaki Maehara |
Assistant | Kazushi Muraoka(NTT DOCOMO) / Shinsuke Ibi(Osaka Univ.) / Hiroshi Nishimoto(Mitsubishi Electric) / Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) |
Paper Information | |
Registration To | Technical Committee on Radio Communication Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study on Indoor Localization based on Unified Fingerprint of Wi-Fi and Bluetooth Low Energy using Machine Learning |
Sub Title (in English) | |
Keyword(1) | Machine Learning |
Keyword(2) | Wi-Fi |
Keyword(3) | BLE |
Keyword(4) | Fingerprint |
Keyword(5) | Indoor Localization |
1st Author's Name | Shunsuke Tsuchida |
1st Author's Affiliation | Osaka University(Osaka Univ.) |
2nd Author's Name | Shinsuke Ibi |
2nd Author's Affiliation | Osaka University(Osaka Univ.) |
3rd Author's Name | Seiivhi Sampei |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2018-06-20 |
Paper # | RCS2018-35 |
Volume (vol) | vol.118 |
Number (no) | RCS-101 |
Page | pp.pp.1-6(RCS), |
#Pages | 6 |
Date of Issue | 2018-06-13 (RCS) |