| Presentation | 2021-01-21 Study on UWB indoor localization method using machine learning-based accurate NLOS detection Keigo Ishida, Eiji Okamoto, Huan-Bang Li, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | According to the automatization of factory and other facilities, there is a growing demand of accurate indoor location information. We have focused on the high resolution of ultra-wideband (UWB) and its application to position estimation. One of the problems for indoor localization is the degradation of positioning accuracy due to the non line-of-sight (NLOS) environment, which is caused by the blockage of obstacles. To tackle this problem, various methods have been investigated. This paper focuses on the range-based methods which detects NLOS sensors based on the variance of multiple measurement data. Range-based methods are simple because they uses only a few metrics, while comparatively having high accuracy. However, conventional methods have problems in versatility because they used empirical thresholds. In addition, since NLOS detected sensors are removed, the performance of localization tends to degrade even if the NLOS detection is successful. Therefore, in this paper, we propose a new localization method introducing machine learning into NLOS detection to improve its versatility and accuracy. In addition, the proposed method also uses the NLOS sensors for localization by utilizing estimated true distances based on the predction function derived by training data. The performance of the proposed method is shown in comparison with other conventional methods in computer simulation. Consequently, it is shown that the proposed method is superior to other conventional methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | indoor localization / UWB / support vector machine / neural network / NLOS |
| Paper # | SeMI2020-50 |
| Date of Issue | 2021-01-13 (SeMI) |
| Conference Information | |
| Committee | SeMI |
|---|---|
| Conference Date | 2021/1/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Susumu Ishihara(Shizuoka Univ.) |
| Vice Chair | Kazuya Monden(Hitachi) / Koji Yamamoto(Kyoto Univ.) |
| Secretary | Kazuya Monden(Kyoto Univ.) / Koji Yamamoto(Cyber Univ.) |
| Assistant | Yuki Katsumata(NTT DOCOMO) / Yu Nakayama(Tokyo Univ. of Agri. and Tech.) / Akira Uchiyama(Osaka Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Sensor Network and Mobile Intelligence |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Study on UWB indoor localization method using machine learning-based accurate NLOS detection |
| Sub Title (in English) | |
| Keyword(1) | indoor localization |
| Keyword(2) | UWB |
| Keyword(3) | support vector machine |
| Keyword(4) | neural network |
| Keyword(5) | NLOS |
| 1st Author's Name | Keigo Ishida |
| 1st Author's Affiliation | Nagoya Institute of Technology(NIT) |
| 2nd Author's Name | Eiji Okamoto |
| 2nd Author's Affiliation | Nagoya Institute of Technology(NIT) |
| 3rd Author's Name | Huan-Bang Li |
| 3rd Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
| Date | 2021-01-21 |
| Paper # | SeMI2020-50 |
| Volume (vol) | vol.120 |
| Number (no) | SeMI-315 |
| Page | pp.pp.39-44(SeMI), |
| #Pages | 6 |
| Date of Issue | 2021-01-13 (SeMI) |