| Presentation | 2022-07-15 [Invited Talk] Application of state-space models to CNN estimation methods for indoor location estimation Kaishin Hori, Satoru Aikawa, Sinichiro Yamamoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Currently, GNSS is the most accurate outdoor location estimation technique. On the other hand, the accuracy of GNSS location estimation indoors is reduced due to the poor reception of satellite signals. Therefore, research is being conducted to achieve highly accurate indoor localization by using wireless LAN. In this study, we employ Convolutional Neural Network (CNN) estimation based on the Fingerprint method for indoor WLAN positioning, which is more accurate than other methods of WLAN information. On the other hand, CNN estimation is time-independent. Therefore, a filter was used to correct for this time-series dependence. As a result, the mean estimation error was improved by up to 0.38 m. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | indoor localization / fingerprint / CNN / state space model |
| Paper # | CS2022-36 |
| Date of Issue | 2022-07-07 (CS) |
| Conference Information | |
| Committee | CS |
|---|---|
| Conference Date | 2022/7/14(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Yakushima Environmental and Cultural Village Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Next Generation Networks, Access Networks, Broadband Access, Power Line Communications, Wireless Communication Systems, Coding Systems, etc. |
| Chair | Daisuke Umehara(Kyoto Inst. of Tech.) |
| Vice Chair | Seiji Kozaki(Mitsubishi Electric) |
| Secretary | Seiji Kozaki(Chiba Inst. of Tech.) |
| Assistant | Hikaru Kawasaki(NICT) / Yuta Ida(Yamaguchi Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Communication Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Talk] Application of state-space models to CNN estimation methods for indoor location estimation |
| Sub Title (in English) | |
| Keyword(1) | indoor localization |
| Keyword(2) | fingerprint |
| Keyword(3) | CNN |
| Keyword(4) | state space model |
| 1st Author's Name | Kaishin Hori |
| 1st Author's Affiliation | University of Hyogo(Univ. of Hyogo) |
| 2nd Author's Name | Satoru Aikawa |
| 2nd Author's Affiliation | University of Hyogo(Univ. of Hyogo) |
| 3rd Author's Name | Sinichiro Yamamoto |
| 3rd Author's Affiliation | University of Hyogo(Univ. of Hyogo) |
| Date | 2022-07-15 |
| Paper # | CS2022-36 |
| Volume (vol) | vol.122 |
| Number (no) | CS-110 |
| Page | pp.pp.100-103(CS), |
| #Pages | 4 |
| Date of Issue | 2022-07-07 (CS) |