Presentation | 2019-01-24 On the Radio Environment Map Construction using Neural Network Residual Kriging Koya Sato, Kei Inage, Takeo Fujii, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we discuss the performance of feedforward neural network (FFNN) in radio environment map (REM) construction. We can realize a highly accurate REM via croudsourcing with Kriging. In the most works on the Kriging-aided REM construction, the measurement datasets are first regressed via linear regression in order to ensure spatial stationarity of the random variable. On the other hand, the path loss in the practical situation often contains an anisotropy due to effects of terrain and obstacles; thus, Kriging may not perform the optimal interpolation because of the regression error. In this paper, FFNN is used for the path loss modeling and the regression. Through theoretical, numerical and experimental discussions, we show situations where the FFNN can improve the accuracy of REM. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | machine learning / neural network / regression analysis / spatial interpolation / radio environment map / crowdsensing |
Paper # | SR2018-106 |
Date of Issue | 2019-01-17 (SR) |
Conference Information | |
Committee | SR |
---|---|
Conference Date | 2019/1/24(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Corasse, Fukushima city (Fukushima prefecture) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | cognitive radio, machine learning application, heterogeneous network, SDN, IoT etc. |
Chair | Kenta Umebayashi(Tokyo Univ. of Agric. and Tech.) |
Vice Chair | Masayuki Ariyoshi(NEC) / Suguru Kameda(Tohoku Univ.) |
Secretary | Masayuki Ariyoshi(NICT) / Suguru Kameda(ATR) |
Assistant | Gia Khanh Tran(Tokyo Inst. of Tech.) / Syusuke Narieda(Mie Univ.) / Koji Ohshima(Kozo Keikaku Engineering) / Mai Ohta(Fukuoka Univ.) / Teppei Oyama(Fujitsu Lab.) |
Paper Information | |
Registration To | Technical Committee on Smart Radio |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | On the Radio Environment Map Construction using Neural Network Residual Kriging |
Sub Title (in English) | |
Keyword(1) | machine learning |
Keyword(2) | neural network |
Keyword(3) | regression analysis |
Keyword(4) | spatial interpolation |
Keyword(5) | radio environment map |
Keyword(6) | crowdsensing |
1st Author's Name | Koya Sato |
1st Author's Affiliation | Tokyo University of Science(TUS) |
2nd Author's Name | Kei Inage |
2nd Author's Affiliation | Tokyo Metropolitan College of Industrial Technology(TMCIT) |
3rd Author's Name | Takeo Fujii |
3rd Author's Affiliation | The University of Electro-Communications(UEC) |
Date | 2019-01-24 |
Paper # | SR2018-106 |
Volume (vol) | vol.118 |
Number (no) | SR-421 |
Page | pp.pp.63-70(SR), |
#Pages | 8 |
Date of Issue | 2019-01-17 (SR) |