講演抄録/キーワード |
講演名 |
2021-11-10 15:55
Channel Parameter Estimation by using Environmental Features ○Inocent Calist・Zhiqiang Li・Minseok Kim(Niigata Univ.) AP2021-106 |
抄録 |
(和) |
Recent developments in the next generation of mobile communication and the application of the Internet of things has raised the need to develop more accurate channel models. This work presents the development of a supervised based machine learning (ML) prediction model for large scale channel parameters (LSCPs) estimation by analyzing the reflected multipath ray's information. The reflected rays varies with the morphology structure of the propagation environment, hence a dynamic LSCPs predictive model can be realized. The input parameters to the prediction model are transmitter (TX) and receiver (RX) positional coordinates, and the reflected rays' information such as the delay, angle of arrival, angle of departure, elevation angle of arrival, elevation angle of departure, and power gain. The proposed model was implemented using Random Forest (RF) which can predict both linear and nonlinear data. Ray tracing (RT) simulation was performed to calculate the input measurement dataset of the LSCPs, and the input information of the reflected rays. Cross validation was then utilized to validate the model. |
(英) |
Recent developments in the next generation of mobile communication and the application of the Internet of things has raised the need to develop more accurate channel models. This work presents the development of a supervised based machine learning (ML) prediction model for large scale channel parameters (LSCPs) estimation by analyzing the reflected multipath ray's information. The reflected rays varies with the morphology structure of the propagation environment, hence a dynamic LSCPs predictive model can be realized. The input parameters to the prediction model are transmitter (TX) and receiver (RX) positional coordinates, and the reflected rays' information such as the delay, angle of arrival, angle of departure, elevation angle of arrival, elevation angle of departure, and power gain. The proposed model was implemented using Random Forest (RF) which can predict both linear and nonlinear data. Ray tracing (RT) simulation was performed to calculate the input measurement dataset of the LSCPs, and the input information of the reflected rays. Cross validation was then utilized to validate the model. |
キーワード |
(和) |
Machine learning / parameter estimation / channel / rays information / prediction model / / / |
(英) |
Machine learning / parameter estimation / channel / rays information / prediction model / / / |
文献情報 |
信学技報, vol. 121, no. 233, AP2021-106, pp. 34-38, 2021年11月. |
資料番号 |
AP2021-106 |
発行日 |
2021-11-03 (AP) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
AP2021-106 |
|