期刊论文

Shouyin, L.

英文

IEEE COMMUNICATIONS LETTERS

1089-7798

2021

25

6

1751-1755

10.1109/LCOMM.2021.3054862

Manuscript received August 12, 2020; revised October 11, 2020, November 17, 2020, and December 25, 2020; accepted January 18, 2021. Date of publication February 10, 2021; date of current version June 10, 2021. This work was supported in part by the Fundamental Research Funds for the Central Universities of China under grant CCNU20QN004. The associate editor coordinating the review of this letter and approving it for publication was M. Chafii. (Corresponding author: Liu Shouyin.) Zheng Yi, Huang Rong, Wang Ji, and Liu Shouyin are with the College of Physical Science and Technology, Central China Normal University, Wuhan 430079, China (e-mail: syliu@mail.ccnu.edu.cn).

本校为第一机构

In this letter, an environmental features (EFs) extraction model is proposed for estimating reference signal received power (RSRP) accurately. Firstly, 18-D measured data is transformed into 15-D physical features (PFs). Then 15-D PFs is reduced to 14-D by performing correlation analysis. Secondly, EFs are extracted from the environmental maps (EMs) by applying Convolution Neural Networks (CNNs). Finally, several Machine Learning Regressors (MLRs) are trained to predict RSRP combining PFs and EFs as inputs. The results, in test dataset, show that prediction performance of MLRs is improved thro...