Feature Extraction in Reference Signal Received Power Prediction Based on Convolution Neural Networks

被引:12
作者
Yi, Zheng [1 ]
Liu, Zhiwen [2 ]
Rong, Huang [1 ]
Ji, Wang [1 ]
Xie, Wenwu [3 ]
Liu, Shouyin [1 ]
机构
[1] Cent China Normal Univ, Coll Phys Sci & Technol, Wuhan 430079, Hubei, Peoples R China
[2] Cent China Normal Univ, Wollongong Joint Inst, Wuhan 430079, Hubei, Peoples R China
[3] Hunan Inst Sci & Technol, Yueyang 414006, Peoples R China
关键词
Feature extraction; reference signal received power; convolution neural networks;
D O I
10.1109/LCOMM.2021.3054862
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
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 through 14-D PFs, and is further improved in nonlinear MLRs combining PFs and EFs.
引用
收藏
页码:1751 / 1755
页数:5
相关论文
共 12 条
[1]   Rich feature hierarchies for accurate object detection and semantic segmentation [J].
Girshick, Ross ;
Donahue, Jeff ;
Darrell, Trevor ;
Malik, Jitendra .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :580-587
[2]   Empirical radio propagation model for DTV applied to non-homogeneous paths and different climates using machine learning techniques [J].
Gomes, Igor Ruiz ;
Gomes, Cristiane Ruiz ;
Gomes, Herminio Simoes ;
dos Santos Cavalcante, Gervasio Protasio .
PLOS ONE, 2018, 13 (03)
[4]  
Kingma DP, 2014, ADV NEUR IN, V27
[5]  
Lin K. P., 2010, Advances in Neural Network Research and Applications, P861
[6]  
OKUMURA Y, 1968, REV ELEC COMMUN LAB, V16, P825
[7]   Macrocell Path-Loss Prediction Using Artificial Neural Networks [J].
Ostlin, Erik ;
Zepernick, Hans-Jurgen ;
Suzuki, Hajime .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2010, 59 (06) :2735-2747
[8]  
Park C., 2019, ARXIV190402383
[9]  
Rani M. S, 2012, Int. J. Agricul. Innovat. Res. (IJAIR), V3, P221
[10]   Two-step path loss prediction by artificial neural network for wireless service area planning [J].
Saito, Kentaro ;
Jin, Yongri ;
Kang, CheChia ;
Takada, Jun-ichi ;
Leu, Jenq-Shiou .
IEICE COMMUNICATIONS EXPRESS, 2019, 8 (12) :611-616