Feature Extraction in Reference Signal Received Power Prediction Based on Convolution Neural Networks
Yi Zheng, Liu Zhiwen, Rong Huang, Ji Wang, Wenwu Xie, Shouyin Liu
Abstract
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.
Topics & Concepts
Convolution (computer science)Feature extractionArtificial neural networkComputer scienceArtificial intelligencePattern recognition (psychology)Feature (linguistics)Convolutional neural networkPower (physics)SIGNAL (programming language)Signal processingDigital signal processingLinguisticsPhilosophyProgramming languageComputer hardwarePhysicsQuantum mechanicsWireless Signal Modulation ClassificationPower Quality and HarmonicsSpeech and Audio Processing