Although various linear log-distance path loss models have been developed for wireless sensor networks, advanced models are required to more accurately and flexibly represent the path loss for complex environments. This paper proposes a machine learning framework for modeling path loss using a combination of three key techniques: artificial neural network (ANN)-based multi-dimensional regression, Gaussian process-based variance analysis, and principle component analysis (PCA)-aided feature selection. In general, the measured path loss dataset comprises multiple features such as distance, antenna height, etc. First, PCA is adopted to reduce the number of features of the dataset and simplify the learning model accordingly. ANN then learns the path loss structure from the dataset with reduced dimension, and Gaussian process learns the shadowing effect. Path loss data measured in a suburban area in Korea are employed. We observe that the proposed combined path loss and shadowing model is more accurate and flexible compared to the conventional linear path loss plus log-normal shadowing model.
The fifth-generation (5G) cellular mobile communications look promising with features that can help improving consumer experience and satisfaction. To be able to provide these features, more spectrum is required according to the Shannon-Hartley theorem. Spectrum is, however, a finite and scarce resource, and it can be allocated to a new service only when the spectral coexistence with other incumbents is ensured. New waveforms for 5G that differ from the conventional orthogonal frequency-division multiplexing (OFDM) are required in order to have a superior performance in terms of out-of-band emissions and to be able to utilize the fragmented spectrum in different bands. We developed the analytical models for evaluating the out-of-band emissions of the conventional cyclic prefix (CP)-OFDM as well as its alternatives: windowed OFDM and filtered OFDM, using their signal spectral modeling. The resulting expressions for the power spectral density (PSD) and the frequency-dependent rejection (FDR) involve simple closed-form expressions or easily computable integrals. We applied the expressions to the advanced minimum coupling loss model for assessing the feasibility of the spectral coexistence between the potential 5G systems (with linearized or nonlinear power amplifier) and the incumbent radar systems. The numerical simulation results indicate that both the windowed OFDM and filtered OFDM guarantee the coexistence at the low expense of the spectrum utilization and their coexistence performance can be reduced and reversed with nonlinearity distortion of the power amplifier.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.