Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions

Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions

This paper analyzes the use of artificial neural networks (ANNs) for predicting the received power/path loss in both outdoor and indoor links. The approach followed has been a combined use of ANNs and ray-tracing, the latter allowing the identification and parameterization of the so-called dominant...

Full description

Bibliographic Details
Main Authors: Ignacio Fernández Anitzine, Juan Antonio Romo Argota, Fernado Pérez Fontán
Format: Article
Language:English
Published: Hindawi Limited 2012-01-01
Series:International Journal of Antennas and Propagation
Online Access:http://dx.doi.org/10.1155/2012/351487
id doaj-f8d963d063ea44fd8c41a7eaacd74615
record_format Article
spelling doaj-f8d963d063ea44fd8c41a7eaacd746152020-11-24T23:18:35ZengHindawi LimitedInternational Journal of Antennas and Propagation1687-58691687-58772012-01-01201210.1155/2012/351487351487Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss PredictionsIgnacio Fernández Anitzine0Juan Antonio Romo Argota1Fernado Pérez Fontán2Department of Electronics and Telecommunications, University of the Basque Country, Alameda Urquijo s/n, 48013 Bilbao, SpainDepartment of Electronics and Telecommunications, University of the Basque Country, Alameda Urquijo s/n, 48013 Bilbao, SpainDepartment of Signal Theory and Communications, University of Vigo, Campus Universitario s/n, 36200 Vigo, SpainThis paper analyzes the use of artificial neural networks (ANNs) for predicting the received power/path loss in both outdoor and indoor links. The approach followed has been a combined use of ANNs and ray-tracing, the latter allowing the identification and parameterization of the so-called dominant path. A complete description of the process for creating and training an ANN-based model is presented with special emphasis on the training process. More specifically, we will be discussing various techniques to arrive at valid predictions focusing on an optimum selection of the training set. A quantitative analysis based on results from two narrowband measurement campaigns, one outdoors and the other indoors, is also presented.http://dx.doi.org/10.1155/2012/351487
collection DOAJ
language English
format Article
sources DOAJ
author Ignacio Fernández Anitzine
Juan Antonio Romo Argota
Fernado Pérez Fontán
spellingShingle Ignacio Fernández Anitzine
Juan Antonio Romo Argota
Fernado Pérez Fontán
Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions
International Journal of Antennas and Propagation
author_facet Ignacio Fernández Anitzine
Juan Antonio Romo Argota
Fernado Pérez Fontán
author_sort Ignacio Fernández Anitzine
title Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions
title_short Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions
title_full Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions
title_fullStr Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions
title_full_unstemmed Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions
title_sort influence of training set selection in artificial neural network-based propagation path loss predictions
publisher Hindawi Limited
series International Journal of Antennas and Propagation
issn 1687-5869
1687-5877
publishDate 2012-01-01
description This paper analyzes the use of artificial neural networks (ANNs) for predicting the received power/path loss in both outdoor and indoor links. The approach followed has been a combined use of ANNs and ray-tracing, the latter allowing the identification and parameterization of the so-called dominant path. A complete description of the process for creating and training an ANN-based model is presented with special emphasis on the training process. More specifically, we will be discussing various techniques to arrive at valid predictions focusing on an optimum selection of the training set. A quantitative analysis based on results from two narrowband measurement campaigns, one outdoors and the other indoors, is also presented.
url http://dx.doi.org/10.1155/2012/351487
work_keys_str_mv AT ignaciofernandezanitzine influenceoftrainingsetselectioninartificialneuralnetworkbasedpropagationpathlosspredictions
AT juanantonioromoargota influenceoftrainingsetselectioninartificialneuralnetworkbasedpropagationpathlosspredictions
AT fernadoperezfontan influenceoftrainingsetselectioninartificialneuralnetworkbasedpropagationpathlosspredictions
_version_ 1725581022899208192

Similar Items