RF coverage and pathloss forecast using neural network

Zia Nadir, Muhammad Idrees Ahmad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The paper addresses the applicability of Okumura-Hata model in an area in Oman in GSM frequency band of 890-960 MHz. The Root Mean Square Error (RMSE) was calculated between measured Pathloss values and those predicated on the basis of Okumura-Hata model. We proposed the modification of model by investigating the variation in Pathloss between the measured and predicted values. This modification is necessary to consider the environmental conditions of OMAN. Artificial Neural Network (ANN) was also used to forecast the data for much larger distance. ANN provides a wide and rich class of reliable and powerful statistical tools to mimic complex nonlinear functional relationships. Here, feed forward Multilayer Perceptron (MLP) network was used. A typical MLP network consists of three layers i.e. input layer, hidden layer and output layer. The trained neural nets are finally used to make desired forecasts. These results are acceptable and can be used for OMAN.

Original languageEnglish
Title of host publicationAdvances in Intelligent Systems and Computing
PublisherSpringer Verlag
Pages375-384
Number of pages10
Volume240
ISBN (Print)9783319018560
DOIs
Publication statusPublished - 2014
EventInternational Conference on Systems Science, ICSS 2013 - Wroclaw, Poland
Duration: Sep 10 2013Sep 12 2013

Publication series

NameAdvances in Intelligent Systems and Computing
Volume240
ISSN (Print)21945357

Other

OtherInternational Conference on Systems Science, ICSS 2013
CountryPoland
CityWroclaw
Period9/10/139/12/13

Fingerprint

Multilayer neural networks
Neural networks
Global system for mobile communications
Mean square error
Frequency bands

Keywords

  • Artificial neural network
  • Hata model
  • Pathloss model
  • Propagation models
  • Semi-urban area

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Nadir, Z., & Ahmad, M. I. (2014). RF coverage and pathloss forecast using neural network. In Advances in Intelligent Systems and Computing (Vol. 240, pp. 375-384). (Advances in Intelligent Systems and Computing; Vol. 240). Springer Verlag. https://doi.org/10.1007/978-3-319-01857-7_36

RF coverage and pathloss forecast using neural network. / Nadir, Zia; Ahmad, Muhammad Idrees.

Advances in Intelligent Systems and Computing. Vol. 240 Springer Verlag, 2014. p. 375-384 (Advances in Intelligent Systems and Computing; Vol. 240).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nadir, Z & Ahmad, MI 2014, RF coverage and pathloss forecast using neural network. in Advances in Intelligent Systems and Computing. vol. 240, Advances in Intelligent Systems and Computing, vol. 240, Springer Verlag, pp. 375-384, International Conference on Systems Science, ICSS 2013, Wroclaw, Poland, 9/10/13. https://doi.org/10.1007/978-3-319-01857-7_36
Nadir Z, Ahmad MI. RF coverage and pathloss forecast using neural network. In Advances in Intelligent Systems and Computing. Vol. 240. Springer Verlag. 2014. p. 375-384. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-01857-7_36
Nadir, Zia ; Ahmad, Muhammad Idrees. / RF coverage and pathloss forecast using neural network. Advances in Intelligent Systems and Computing. Vol. 240 Springer Verlag, 2014. pp. 375-384 (Advances in Intelligent Systems and Computing).
@inproceedings{b3fa5ee75e6f436fb111186c1b101cb4,
title = "RF coverage and pathloss forecast using neural network",
abstract = "The paper addresses the applicability of Okumura-Hata model in an area in Oman in GSM frequency band of 890-960 MHz. The Root Mean Square Error (RMSE) was calculated between measured Pathloss values and those predicated on the basis of Okumura-Hata model. We proposed the modification of model by investigating the variation in Pathloss between the measured and predicted values. This modification is necessary to consider the environmental conditions of OMAN. Artificial Neural Network (ANN) was also used to forecast the data for much larger distance. ANN provides a wide and rich class of reliable and powerful statistical tools to mimic complex nonlinear functional relationships. Here, feed forward Multilayer Perceptron (MLP) network was used. A typical MLP network consists of three layers i.e. input layer, hidden layer and output layer. The trained neural nets are finally used to make desired forecasts. These results are acceptable and can be used for OMAN.",
keywords = "Artificial neural network, Hata model, Pathloss model, Propagation models, Semi-urban area",
author = "Zia Nadir and Ahmad, {Muhammad Idrees}",
year = "2014",
doi = "10.1007/978-3-319-01857-7_36",
language = "English",
isbn = "9783319018560",
volume = "240",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "375--384",
booktitle = "Advances in Intelligent Systems and Computing",

}

TY - GEN

T1 - RF coverage and pathloss forecast using neural network

AU - Nadir, Zia

AU - Ahmad, Muhammad Idrees

PY - 2014

Y1 - 2014

N2 - The paper addresses the applicability of Okumura-Hata model in an area in Oman in GSM frequency band of 890-960 MHz. The Root Mean Square Error (RMSE) was calculated between measured Pathloss values and those predicated on the basis of Okumura-Hata model. We proposed the modification of model by investigating the variation in Pathloss between the measured and predicted values. This modification is necessary to consider the environmental conditions of OMAN. Artificial Neural Network (ANN) was also used to forecast the data for much larger distance. ANN provides a wide and rich class of reliable and powerful statistical tools to mimic complex nonlinear functional relationships. Here, feed forward Multilayer Perceptron (MLP) network was used. A typical MLP network consists of three layers i.e. input layer, hidden layer and output layer. The trained neural nets are finally used to make desired forecasts. These results are acceptable and can be used for OMAN.

AB - The paper addresses the applicability of Okumura-Hata model in an area in Oman in GSM frequency band of 890-960 MHz. The Root Mean Square Error (RMSE) was calculated between measured Pathloss values and those predicated on the basis of Okumura-Hata model. We proposed the modification of model by investigating the variation in Pathloss between the measured and predicted values. This modification is necessary to consider the environmental conditions of OMAN. Artificial Neural Network (ANN) was also used to forecast the data for much larger distance. ANN provides a wide and rich class of reliable and powerful statistical tools to mimic complex nonlinear functional relationships. Here, feed forward Multilayer Perceptron (MLP) network was used. A typical MLP network consists of three layers i.e. input layer, hidden layer and output layer. The trained neural nets are finally used to make desired forecasts. These results are acceptable and can be used for OMAN.

KW - Artificial neural network

KW - Hata model

KW - Pathloss model

KW - Propagation models

KW - Semi-urban area

UR - http://www.scopus.com/inward/record.url?scp=84916237494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84916237494&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-01857-7_36

DO - 10.1007/978-3-319-01857-7_36

M3 - Conference contribution

AN - SCOPUS:84916237494

SN - 9783319018560

VL - 240

T3 - Advances in Intelligent Systems and Computing

SP - 375

EP - 384

BT - Advances in Intelligent Systems and Computing

PB - Springer Verlag

ER -