A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz
Abstract This article presents the analysis of a hybrid, error correction-based, neural network model to predict the path loss for suburban areas at 800 MHz and 2600 MHz, obtained by combining empirical propagation models, ECC-33, Ericsson 9999, Okumura Hata, and 3GPP's TR 36.942, with a feedfo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sociedade Brasileira de Microondas e Optoeletrônica; Sociedade Brasileira de Eletromagnetismo
|
| Series: | Journal of Microwaves, Optoelectronics and Electromagnetic Applications |
| Subjects: | |
| Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S2179-10742017000300708&lng=en&tlng=en |
| _version_ | 1819210714280099840 |
|---|---|
| author | Bruno J. Cavalcanti Gustavo A. Cavalcante Laércio M. de Mendonça Gabriel M. Cantanhede Marcelo M.M. de Oliveira Adaildo G. D’Assunção |
| author_facet | Bruno J. Cavalcanti Gustavo A. Cavalcante Laércio M. de Mendonça Gabriel M. Cantanhede Marcelo M.M. de Oliveira Adaildo G. D’Assunção |
| author_sort | Bruno J. Cavalcanti |
| collection | DOAJ |
| description | Abstract This article presents the analysis of a hybrid, error correction-based, neural network model to predict the path loss for suburban areas at 800 MHz and 2600 MHz, obtained by combining empirical propagation models, ECC-33, Ericsson 9999, Okumura Hata, and 3GPP's TR 36.942, with a feedforward Artificial Neural Network (ANN). The performance of the hybrid model was compared against regular versions of the empirical models and a simple neural network fed with input parameters commonly used in related works. Results were compared with data obtained by measurements performed in the vicinity of the Federal University of Rio Grande do Norte (UFRN), in the city of Natal, Brazil. In the end, the hybrid neural network obtained the lowest RMSE indexes, besides almost equalizing the distribution of simulated and experimental data, indicating greater similarity with measurements. |
| first_indexed | 2024-12-23T06:15:34Z |
| format | Article |
| id | doaj.art-dae115aa596a439f8dda6272e42ace49 |
| institution | Directory Open Access Journal |
| issn | 2179-1074 |
| language | English |
| last_indexed | 2024-12-23T06:15:34Z |
| publisher | Sociedade Brasileira de Microondas e Optoeletrônica; Sociedade Brasileira de Eletromagnetismo |
| record_format | Article |
| series | Journal of Microwaves, Optoelectronics and Electromagnetic Applications |
| spelling | doaj.art-dae115aa596a439f8dda6272e42ace492022-12-21T17:57:18ZengSociedade Brasileira de Microondas e Optoeletrônica; Sociedade Brasileira de EletromagnetismoJournal of Microwaves, Optoelectronics and Electromagnetic Applications2179-107416370872210.1590/2179-10742017v16i3925S2179-10742017000300708A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHzBruno J. CavalcantiGustavo A. CavalcanteLaércio M. de MendonçaGabriel M. CantanhedeMarcelo M.M. de OliveiraAdaildo G. D’AssunçãoAbstract This article presents the analysis of a hybrid, error correction-based, neural network model to predict the path loss for suburban areas at 800 MHz and 2600 MHz, obtained by combining empirical propagation models, ECC-33, Ericsson 9999, Okumura Hata, and 3GPP's TR 36.942, with a feedforward Artificial Neural Network (ANN). The performance of the hybrid model was compared against regular versions of the empirical models and a simple neural network fed with input parameters commonly used in related works. Results were compared with data obtained by measurements performed in the vicinity of the Federal University of Rio Grande do Norte (UFRN), in the city of Natal, Brazil. In the end, the hybrid neural network obtained the lowest RMSE indexes, besides almost equalizing the distribution of simulated and experimental data, indicating greater similarity with measurements.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S2179-10742017000300708&lng=en&tlng=enArtificial Neural Networks - ANNLong Term Evolution - LTELong Term Evolution Advanced - LTE-Apropagation modelspath loss |
| spellingShingle | Bruno J. Cavalcanti Gustavo A. Cavalcante Laércio M. de Mendonça Gabriel M. Cantanhede Marcelo M.M. de Oliveira Adaildo G. D’Assunção A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz Journal of Microwaves, Optoelectronics and Electromagnetic Applications Artificial Neural Networks - ANN Long Term Evolution - LTE Long Term Evolution Advanced - LTE-A propagation models path loss |
| title | A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz |
| title_full | A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz |
| title_fullStr | A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz |
| title_full_unstemmed | A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz |
| title_short | A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz |
| title_sort | hybrid path loss prediction model based on artificial neural networks using empirical models for lte and lte a at 800 mhz and 2600 mhz |
| topic | Artificial Neural Networks - ANN Long Term Evolution - LTE Long Term Evolution Advanced - LTE-A propagation models path loss |
| url | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S2179-10742017000300708&lng=en&tlng=en |
| work_keys_str_mv | AT brunojcavalcanti ahybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT gustavoacavalcante ahybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT laerciomdemendonca ahybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT gabrielmcantanhede ahybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT marcelommdeoliveira ahybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT adaildogdassuncao ahybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT brunojcavalcanti hybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT gustavoacavalcante hybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT laerciomdemendonca hybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT gabrielmcantanhede hybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT marcelommdeoliveira hybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz AT adaildogdassuncao hybridpathlosspredictionmodelbasedonartificialneuralnetworksusingempiricalmodelsforlteandlteaat800mhzand2600mhz |