Optimal Artificial Neural Network design for propagation path-loss prediction using adaptive evolutionary algorithms

Optimal Artificial Neural Network design for propagation path-loss prediction using adaptive evolutionary algorithms. Sotiroudis, S., Goudos, S., Gotsis, K., Siakavara, K., & Sahalos, J. In 2013 7th European Conference on Antennas and Propagation, EuCAP 2013, 2013.
abstract bibtex

In this paper we present an alternative procedure for the prediction of propagation path loss in urban environments, which is based on Artificial Neural Networks (ANN). The size of a neural network must be defined before it can be trained for any application. We apply different adaptive Differential Evolution (DE) algorithms, in order to design an optimal ANN for path loss propagation prediction. We present two different ANN design cases with two and three hidden layers respectively. The general performance of the both ANN shows their effectiveness to yield results with satisfactory accuracy in short time. The received results are compared to the respective ones yielded by the Ray-Tracing model and exhibit satisfactory accuracy. © 2013 EurAAP.

@inproceedings{
 title = {Optimal Artificial Neural Network design for propagation path-loss prediction using adaptive evolutionary algorithms},
 type = {inproceedings},
 year = {2013},
 keywords = {Differential Evolution,Neural Network,Self-adaptive Differential Evolution,evolutionary algorithms,mobile communications,optimization methods,propagation path-loss},
 id = {86994c56-5c35-31a9-a615-806779420894},
 created = {2020-02-29T16:57:44.368Z},
 file_attached = {false},
 profile_id = {c69aa657-d754-373c-91b7-64154b7d5d91},
 last_modified = {2023-02-11T18:08:48.894Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Sotiroudis2013a},
 private_publication = {false},
 abstract = {In this paper we present an alternative procedure for the prediction of propagation path loss in urban environments, which is based on Artificial Neural Networks (ANN). The size of a neural network must be defined before it can be trained for any application. We apply different adaptive Differential Evolution (DE) algorithms, in order to design an optimal ANN for path loss propagation prediction. We present two different ANN design cases with two and three hidden layers respectively. The general performance of the both ANN shows their effectiveness to yield results with satisfactory accuracy in short time. The received results are compared to the respective ones yielded by the Ray-Tracing model and exhibit satisfactory accuracy. © 2013 EurAAP.},
 bibtype = {inproceedings},
 author = {Sotiroudis, S.P. and Goudos, S.K. and Gotsis, K.A. and Siakavara, K. and Sahalos, J.N.},
 booktitle = {2013 7th European Conference on Antennas and Propagation, EuCAP 2013}
}

Downloads: 0