Artificial Neural Network Optimal Modeling and Optimization of UAV Measurements for Mobile Communications Using the L-SHADE Algorithm

Artificial Neural Network Optimal Modeling and Optimization of UAV Measurements for Mobile Communications Using the L-SHADE Algorithm. Goudos, S., K., Tsoulos, G., V., Athanasiadou, G., Batistatos, M., C., Zarbouti, D., & Psannis, K., E. IEEE Transactions on Antennas and Propagation, 67(6):4022-4031, 2019.
doi abstract bibtex

Channel modeling of wireless communications from unmanned aerial vehicles (UAVs) is an emerging research challenge. In this paper, we propose a solution to this issue by applying a new framework for the prediction of received signal strength (RSS) in mobile communications based on artificial neural networks (ANNs). The experimental data measurements are taken with a UAV at different altitudes. We apply several evolutionary algorithms (EAs) in conjunction with the Levenberg-Marquardt (LM) backpropagation algorithm in order to train different ANNs and in particular the L-SHADE algorithm, which self-adapts control parameters and dynamically adjusts population size. Five new hybrid training methods are designed by combining LM with self-adaptive differential evolution (DE) strategies. These new training methods obtain better performance to ANN weight optimization than the original LM method. The received results are compared with the real values using representative ANN performance indices and exhibit satisfactory accuracy.

@article{
 title = {Artificial Neural Network Optimal Modeling and Optimization of UAV Measurements for Mobile Communications Using the L-SHADE Algorithm},
 type = {article},
 year = {2019},
 keywords = {Artificial neural network (ANN),cellular communications,differential evolution (DE),optimization methods,unmanned aerial vehicle (UAV)},
 pages = {4022-4031},
 volume = {67},
 id = {87a504a8-eeac-3ac2-ab15-5c1687465e6d},
 created = {2020-02-29T16:57:44.914Z},
 file_attached = {false},
 profile_id = {c69aa657-d754-373c-91b7-64154b7d5d91},
 last_modified = {2023-02-11T18:54:04.401Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Goudos2019a},
 private_publication = {false},
 abstract = {Channel modeling of wireless communications from unmanned aerial vehicles (UAVs) is an emerging research challenge. In this paper, we propose a solution to this issue by applying a new framework for the prediction of received signal strength (RSS) in mobile communications based on artificial neural networks (ANNs). The experimental data measurements are taken with a UAV at different altitudes. We apply several evolutionary algorithms (EAs) in conjunction with the Levenberg-Marquardt (LM) backpropagation algorithm in order to train different ANNs and in particular the L-SHADE algorithm, which self-adapts control parameters and dynamically adjusts population size. Five new hybrid training methods are designed by combining LM with self-adaptive differential evolution (DE) strategies. These new training methods obtain better performance to ANN weight optimization than the original LM method. The received results are compared with the real values using representative ANN performance indices and exhibit satisfactory accuracy.},
 bibtype = {article},
 author = {Goudos, Sotirios K. and Tsoulos, George V. and Athanasiadou, Georgia and Batistatos, Michael C. and Zarbouti, Dimitra and Psannis, Kostas E.},
 doi = {10.1109/TAP.2019.2905665},
 journal = {IEEE Transactions on Antennas and Propagation},
 number = {6}
}

Downloads: 0