Prediction of Received Signal Power in Mobile Communications Using Different Machine Learning Algorithms:A Comparative Study

Prediction of Received Signal Power in Mobile Communications Using Different Machine Learning Algorithms:A Comparative Study. Karra, D., Goudos, S., K., Tsoulos, G., V., & Athanasiadou, G. In 5th Panhellenic Conference on Electronics and Telecommunications, PACET 2019, 2019.
doi abstract bibtex

In this paper, we apply and compare various machine learning techniques to predict the received signal strength (RSS) in cellular communications. We generate the training set using experimental measurements from an unmanned aerial vehicle (UAV). We make a prediction model for the RSS using five base learners. We create a new ensemble method that averages the results from these five base learners. The proposed model outperforms all the original base learners. The obtained numerical results are compared with the original data from the test dataset using representative performance indicators and exhibit good precision.

@inproceedings{
 title = {Prediction of Received Signal Power in Mobile Communications Using Different Machine Learning Algorithms:A Comparative Study},
 type = {inproceedings},
 year = {2019},
 keywords = {UAV,cellular communications,ensemble learning,machine learning,voting regressor},
 id = {7ef523a6-cbcc-3e09-88ec-6b94d94f1756},
 created = {2020-02-29T16:57:43.173Z},
 file_attached = {false},
 profile_id = {c69aa657-d754-373c-91b7-64154b7d5d91},
 last_modified = {2023-02-11T18:54:04.386Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Karra2019},
 private_publication = {false},
 abstract = {In this paper, we apply and compare various machine learning techniques to predict the received signal strength (RSS) in cellular communications. We generate the training set using experimental measurements from an unmanned aerial vehicle (UAV). We make a prediction model for the RSS using five base learners. We create a new ensemble method that averages the results from these five base learners. The proposed model outperforms all the original base learners. The obtained numerical results are compared with the original data from the test dataset using representative performance indicators and exhibit good precision.},
 bibtype = {inproceedings},
 author = {Karra, Despoina and Goudos, Sotirios K. and Tsoulos, George V. and Athanasiadou, Georgia},
 doi = {10.1109/PACET48583.2019.8956271},
 booktitle = {5th Panhellenic Conference on Electronics and Telecommunications, PACET 2019}
}

Downloads: 0