PREDICTION OF MEASURED POWER SPECTRAL DENSITY OF GSM 900 REVERSE LINK USING ARTIFICIAL NEURAL NETWORK

Frederick, O.E. and EZE, B.E (2020) PREDICTION OF MEASURED POWER SPECTRAL DENSITY OF GSM 900 REVERSE LINK USING ARTIFICIAL NEURAL NETWORK. International Research Journal of Modernization in Engineering Technology and Science, 2 (9). pp. 709-717. ISSN 2582-5208

Text journal 3.pdf Download (1MB)

Abstract

An efficient spectrum resource utilization demands continuous spectrum sensing, this however is costly. Spectrum prediction has been proposed as a solution to continuous spectrum sensing. By conception, spectrum prediction utilizes previous spectrum measurements to forecasts the future status of the channel. In this paper, Artificial Neural Network (ANN) is explored in the prediction of spectrum occupancy of 925 - 960 MHz link in a selected location in Ilorin, Nigeria. Different sample partitions were examined. The sample partition 70-15-15% of training, validation and testing gave the best Mean Square Error of 3.9090 for the predicted power spectral densities based on frequency points and MSE of 0.0025 for the predicted power spectral densities based on time instances.

Item Type:	Article
Uncontrolled Keywords:	ANN, artificial neural network, cognitive radio network, spectrum occupancy, spectrum prediction.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Engineering, Science and Mathematics > School of Engineering Sciences
Depositing User:	Joy Oluwabukola Olayiwola
Date Deposited:	04 Oct 2021 13:52
Last Modified:	04 Oct 2021 13:52
URI:	http://eprints.federalpolyilaro.edu.ng/id/eprint/1781

Actions (login required)

View Item