Received signal strength computation for broadcast services using artificial neural network

Igwe, K. C.; Oyedum, O.D.; Ajewole, M. O.; Aibinu, Abiodun Musa

doi:10.1109/icecco.2017.8333322

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The neural network training is based on measurements of some weather variables: temperature, pressure, humidity and wind speed. This paper is a continuation and extension of an earlier version [ 15 ]. In this paper, we propose an increase of the number of hidden layer neurons to 20 and the number of normalisation types to 4.…”

Section: Introductionmentioning

confidence: 79%

See 1 more Smart Citation

Application of artificial neural network modeling techniques to signal strength computation

Igwe

Oyedum

Aibinu

et al. 2021

Heliyon

View full text Add to dashboard Cite

This paper presents development of artificial neural network (ANN) models to compute received signal strength (RSS) for four VHF (very high frequency) broadcast stations using measured atmospheric parameters. The network was trained using Levenberg-Marquardt back-propagation (LMBP) algorithm. Evaluation of different effects of activation functions at the hidden and output layers, variation of number of neurons in the hidden layer and the use of different types of data normalisation were systematically applied in the training process. The mean and variance of calculated MSE (mean square error) for ten different iterations were compared for each network. From the results, the ANN model performed reasonably well as computed signal strength values had a good fit with the measured values. The computed MSE were very low with values ranging between 0.0027 and 0.0043. The accuracy of the trained model was tested on different datasets and it yielded good results with MSE of 0.0069 for one dataset and 0.0040 for another dataset. The measured field strength was also compared with ANN and ITU-R P. 526 diffraction models and a strong correlation was found to exist between the measured field strength and ANN computed signals, but no correlation existed between the measured field strength and the predicted field strength from diffraction model. ANN has thus proved to be a useful tool in computing signal strength based on atmospheric parameters.

show abstract

Section: Introductionmentioning

confidence: 79%

“…In this case, the number of neurons was varied from 1 to 20, while the already established transfer functions were held constant. This was done to test the assertion of the authors in the previous work [ 15 ] where the number of neurons was only varied from 1 to 10. The effect of number of neurons on the neural network is shown in Figure 6 .…”

Section: Resultsmentioning

confidence: 99%

Application of artificial neural network modeling techniques to signal strength computation

Igwe

Oyedum

Aibinu

et al. 2021

Heliyon

View full text Add to dashboard Cite

show abstract

Prediction of environmental effects in received signal strength in FM/TV station based on meteorological parameters using artificial neural network and data mining

Mirbagheri¹,

Mohammadi²

2019

Journal of Environmental Management

View full text Add to dashboard Cite

Computation of VHF Signal Strength for Point to Area Network using Machine Learning Modeling Techniques

Igwe,

Nurudeen Olawale Adeyemi,

Lukman Folorunso Onadiran

2023

Malaysian J. Sci. Adv. Tech.

View full text Add to dashboard Cite

In this paper, computation of very high frequency (VHF) signal strength for point to area network was carried out using machine learning modeling techniques. Seven different machine learning models were adopted: Decision Tree, Random Forest, AdaBoost, k-Nearest Neighbor, Support Vector Machine, Artificial Neural Network and Linear Regression. A total of 120 data points was used in computing the signal strength. 72 data points (60%) was used to train the model, while the remaining 48 data points (40%) were used as test data to determine the accuracy of the computation for all the models. From the results, it was observed that the accuracy of the computations was greatly influenced by the amount of training data that was used. Also, from the results, in highest order of accuracy, AdaBoost was adjudged the best model. This was followed by the Artificial Neural Network model. Generally, the error margin of computation obtained for these two models were low, hence indicating that the models can be effectively relied on for computation of signal strength in the study area.

show abstract

Received signal strength computation for broadcast services using artificial neural network

Cited by 3 publications

References 8 publications

Application of artificial neural network modeling techniques to signal strength computation

Application of artificial neural network modeling techniques to signal strength computation

Prediction of environmental effects in received signal strength in FM/TV station based on meteorological parameters using artificial neural network and data mining

Computation of VHF Signal Strength for Point to Area Network using Machine Learning Modeling Techniques

Contact Info

Product

Resources

About