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

In this paper, meteorological parameters, electric field strength and transmitters' output power measured during six months in a TV/FM station. There are 13 frequencies in FM and UHF frequency bands in pilot broadcast station. The analysis of results were carried out using data mining techniques. In addition, a prediction model on the basis of a Neural Network is identified. The electric field is affected by distance between the antenna and the receiver point, transmitters' output power and meteorological constituents of air pressure, temperature and humidity. The meteorological parameters and transmitters' power are used as inputs and the electric field is used as the output. After data acquisition, preprocessing is performed and the Neural Network of a multilayer perceptron model is applied. In addition, Multi Linear Regression is performed. In evaluation, the performance of the proposed techniques is based on the root mean square error (RMSE) property. The least MSE obtained for the proposed model based on Neural Network amounted to 0.198 while the least MSE of Regression was 0.280. The results showed that for a given input of the atmospheric parameters as well as the transmitter power, the intensity of electric field can be predicted as well as the determining the relationship between the atmospheric parameters, transmitters' power and electric field strength. The statistical and correlation analysis used to assess the relation between each parameter and signal strength concluded that the temperature and wind direction have an inverted linear relationship with the signal level while the others have a direct linear relationship.