Smart mobile application for the prediction of the loss of signal in telecommunication networks basing on meteorological variables

Abstract

The objective of the research project was developing a mobile app to allow the signal loss prediction. The prediction is based on meteorological characteristic, because it is looking to support the decision-making by the telecommunication specialists. A data Pre-processing realized by the outlier’s deletion and variables correlations resulted in a new Dataset. Different data mining classification techniques were analyzed using an optimization approach. The result of this analysis allows to determinate that, the algorithm based on Artificial Neural Networks was the one who has the better accuracy index. It was almost the 100% of accuracy. The project Aim to take advantage of an obtained model, it was represented in the Predictive Model Markup Language (PMML) and processed with JAVA technologies in a mobile app development. The app name is SignalPred; this app predicts signal loss through the signal reading of meteorological variables.