Vol.:(0123456789) Wireless Personal Communications https://doi.org/10.1007/s11277-020-07550-5 1 3 Wavelet Generalized Regression Neural Network Approach for Robust Field Strength Prediction Joseph Isabona 1 © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract Accurate predictive feld strength and coverage modelling during and after cellular network planning process is one key factor that contribute to a successful and robust wireless com- munication network performance. Accurate feld strength coverage prediction will provide realistic idea about the level of feld strength and link quality in the entire coverage service areas. It will also assist in close-ftting fringe areas that are likely to be imparted nega- tively by interference, and cell edge/contour areas with poor signal coverage. Therefore, opting for a suitable predictive feld strength system model that will enable superb cel- lular network planning environment will be of a great succor to the radio network plan- ner and stakeholders, including the network end users as well. This work presents spatial electric feld strength prediction engaging hybrid wavelet-neural modelling approach. The proposed is called Wavelet-GRNN. To accomplish this task, the spatial feld strength data is frst routed through a wavelet-based decomposition process employing three decomposi- tion levels. The decomposed feld strength constituents are then utilised as input data to GRNN neural network model where relevant extracted information is captured and trained for robust predictive learning. In the third phase of the model, the outputs from the GRNN predictor are combined with wavelet coefcients to form the fnal predicted output. The degree of prediction accuracy using the Wavelet-GRNN model over other prediction tech- niques are also statistically quantifed and provided using six diferent frst order statistics. Keywords Field strength · Coverage distance · Accurate predictive modelling · Wavelet · Neural network · Wavelet-neural modelling 1 Introduction One fundamental aim of radio frequency (RF) coverage planning is to resourcefully utilize the allotted frequency band. As a result, RF coverage planning and prediction tools are of immense signifcance, as they assist radio network planers and designers to examine diferent system network confgurations before and after deployment. However, the precision attained * Joseph Isabona josabone@yahoo.com 1 Department of Physics, Federal University Lokoja, BPMB 1154, Lokoja, Kogi State, Nigeria