Prediction of Signal Power Loss (at Micro-Cell Environments) Using Generalized Adaptive Regression and Radial Basis Function ANN Models Built on Filter for Error Correction

Abstract

The Prediction of an accurate field signal power is of utmost importance in the design and placement of base station transmitters. This research work has designed and utilized two adaptive neural network models named Generalized Adaptive Regression (GR)-ANN and Radial Basis Function (RBF)-ANN made on vector Non-Linear Median Filter (NLMF) and it has compared their prediction performances with conventional GR-ANN and RBF-ANN. The prediction accuracy of the neural network models has been tested and evaluated using measurement experimental field strength data acquired from the LTE radio network from the line-of-sight (LOS) urban environment named location-1 Non-Line-of-Sight (NLOS) rural environment named location-2. Prediction error, average spread prediction error, and mean squared error have been used for analyzing the performance abilities of the models in the prediction of the measurement data during neural network training. Their performance accuracies have been compared. The GR-ANN and RBF-ANN's superior performances built on vector NLMF over the conventional GR-ANN, and RBF-ANN can be attributed to the high-quality datasets generated through filtering using NLMF. This improves the adaptive models' capability to learn, adaptively respond, and predict the reference propagation loss data's fluctuating pattern during neural network training. A further comparison shows GR-ANN's superiority in performance accuracy built on vector NLMF over RBF-ANN built on vector NLMF. This shows that GR-ANN's capability of solving any function approximation problem is better than RBF-ANN. However, RBF-ANN requires less training time.