Specific Attenuation Estimation in Perturbed Radio Wave Propagation Using Artificial Neural Networks

Path loss modeling is a crucial consideration in radio engineering for wireless networks. Over the years, diverse techniques have been implemented attempts to accurately predict path across given terrain. In this study, predictors created on bases of artificial neural networks (ANN) were used estimate rural section Nigerian middle-belt grassland. The ANN structures considered Generalized Regression Neural network (GRNN) and Radial Basis Function Network (RBFNN), which exhibit few differences similarities. These based trained, validated tested prediction using values computed from received power measured at 900MHz six Base Transceiver Stations (BTSs) situated along Findings show that RBFNN predictor with Root Mean Squared Error (RMSE) 5.17dB GRNN 4.9dB are slightly more accurate than COST 231 Hata model 6.64dB, while Hata-Okumura 25.78dB simply not suitable terrain under investigation. Overall, GRNN, proffers 26.21% improvement over recommended question.