Estimating the pathloss and signal strength of the transmitted signal at specific distances is one of the main objectives of network designers. This paper aims to provide generalized pathloss models appropriate for urban areas in Muscat the capital city of the Sultanate of Oman environment. The research includes studying different models of pathloss for the 4G cellular network at Muttrah Business District (MBD) at Muscat. Different models (Free Space model, Okumura Hata, Extended Sakagami, Cost231 Hata, ECC-33 Hata – Okumura extended, Ericsson, Egli, and SUI) are used with 800MHz. The results of the prediction models are compared with real measured data by calculating RMSE. The generalized models are created by modified original models to get accepted RMSE values. Different cells at MBD are tested by modified models. The RMSE values are then calculated for verification purposes. To validate the modified pathloss models of 4G, they are also applied at different cells in a different city in the capital. It has approximately the same environment as MBD. The modified pathloss models provided accepted predictions in new locations.

In this paper, the future Fifth Generation (5G New Radio) radio communication system has been considered, coexisting and sharing the spectrum with the incumbent Fourth Generation (4G) Long-Term Evolution (LTE) system. The 4G signal presence is detected in order to allow for opportunistic and dynamic spectrum access of 5G users. This detection is based on known sensing methods, such as energy detection, however, it uses machine learning in the domains of space, time and frequency for sensing quality improvement. Simulation results for the considered methods: k-Nearest Neighbors and Random Forest show that these methods significantly improves the detection probability.