TY - JOUR N2 - 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. L1 - http://www.czasopisma.pan.pl/Content/115193/PDF/29_2020.pdf L2 - http://www.czasopisma.pan.pl/Content/115193 PY - 2020 IS - No 1 EP - 223 DO - 10.24425/ijet.2020.131866 KW - spectrum sensing KW - cognitive radio KW - machine learning KW - energy detection KW - 4G KW - LTE KW - 5G KW - k-nearest neighbors KW - random forest A1 - Wasilewska, MaƂgorzata A1 - Bogucka, Hanna PB - Polish Academy of Sciences Committee of Electronics and Telecommunications VL - vol. 66 DA - 2020.02.20 T1 - Space-Time-Frequency Machine Learning for Improved 4G/5G Energy Detection SP - 217 UR - http://www.czasopisma.pan.pl/dlibra/publication/edition/115193 T2 - International Journal of Electronics and Telecommunications ER -