Skip to Main Content
This paper presents an efficient method for evaluating the carrier frequency error in Gaussian minimum shift-keying (GMSK) communication systems. This method operates in a nonintrusive way. It uses the learning vector quantization neural network-based demodulator for reconstructing the transmitted phases. From these and the expected phases, the carrier frequency error is estimated. The method is able to operate both in static and multipath propagation cases, and as the base-band signal is processed, it does not require a high-frequency sampling rate. In order to apply the method, two procedures, a procedure for static propagation and a procedure for multipath propagation, are set up. Tests performed on GMSK signals show that the method is attractive, fast, and more accurate if compared with other approaches.