Communication system recognition by modulation recognition

Abstract

Communication system recognition is major part of some civilian and military applications. The recognition of the system is done by inspecting the received signal properties like modulation type, carrier frequency, baud rate and so on. Therefore we need Automatic Modulation Recognition (AMR) methods plus carrier and baud rate estimation methods. In this paper we introduce a new AMR method based on time-domain and spectral features of the received signal. We have used neural network as the classifier. Some analog and digital modulations including AM, LSSB, USSB, FM, ASK2, ASK4, ASK8, PSK2, PSK4, PSK8, FSK2, FSK4, FSK8 and MSK are considered. Then using information from the received signal like baud rate, carrier frequency and modulating scheme the protocol used for signal transmission is detected. © Springer-Verlag 2004.