Automatic Digital Modulation Recognition in the Presence of Phase Offset

Abstract

Automatic Digital Modulation Recognition (ADMR) is a critical component in modern communication systems, enabling efficient and flexible data transmission. This paper investigates the challenges associated with ADMR in scenarios where the received signal has a phase offset. A set of features, extracted from the instantaneous amplitude and phase of the signal, is proposed for the implementation of ADMR algorithms. An artificial neural network (ANN) based recognition system is developed in the LabVIEW programming environment to classify four types of digital modulation: BPSK, QPSK, 16-QAM and 64-QAM. The simulation results indicate that the developedclassifier can effectively operate in the presence of additive whiteGaussian noise (AWGN) and a phase offset in the signal. Theimplemented ADMR algorithm achieves a recognition probabilityof approximately 97-99% in the signal-to-noise ratio (SNR) rangeof 7-30 dB for each phase offset value. The proposed ADMRalgorithms achieve high recognition accuracy using fewercomputational resources then other existing works.

Keywords

• automatic digital modulation recognition
• feature extraction
• phase offset
• neural network