International Symposium on Telecommunication (IST)

Home / 11th International Symposium on Telecommunication (IST'2024)

Automatic Modulation Detection in Non-orthogonal Multiple Access Systems

Authors :

Fatemeh Shabanali¹ Mehrdad Ardebilipour²

1- School of Electrical and Computer Engineering, K.N. Toosi University of Technology Tehran, Iran 2- Associate Professor at School of Electrical and Computer Engineering, K.N. Toosi University of Technology Tehran, Iran

Keywords :

Non-Orthogonal Multiple Access،Automatic Modulation Recognition،Deep Learning

Abstract :

Increasing demand and spectrum limitations are ongoing challenges in telecommunications that constantly engage researchers in this field. Recently, various wireless systems have been developed, including Non-Orthogonal Multiple Access (NOMA), which is proposed for 5G and 6G networks. NOMA improves capacity while maintaining spectral resources by allowing the transmitter to send predefined user symbols with user-specific power over the same resources. The conventional receiver for NOMA, Serial Interference Cancellation (SIC),that requires knowledge of their modulation types to separates user signals. To improve spectral efficiency and reduce signaling overhead issues, an Automatic Modulation Recognition (AMR) algorithm has been proposed. This algorithm identifies modulation in the receiver so that transmitter don’t need to send information about the modulation type. The thesis introduces a new AMR algorithm for a two-user NOMA system using feature extraction and deep learning, offering high detection rates with manageable computational complexity. It demonstrates better performance than previous methods, achieving a 93% detection rate at a 5 dB signal-to-noise ratio, compared to 78.36% in other studies.