Classification of Single- and Multi-carrier Signals Using CNN Based Deep Learning

An, Sungbae; Jang, Mingyu; Yoon, Dongweon

doi:10.1109/IC-NIDC54101.2021.9660515

상세 보기

Classification of Single- and Multi-carrier Signals Using CNN Based Deep Learning

An, Sungbae;
Jang, Mingyu;
Yoon, Dongweon

Citations

SCOPUS

3

초록

In a non-cooperative context, to recover data from the received signal, the receiver must estimate the communication parameters used in the transmitter. In this paper, we propose an algorithm for classifying single-carrier and multi-carrier signals by using convolutional neural network based deep learning and analyze classification performance. Simulation results show that the proposed algorithm outperforms the conventional methods in an additive white Gaussian noise channel and Rician fading channel. © 2021 IEEE.

키워드

classification; convolutional neural network; deep learning; orthogonal frequency division multiplexing; single-carrier; Convolutional neural networks; Cooperative communication; Decoding; Deep learning; Fading channels; Gaussian noise (electronic); Orthogonal frequency division multiplexing; Signal receivers; Turbo codes; White noise; Classification performance; Communication parameters; Convolutional neural network; Deep learning; Multicarrier signal; Network-based; Non-cooperative; Orthogonal frequency-division multiplexing; Received signals; Single carrier; Convolution

제목: Classification of Single- and Multi-carrier Signals Using CNN Based Deep Learning

저자: An, Sungbae; Jang, Mingyu; Yoon, Dongweon

DOI: 10.1109/IC-NIDC54101.2021.9660515

발행일: 2022-01

유형: Conference Paper

저널명: Proceedings of 2021 7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021

페이지: 196 ~ 199