Feature Image-Based Automatic Modulation Classification Method Using CNN Algorithm

In this paper, we propose a feature image-based automatic modulation classification (AMC) method to classify modulation type. The proposed method uses a convolutional neural network (CNN) which is one of deep learning algorithms for image classification. In order to classify the modulation type, var...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) S. 1 - 4
Hauptverfasser:	Lee, Jung Ho, Kim, Kwang-Yul, Shin, Yoan
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.02.2019
Schlagworte:	automatic modulation classification Classification algorithms convolutional neural network Convolutional neural networks cumulant Deep learning Feature extraction Modulation Signal to noise ratio
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	In this paper, we propose a feature image-based automatic modulation classification (AMC) method to classify modulation type. The proposed method uses a convolutional neural network (CNN) which is one of deep learning algorithms for image classification. In order to classify the modulation type, various features are transformed in a two-dimensional image and this image is used as the input of the CNN. From the simulation results, we show that the proposed method improves classification performance.
DOI:	10.1109/ICAIIC.2019.8669002