Modulation Classification Based on Signal Constellation Diagrams and Deep Learning

By Shengliang Peng, Hanyu Jiang, Huaxia Wang, H. Alwageed, Yu Zhou, Marjan Mazrouei Sebdani, Yu-dong Yao. IEEE Transactions on Neural Networks and Learning Systems, 2019

467 citations recorded by the source corpus.

Deep learning (DL) is a new machine learning (ML) methodology that has found successful implementations in many application domains. However, its usage in communications systems has not been well explored. This paper investigates the use of the DL in modulation classification, which is a major task in many communications systems. The DL relies on a massive amount of data and, for research and applications, this can be easily available in communications systems. Furthermore, unlike the ML, the DL has the advantage of not requiring manual feature selections, which significantly reduces the task complexity in modulation classification. In this paper, we use two convolutional neural network (CNN)-based DL models, AlexNet and GoogLeNet. Specifically, we develop several methods to represent modulated signals in data formats with gridlike topologies for the CNN. The impacts of representation on classification performance are also analyzed. In addition, comparisons with traditional cumulant and ML-based algorithms are presented. Experimental results demonstrate the significant performance advantage and application feasibility of the DL-based approach for modulation classification.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/4876f8df26b3eb92b8169c3811fb772d8c8f6fd2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Weihua Zhuang
2. Zheng Dou
3. Yun Lin
4. Shiwen Mao
5. Xuemin Shen
6. Jie Gao
7. Wen Wu
8. Conghao Zhou

Citations in the corpus

• Holistic Network Virtualization and Pervasive Network Intelligence for 6G (2023, methodology): “utilize convolutional and pooling layers to identify the correlation of multi-dimensional input data and have been applied in modulation classification [112]; recurrent neural networks”
• Contour Stella Image and Deep Learning for Signal Recognition in the Physical Layer (2020, methodology): “SVM-7 [12] uses three fourth-order cumulants, i.e., C40, C41, and C42, and four sixth-order cumulants, i.e., C60, C61, C62, and C63.”