Modulation Classification Based on Eye Diagrams and Deep Learning
Alhussain Almarhabi, Hatim Alhazmi, Abdullah Samarkandi, Yudong Yao · 2022
New emerging technologies such as the Internet of Things (IoT) and fifth generation wireless communication New Radio (5G NR) are introducing challenges in spectrum and systems' complexity. Radio spectrum awareness is overcoming many challenges through tasks related to signal detection and channel identification that improves overall the system's reliability, efficiency, and security. The eye diagram is one of the signal representations useful in many applications for simulation and debugging of the system. The eye diagram shows vital parameters such as timing jitter and inter-symbol interference. The eye diagram contains essential features that could be used for spectrum awareness tasks. This paper uses deep learning with an eye diagram to study and identify modulated signals in narrowband fading channels, e.g., Rayleigh and Rician fading. Our results show that deep learning neural networks can classify modulated signals with the impact of the fading channel using an eye diagram.