1. AI-Driven Signal Recognition in B5G FBMC-OQAM Industrial Cognitive Radio Networks via Transform Channel Convolution Strategy
- Author
-
An, Zeliang, Xu, Yuqing, Pedersen, Gert Frølund, and Shen, Ming
- Subjects
FBMC, Modulation recognition, cognitive communications, deep learning - Abstract
With the advent of the Industry 5.0 era, the Internet of Things (IoT) devices face unprecedented proliferation, requiring higher communications rates and lower transmission delay. Considering its high spectrum efficiency, the promising filter bank multicarrier (FBMC) technique using offset quadrature amplitude modulation (OQAM) has been applied to Beyond 5G (B5G) industry IoT networks. However, due to the broadcasting nature of wireless channels, the FBMC-OQAM industry IoT network is inevitably vulnerable to adversary attacks from malicious IoT nodes. To tackle this challenge, the FBMC-OQAM industry cognitive radio network (ICRNet) is proposed to ensure security at the physical layer. As a pivotal step of ICRNet, blind modulation recognition (BMR) can detect and recognize the modulation type of malicious signals. In this work, we propose a novel FBMC BMR algorithm (TCCNet) using the one-dimensional transform channel convolution strategy, rather than complicated two-dimensional convolution. Firstly, this is achieved by firstly designing a low-complexity binary constellation diagram (BCD) gridding matrix as the input to TCCNet. Then, we develop a transform channel convolution strategy to convert the image-like BCD matrix into a series-like data format, accelerating the BMR process while keeping discriminative features. Monte Carlo experimental results demonstrate that the proposed TCCNet obtain the performance gain of 8% and 40% than the traditional I/Q-based and constellation-based methods at an SNR of 12 dB, respectively. Moreover, our TCCNet can achieve around 29.682 and 2.356 times faster than existing CD-AlexNet and I/Q-CLDNN algorithms.
- Published
- 2023