Blind Recognition of Channel Coding Based on CNN-BLSTM
Shuying Zhang, Lin Zhou, Yiduo Tang, Lin Wang, Qiwang Chen · 2021 IEEE International Conference on Networking, Sensing and Control (ICNSC) · 2021
In cognitive radio or military communication systems, the channel coding type recognition of the primary user signal is an important task to realize full awareness of the wireless communication environment. Previous methods to solve this problem usually have high computational complexity, which are not suitable for real-time applications and require rich experience and professional knowledge in manual feature extraction. In this paper, a blind channel coding recognition algorithm based on CNN-BLSTM is proposed. Firstly, this method uses convolutional neural network to extract the data features of coding sequence and also avoids the problem of low recognition accuracy caused by inputting the original codeword data with inconspicuous features directly into neural network. Then, the context dependence of features is obtained through bidirectional long short-term memory network. Finally, the classification task is accomplished by softmax function. The experiments use spatially coupled LDPC codes and 5G NR LDPC codes as candidate codes. The experimental results show that the algorithm achieves quite high recognition accuracy under good channel conditions.