【摘要】 通信链路层特征盲识别是智能通信和通信对抗领域关键技术。为提高基于IEEE 802.11协议的无线(局域)网/无线保真(wireless fidelity, Wi-Fi)信号的编码参数盲识别精度,提出了一种基于深度学习的低密度奇偶校验码(low density parity check code, LDPC)编码参数盲识别算法,可准确盲识别信道编码算法的信息位码长和码率。算法以解调后的比特流为训练数据集,搭建多层深度神经网络模型,经过多次调参和迁移训练,最终得到了能够准确预测编码参数的网络模型。实验结果表明,该网络模型能够在高达10%误码条件下得到优于91%的编码参数盲预测率,在无误码的条件下,编码参数盲预测准确度高达95.32%,为智能通信和通信对抗的研究提供了一定参考价值。更多还原

【Abstract】 Blind identification of communication link layer features is a key technology in the field of intelligent communication and communication countermeasures. In order to improve the blind identification accuracy of coding parameters of wireless fidelity(Wi-Fi) signal based on IEEE 802.11 protocol, a blind identification algorithm of low density parity check code(LDPC) coding parameters based on deep learning was proposed, which can accurately identify the length of information bit and code rate of channel coding algorithm. Taking the demodulated bit stream as the training dataset, a multi-layer deep neural network model was built, and a network model that can accurately predict the coding parameters after multiple parameter tuning and migration training was finally obtained. The experimental results show that the network model can get better than 91% coding parameter blind prediction rate under the condition of up to 10% error code, and the coding parameter blind prediction accuracy is up to 95.32% under the condition of no error code, which provides a certain reference value for the research of intelligent communication and communication countermeasures.更多还原