ID 原文 译文
40386 该方法首先通过分析矩阵的构造、数据压缩和矩阵扩展3个步骤将数字序列转化为图像； Firstly, the digital sequence is transformed into an image by following three steps including matrix construction, data compression and matrix expansion.
40387 然后用已有的样本训练卷积神经网络，用训练好的卷积神经网络识别未知协议的帧长； Then, the convolutional neural network is trained with the existing samples and the trained convolutional neural network is employed to identify the frame length of the unknown protocol.
40388 最后在帧长识别的基础上，通过相关滤波方法完成帧起始位置的识别，实现对物理帧的切割。 Finally, on the basis of frame length recognition, the initial position of the frame is identified using correlation filtering method.Therefore, each frame can be extracted from the bit stream.
40389 仿真实验验证了算法的有效性，表明本文方法具有一定的工程应用价值。 The proposed method, which has higher accurate recognition than existing algorithms suggested by simulation results, has significant potential in engineering application.
40390 利用神经网络进行辐射源个体识别时，训练样本的单一性会导致深度网络出现过拟合的现象，继而影响辐射源个体识别的精确性。 With the singleness of the training sample, the phenomenon of overfitting occurs in the deep neural network when used for specific emitter identification(SEI), which in turn affects the accuracy.
40391 针对该问题，本文提出一种基于PID算法的深度卷积网络结构， In this paper, a deep convolutional neural network(CNN)structure based on PID algorithm is proposed to alleviate the problem.
40392 该结构通过在传统卷积神经网络的输出层与输入层间构建一条反馈回路，采用PID算法将网络输出错误率转化为划分训练集数据构成的概率，通过优化训练集数据构成，达到抑制过拟合的目的。 The structure builds a feedback loop between the output layer and the input layer of the traditional CNN, transforms the error rate of output layer into the probability of dividing the training set data by using PID algorithm, and inhibits the overfitting by optimizing the composition of training set data.
40393 将该方法应用于超短波电台识别，平均识别率达到92.59%， The average recognition rate of the network reaches 92.59% when the method is applied to the recognition of ultrashort wave radio.
40394 识别率方差约为传统算法的1/3，训练用时减少约35 min，上述指标均优于传统神经网络。 The variance of the recognition rate is about 1/3 of that of the traditional algorithm, and the training time is reduced by about 35 min, obviously the performance of this method is better than that of the traditional neural network.
40395 实验结果表明，该算法增强了深度网络的鲁棒性，有效地抑制了过拟合现象。 Experimental results show that the algorithm can enhance the robustness of the deep network and effectively suppress the overfitting phenomenon.