本文为美国普渡大学（作者：Xiaoyu Liu）的硕士论文，共62页。

本文研究了深度学习在无线信号调制识别中的应用价值。最近，在AMC的深度学习研究中，引入了一种框架，通过使用GNU无线电产生一个数据集来模拟真实无线信道中的缺陷，其中采用10种不同的调制类型。此外，CNN的体系结构已经被开发出来，展示出超越基于专家的方法的性能。在这里，我们遵循O'shea的框架，并发现深度神经网络架构能够提供比最新技术更高的准确性。我们测试了O'shea架构，发现它能够准确识别不同的调制类型，准确率约为75%。我们首先调整CNN架构，找到一种具有四个卷积层和两个密集层的设计，在高信噪比下，分类精度约为83.8%。然后，我们基于最近引入的剩余网络（ResNet）和密集连接网络（DenseNet）的思想开发架构，以分别达到高信噪比下大约83%和86.6%的精度。我们还引入了CLDNN，在高信噪比下达到约88.5%的精度。为了提高QAM的分类精度，我们将QAM16和QAM64的高阶累积量作为专家特征进行了计算，总精度提高到90%左右。最后，通过对输入进行预处理并将其输入到LSTM模型中，我们将分类成功率提高到100%，但WBFM（46%）除外。本论文的平均调制分类精度提高了约22%。

This thesis investigates the value of employing deep learning for the task of wireless signal modulation recognition. Recently in deep learning research on AMC, a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a CNN architecture was developed and shown to deliver performance that exceeds that of expert-based approaches. Here, we follow the framework of O'shea [1] and find deep neural network architectures that deliver higher accuracy than the state of the art. We tested the architecture of O'shea [1] and found it to achieve an accuracy of approximately 75% of correctly recognizing the modulation type. We first tune the CNN architecture and find a design with four convolutional layers and two dense layers that gives an accuracy of approximately 83.8% at high SNR. We then develop architectures based on the recently introduced ideas of Residual Networks (ResNet) and Densely Connected Network (DenseNet) to achieve high SNR accuracies of approximately 83% and 86.6%, respectively. We also introduce a CLDNN to achieve an accuracy of approximately 88.5% at high SNR. To improve the classification accuracy of QAM, we calculate the high order cumulants of QAM16 and QAM64 as the expert feature and improve the total accuracy to approximately 90%. Finally, by preprocessing the input and send them into a LSTM model, we improve all classification success rates to 100% except the WBFM which is 46%. The average modulation classification accuracy got a improvement of roughly 22% in this thesis.

1 引言

1.1 研究动机

1.2 项目背景

2 实验设置

2.1 产生数据集

2.2 硬件

3 神经网络架构

3.1 CNN

3.2 ResNet

3.3 DenseNet

3.4 CLDNN

3.5 基于累积量的特征

3.6 LSTM

4 结论与未来研究展望 

下载英文原文地址：

http://page2.dfpan.com/fs/flecaj8282a1a219160/ 

更多精彩文章请关注微信号：