This dissertation presents several novel deep-learning (DL)-based approaches for classifying digitally modulated signals, one method of which involves the use of capsule networks (CAPs) together with cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in this dissertation outperformed alternative approaches for classifying digitally modulated signals that included conventional classifiers that employed CSP-based techniques, as well as alternative DL-based classifiers that used various conventional neural networks (NNs) with in-phase/quadrature (I/Q) data used for training and classification.
Another method of digital modulation classification presented in this dissertation showcases two novel DL-based classifiers that each use a CAP with custom-designed feature extraction layers. The classifiers take I/Q data as input, and the feature extraction layers are inspired by CSP techniques, which extract the CC features employed by conventional CSP-based approaches to blind modulation classification and signal identification. Specifically, the feature extraction layers implement a proxy of the mathematical functions used in the calculation of the CC features and include a squaring layer, a raise-to-the-power-of-three layer, and a fast-Fourier-transform (FFT) layer, along with additional normalization and warping layers to ensure that the relative signal powers are retained and to prevent the trainable NN layers from diverging in the training process.
DeepAoANet: Learning Angle of Arrival from Software Defined Radios with Deep Neural Networks
University of Oxford（牛津大学）
基于RF信号的测向和定位系统受到多径传播的显著影响，特别是在室内环境中。现有的算法（例如MUSIC）在多径存在下或在弱信号状态下操作时在分辨到达角（AoA）方面表现不佳。我们注意到，数字采样RF前端允许轻松分析信号及其延迟分量。低成本的软件定义无线电（SDR）模块能够在宽频谱范围内提取信道状态信息（CSI），从而推动了增强型到达角（AoA）解决方案的设计。我们提出了一种深度学习方法，从SDR多通道数据的单个快照中获得AoA。我们比较和对比基于深度学习的角度分类和回归模型，以准确估计多达两个AoA。我们已经在不同的平台上实现了推理引擎，以实时提取AoA，证明了我们的方法的计算易处理性。为了证明我们的方法的实用性，我们已经从四元件通用线性阵列（Universal Linear Array，简称UART）中收集了各种视距（LOS）和非视距（NLOS）环境中的IQ（同相和正交分量）样本，并发布了数据集。我们所提出的方法在确定碰撞信号的数量方面表现出良好的可靠性，并且实现了小于$2^{\circ}$的平均绝对AoA误差。
Signal Demodulation with Machine Learning Methods for Physical Layer Visible Light Communications: Prototype Platform, Open Dataset and Algorithms
School of Information and Control Engineering, China University of Mining and Technology（中国矿业大学信息与控制工程学院）；State Key Laboratory of Integrated Services Networks, Xidian University（西安电子科技大学综合业务网理论与关键技术国家重点实验室）；Department of Electrical and Computer Engineering, University of Minnesota（明尼苏达大学电气与计算机工程系）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Department of Electrical and Computer Engineering, University of California, Davis（加利福尼亚大学戴维斯分校电气与计算机工程系）；China University of Mining and Technology（中国矿业大学）；Xidian University（西安电子科技大学）；University of Minnesota（明尼苏达大学）；University of California, Davis（加利福尼亚大学戴维斯分校）
