基于轻量化深度学习网络的调制信号识别模型

电磁态势分析是信息化战争中至关重要的工作,如何利用深度学习技术有效实现调制信号识别是其中一项关键技术。首先将调制信号转化为带有颜色信息的星座图形式,并用深度学习方法,选用VGG16和AlexNet两个卷积神经网络完成调制识别任务。结果显示,当信噪比大于等于0 dB时,可以达到99%以上的识别准确率。由于军用设备对于计算性能和存储性能把控较为严格,因此采用全零矩阵平均百分比的方法对深度学习模型进行压缩。结果显示,在不损失识别准确率的前提下,信噪比为0 dB时,对于模型参数量,AlexNet可以压缩3 466倍,VGG16可以压缩20 156倍;对于浮点运算量,AlexNet可以压缩2 314倍,VGG16可以压缩13 475倍。表明本研究方法对调制信号识别具可行性以及高效性。     

基于?2 -范式的特征抽取框架研究

针对由时频分析引起的失真而导致的特征自动抽取质量低的问题,文中将一个自动抽取微多普勒特征过程转化为 一个?2 -范式凸优化问题, 并通过搭建迭代的卷积神经网络框架近似求解。文中仿真运用四种运动捕捉数据库的测量数据,通过仿真模型模拟了雷达视线方向5 m 处的目标的雷达回波。仿真与实验样本所提取的特征用支持向量机分类。仿真和实验的分类性能表明,该框架抽取的特征的分类性能明显优于时频图像主成分分析所自动抽取特征的分类性能。     

A software‐defined radio testbed for deep learning‐based automatic modulation classification

Automatic modulation classification (AMC) is the demodulation process on the receiver side, which is a crucial protocol for current and next‐generation intelligent communication systems. This method becomes complicated, in the presence of channel noise, to identify the modulation of the transmitted signal, that is, the transmitter and receiver with its ambiguous parameters like timing information, signal strength, phase offset, and carrier frequency. Two fundamental approaches are used for the AMC, namely, the signal statistical feature‐based approach and the maximum likelihood approach. Current Feature‐Based AMC approaches typically built for a limited set of modulation; a comprehensive AMC approach utilizing convolutional neural networks (CNN) is suggested in this article to overcome this obstacle. Altogether, 11 different types of modulations considered. In this method, without an extraction function, the transmitted signal can be identified directly. Also, the features of the received signal are known directly by using this method. The classification accuracy using CNN seems to be remarkable, especially for low SNRs. In this article, a realistic AMC framework that can be quickly applied to provide reliable efficiency in numerous commercial real‐time scenarios has developed and tested. Therefore, to prove the functional viability of our proposed model, it was applied to the software‐defined radio test‐bed.     

一种基于星座图恢复的多进制相位调制信号识别算法

在实际调制过程中,无线电波传输多径及衰落引起的符号间干扰和信号接收端的载波频偏会造成星座图难以识别。针对这一问题,提出了一种基于星座图恢复和卷积神经网络的多进制相位调制信号识别算法。首先,设定相邻采样点距离和相位角的阈值以筛除发生符号间干扰时的采样点,保留剩余的有效采样点并形成聚类组;然后,通过旋转相邻聚类组抵消载波频偏带来的影响,实现星座图的恢复;最后,利用卷积神经网络对星座图进行特征自动提取和调制识别。实验结果表明,对于实测信号,所提算法能够较好地恢复星座图并实现BPSK、QPSK和8PSK的准确识别。最终的识别准确率达到了99.9%,较星座图恢复前提高了24.2%。     

非频率选择性衰落MIMO信道上基于序列蒙特卡罗的数字调制识别方法

该文针对非频率选择性衰落多输入多输出(MIMO)信道提出了一种基于序列蒙特卡罗(SMC)方法的幅度-相位调制方式识别方法。首先将MIMO系统等效为一个动态状态空间模型,然后利用序列重要性采样和模式转移步骤估计每根发送天线采用的各种可能调制方式的概率,最后利用各个信道上发送符号的不相关性在长为N的观测信道上进行噪声平均。该方法能够在识别数字调制方式的同时估计发送数据符号。其复杂度是信道观测长度、发送天线数、采样大小、调制星座大小的线性函数。仿真结果表明提出的数字调制识别方法在各种调制星座上具有良好的性能。     

Framework for COVID-19 Segmentation and Classification Based on Deep Learning of Computed Tomography Lung Images

Corona Virus Disease 2019 (COVID-19) has affected millions of people worldwide and caused more than 6.3 million deaths (World Health Organization, June 2022). Increased attempts have been made to develop deep learning methods to diagnose COVID-19 based on computed tomography (CT) lung images. It is a challenge to reproduce and obtain the CT lung data, because it is not publicly available. This paper introduces a new generalized framework to segment and classify CT images and determine whether a patient is tested positive or negative for COVID-19 based on lung CT images. In this work, many different strategies are explored for the classification task. ResNet50 and VGG16 models are applied to classify CT lung images into COVID-19 positive or negative. Also, VGG16 and ReNet50 combined with U-Net, which is one of the most used architectures in deep learning for image segmentation, are employed to segment CT lung images before the classifying process to increase system performance. Moreover, the image size dependent normalization technique (ISDNT) and Wiener filter are utilized as the preprocessing techniques to enhance images and noise suppression. Additionally, transfer learning and data augmentation techniques are performed to solve the problem of COVID-19 CT lung images deficiency, therefore the over-fitting of deep models can be avoided. The proposed frameworks, which comprised of end-to-end, VGG16, ResNet50, and U-Net with VGG16 or ResNet50, are applied on the dataset that is sourced from COVID-19 lung CT images in Kaggle. The classification results show that using the preprocessed CT lung images as the input for U-Net hybrid with ResNet50 achieves the best performance. The proposed classification model achieves the 98.98% accuracy (ACC), 98.87% area under the ROC curve (AUC), 98.89% sensitivity (Se), 97.99 % precision (Pr), 97.88% F₁-score, and 1.8974-seconds computational time.     

基于稀疏自动编码网络的水声通信信号调制识别

研究了基于稀疏自动编码网络的水声通信信号识别方法。首先利用稀疏自动编码网络对接收信号的功率谱识别分类,得到除PSK外信号的调制类型,然后对识别结果为PSK的信号做四次方谱,最后利用稀疏自动编码网络完成对QPSK和8PSK的识别分类。仿真实验表明,稀疏自动编码网络能从接收信号的谱信息中自动提取有效谱特征。与传统基于功率谱特征提取的识别方法相比,本文算法减少了依赖领域知识的特征提取环节,识别性能优于传统算法。      

Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN

Computer-empowered detection of possible faults for Heating, Ventilation and Air-Conditioning (HVAC) subsystems, e.g., chillers, is one of the most important applications in Artificial Intelligence (AI) integrated Internet of Things (IoT). The cyber-physical system greatly enhances the safety and security of the working facilities, reducing time, saving energy and protecting humans’ health. Under the current trends of smart building design and energy management optimization, Automated Fault Detection and Diagnosis (AFDD) of chillers integrated with IoT is highly demanded. Recent studies show that standard machine learning techniques, such as Principal Component Analysis (PCA), Support Vector Machine (SVM) and tree-structure-based algorithms, are useful in capturing various chiller faults with high accuracy rates. With the fast development of deep learning technology, Convolutional Neural Networks (CNNs) have been widely and successfully applied to various fields. However, for chiller AFDD, few existing works are adopting CNN and its extensions in the feature extraction and classification processes. In this study, we propose to perform chiller FDD using a CNN-based approach. The proposed approach has two distinct advantages over existing machine learning-based chiller AFDD methods. First, the CNN-based approach does not require the feature selection/extraction process. Since CNN is reputable with its feature extraction capability, the feature extraction and classification processes are merged, leading to a more neat AFDD framework compared to traditional approaches. Second, the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.     

Automatic modulation classification based on AlexNet with data augmentation

Deep learning (DL) requires massive volume of data to train the network. Insufficient training data will cause serious overfitting problem and degrade the classification accuracy. In order to solve this problem, a method for automatic modulation classification ( AMC) using AlexNet with data augmentation was proposed. Three data augmentation methods is considered, i. e. , random erasing, CutMix, and rotation. Firstly, modulated signals are converted into constellation representations. And all constellation representations are divided into training dataset and test dataset. Then, training dataset are augmented by three methods. Secondly, the optimal value of execution probability for random erasing and CutMix are determined. Simulation results show that both of them perform optimally when execution probability is 0.5. Thirdly, the performance of three data augmentation methods are evaluated. Simulation results demonstrate that all augmentation methods can improve the classification accuracy. Rotation improves the classification accuracy by 13.04% when signal noise ratio (SNR) is 2 dB. Among three methods, rotation outperforms random erasing and CutMix when SNR is greater than - 6 dB. Finally, compared with other classification algorithms, random erasing, CutMix, and rotation used in this paper achieved the performance significantly improved. It is worth mentioning that the classification accuracy can reach 90.5% with SNR at 10 dB.     

基于无监督域适应的仿真辅助SAR目标分类方法及模型可解释性分析

卷积神经网络(CNN)在光学图像分类领域中得到广泛应用,然而,合成孔径雷达(SAR)图像样本标注难度大、成本高,难以获取满足CNN训练所需的样本数量.随着SAR仿真技术的发展,生成大量带标签的仿真SAR图像并不困难.然而仿真SAR图像样本与真实样本间难免存在差异,往往难以直接支撑实际样本的分类任务.为此,该文提出了一种...