基于盒维数的灵巧噪声干扰识别方法

灵巧噪声干扰因兼有欺骗干扰和噪声干扰的特点,已成为1种干扰新体制雷达的有效样式,干扰识别也成为电子战领域研究的热点课题.针对卷积调制、数字多时延和间歇采样转发3种灵巧噪声干扰识别问题,通过分析干扰信号的产生机理和频谱特性,提出了1种基于盒维数特征的干扰识别方法.采用支持向量机进行分类识别,仿真验证了该方法具有较高的识别...     

机器视觉在军事领域的应用现状及发展趋势

机器视觉技术凭借其非接触测量、实时性好、可持续工作等优点，在军事领域中有着广阔的应用前景。在对机器视觉光学照明系统、成像系统、视觉信息处理系统等关键技术进行概述的基础上，详细分析了机器视觉技术在军事领域进行典型目标物识别、人员识别、装备缺陷检测等典型场景以及典型军事装备上的应用现状。在此基础上，指出了机器视觉在军事领域的应用，仍然存在视觉传感器硬件系统难以适应极端环境、复杂的军事目标适应性不足、目标识别的实时性难以保证、多传感器融合获取军事目标信息能力缺乏等问题。同时，对机器视觉技术在军事领域应用的未来发展趋势进行了展望，研究分析结果可为机器视觉在军事领域的进一步实用化提供参考。     

基于混合神经网络的无线电信号自动调制识别

随着无线电信号数据海量增加，复杂电磁环境下面临着未知威胁和目标侦察识别复杂度高的问题，本文针对未知无线电信号的特征提取任务，设计了一种混合神经网络以提高目标无线电信号的识别能力。先通过胶囊神经网络对未知信号的空间信息进行提取，再进一步运用门控循环单元提取信号在时间上的特征信息。设计混合网络模型将信号的时间和空间特征相结合，提高对目标信号的分类精度。通过RML2016.04C调制信号数据集，验证了混合神经网络的识别性能。结果表明:当信噪比为6 dB时，混合网络模型对多种不同调制信号的分类精度大于95%。因此，本文所设计的混合神经网络能够有效对不同调制信号进行准确分类。     

Evolutionary features of polar and non-polar coronal holes during solar cycle 24 and the rising phase of cycle 25

This paper presents the results of the analysis of the evolution of coronal holes (CHs) on the Sun during the period May 13, 2010 – March 20, 2022, covering Solar Cycle 24. Our study uses images in the extreme-ultraviolet iron line (Fe XII 193 Å) obtained with the Atmospheric Imager Assembly of the Solar Dynamics Observatory (AIA/SDO). To localize CHs and determine their areas, we used the Heliophysics Event Knowledgebase (HEK). We separate the CHs into polar and non-polar and study the evolutionary features of each group. During this period, an asymmetry between the Northern (N) and Southern (S) Hemispheres (N-S or hemispheric asymmetry) is detected both in the solar activity (SA) indices and in the localization of the maximum areas of the polar and non-polar CHs. It is shown that the hemispheric asymmetry of the areas of polar and non-polar CHs varies significantly over time and that the nature of these changes is clearly related to the SA cycle. We find that for most of the period, the polar CHs were predominated generated in the S- hemisphere while the non-polar CHs were dominant in the N- hemisphere. It is found that the maximum and minimum of the hemispheric imbalance in the areas of non-polar CHs are close in time to the maximum and minimum of the asymmetry of the SA indices (the number and areas of sunspots). The maximum hemispheric imbalance of the polar CH areas is observed at the maximum of Cycle 24, and the minimum imbalance is found at the cycle minimum. These results confirm our assumption that these two types of CHs are of a different nature and that the non-polar CHs, like sunspots, are elements of the general magnetic activity.     

Large-scale real-world radio signal recognition with deep learning

In the past ten years, many high-quality datasets have been released to support the rapid development of deep learning in the fields of computer vision, voice, and natural language processing. Nowadays, deep learning has become a key research component of the Sixth-Generation wireless systems (6G) with numerous regulatory and defense applications. In order to facilitate the application of deep learning in radio signal recognition, in this work, a large-scale real-world radio signal dataset is created based on a special aeronautical monitoring system - Automatic Dependent Surveillance-Broadcast (ADS-B). This paper makes two main contributions. First, an automatic data collection and labeling system is designed to capture over-the-air ADS-B signals in the open and real-world scenario without human participation. Through data cleaning and sorting, a high-quality dataset of ADS-B signals is created for radio signal recognition. Second, we conduct an in-depth study on the performance of deep learning models using the new dataset, as well as comparison with a recognition benchmark using machine learning and deep learning methods. Finally, we conclude this paper with a discussion of open problems in this area.     

An online ensemble semi-supervised classification framework for air combat target maneuver recognition

Online target maneuver recognition is an important prerequisite for air combat situation recognition and maneuver decision-making. Conventional target maneuver recognition methods adopt mainly supervised learning methods and assume that many sample labels are available. However, in real-world applications, manual sample labeling is often time-consuming and laborious. In addition, airborne sensors collecting target maneuver trajectory information in data streams often cannot process information in real time. To solve these problems, in this paper, an air combat target maneuver recognition model based on an online ensemble semi-supervised classification framework based on online learning, ensemble learning, semi-supervised learning, and Tri-training algorithm, abbreviated as Online Ensemble Semi-supervised Classification Framework (OESCF), is proposed. The framework is divided into four parts: basic classifier offline training stage, online recognition model initialization stage, target maneuver online recognition stage, and online model update stage. Firstly, based on the improved Tri-training algorithm and the fusion decision filtering strategy combined with disagreement, basic classifiers are trained offline by making full use of labeled and unlabeled sample data. Secondly, the dynamic density clustering algorithm of the target maneuver is performed, statistical information of each cluster is calculated, and a set of micro-clusters is obtained to initialize the online recognition model. Thirdly, the ensemble K-Nearest Neighbor (KNN)-based learning method is used to recognize the incoming target maneuver trajectory instances. Finally, to further improve the accuracy and adaptability of the model under the condition of high dynamic air combat, the parameters of the model are updated online using error-driven representation learning, exponential decay function and basic classifier obtained in the offline training stage. The experimental results on several University of California Irvine (UCI) datasets and real air combat target maneuver trajectory data validate the effectiveness of the proposed method in comparison with other semi-supervised models and supervised models, and the results show that the proposed model achieves higher classification accuracy.     

基于改进的卷积神经网络的步态识别

为了提高惯性传感器采集到的序列数据中步态识别的准确率，建立了一个激励层改进的卷积神经网络(CNN)模型。针对三轴加速度传感器对运动太过敏感导致步态周期划分不准确的问题，采用加速度传感器与弯曲度传感器组合获取人体运动信息。将CNN模型中激励层的线性整流函数（ReLU）改进为带泄露线性整流函数(Leaky ReLU)，以解决遇到卷积输出数据小于0时神经元被抑制的问题，进而达到提高步态识别准确率的目的。实验结果表明：激励层优化的CNN模型在行走、上下楼和上下坡五种步态模式下识别率达到了95.79%，与未采用弯曲度传感器的改进CNN模型和未进行激励层改进的CNN模型相比，步态识别率有所提高。     

基于极化神经网络的雷达舰船检测识别方法

相参雷达捕获的全极化海面目标距离-多普勒(RD)回波数据中，目标区域占比小、信噪比低，且海况环境与干扰种类多变，使得经典的深度神经网络在此种条件下检测识别精度较低。为此，本文提出了一种基于极化深度神经网络的全极化相参雷达海面目标检测识别算法。首先，引入极化特征提取模块挖掘目标与干扰的差异化特征;其次，通过特征金字塔网络解决小目标检测识别的问题;最后，使用级联结构进一步提升算法性能。在全极化相参雷达回波数据集上的测试结果表明:基于特征值与特征矢量的极化特征对于数据集中两类舰船目标的平均精度分别达到0.907 9与1.0，相比不采用极化特征有着显著提高。     

海面舰船目标雷达距离高分辨特性测量

雷达距离高分辨特性,即目标的一维高分辨距离像特性,能够体现目标的形状及结构信息,且易获取,有利于对目标进行准确识别,这已成为目前雷达目标识别领域的一个重要研究方向。开展目标一维高分辨特性研究的一个重要基础是测量,因而通过测量目标的一维高分辨距离像并分析目标特性,对目标识别具有重大理论意义与实际应用价值。基于此,文章利用实验室现有全相参新体制雷达导引头目标测量平台,对海面舰船目标的距离高分辨特性进行了初步实测,获取了海面舰船的米级高分辨距离像,为今后深入开展海面舰船目标识别研究奠定了坚实基础。