ADS-B Anomaly Data Detection Model Based on Deep Learning and Difference of Gaussian Approach

Due to the influence of terrain structure,meteorological conditions and various factors,there are anomalous data in automatic dependent surveillance-broadcast(ADS-B)message.The ADS-B equipment can be used for positioning of general aviation aircraft.Aim to acquire the accurate position information of aircraft and detect anomaly data,the ADS-B anomaly data detection model based on deep learning and difference of Gaussian(DoG)approach is proposed.First,according to the characteristic of ADS-B data,the ADS-B position data are transformed into the coordinate system.And the origin of the coordinate system is set up as the take-off point.Then,based on the kinematic principle,the ADS-B anomaly data can be removed.Moreover,the details of the ADS-B position data can be got by the DoG approach.Finally,the long short-term memory(LSTM)neural network is used to optimize the recurrent neural network(RNN)with severe gradient reduction for processing ADS-B data.The position data of ADS-B are reconstructed by the sequence to sequence(seq2seq)model which is composed of LSTM neural network,and the reconstruction error is used to detect the anomalous data.Based on the real flight data of general aviation aircraft,the simulation results show that the anomaly data can be detected effectively by the proposed method of reconstructing ADS-B data with the seq2seq model,and its running time is reduced.Compared with the RNN,the accuracy of anomaly detection is increased by 2.7%.The performance of the proposed model is better than that of the traditional anomaly detection models.

The Exact Formulation of the Inverse of the Tridiagonal Matrix for Solving the 1D Poisson Equation with the Finite Difference Method

A new method for solving the 1D Poisson equation is presented using the finite difference method. This method is based on the exact formulation of the inverse of the tridiagonal matrix associated with the Laplacian. This is the first time that the inverse of this remarkable matrix is determined directly and exactly. Thus, solving 1D Poisson equation becomes very accurate and extremely fast. This method is a very important tool for physics and engineering where the Poisson equation appears very often in the description of certain phenomena.

Square-root divided difference Rauch-Tung-Striebel smoother

A square-root version of the divided difference Rauch-Tung-Striebel (RTS) smoother is proposed in this paper. The square-root variant essentially propagates the square roots of the covariance matrices and can consistently improve the numerical stability because all the resulting covariance matrices are guaranteed to stay positive semi-definite. Furthermore, the square-root form ensures reliable implementation in an embedded system with fixed or limited precision although it is algebraically equivalent to the standard form. The new smoothing algorithm is tested in a challenging two-dimensional maneuvering target tracking problem with unknown and time-varying turn rate, and its performance is compared with that of other de-facto standard filters and smoothers. The simulation results indicate that the proposed RTS smoother markedly outperforms the associated filters and gives slightly smaller error than an unscented-based RTS smoother.

基于Gaussian Copula的木结构古建筑多准则地震易损性分析

为了解决木结构古建筑不同失效模式之间相关性的问题,基于Copula函数提出考虑结构不同失效模式之间相关性的木结构古建筑地震易损性分析方法.以一座中国明代古建筑为研究对象,首先,根据该建筑的结构特性和相关历史震害资料,选取层间位移角和榫卯节点转角作为地震需求参数.运用Ansys对其进行增量动力分析,建立结构在不同失效模式下的地震易损性曲线.其次,通过建立样本数据的二维频率直方图来选取适宜的Copula函数,进而获得考虑不同失效模式相关性的综合易损性曲线.再次,运用一阶界限法建立结构的易损性曲线.结果表明:基于Copula函数得到的结构易损性大于任何一个失效模式下的结构易损性;其计算结果,小于一阶界限法的上界,略大于一阶界限法的下界.

Audio-Visual Underdetermined Blind Source Separation Algorithm Based on Gaussian Potential Function

Most existing algorithms for the underdetermined blind source separation(UBSS) problem are two-stage algorithm, i.e., mixing parameters estimation and sources estimation. In the mixing parameters estimation, the previously proposed traditional clustering algorithms are sensitive to the initializations of the mixing parameters. To reduce the sensitiveness to the initialization, we propose a new algorithm for the UBSS problem based on anechoic speech mixtures by employing the visual information, i.e., the interaural time difference(ITD) and the interaural level difference(ILD), as the initializations of the mixing parameters. In our algorithm, the video signals are utilized to estimate the distances between microphones and sources, and then the estimations of the ITD and ILD can be obtained. With the sparsity assumption in the time-frequency domain, the Gaussian potential function algorithm is utilized to estimate the mixing parameters by using the ITDs and ILDs as the initializations of the mixing parameters. And the time-frequency masking is used to recover the sources by evaluating the various ITDs and ILDs. Experimental results demonstrate the competitive performance of the proposed algorithm compared with the baseline algorithms.

An Improved Moving Object Detection Algorithm Based on Gaussian Mixture Models

Aiming at the problems that the classical Gaussian mixture model is unable to detect the complete moving object, and is sensitive to the light mutation scenes and so on, an improved algorithm is proposed for moving object detection based on Gaussian mixture model and three-frame difference method. In the process of extracting the moving region, the improved three-frame difference method uses the dynamic segmentation threshold and edge detection technology, and it is first used to solve the problems such as the illumination mutation and the discontinuity of the target edge. Then, a new adaptive selection strategy of the number of Gaussian distributions is introduced to reduce the processing time and improve accuracy of detection. Finally, HSV color space is used to remove shadow regions, and the whole moving object is detected. Experimental results show that the proposed algorithm can detect moving objects in various situations effectively.

Electron acceleration by two crossed Bessel-Gaussian beams in vacuum

The direct acceleration of electrons by using two linearly polarized crossed Bessel-Gaussian （BG） beams with equal frequency and amplitude in vacuum is proposed and studied. It is shown that two linearly polarized BG beams of the same order （0 or 1） with a π-rad phase difference have a resultant non-zero longitudinal electric field on the z-axis and can be used, in principle, to accelerate electrons.

海洋湍流下双拉盖尔-高斯涡旋光束的闪烁指数与误码率研究

采用功率谱反演法模拟了同轴叠加产生的双拉盖尔-高斯涡旋光束(Double Laguerre-Gaussian Vortex Beam,DLGVB)在海洋湍流中传输时的光强和相位分布,仿真分析了DLGVB光束在不同海洋湍流参数下的闪烁指数以及在基于开关键控调制的水下光通信系统中的通信误码率。结果表明,随着湍流动能耗散率的减小,盐度温度波动平衡参数、温度方差耗散率及传输距离的增加,闪烁指数逐渐增加;随着湍流动能耗散率以及拓扑电荷差值的增加,误码率减小。在海洋湍流环境下,使用DLGVB光束进行传输可以抑制海洋湍流带来的干扰,选择最佳的拓扑电荷差值,可以有效提高传输通信质量及通信系统容量。本文研究结果对涡旋光束及其叠加态在海洋湍流下传输特性研究及水下光通信系统持续扩容的发展需求方面具有重要的参考价值。

适应波达时刻不确定性及较低采样率的新能源送出线路就地暂态量主保护判据

不对称接地故障占所有线路故障的90%以上,接地距离保护在应对此类故障方面发挥了不可替代的作用。随着新能源高比例渗透,各种传统单端工频量保护性能显著下降已成为共识。基于故障分量线模和零模波速差的保护判据理论上仅需利用到故障初始行波到达时刻信息,是一种原理简单可靠的单端量快速保护判据,已经在直流电网中成功实践。但在尝试将这类保护应用于交流电网时发现,受波头前陡较缓而难以精确定位波到时刻、依赖高采样率等诸多不利因素影响,存在过大的模糊判别区,除了特长线路外,对绝大部分线路几乎没有应用可行性。波到时刻的精准辨识是一个复杂的非线性问题,利用人工智能的方法进行辨识是一条可行的解决思路,对此,该文提出一种新的单端暂态量主保护判据。首先,分析波达时刻与波形关系,并指出这种关系能够采用机器学习来映射;其次,引入高斯过程回归(Gaussian process regression,GPR),在对初始行波数据进行预处理得到样本集后,输入GPR预测模型进行训练;然后,依据模型评估指标得到最优训练模型以输出高可信性的线-零模波达时差,据此实现了基于行波模量传输时间差的保护判据;最后,在利用PSCAD仿真验证所提保护判据有效性和普适性的基础上,进一步利用现场实测数据对判据进行测试,验证其实用性。该文工作为新能源交流系统下单端暂态量保护的性能提升提供新的解决思路。

改进的U-Net在建筑物变化检测中的应用

变化检测是对地观测应用中的一项重要任务。然而现有的基于深度学习的变化检测方法在高分遥感图像建筑物变化检测任务中仍存在变化对象和背景之间分界模糊、小变化目标漏检等问题。针对这些问题,提出了一种基于高斯差分金字塔和注意力特征传递的遥感图像建筑物变化检测方法。该方法采用编码器解码器结构,在编码阶段使用高斯差分金字塔获取双时相遥感图像多尺度边缘特征信息,融合不同尺度下的边缘特征信息,增强图像边缘特征表达能力。在解码部分引入注意力特征传递机制,将高层语义信息与低层建筑物细节有效融合,以捕获特征中的显著信息、抑制无效特征信息,提升小变化目标的检测能力。该方法在公开的LEVIR-CD、WHU-CD数据集上进行训练和测试。实验结果表明,相比于其他同类方法,改进方法在对不同尺度建筑物目标的变化检测中展现了良好的适应性,在保证较低算力消耗的基础上,精确率、召回率、F1和Kappa值方面均有较大提升。

局部高斯均差变分保边图像平滑算法

针对图像平滑过程中无法保留细节的问题,提出了基于局部高斯均差变分的保边图像平滑算法。首先,通过统计学分析建立局部高斯均差变分算子。其可以衡量局部梯度与高斯滤波处理后的梯度差异,区分结构和纹理。其次,构建局部高斯均差变分平滑模型,由稀疏求解得到初始平滑图像。最后,针对复杂纹理图像存在纹理残留的问题,提出孤立噪声去除模型。模型通过自适应窗口设定像素值,在不影响结构的前提下去除初始平滑图像中的纹理残留。通过主观、客观实验,与经典的算法对比,证明该算法有更高质量的平滑结果。评价指标整体提升了0.7%。通过压缩伪影去除、HDR色调映射、图像去雾和拉普拉斯金字塔加速的扩展实验,验证该算法在不同视觉任务上的适用性和效率可提升性。

有偏量测下基于最大相关熵卡尔曼滤波的目标跟踪方法

针对传感器存在系统偏差且噪声非高斯条件下目标状态估计精度较差的问题,提出一种有偏量测下基于最大相关熵卡尔曼滤波(Maximum Correntropy Kalman Filter,MCKF)的目标跟踪方法。该方法通过引入差分机制,利用目标相邻时刻的有偏量测之差构建差分量测方程,有效克服了系统偏差的影响。随后基于最大相关熵准则(Maximum Correntropy Criterion,MCC)量化估计误差的高阶矩信息,并以差分量测为先验条件推导出有偏量测下算法的滤波迭代方程。仿真结果表明,当系统观测值受传感器系统偏差和非高斯噪声干扰时,与现有方法相比,所提方法具有更好的跟踪性能。

基于多参数Gabor滤波器融合和高斯差分的生丝疵点分割

针对生丝疵点图像背景与疵点差别极小的特点,提出一种基于多方向、多频率Gabor滤波器融合和高斯差分滤波的疵点分割算法。根据疵点纹理特性,首先采用极大值的方法对特定频率多方向疵点Gabor滤波图像进行融合,并基于均值法对不同频率Gabor滤波器图像进行融合,然后使用高斯差分滤波进一步凸显疵点,最后采用全局阈值将疵点与背景分割开来。测试结果表明:该研究算法召回率达到了93.2%,能够准确分割出生丝疵点。

一种针对抖动无人机视频的运动目标检测算法

针对悬浮无人机在运动目标检测中易受抖动影响,导致大量背景噪声的问题,提出一种多尺度的EA-KDE背景差分算法(MEA-KDE)。该算法首先对图像序列进行多尺度分解,以获取多尺度的图像序列。然后,在进行检测之前,通过考虑面积阈值和当前图像帧,计算并更新检测的分割阈值,引入当前图像帧信息。其次,对不同尺度的图像帧采用高低双分割阈值进行背景差分运算,以提高检测的鲁棒性。最后,通过对各尺度的检测结果采用一种自顶向下的融合策略进行融合,以在保留目标的清晰轮廓同时消除噪声。此外,提出的一种边界扩展融合后处理算法有助于减轻检测断裂引起的目标破碎现象。实验结果表明,所提算法能够有效抑制抖动导致的背景噪声。在2个真实拍摄的无人机数据集上,分别获得了0.951和0.952的平均F1分数,相较于原算法分别提高了0.144和0.276。

An algorithm that minimizes audio fingerprints using the difference of Gaussians

Recently,many audio search sites headed by Google have used audio fingerprinting technology to search for the same audio and protect the music copyright using one part of the audio data.However,if there are fingerprints per audio file,then the amount of query data for the audio search increases.In this paper,we propose a novel method that can reduce the number of fingerprints while providing a level of performance similar to that of existing methods.The proposed method uses the difference of Gaussians which is often used in feature extraction during image signal processing.In the experiment,we use the proposed method and dynamic time warping and undertake an experimental search for the same audio with a success rate of 90%.The proposed method,therefore,can be used for an effective audio search.

一种融合背景差分和帧间差分的运动目标检测方法

针对背景差分法和帧间差分法在运动目标检测中的缺点,提出了一种结合背景差分法和帧间差分法的新算法。首先将混合高斯模型建立的背景与当前帧进行差分处理,再使用帧间差分法获得差分图像,最后将两种差分结果融合检测运动目标,对目标轮廓和边界区域进行标记。实验显示,新算法对检测效果提升明显。

Human Action Recognition Using Difference of Gaussian and Difference of Wavelet

Human Action Recognition(HAR)attempts to recognize the human action from images and videos.The major challenge in HAR is the design of an action descriptor that makes the HAR system robust for different environments.A novel action descriptor is proposed in this study,based on two independent spatial and spectral filters.The proposed descriptor uses a Difference of Gaussian(DoG)filter to extract scale-invariant features and a Difference of Wavelet(DoW)filter to extract spectral information.To create a composite feature vector for a particular test action picture,the Discriminant of Guassian(DoG)and Difference of Wavelet(DoW)features are combined.Linear Discriminant Analysis(LDA),a widely used dimensionality reduction technique,is also used to eliminate duplicate data.Finally,a closest neighbor method is used to classify the dataset.Weizmann and UCF 11 datasets were used to run extensive simulations of the suggested strategy,and the accuracy assessed after the simulations were run on Weizmann datasets for five-fold cross validation is shown to perform well.The average accuracy of DoG+DoW is observed as 83.6635%while the average accuracy of Discrinanat of Guassian(DoG)and Difference of Wavelet(DoW)is observed as 80.2312%and 77.4215%,respectively.The average accuracy measured after the simulation of proposed methods over UCF 11 action dataset for five-fold cross validation DoG+DoW is observed as 62.5231%while the average accuracy of Difference of Guassian(DoG)and Difference of Wavelet(DoW)is observed as 60.3214%and 58.1247%,respectively.From the above accuracy observations,the accuracy of Weizmann is high compared to the accuracy of UCF 11,hence verifying the effectiveness in the improvisation of recognition accuracy.

基于卡尔曼(Kalman)滤波算法的体育训练视频中的运动目标检测

体育训练视频中的运动目标检测往往存在目标快速移动、目标遮挡和场景变化等问题,导致运动目标检测的难度增大。为了解决这些问题,提出了基于卡尔曼(Kalman)滤波算法的体育训练视频中运动目标检测的方法。为了提升体育训练视频图像的质量,首先对体育训练视频的图像进行一系列预处理(包括灰度变换、轮廓对比增强和噪声抑制等);然后借助混合高斯模型(Gaussian mixture module,GMM)有效提取体育训练视频的前景信息;为了精准捕捉体育训练视频中的运动目标,运用三帧差分法设定Kalman滤波器的初始状态,利用高效检测算法准确获取每一帧图像中运动目标的观测位置;随后将初始状态和观测位置的数据输入Kalman滤波器;最后在Kalman滤波器中,结合上一帧的预估值和当前帧的监测值,对体育训练视频中运动目标的当前状态进行精确估算和优化,并对下一帧的状态进行预测,从而实现了对运动目标的持续跟踪与精准预测。实验结果表明,与基于特征融合的全卷积孪生网络(siamese full convolution,Siamfc)目标追踪算法和基于连续自适应均值漂移(continuously adapting mean shift,Camshift)的均值漂移(mean shift,Meanshift)改进算法相比,采用基于Kalman滤波算法的运动目标检测方法对运动目标的重叠精度(overlap precision,OP)和中心位置误差(center location error,CLE)进行检测,不仅能够有效检测到体育训练视频中的运动目标,还可表现出较高的准确性和实时性。

基于对称KL散度的电力用户负荷聚类方法研究

随着源网荷储四侧资源的建设,电力部门积累了海量用户的用电数据,如何有效挖掘这些数据的潜在信息,促进电力用户的精细化管理,是当前电力系统分析的一个重要问题。基于此,提出了基于对称KL散度(Kullback-Leibler Divergence)的电力用户负荷聚类方法。首先,利用高斯混合模型(Gaussian Mixture Model,GMM)表示用户的日常用电规律,并通过最大均值差异(Maximum Mean Discrepancy,MMD)检验模型的合理性;然后,将对称KL散度作为相似性判据,从划分聚类的角度出发,对GMM表示的电力负荷用户进行聚类;最后,以所提算法对MNIST以及某小区用户数据进行分析,实验结果表明所提方法具有可行性和有效性。

一种重频分组雷达信号时差解模糊算法

相控阵雷达具有高速灵活的波束调度能力且其信号广泛采用高重频设计,导致无源时差估计中出现大量的非均匀时差模糊点,难以精确定位。为解决时差模糊问题,基于团簇分组的方法提出一种卡尔曼滤波联合概率关联的重频分组雷达信号时差解模糊算法,该方法在时差层面充分利用了相控阵雷达信号重频组变的特性,融合多普勒频率、重周等多维信息,能够基于双站观测场景序贯完成单路时差模糊点的修正,从而得到目标真实时差轨迹。仿真验证了所提方法的可行性。