A Novel Clutter Suppression Algorithm for Low-Slow-Small Targets Detecting Based on Sparse Adaptive Filtering

Passive detection of low-slow-small(LSS)targets is easily interfered by direct signal and multipath clutter,and the traditional clutter suppression method has the contradiction between step size and convergence rate.In this paper,a frequency domain clutter suppression algorithm based on sparse adaptive filtering is proposed.The pulse compression operation between the error signal and the input reference signal is added to the cost function as a sparsity constraint,and the criterion for filter weight updating is improved to obtain a purer echo signal.At the same time,the step size and penalty factor are brought into the adaptive iteration process,and the input data is used to drive the adaptive changes of parameters such as step size.The proposed algorithm has a small amount of calculation,which improves the robustness to parameters such as step size,reduces the weight error of the filter and has a good clutter suppression performance.

Alzheimer’s Disease Stage Classification Using a Deep Transfer Learning and Sparse Auto Encoder Method

Alzheimer’s Disease(AD)is a progressive neurological disease.Early diagnosis of this illness using conventional methods is very challenging.Deep Learning(DL)is one of the finest solutions for improving diagnostic procedures’performance and forecast accuracy.The disease’s widespread distribution and elevated mortality rate demonstrate its significance in the older-onset and younger-onset age groups.In light of research investigations,it is vital to consider age as one of the key criteria when choosing the subjects.The younger subjects are more susceptible to the perishable side than the older onset.The proposed investigation concentrated on the younger onset.The research used deep learning models and neuroimages to diagnose and categorize the disease at its early stages automatically.The proposed work is executed in three steps.The 3D input images must first undergo image pre-processing using Weiner filtering and Contrast Limited Adaptive Histogram Equalization(CLAHE)methods.The Transfer Learning(TL)models extract features,which are subsequently compressed using cascaded Auto Encoders(AE).The final phase entails using a Deep Neural Network(DNN)to classify the phases of AD.The model was trained and tested to classify the five stages of AD.The ensemble ResNet-18 and sparse autoencoder with DNN model achieved an accuracy of 98.54%.The method is compared to state-of-the-art approaches to validate its efficacy and performance.

Super-Resolution Based on Curvelet Transform and Sparse Representation

Super-resolution techniques are used to reconstruct an image with a high resolution from one or more low-resolution image(s).In this paper,we proposed a single image super-resolution algorithm.It uses the nonlocal mean filter as a prior step to produce a denoised image.The proposed algorithm is based on curvelet transform.It converts the denoised image into low and high frequencies(sub-bands).Then we applied a multi-dimensional interpolation called Lancozos interpolation over both sub-bands.In parallel,we applied sparse representation with over complete dictionary for the denoised image.The proposed algorithm then combines the dictionary learning in the sparse representation and the interpolated sub-bands using inverse curvelet transform to have an image with a higher resolution.The experimental results of the proposed super-resolution algorithm show superior performance and obviously better-recovering images with enhanced edges.The comparison study shows that the proposed super-resolution algorithm outperforms the state-of-the-art.The mean absolute error is 0.021±0.008 and the structural similarity index measure is 0.89±0.08.

噪声干扰下基于PCA-SF的轴承故障诊断方法

机械故障诊断对降低维修成本和预防事故至关重要。振动信号监测是机械故障诊断中一种有效可行的方法。然而,所采集故障信号往往容易受到其他设备噪声的干扰。因此,从受噪声干扰的监测信号中提取与故障相关的周期脉冲是故障诊断的基础,也是难点。为解决此问题,提出一种基于主成分分析(Principal Component Analysis,PCA)和稀疏滤波(Sparse Filtering,SF)的机械故障特征提取方法。具体来说,首先利用PCA提取噪声干扰信号段的主成分,然后利用SF从主成分中提取有效特征。为减小SF模型的过拟合问题,采用L1/2范数对其目标函数进行正则化约束。最后,将提取的特征输入到Softmax分类器中进行故障识别。分别通过一组仿真和实验案例对所提PCA-SF方法的有效性进行验证。实验结果表明,该方法不仅能准确实现故障分类,而且优于其他传统方法。

A novel sparse filtering approach based on time-frequency feature extraction and softmax regression for intelligent fault diagnosis under different speeds

Modern agricultural mechanization has put forward higher requirements for the intelligent defect diagnosis.However,the fault features are usually learned and classified under all speeds without considering the effects of speed fluctuation.To overcome this deficiency,a novel intelligent defect detection framework based on time-frequency transformation is presented in this work.In the framework,the samples under one speed are employed for training sparse filtering model,and the remaining samples under different speeds are adopted for testing the effectiveness.Our proposed approach contains two stages:1)the time-frequency domain signals are acquired from the mechanical raw vibration data by the short time Fourier transform algorithm,and then the defect features are extracted from time-frequency domain signals by sparse filtering algorithm;2)different defect types are classified by the softmax regression using the defect features.The proposed approach can be employed to mine available fault characteristics adaptively and is an effective intelligent method for fault detection of agricultural equipment.The fault detection performances confirm that our approach not only owns strong ability for fault classification under different speeds,but also obtains higher identification accuracy than the other methods.

Image Fusion Based on NSCT and Sparse Representation for Remote Sensing Data

The practice of integrating images from two or more sensors collected from the same area or object is known as image fusion.The goal is to extract more spatial and spectral information from the resulting fused image than from the component images.The images must be fused to improve the spatial and spectral quality of both panchromatic and multispectral images.This study provides a novel picture fusion technique that employs L0 smoothening Filter,Non-subsampled Contour let Transform(NSCT)and Sparse Representation(SR)followed by the Max absolute rule(MAR).The fusion approach is as follows:first,the multispectral and panchromatic images are divided into lower and higher frequency components using the L0 smoothing filter.Then comes the fusion process,which uses an approach that combines NSCT and SR to fuse low frequency components.Similarly,the Max-absolute fusion rule is used to merge high frequency components.Finally,the final image is obtained through the disintegration of fused low and high frequency data.In terms of correlation coefficient,Entropy,spatial frequency,and fusion mutual information,our method outperforms other methods in terms of image quality enhancement and visual evaluation.

稀疏约束与时间一致的背景感知相关滤波目标跟踪

背景感知滤波算法通过循环移位采集真实负样本,有效解决了边界效应.但在复杂场景例如遮挡、快速移动、背景干扰等,其较大的采样区域导致过多背景在杂波干扰,从而影响跟踪效果.针对这一问题,本文首先提取灰度HOG特征与颜色CN特征来提高目标外观模型,在基准目标函数基础上引入L1稀疏正则约束形成弹性网络以自适应筛选关键特征,增强滤波器在复杂背景下的判别能力.同时针对BACF在跟踪过程中目标快速变化,本文引入时间正则项提高滤波器抑制畸变的能力.最后,本文提出了一种独立的尺度滤波器算法,准确提供目标尺度大小.实验仿真结果表明,在公开数据集OTB-2013和OTB-2015上,本文算法较基准算法有很大提升,能够较好应对不同复杂场景下的跟踪难题.

多任务联合学习的图卷积神经网络推荐

基于图神经网络的协同过滤推荐可以更有效地挖掘用户项目之间的交互信息,但其性能依然受到数据稀疏和表征学习质量不高问题的影响,因此提出一种多任务联合学习的图卷积神经网络推荐(multi-task joint learning for graph convolutional neural network recommendations,MTJL-GCN)模型。利用图神经网络在用户-项目交互图上所聚集到的同质结构信息与初始嵌入信息形成结构邻居关系,设计节点邻居关系的对比学习辅助任务来缓解数据稀疏问题;向节点的原始表征添加随机的统一噪声进行表征级数据增强,构建节点表征关系的对比学习辅助任务,并提出直接优化对齐性和均匀性两个属性的学习目标来提高表征学习质量;将图协同过滤推荐任务与对比学习辅助任务和直接优化学习目标进行联合训练,从而提升推荐性能。在Amazon-books和Yelp2018两个公开数据集上进行实验,该模型在Recall@k和NDCG@k两个推荐性能指标上的表现均优于基线模型,证明了MTJL-GCN模型的有效性。

基于稀疏贝叶斯学习的GFDM系统联合迭代信道估计与符号检测

针对当前广义频分复用(Generalized Frequency Division Multiplexing,GFDM)系统时变信道估计精度低的问题,提出基于稀疏贝叶斯学习的GFDM系统联合信道估计与符号检测算法.具体地,采用无干扰导频插入的GFDM多重响应信号模型,在稀疏贝叶斯学习框架下,结合期望最大化算法(Expectation-Maximization,EM)和卡尔曼滤波与平滑算法实现块时变信道的最大似然估计;基于信道状态信息的估计值进行GFDM符号检测,并通过信道估计与符号检测的迭代处理逐步提高信道估计与符号检测的精度.仿真结果表明,所提算法能够获得接近完美信道状态信息条件下的误码率性能,且具有收敛速度快、对多普勒频移鲁棒性高等优点.

面向电力设备红外图像的混合噪声去除方法研究

电力设备的红外图像在采集传输过程中,易受高斯噪声与脉冲噪声的影响从而破坏图像的真实信息,为满足图像处理过程对图像质量的要求,文中提出了一种针对红外图像混合噪声的滤除方法。首先利用三方加权稀疏编码(TWSC)模型有效滤除红外图像中的高斯噪声,然后利用图像结构纹理分解结合中值滤波算法实现剩余脉冲噪声的分离与去除,实现在滤除红外图像混合噪声的同时较好地保持图像的边缘结构信息,结合实例分析表明文中方法能够有效滤除噪声并获得较高的峰值信噪比(PSNR)与结构相似度(SSIM)。

基于L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法

为解决传统数字滤波器在有限精度实现时因有限字长(Finite Word Length,FWL)效应导致滤波器性能下降的问题,提出一种L_(2)灵敏度最小化的数字滤波器状态空间实现稀疏化方法.推导前向差分算子数字滤波器结构传输函数及其等效状态空间实现,根据可控及可观格莱姆矩阵得到基于相似变换矩阵的L_(2)灵敏度表达式,并进行稀疏化校准,将L_(2)灵敏度最小化问题转换为凸函数求最值问题,求导得到L_(2)灵敏度最小化表达式,代回即得前向差分算子数字滤波器的稀疏化状态空间实现.仿真结果表明,所提方法设计的数字滤波器具有更好的抗FWL效应.

占空比传输机制下基于协同预测的时变不确定系统递推滤波

以工业互联网为背景,研究占空比传输机制下一类时变不确定系统的滤波问题,结合协同预测方法设计了新颖的递推滤波算法,解决了占空比传输机制下滤波性能降低的问题。首先给出描述占空比传输机制的数学模型,然后提出结合协同预测方法的递推滤波方案,设计基于占空比机制的递推滤波算法,推导了滤波误差协方差矩阵的一个上界,随后分析这个上界的有界性,实现了在稀疏数据情形下提高滤波性能的目的。仿真结果验证了所提算法的高效性和有效性。

面向稀疏数据的协同过滤算法相似度

针对数据稀疏加剧导致传统相似度模型的推荐准确性低的问题,提出一种混合的协同过滤相似度模型。引入Jensen-Shannon(JS)散度作为基函数,利用全局评级概率分布衡量用户间评级偏好相似度。定义融合评级值的结构型相似度作为权重因子,针对用户的共同评级项目设计差异化的相似度计算方式,提高相似用户的区分度,得到基于相对区间跨度的相似度。在不同稀疏度数据集上与7种具有代表性的相似度方法进行对比实验,其结果表明了所提方法在预测和推荐准确性指标上均有良好性能。

面向稀疏卷积神经网络的CGRA加速器研究

本文针对规模日益增长和演变迅速的稀疏卷积神经网络(CNN)应用,提出一款高能效且灵活的加速结构DyCNN来提升其性能和能效。DyCNN基于兼具灵活性和高能效的粗粒度可重构架构(CGRA)设计,可以利用其指令的高并行性来高效支持CNN的操作。DyCNN使用基于数据感知的指令动态过滤机制来滤除各计算单元中由于稀疏CNN中权值静态稀疏性和激活值动态稀疏性产生的大量无效计算和访存指令,使它们能像执行稠密网络一样高效复用一组指令。此外DyCNN利用基于负载感知的动静结合负载调度策略解决了稀疏导致的负载不均衡问题。实验结果表明,DyCNN运行稀疏CNN与运行密集CNN相比实现了平均1.69倍性能提升和3.04倍能效提升,比先进的GPU(cuSPARSE)和Cambricon-X上的解决方案分别实现了2.78倍、1.48倍性能提升和35.62倍、1.17倍能效提升。

融合词性语义扩展信息的事件检测模型

事件检测是事件抽取中的关键步骤,依赖于触发词进行事件类型分类。现有主流事件检测方法在稀疏标记数据上性能较差,模型过度拟合密集标注的触发词,在稀疏标记的触发词或者未见过的触发词上容易失效。改进方法通常通过扩充更多训练实例来缓解这一问题,但扩充后的数据分布不平衡,存在内置偏差,仍然表现不佳。为此,建立一种融合词性语义扩展信息的事件检测模型。对词粒度扩展信息进行分析,在不增加训练实例的条件下缩小候选触发词的范围,并对候选触发词进行语义扩展,挖掘候选触发词的上下文中蕴含的丰富语义,缓解了标记数据稀疏造成模型训练不充分的情况。通过词性筛选模块寻找候选触发词并对其进行语义扩展挖掘词粒度语义信息,融合句子粒度语义信息提升语义表征的鲁棒性,最终利用Softmax分类器进行分类完成事件检测任务。实验结果表明,该模型在ACE2005和KBP2015数据集上的事件检测任务中的F1值分别达到79.5%和67.5%,有效提升了事件检测性能,并且在稀疏标记数据实验中的F1值达到78.5%,明显改善了标记数据稀疏带来的不良影响。

基于改进群稀疏正则化的稀疏角度图像重建

计算机断层扫描(Computer Tomography,CT)是临床医学中广泛使用的医学图像,可以清楚地显示人体的精细结构细节,为医生诊断疾病提供很大帮助。通过最近的研究表明,基于群稀疏正则化的联合代数重建技术(Simultaneous Algebraic Reconstruction Technique,SART)重建在稀疏角度采样背景下可以获得较好的性能。然而,群稀疏正则化在去掉伪影的同时,可能将边缘或细节过度平滑,使得对比度降低,无法获得符合人类视觉效果的高分辨率图像。因此,该文提出了一种基于改进群稀疏正则化的稀疏角度图像重建方法。首先对稀疏角度下的Shepp-Logan模型进行SART重建,再利用群稀疏正则化去除图像伪影,最后利用滚动引导滤波(Rolling Guided Filtering,RGF)进行对比度提升,再次作为SART的输入进行迭代。实验结果表明,该方法在视觉上以及PSNR(Peak Signal-to-Noise Ratio),MSE(Mean Squared Error)和FSIM(Feature Similarity)上均优于其他算法,并且在迭代初始阶段就具有较好的收敛性能。

基于EKF/SF的BDS短基线多径抑制方法

多径是影响载波相位差分定位性能的主要误差源。针对传统恒星日滤波(sidereal filter,SF)无法同时抑制系统部分和随机部分多径误差影响的问题,提出一种扩展卡尔曼滤波(extended Kalman filter,EKF)和SF组合的北斗卫星导航系统(BeiDou navigation satellite system,BDS)短基线多径误差抑制方法(EKF/SF)。首先使用基于单差观测量的SF削弱多径系统误差带来的影响,再结合EKF的优势,对残余多径误差所包含的随机误差影响进行抑制,从而达到最大化抑制多径误差的目的。BDS短基线单频载波相位差分定位实验表明,相对于单纯的SF和EKF,采用EKF/SF方法的模糊度固定率分别提高了10%和43%,定位精度可分别提高84%和90%。

基于稀疏约束的低复杂度可变分数时延滤波器

针对基于Farrow结构的可变分数时延(Variable fractional delay,VFD)滤波器需求解大量子滤波器系数这一关键问题,本文将稀疏约束理论引入滤波器的权系数优化中,研究具有稀疏系数的Farrow结构滤波器。在极大极小(Minimax)准则下,通过添加L1正则化约束项改进权系数优化模型,在系数(反)对称性基础上进一步增加系数的稀疏度。然后,采用交替方向乘子法(Alternating direction method of multipliers,ADMM)进行权系数迭代求解。仿真实验表明,本文提出的基于稀疏约束的VFD滤波器在保证高延迟精度的同时,乘法器和加法器分别减少了47.69%和58.60%,极大地降低了系统运算量以及复杂度。

基于图滤波与自表示的无监督特征选择算法

针对现有方法未考虑数据的高阶邻域信息而不能完全捕捉数据内在结构的问题,提出一种基于图滤波与自表示的无监督特征选择算法.首先,将高阶图滤波器应用于数据获得其平滑表示,并设计一个正则化器联合高阶图信息进行自表示矩阵学习以捕捉数据的内在结构;其次,应用l_(2,1)范数重建误差项和特征选择矩阵,以增强模型的鲁棒性与稀疏性选择判别的特征;最后,用一个迭代算法有效地求解所提出的目标函数,并进行仿真实验以验证该算法的有效性.

低照度宽视场视频中微小目标相关滤波跟踪方法

此前的相关滤波目标跟踪算法,关于低照度宽视场小目标跟踪的研究工作未见报道。针对此,提出一种将图像差异检测框架与基于相关滤波器(CF)的跟踪框架相结合的算法,并引入双重滤波器对抗环境带来的不利因素。提出用l2范数的稀疏响应正则化项来抑制CF框架产生的异常波峰。在响应阶段,根据双重滤波器加权融合,预测小目标的位置。结果表明,提出算法在低照度宽视场中对小目标的快速移动、形变、运动模糊有优异的跟踪性能,并且满足实时性能。采集了全新的具有41条由鹰眼摄像头拍摄的夜晚监控序列数据集作为基准。实验结果表明本算法在DP提升了8.8%,AUC提升了7.4%,并在单个CPU上实现30.6帧每秒的实时运行。