Improved SMB speckle filtering of polarimetric SAR data with synergistic use of orientation angle compensation and spatial majority rule

The scattering-model-based(SMB)speckle filtering for polarimetric SAR(Pol SAR)data is reasonably effective in preserving dominant scattering mechanisms.However,the efficiency strongly depends on the accuracies of both the decomposition and classification of the scattering properties.In addition,a relatively weak speckle reduction particularly in distributed media was reported in the related literatures.In this work,an improved SMB filtering strategy is proposed considering the aforementioned deficiencies.First,the orientation angle compensation is incorporated into the SMB filtering process to remedy the overestimation of the volume scattering contribution in the Freeman-Durden decomposition.In addition,an algorithm to select the homogenous pixels is developed based on the spatial majority rule for adaptive speckle reduction.We demonstrate the superiority of the proposed methods in terms of scattering property preservation and speckle noise reduction using L-band Pol SAR data sets of San Francisco that were acquired by the NASA/JPL airborne SAR(AIRSAR)system.

基于改进SPRINT分类算法的数据挖掘模型

为解决目前数据挖掘模型分类时间长、挖掘准确率不高的问题,提出基于改进决策树分类算法(SPRINT)的数据挖掘模型。先采用最大-最小规范化公式完成原始数据线性变换,利用改进后的SPRINT分类算法按照输入数据特性进行分类,使用协同过滤技术生成与数据相近的属性集,计算数据属性相似度,生成语义规则集,为用户提供更优的数据服务。选取某公司营销数据集作为样本进行对比实验,结果表明,与对比模型相比,所提出的数据挖掘模型分类时间更短,挖掘准确率更高,能为用户提供更优质的数据服务。

基于CNN和关联规则的协同过滤混合推荐

针对传统协同过滤算法在药品推荐领域中对用户评价过于依赖、数据稀疏性严重等问题,提出一种基于卷积神经网络(CNN)和关联规则的协同过滤混合推荐算法。首先利用CNN从药品文本数据中获取深层功效特征向量,然后使用Apriori算法发掘药品间的关联规则。在此基础上,从药品功效特征和关联性两个角度结合对应的相似度计算公式计算药品相似度,进而预测评分缺失值,最终对稀疏矩阵进行叠加填充实现药品推荐的优化。经试验对比,论文算法相比传统的协同过滤算法在MAE和RMSE指标上下降了3%~4%,在数据较稀疏的情况下具有良好的推荐效果。

Web3.0时代短视频产业版权过滤义务规则探析

Web3.0时代背景下,短视频平台凭借数字技术的发展已由简单服务中立者转变为内容服务辅助者。从规范角度检视,传统的“通知—删除”规则不仅成为平台滥用并逃避责任的借口,还因被动等待、事后保护的特征导致短视频产业发展同规则治理错位明显。因此,尝试引入内容过滤义务是解决该冲突的关键。通过深入对过滤义务规则进行正当性论证,建议不仅需引入事前过滤义务还应结合事后保护规则,形成产业保护链,充分发挥事前、事后双向保障之功效。最后,在借鉴欧盟立法的同时应立足我国实际,重新审视产业职责以营造数字营商环境。提出分层级过渡适用事前过滤方案,不仅施以“硬法”保护也加以“软法”塑造,以期发掘短视频产业治理的新路径。

基于Filter-Hook技术的防火墙软件设计与实现

为了解决网络安全问题,设计了一个基于Filter-Hook技术的防火墙软件,该软件能够根据数据包过滤规则实现防火墙的功能。实验结果显示,该防火墙软件有效地改善了网络的安全性能。

智能媒介内容过滤义务的理论基础与规范构造——以短视频平台为考察

算法推荐技术使传统避风港规则饱受质疑,影响着平台权责适配的逻辑起点。短视频平台对用户内容的推送无疑解决了信息过载问题,却也导致了现阶段用户权利的事前保护阙如和事后救济失范的局面。由此产生了实践上注意义务的扩张和学理上针对平台应然义务的争论。而施以平台过滤义务是解决该问题的关键。从侵权法的预防功能来看,过滤义务属于较高程度的注意义务,是民事注意义务内涵的延伸。同时,守门人理论是引入过滤义务正当性的支撑,具有缓解现行法对平台类型不足和过错归责解释受限的功能。有鉴于此,应以守门人理论为基础对平台的应然义务进行教义学的归位。通过对事前过滤机制的规范构造,增设或解释过滤义务条款,将过滤义务严格限缩于特定情形与用户申请两种模式;在构造时也应做好同避风港规则的相衔接和搭建错误过滤的救济程序,以期在私法上为“平台-用户”的权益分配提供新方案。

Cubature Kalman filters: Derivation and extension

This paper focuses on the cubature Kalman filters （CKFs） for the nonlinear dynamic systems with additive process and measurement noise. As is well known, the heart of the CKF is the third-degree spherical–radial cubature rule which makes it possible to compute the integrals encountered in nonlinear filtering problems. However, the rule not only requires computing the integration over an n-dimensional spherical region, but also combines the spherical cubature rule with the radial rule, thereby making it difficult to construct higher-degree CKFs. Moreover, the cubature formula used to construct the CKF has some drawbacks in computation. To address these issues, we present a more general class of the CKFs, which completely abandons the spherical–radial cubature rule. It can be shown that the conventional CKF is a special case of the proposed algorithm. The paper also includes a fifth-degree extension of the CKF. Two target tracking problems are used to verify the proposed algorithm. The results of both experiments demonstrate that the higher-degree CKF outperforms the conventional nonlinear filters in terms of accuracy.

Signal reconstruction in wireless sensor networks based on a cubature Kalman particle filter

For solving the issues of the signal reconstruction of nonlinear non-Gaussian signals in wireless sensor networks （WSNs）, a new signal reconstruction algorithm based on a cubature Kalman particle filter （CKPF） is proposed in this paper. We model the reconstruction signal first and then use the CKPF to estimate the signal. The CKPF uses a cubature Kalman filter （CKF） to generate the importance proposal distribution of the particle filter and integrates the latest observation, which can approximate the true posterior distribution better. It can improve the estimation accuracy. CKPF uses fewer cubature points than the unscented Kalman particle filter （UKPF） and has less computational overheads. Meanwhile, CKPF uses the square root of the error covariance for iterating and is more stable and accurate than the UKPF counterpart. Simulation results show that the algorithm can reconstruct the observed signals quickly and effectively, at the same time consuming less computational time and with more accuracy than the method based on UKPF.

Generalized cubature quadrature Kalman filters:derivations and extensions

A new Gaussian approximation nonlinear filter called generalized cubature quadrature Kalman filter (GCQKF) is introduced for nonlinear dynamic systems. Based on standard GCQKF, two extensions are developed, namely square root generalized cubature quadrature Kalman filter (SR-GCQKF) and iterated generalized cubature quadrature Kalman filter (I-GCQKF). In SR-GCQKF, the QR decomposition is exploited to alter the Cholesky decomposition and both predicted and filtered error covariances have been propagated in square root format to make sure the numerical stability. In I-GCQKF, the measurement update step is executed iteratively to make full use of the latest measurement and a new terminal criterion is adopted to guarantee the increase of likelihood. Detailed numerical experiments demonstrate the superior performance on both tracking stability and estimation accuracy of I-GCQKF and SR-GCQKF compared with GCQKF.

Adaptive “Cubature and Sigma Points” Kalman Filtering Applied to MEMS IMU/GNSS Data Fusion during Measurement Outlier

In this paper, adaptive sensor fusion INS/GNSS is proposed to solve specific problem of non linear time variant state space estimation with measurement outliers, different algorithms are used to solve this specific problem generally occurs in intentional and non-intentional interferences caused by other radio navigation sources, or by the GNSS receiver’s deterioration. Non linear approximation techniques such as Extended Kalman filter EKF, Sigma Point Kalman Filters such as UKF and CDKF are computed to estimate the navigation states for UAV flight control. Several comparisons are conduced and analyzed in order to compare the accuracy and the convergence of different approaches usually applied in navigation data fusion purposes. The last non linear filter algorithm developed is the Cubature Kalman Filter CKF which provides more accurate estimation with more stability in Tracking data fusion application. In this work, CKF is compared with SPKF and EKF in ideal conditions and during GNSS outliers supposed to occur during specific interval of time, innovation based adaptive approach is selected and used to modify the covariance calculation of the non linear filters performed in this paper. Interesting results are observed, discussed with real perspectives in navigation data fusion for real time applications. Three parallel modified algorithms are simulated and compared to non-adaptive forms according to Root Mean Square Error (RMSE) criteria.

海量大数据定向采样有差别挖掘算法仿真

在大数据中,不同类别之间可能存在数据分布不均衡的情况,即某些类别的数据样本数量远远少于其他类别。这种情况下,传统的采样方法无法正确反映所有类别的特征和差异。为提升大数据信息的应用性,文中研究海量大数据定向采样有差别挖掘算法。以网站统一资源定位器(URL)初始化为基础,在网络上抓取网页,采集网页的超文本标记语言(HTML)数据,提取定向数据的相关链接,并将其导入URL队列。根据网络搜索策略,实施相关的数据搜索和处理。完成数据搜索后,将自动进行下一网页的URL,继续进行海量大数据定向采样。结合模糊特征匹配与检测滤波方法实现大数据定向采样过程中的抗干扰处理。采用粗糙集算法实施挖掘,利用扩展差别矩阵对大数据决策表内的值实施约简,实现海量大数据的模式分类。实验结果显示,该算法数据采集过程中的丢包率基本控制在0.2%以下,具有较高的鲁棒性。

SCADA告警系统中智能化收敛策略的设计与实现

当前水电监控系统告警存在着重复相似告警数量过大、告警语义不清晰、无法反映深层次原因等问题,给安全运管带来了不利影响。本文首先简明分析了噪声冗余告警产生的原因,提出基于版面管理的告警折叠的处理方法,可有效降低重复告警对浏览器版面的视觉干扰和冲击;提出了基于动态过滤的信息索引方法,可提高告警信息查询的精度和效率;提出了基于逻辑规则引擎和基于状态的时序引擎的告警审计处理功能,可对原有数据进行智能化的提炼加工和屏蔽,不仅进一步减少滋扰告警数量,还可提高告警信息的表达效率,提升系统的智慧化水平。

基于Apriori算法的混合型数据频繁项集挖掘算法

由于混合型数据同时涉及离散型和连续型属性,导致计算复杂度较高,为此提出面向混合型数据的频繁项集挖掘算法,以提高计算效率。利用Apriori算法分析事务数据库内各项集之间相互关联关系,通过最小支持度计算结果制定关联度规则,生成无向图。建立邻接矩阵,并分析事务数据库内项集在邻接矩阵中的所处位置。将无向图内事务数据全部存储至邻接矩阵中,快速生成频繁1-项集、频繁2-项集;结合项集之间的连接操作,实现频繁项集的挖掘。引入滤波算法对不同存储链路中频繁项集的滤波处理,提高数据挖精准度。实验结果表明,所提方法在频繁项集的挖掘过程中,内存占用较小,频繁项集挖掘效率较高,对数据挖掘技术的发展具有重大意义。

基于自适应简化容积卡尔曼滤波的编队卫星相对导航

针对在星间相对导航中噪声的统计特性未知可能引起滤波估计精度下降甚至发散的问题,提出了一种自适应简化容积卡尔曼滤波(ASCKF)算法。将Sage-Husa自适应滤波与容积卡尔曼滤波(CKF)相结合,通过容积规则摆脱线性滤波的局限性。改进Sage-Husa噪声估计器以避免噪声方差在线估计可能出现的非正定现象,从而保证了滤波器对噪声统计变化的自适应能力。结合编队卫星运动模型的特点,用常规卡尔曼滤波(KF)的时间更新代替相应的容积变换过程,在不影响滤波器性能的前提下减少了运算量。仿真结果表明:在测量噪声统计特性未知的情况下,与CKF相比,该文算法对相对状态的估计精度提高了近25%,同时滤波器的稳定性也得到了提高。

基于分数阶小波与引导滤波的多聚焦图像融合方法

针对多聚焦图像融合中存在易丢失细节信息、图像边缘处产生伪影等问题,提出了一种基于离散分数阶小波变换(DFRWT)结合引导滤波的多聚焦图像融合新方法。首先,采用DFRWT将多聚焦源图像进行多尺度分解,得到低频部分与高频部分。其次,为了使图像信息有效地融合,根据小波模系数的能量在不同阶数下的分布特征,选取最适合分数阶阶数,在低频部分应用拉普拉斯能量并获得初始决策,再用引导滤波修正决策图得到融合规则;高频部分采用分数阶空间频率的融合规则。最后,通过DFRWT逆变换获得融合后的图像。新方法与现有5种算法进行视觉对比和定量评估,仿真实验表明,本文方法有效抑制了Gibbs效应和边缘处的伪影效应,视觉效果和客观评价均令人满意,融合图像的质量优于已有的几类经典算法。

欧盟《版权指令》强制过滤义务立法转化研究

2019年欧盟《数字化单一市场版权指令》第17条在制定阶段备受争议,转化过程十分艰难。以荷兰、德国及芬兰为例进行研究,发现:(1)第17条是转化《数字化单一市场版权指令》为国内法的重大障碍之一;(2)转化第17条的法律文本常伴随弹性条款;(3)成员国采用不同方案对第17条进行转化,加剧了欧盟内部的分化;(4)成员国在转化第17条时均不同程度地关注对用户自由的保障。中国应当持续关注《数字化单一市场版权指令》第17条的转化及实施,一方面鼓励权利人与服务提供者加强合作;另一方面重视用户自由的保障,结合自身现状完善版权领域服务提供者的侵权责任规则。

数字版权时代下短视频平台义务范围研究

【目的/意义】近年来,短视频版权侵权问题日益凸显。短视频平台义务范围的确定既是理论界和实务界争论的焦点,也是治理短视频侵权问题的关键着力点。【设计/方法】总结归纳理论界和实务界就短视频平台义务范围的争论焦点,并在此基础上对短视频平台的义务范围进行重新界定。【结论/发现】就主动审查义务,应要求平台运用版权过滤技术对用户上传的短视频进行主动筛查,但须就义务的履行方式、条件等进行调适以缓解技术的局限性和成本问题。就通知审核义务,应要求平台对通知内容进行实质性审查,对二创短视频的合理使用情形进行着重审查。就事后保障义务,应规定平台须采取必要措施防止重复侵权,并根据具体情形界定必要措施的范畴。

基于智能分发的课程系统推荐算法研究

介绍了主流的智能推荐算法,结合某线上学习平台课程现状,提出了基于课程标签关联规则、基于课程相似度协同过滤的两种推荐算法。基于两种算法的优点,构建了具有多路备选集的课程推荐系统,为每一类推荐方式赋值权重,可根据实际需要调整权重参数达到灵活召回推荐结果的目的。

基于知识推理和兴趣区域过滤的军事标图作业评判方法

军事标图是军队参谋人员一项重要的指挥技能训练内容。提出基于知识推理和兴趣区域过滤的标图评判方法,用于实现军事标图作业的自动化评判。阐述了知识推理的一般原理,以及针对标图要素的知识表示,分析基于Rete算法的知识推理网络运用;采用兴趣区域过滤的方式,提高评判精准度,阐述标图作业智能化评判的具体实现流程。通过在标图训练系统中的运用,证实了方法的有效性。