A Non-Parametric Scheme for Identifying Data Characteristic Based on Curve Similarity Matching

For accurately identifying the distribution charac-teristic of Gaussian-like noises in unmanned aerial vehicle(UAV)state estimation,this paper proposes a non-parametric scheme based on curve similarity matching.In the framework of the pro-posed scheme,a Parzen window(kernel density estimation,KDE)method on sliding window technology is applied for roughly esti-mating the sample probability density,a precise data probability density function(PDF)model is constructed with the least square method on K-fold cross validation,and the testing result based on evaluation method is obtained based on some data characteristic analyses of curve shape,abruptness and symmetry.Some com-parison simulations with classical methods and UAV flight exper-iment shows that the proposed scheme has higher recognition accuracy than classical methods for some kinds of Gaussian-like data,which provides better reference for the design of Kalman filter(KF)in complex water environment.

Similarity matching method of power distribution system operating data based on neural information retrieval

Operation control of power systems has become challenging with an increase in the scale and complexity of power distribution systems and extensive access to renewable energy.Therefore,improvement of the ability of data-driven operation management,intelligent analysis,and mining is urgently required.To investigate and explore similar regularities of the historical operating section of the power distribution system and assist the power grid in obtaining high-value historical operation,maintenance experience,and knowledge by rule and line,a neural information retrieval model with an attention mechanism is proposed based on graph data computing technology.Based on the processing flow of the operating data of the power distribution system,a technical framework of neural information retrieval is established.Combined with the natural graph characteristics of the power distribution system,a unified graph data structure and a data fusion method of data access,data complement,and multi-source data are constructed.Further,a graph node feature-embedding representation learning algorithm and a neural information retrieval algorithm model are constructed.The neural information retrieval algorithm model is trained and tested using the generated graph node feature representation vector set.The model is verified on the operating section of the power distribution system of a provincial grid area.The results show that the proposed method demonstrates high accuracy in the similarity matching of historical operation characteristics and effectively supports intelligent fault diagnosis and elimination in power distribution systems.

Outliers rejection in similar image matching

Background Image matching is crucial in numerous computer vision tasks such as 3D reconstruction and simultaneous visual localization and mapping.The accuracy of the matching significantly impacted subsequent studies.Because of their local similarity,when image pairs contain comparable patterns but feature pairs are positioned differently,incorrect recognition can occur as global motion consistency is disregarded.Methods This study proposes an image-matching filtering algorithm based on global motion consistency.It can be used as a subsequent matching filter for the initial matching results generated by other matching algorithms based on the principle of motion smoothness.A particular matching algorithm can first be used to perform the initial matching;then,the rotation and movement information of the global feature vectors are combined to effectively identify outlier matches.The principle is that if the matching result is accurate,the feature vectors formed by any matched point should have similar rotation angles and moving distances.Thus,global motion direction and global motion distance consistencies were used to reject outliers caused by similar patterns in different locations.Results Four datasets were used to test the effectiveness of the proposed method.Three datasets with similar patterns in different locations were used to test the results for similar images that could easily be incorrectly matched by other algorithms,and one commonly used dataset was used to test the results for the general image-matching problem.The experimental results suggest that the proposed method is more accurate than other state-of-the-art algorithms in identifying mismatches in the initial matching set.Conclusions The proposed outlier rejection matching method can significantly improve the matching accuracy for similar images with locally similar feature pairs in different locations and can provide more accurate matching results for subsequent computer vision tasks.

A Portfolio Selection Method Based on Pattern Matching with Dual Information of Direction and Distance

Pattern matching method is one of the classic classifications of existing online portfolio selection strategies. This article aims to study the key aspects of this method—measurement of similarity and selection of similarity sets, and proposes a Portfolio Selection Method based on Pattern Matching with Dual Information of Direction and Distance (PMDI). By studying different combination methods of indicators such as Euclidean distance, Chebyshev distance, and correlation coefficient, important information such as direction and distance in stock historical price information is extracted, thereby filtering out the similarity set required for pattern matching based investment portfolio selection algorithms. A large number of experiments conducted on two datasets of real stock markets have shown that PMDI outperforms other algorithms in balancing income and risk. Therefore, it is suitable for the financial environment in the real world.

A Novel Mathematical Model for Similarity Search in Pattern Matching Algorithms

Modern applications require large databases to be searched for regions that are similar to a given pattern. The DNA sequence analysis, speech and text recognition, artificial intelligence, Internet of Things, and many other applications highly depend on pattern matching or similarity searches. In this paper, we discuss some of the string matching solutions developed in the past. Then, we present a novel mathematical model to search for a given pattern and it’s near approximates in the text.

AN IMPROVED HYBRID SEMANTIC MATCHING ALGORITHM WITH LEXICAL SIMILARITY

In this paper, we proposed an improved hybrid semantic matching algorithm combining Input/Output (I/O) semantic matching with text lexical similarity to overcome the disadvantage that the existing semantic matching algorithms were unable to distinguish those services with the same I/O by only performing I/O based service signature matching in semantic web service discovery techniques. The improved algorithm consists of two steps, the first is logic based I/O concept ontology matching, through which the candidate service set is obtained and the second is the service name matching with lexical similarity against the candidate service set, through which the final precise matching result is concluded. Using Ontology Web Language for Services (OWL-S) test collection, we tested our hybrid algorithm and compared it with OWL-S Matchmaker-X (OWLS-MX), the experimental results have shown that the proposed algorithm could pick out the most suitable advertised service corresponding to user's request from very similar ones and provide better matching precision and efficiency than OWLS-MX.

Research on Vector Road Data Matching Method Based on Deep Learning

Most of the existing vector data matching methods use traditional feature geometry attribute features to match, however, many of the similarity indicators are not suitable for cross-scale data, resulting in less accuracy in identifying objects. In order to solve this problem effectively, a deep learning model for vector road data matching is proposed based on siamese neural network and VGG16 convolutional neural network, and matching experiments are carried out. Experimental results show that the proposed vector road data matching model can achieve an accuracy of more than 90% under certain data support and threshold conditions.

考虑关联波段特性的光谱相似图像分类方法

光谱相似图像分类性能过差会增加光谱信息冗余度,降低地物勘探与军事防御等多种领域的光谱探测效率。为了多元素匀质区分光谱信息与光谱曲线,提出考虑关联波段特性的光谱相似图像分类方法。该方法首先利用光谱匹配消除光谱相似图像白色光源过曝现象。然后提取优化图像的关联波段,并将其作为聚类特征输入支持向量机中。最后根据支持向量机的输出结果,实现光谱相似图像分类。实验结果表明,所提方法分类结果清晰度较高,分类误差或像素块填色错误小,混淆矩阵中同行同列矩形块的分类精度较高。

Measuring Musical Rhythm Similarity: Further Experiments with the Many-to-Many Minimum-Weight Matching Distance

Musical rhythms are represented as sequences of symbols. The sequences may be composed of binary symbols denoting either silent or monophonic sounded pulses, or ternary symbols denoting silent pulses and two types of sounded pulses made up of low-pitched (dum) and high-pitched (tak) sounds. Experiments are described that compare the effectiveness of the many-to-many minimum-weight matching between two sequences to serve as a measure of similarity that correlates well with human judgements of rhythm similarity. This measure is also compared to the often used edit distance and to the one-to-one minimum-weight matching. New results are reported from experiments performed with three widely different datasets of real- world and artificially generated musical rhythms (including Afro-Cuban rhythms), and compared with results previously reported with a dataset of Middle Eastern dum-tak rhythms.

基于双前沿面数据包络分析的云制造服务功能匹配

针对云制造环境下功能匹配过程中属性权重需提前确定,进而影响匹配精度的问题,提出了一种基于本体相似度的双前沿面数据包络分析(DEA)匹配方法,该方法根据总体几何平均相似度进行服务排序,并自动生成属性权重。首先,为了提高匹配效率,从基本信息、类型、状态及功能四方面对云制造服务与需求进行描述;然后,引入信息量并改进相似度计算方法,提出基于概念语义距离、信息量和概念层次顺序的本体概念综合语义相似度计算方法;在此基础上,运用双前沿面DEA模型衡量总体效率,以此进行服务排序;最后通过算例证明了该方法的可行性。所提方法为改善云制造服务功能匹配效果提供了参考。

联合高阶目标感知与相似匹配的目标跟踪算法

视觉目标跟踪算法利用自注意力机制增强上下文联系,但面对复杂场景时,自注意力机制中的相关性易发生失配,为此提出一种联合高阶目标感知与相似匹配的目标跟踪算法。构建高阶目标感知模型,针对自注意力机制中的一阶自注意图,利用坍塌的极化过滤方式进行空间和通道维度的正交化建模,优化内部相关性;同时组合非线性拟合函数避免坍塌引起的信息损失,进而获得高阶自注意图,捕获具有高阶上下文信息的感知特征。通过不同维度分解目标的感知特征来细化匹配区域,抑制背景噪声并约束当前帧的响应图,提高网络的判别力。在OTB100和UAV123基准的实验结果表明,所提算法有更好的跟踪性能,可以有效应对相似干扰等问题。

基于文本摘要的无监督关键词抽取方法

为克服基于嵌入的关键词抽取方法在长文档上性能下降的问题,提出一种基于文本摘要的方法(summarization-based document embedding rank,SDERank)。将句向量的加权和作为文档嵌入,根据每个句子与文档主题的语义相关度赋予权重。以往基于嵌入的方法选择关键词时忽略候选词之间的关联,针对该问题,在SDERank的改进版SDERank+中,PageRank算法被用于提取候选词之间的共现权重作为相似度分数的修正。实验结果表明,在4个广泛使用的数据集上SDERank和SDERank+比之前最好的模型MDERank的F1分数平均高出2.2%和3.29%。

基于地震波波形相似的薄互层识别方法

随着油田勘探开发程度的深入,目标储层大都具有薄、小、深、碎的特点,高精度薄互层识别成为储层预测的热点和重点。目前常用的时频分析方法和谱分解技术受限于地震数据,无法满足薄互层精确刻画的要求;高分辨率反演方法也因地球物理反演的非线性特征导致结果存在多解性。为此,提出基于地震波波形相似的薄互层识别方法:首先采用波形库思想,构建井旁道—测井敏感曲线波形库;之后利用改进Manhattan距离联合线性相关系数法计算波形相似度,进行波形匹配;最后将波形相似度作为唯一驱动,建立地震数据与高分辨率测井数据间的数学联系,最终得到高分辨率处理剖面。该方法充分利用了地震、测井数据分别具有的横向和纵向高分辨率优势,能够有效识别薄互层目标,极大地降低了反演结果的多解性。模型试算验证了方法的可行性;实际资料处理结果表明该方法显著提高了纵向分辨率,对调谐尺度内的薄互层识别提供了技术支撑。

基于Mult-TWDTW算法的时序SAR图像土地覆盖分类

合成孔径雷达(SAR)图像为土地覆盖分类提供了重要的时序数据源.现有的时间序列匹配算法可以充分挖掘时序特征的相似性信息,从而获得较好的分类效果.本文引入了综合考虑形状相似性和物候差异的经典时序匹配算法TWDTW (time weighted dynamic time warping)指导SAR土地覆盖分类,并针对传统TWDTW仅考虑单一特征时间序列上的相似性匹配问题,提出了一种基于多特征联合的时间加权动态时间规整算法(Mult-TWDTW).该方法首先提取后向散射系数、干涉相干性以及双极化雷达植被指数(dual polarization radar vegetation Index,DpRVI)这3种特征,然后在TWDTW算法基础上联合多个特征设计了Mult-TWDTW模型.为验证所提方法的有效性,使用Sentinel-1A时序数据在丹江口区域完成土地覆盖分类,并将Mult-TWDTW与MLP、1D-CNN、Kmeans、SVM和使用单特征的TWDTW算法进行对比.实验结果显示,Mult-TWDTW算法得到了最好的分类效果,总体精度和Kappa系数可以达到95.09%和91.76,表明Mult-TWDTW算法有效联合了多个特征信息,能够提升时序匹配算法在多种土地覆盖类别分类中的潜力.

面向借贷案件的相似案例匹配模型

相似案例匹配任务是文本匹配在司法领域的具体应用之一,目的在于区分法律文书是否相似,对类案检索具有重要意义。与传统文本匹配任务相比,法律文本通常篇幅较长,同时相似案例匹配是针对相同案由案件的匹配,案情文本之间的差异较小,以往的文本匹配方法很难计算文本相似度。针对借贷案件文本匹配存在的问题,建立一种融合借贷案件关键要素的相似案例匹配模型。为了获取文本中更丰富的语义特征,构建正则表达式获得借贷案件的特定案件要素,如借款交付形式、借款人基本属性等,并与原有的案情文本相结合,联合学习法律文本与案件关键要素的语义特征。同时,利用共享权重的预训练模型分别对不同的文书进行编码,并且对预训练模型特定编码层的输出进行融合,得到更加丰富的语义信息。引入有监督对比学习框架,更好地利用样本信息,进一步提高相似案例匹配的性能。在CAIL2019-SCM数据集上的实验结果表明,与LFESM模型相比,该模型在测试集上的准确率提高了1.05个百分点。

短期光伏功率模糊Elman-DIOC神经网络预测分析

为了提高短期光伏功率预测效率,设计了一种基于Elman神经网络的短期光伏功率预测方法。在确定网络结构与各项参数的基础上实现准确预测,该方法受到训练后表现出很高的准确率和合理性。研究结果表明:类簇数据表达到了较大相似度,类簇间数据表现出了明显差异特征。采用优化方法开展发电功率预测,建立预测值和实测值的关系,预测日达到了与实测值相近的预测结果,采用优化聚类算法获得了更精确预测结果。通过该算法优化后,预测误差均值明显下降,IMSE均值下降幅度约80%,获得更有效的聚类结果,采用优化聚类处理可以促进短期预测精度的有效提升。该研究可以拓宽到其它的同类领域中,具有很好的实际推广价值。

基于时空金字塔匹配的轨迹相似度算法

轨迹相似性度量是轨迹数据挖掘的基础问题。受设备型号、信号强度和周围环境的影响,轨迹数据具有噪声大、数据量大、采样不均匀等特征,给轨迹相似性度量带来了极大的挑战。因此,提出了基于时空金字塔匹配的轨迹相似度算法,通过在时间和空间维度上对轨迹进行不同粒度的划分,然后利用不同粒度的权重组合来衡量轨迹之间的相似性。该算法能够有效克服轨迹噪声的影响,同时兼顾了轨迹的时间特性和空间特性,并具有较低的计算复杂度。最后,利用真实的信令数据集和人工合成的全球定位系统数据集进行实验,实验结果证明了该算法在准确率和计算复杂度方面都优于目前的主流算法。

基于可微池化的层级图相似性学习

目前,大多数关于图相似性学习的工作仅考虑图级匹配或节点级匹配,忽略了多层级的粗图级匹配,为解决该问题提出一种可微池化层级图匹配网络(PHMN)模型。逐层将图的节点表示进行软聚类进而将源图转化为尺寸缩小的粗图;在图对上使用多角度多层级的跨图匹配层,获取匹配矩阵;由注意力机制将图对匹配矩阵转化为匹配向量后,传入LSTM模型和多层感知机进行相似度预测。该模型在图回归任务和图分类任务的对比实验中,分别取得8项最优表现和6项最优表现。

基于正则表达式和Jaccard系数的智能变电站录波通道同源匹配

针对220kV及以上电压等级智能变电站双套录波通道同源匹配问题,提出一种基于正则表达式和Jaccard系数的智能变电站录波通道同源匹配方法。首先,针对录波通道命名不规范的问题,使用正则表达式对通道名称文本进行预处理,统一通道名称的表达形式;同时,使用jieba分词算法和去停用词操作,去除通道名称文本中可能存在的冗余信息。然后,使用Jaccard相似系数匹配算法计算录波通道名称文本之间的相似度,依据相似度大小筛选出同源通道。最后,基于电网实际的录波文件数据进行仿真分析。仿真结果表明:所提方法可有效实现智能变电站录波通道同源匹配。

基于卷积神经网络的分形图像编码研究

为了解决图像压缩时间较长的问题,提出了一种基于卷积神经网络的分形图像编码方法。方法将分形图像编码中的Range块和Domain块进行相似度分类,通过采用卷积神经网络来设计新的图像块分类方法,实现编码过程中的并行化图像块分类,编码时每个类在各自类别中进行搜索,减少一些不必要的匹配过程,以此达到减少图像块匹配的计算量,减少图像压缩的时间。实验结果表明,上述方法的图像还原质量更高,且图像压缩编码时间较短,说明其具有较高的应用价值。