Improved Pattern Tree for Incremental Frequent-Pattern Mining

By analyzing the existing prefix-tree data structure, an improved pattern tree was introduced for processing new transactions. It firstly stored transactions in a lexicographic order tree and then restructured the tree by sorting each path in a frequency-descending order. While updating the improved pattern tree, there was no need to rescan the entire new database or reconstruct a new tree for incremental updating. A test was performed on synthetic dataset T1014D100K with 100 000 transactions and 870 items. Experimental results show that the smaller the minimum sup- port threshold, the faster the improved pattern tree achieves over CanTree for all datasets. As the minimum support threshold increased from 2% to 3.5%, the runtime decreased from 452.71 s to 186.26 s. Meanwhile, the runtime re- quired by CanTree decreased from 1 367.03 s to 432.19 s. When the database was updated, the execution time of im- proved pattern tree consisted of construction of original improved pattern trees and reconstruction of initial tree. The experiment results showed that the runtime was saved by about 15% compared with that of CanTree. As the number of transactions increased, the runtime of improved pattern tree was about 25% shorter than that of FP-tree. The improved pattern tree also required less memory than CanTree.

基于模式语义的非膨胀性Pattern Tree简化

近年来,XQuery逐渐成为XML查询语言的事实标准。PatternTree被广泛应用于XQuery查询处理。PatternTree用匹配方法处理查询,其本身的大小和复杂程度决定了匹配的效率。该文论述了利用模式语义简化PatternTree的规则。这种方法避免了因插入冗余节点而导致PatternTree的膨胀。三个判断冗余节点的规则不但可以判断叶节点的冗余,而且可以在保留叶节点的情况下,判断非叶节点的冗余。实验证明了方法的可行性和有效性。

Pattern Tree最小简单分解策略

PatternTree(PTQ)是复杂的树状结构,求解PTQ需要在XML文档集合中查找与之匹配的数据。在PTQ中,只有部分节点是需要输出的查询目标节点,其余节点则是中间结果。因此,如何在求解过程中尽量避免中间结果的产生,是XML查询优化面临的一个关键问题。论文提出了一种PTQ分解策略,能够根据不同查询操作的粒度,将PTQ分解为可用一种内部操作实现的最大片断集合。从而有效的限制中间结果的产生,提高查询效率。

Introducing tree neighbouring relationship factors in forest pattern spatial analysis:weighted Delaunay triangulation method

It is important to quantify and analyze forest spatial patterns for studying biological characteristics,population interaction and the relationship between the population and environment.In this study,the forest spatial structure unit was generated based on the Delaunay triangulation model(DTM),and the weights were generated using the comprehensive values of the tree diameter at breast height,total height and crown width.The distance between neighbors determined by the DTM was weighted to transform the original coordinates of trees into logical coordinates.Then,a weighted spatial pattern(WSP)was developed.After weighting,the neighboring trees were replaced,the replacement ratio was 38.3%,and there was 57.4%of the central tree.Correlation analysis showed that the uniform angle index of the WSP was significantly correlated with the tree size standard deviation under uniformity(r=0.932)and randomness(r=0.711).The DTM method not only considers the spatial distance between trees,but also considers the non-spatial attributes of trees.By changing the spatial topological relation between trees,this method further improves the spatial structure measurement of forest.

Generating IDS Attack Pattern Automatically Based on Attack Tree

Generating attack pattern automatically based on attack tree is studied. The extending definition of attack tree is proposed. And the algorithm of generating attack tree is presented. The method of generating attack pattern automatically based on attack tree is shown, which is tested by concrete attack instances. The results show that the algorithm is effective and efficient. In doing so, the efficiency of generating attack pattern is improved and the attack trees can be reused.

Study on Bush Tree Growth in XLPE Using 3D PD Patterns

Exploitation of equipment with cross linked polyethylene (XLPE ) insulation requires its condition monitoring and diagnostic. Traditionally diagnostics of insulation is carried out by means of partial discharge detection. However, such identification of a defect, for example, void, inclusion or treeing, does not say about its danger from a point of view of full insulation gap breakdown and insulation construction failure. For this purpose a 29 kV CN-CV cable sample is studied. The experiment is based on research for determination of the dependencies between PD characteristics in XLPE upon time and three dimension PD patterns of corresponding treeing. The investigations were carried out by means of electrical measurement of PD current and simultaneous optical recording of treeing image. The needleplane electrode is applied as the electrode. As a result, -q-n PD patterns which are used as the bases to bush tree initialization and growth can be obtained. Test results show that PD pattern recognition can be applied as a powerful tool for recognizing electrical tree initialization and growth. This can make a good basis for on-line condition monitoring of high voltage power cable.

A Tree Pattern Matching Algorithm for XML Queries with Structural Preferences

In the XML community, exact queries allow users to specify exactly what they want to check and/or retrieve in an XML document. When they are applied to a semi-structured document or to a document with an overly complex model, the lack or the ignorance of the explicit document model (DTD—Document Type Definition, Schema, etc.) increases the risk of obtaining an empty result set when the query is too specific, or, too large result set when it is too vague (e.g. it contains wildcards such as “*”). The reason is that in both cases, users write queries according to the document model they have in mind;this can be very far from the one that can actually be extracted from the document. Opposed to exact queries, preference queries are more flexible and can be relaxed to expand the search space during their evaluations. Indeed, during their evaluation, certain constraints (the preferences they contain) can be relaxed if necessary to avoid precisely empty results;moreover, the returned answers can be filtered to retain only the best ones. This paper presents an algorithm for evaluating such queries inspired by the TreeMatch algorithm proposed by Yao et al. for exact queries. In the proposed algorithm, the best answers are obtained by using an adaptation of the Skyline operator (defined in relational databases) in the context of documents (trees) to incrementally filter into the partial solutions set, those which satisfy the maximum of preferential constraints. The only restriction imposed on documents is No-Self-Containment.

Ethnographic Decision Tree Modeling of the Decision Criteria and Decision Patterns for Adult Married Women with Unexpected Pregnancies

Introduction: As far as adult and married women were concerned, when they occurred to “unplanned pregnancy”, they felt so surprised and concussive all the time. Besides, the unplanned pregnancy also affects the other members in the family system. Therefore, when married women have to face the choice: “birth” or “abortion”, they’ll consider lots of thoughts and different decision criteria and decision pattern under various influences on physician, mind, mental and society. The purpose of this study was to investigate the criteria considered and the decision patterns involved when adult married women decide whether to terminate or continue an unplanned pregnancy. Methods: The study uses the method—“Ethnographic Decision Tree Modeling” [1] to build model of the decision criteria and decision patterns involved when adult married women make a decision about their unplanned pregnancy. There are three process in the research method: “Pilot Study”—interview two groups, every group distinct 4 married adult women with unplanned pregnancies, which decide whether to terminate or continue an unplanned pregnancy, what is the items of decision characters affect to the choice: “birth” or “abortion”. “Building of the Model”, displays the importance in proper order of those items and build the modeling with these two groups of women. “Testing of the Model”: investigate the criteria considered and the decision patterns involved when adult married women decide whether to terminate or continue an unplanned pregnancy. The study interviewed 34 married adult women with 43 unplanned pregnancies totally. Results: The result of the study finds out 12 items of decision characters, including planning to get pregnant or not, stability of feelings for married partner, the points of view on life, was affected by mother, mother-in-law, an husband’s emphasis on male, the meanings of children, the financial burden, the plan an assignment of career and time, the past pregnant experiences, the status of raising children, the health of parents and fetus, the effect of living environment, and social and cultural vision. Besides, there are four decision patterns of married adult women with unplanned pregnancy are “receiving abortion positively”;“giving birth as long as getting pregnancy naturally”;“ the minds are hesitative and changeable”, and “being forced by important others.” Conclusion: By setting the decision model tree, we found several decision criteria and patterns, and possible modes actions to be taken, could offer to see the adult married women’s decision-making and struggles in mind about unplanned pregnancy.

基于FP-Tree的最大频繁项目集挖掘及更新算法

挖掘最大频繁项目集是多种数据挖掘应用中的关键问题,之前的很多研究都是采用Apriori类的候选项目集生成-检验方法.然而,候选项目集产生的代价是很高的,尤其是在存在大量强模式和/或长模式的时候.提出了一种快速的基于频繁模式树(FP-tree)的最大频繁项目集挖掘DMFIA(discover maximum frequent itemsets algorithm)及其更新算法UMFIA(update maximum frequent itemsets algorithm).算法UMFIA将充分利用以前的挖掘结果来减少在更新的数据库中发现新的最大频繁项目集的费用.

基于FP-tree和约束概念格的关联规则挖掘算法及应用研究

现有的基于频繁模式树FP-tree和概念格的规则挖掘算法在构造概念格时存在重复遍历FP-tree问题,在挖掘后件约束的规则时算法构造的概念格包含冗余结点。针对这两个问题,提出了通过遍历FP-tree生成候选概念格节点的策略,并根据候选概念格节点进一步构造规则约束条件下无冗余概念格。通过实际项目中大气腐蚀数据进行算法的应用,结果表明该算法比现有算法具有更高的挖掘效率且腐蚀规则结果对材料腐蚀现状研究具有重要指导价值。

基于FP-tree的最大频繁模式挖掘算法

在FP-tree结构的基础上提出了最大频繁模式挖掘算法FP-Max。算法FP-Max只需要两次数据库扫描,挖掘过程不会产生候选项集。实验表明,算法FP-Max在挖掘密集型数据集方面是高效的。

基于OWSFP-Tree的最大频繁项目集挖掘算法

为了解决FP-Max算法挖掘最大频繁项目集时递归生成条件模式树和超集检验的问题,提出了基于单向有序FP-Tree的NCFP-Max算法。该算法在挖掘过程中采用预剪枝策略减少挖掘结点,利用单向有序FP-Tree避免每次存储当前挖掘出的频繁项目集之前都需要超集检验,利用项目表格避免递归生成条件模式树减少时空资源。实验结果表明,在事务条数多、项的数量大的情况下,NCFP-Max算法的挖掘时间比FP-Max算法缩短了50%左右。

基于改进FP-tree的最大频繁项集挖掘算法

现有的最大频繁项集挖掘算法在挖掘过程中需要进行超集检测,基于FP-tree的算法需要递归的建立条件频繁模式树,挖掘效率不高。提出了一种基于改进FP-tree高效挖掘最大频繁项集的算法(MMFI)。该算法修改了FP-tree结构并采用NBN策略,在挖掘过程中既不需要进行超集检测也不需要递归的建立条件频繁模式树。算法分析和实验结果表明,该算法是一种有效、快速的算法。

基于FP-Tree的快速选择性集成算法

选择性集成通过选择部分基分类器参与集成,从而提高集成分类器的泛化能力,降低预测开销.但已有的选择性集成算法普遍耗时较长,将数据挖掘的技术应用于选择性集成,提出一种基于FP-Tree(frequent pattern tree)的快速选择性集成算法:CPM-EP(coverage based pattern mining for ensemble pruning).该算法将基分类器对校验样本集的分类结果组织成一个事务数据库,从而使选择性集成问题可转化为对事务数据集的处理问题.针对所有可能的集成分类器大小,CPM-EP算法首先得到一个精简的事务数据库,并创建一棵FP-Tree树保存其内容;然后,基于该FP-Tree获得相应大小的集成分类器.在获得的所有集成分类器中,对校验样本集预测精度最高的集成分类器即为算法的输出.实验结果表明,CPM-EP算法以很低的计算开销获得优越的泛化能力,其分类器选择时间约为GASEN的1/19以及Forward-Selection的1/8,其泛化能力显著优于参与比较的其他方法,而且产生的集成分类器具有较少的基分类器.

基于FP-tree的最大频繁项目集挖掘算法

最大频繁项目集挖掘是数据挖掘领域最重要的基本问题之一,在分析已有算法的基础上提出了FP-MMFI算法,它是对FP-growth算法在最大频繁项目集挖掘上的扩展。提出了频繁路径的概念,用它可以有效地对FP-tree进行压缩和缩小搜索空间,同时使用投影的方法对超集检测进行了优化,减少了项目匹配的次数。最后实验结果表明,该算法在性能上优于已有的同类算法。

针对XML流数据的复杂Twig Pattern查询处理

XML流数据处理在研究领域引起了研究者的广泛兴趣.针对XML流数据的、具有嵌套AND/OR谓词的复杂Twig Pattern查询处理,提出一种新方法.为了提高查询处理性能,将所有Twig Pattern合并为一个共享前缀的查询树,其中,AND/OR谓词被表示为单独的抽象语法树,因而能够以文档顺序、单遍地处理复杂Twig Pattern的匹配,并避免了YFilter中对嵌套谓词进行后置处理所产生的中间结果.实验结果表明,该方法能够有效改善Twig Pattern的处理性能,尤其是在处理大文档的情况下.基于已有的研究工作,讨论如何利用DTD(document type definition)的结构和约束信息优化Twig Pattern,即这种优化是在系统运行前进行的预处理.

基于FP-Tree的最大频繁项目集更新挖掘算法

发现最大频繁项目集是多种数据挖掘应用中的重要问题 .在应用中用户需要调整最小支持度 ,以发现更有用的最大频繁项目集 .为此提出了一种最大频繁项目集更新算法 (UMFPA) ,该算法通过对频繁模式树(FP Tree)中的频繁项目头表 (HTable)增加两个域 ,从而将减少在数据库不变而最小支持度变化的情况下的更新挖掘最大频繁项目集的费用 .实验结果表明 。

一种改进的基于FP-Tree的高效挖掘最大频繁项目集算法

为了解决最大频繁项目集算法DMFIA(discover maximum frequent itemsets algorithm)在挖掘候选项目集维数较大而最大频繁项目集维数较小的情况下产生大量候选项目集的问题,提出一种改进的基于FP-Tree(frequent pattern tree)的最大频繁项目集挖掘的FP-EMFIA算法;该算法在挖掘过程中根据项目头表,采用自上而下和自下而上的双向搜索策略,并通过条件模式基中的频繁项目和较小维数的非频繁项目集对候选项目集进行降维和剪枝,以减少候选项目集的数量,加速对候选集计数的操作。在经典数据集mushroom、chess和connect上的实验结果表明,FP-EMFIA算法在支持度较小时的时间效率优于DMFIA、IDMFIA(improved algorithm of DMFIA)和BDRFI(algorithm for mining frequent itemsets based on decreasing dimensionality reduction of frequent itemsets)算法的,说明FP-EMFIA算法在候选项目集维数较大时有相对优势。

关联规则中FP-tree的最大频繁模式非检验挖掘算法

基于FP-tree的最大频繁模式挖掘算法是目前较为高效的频繁模式挖掘算法,针对这些算法需要递归生成条件FP-tree、做超集检验等问题,在分析DMFIA-1算法的基础上,提出了最大频繁模式的非检验挖掘算法NCMFP。该算法改进了FP-tree的结构,使挖掘过程中不需要生成条件频繁模式树也不需要超集检验。算法采用的预测剪枝策略减少了挖掘的次数,采用的求取公共交集的方式保证了挖掘结果的完整性。实验结果表明在支持度相对较小情况下,NCMFP的效率是同类算法的2～5倍。

基于FP-tree的多层关联规则快速挖掘算法

研究了多层关联规则挖掘的理论和方法,提出了一种基于FP-tree的快速挖掘算法FAMML_FPT。该算法不仅实现了同层次关联规则的挖掘,也能实现跨层次关联规则的挖掘,其中引入了修补项、跨层修补项的概念,以便从低到高逐层建立FP-tree,有效减少了扫描数据库的次数,且不用产生大量的候选项集,提高了数据挖掘的效率。