公开(公告)号：US08659604B2

公开(公告)日：2014-02-25

申请号：US12568719

申请日：2009-09-29

Applicant: Charu C. Aggarwal

Inventor： Charu C. Aggarwal

IPC: G06T11/20

CPC classification number: G06F17/30572 ,  G06T11/206

Abstract: Mechanisms are provided for transforming an original graph data set into a representative form having a smaller number of dimensions that the original graph data set. The mechanisms generate a graph transformation basis structure based on an input graph data structure. The mechanisms further transform an original graph data set based on an intersection of the graph transformation basis structure and the input graph data structure to thereby generate a transformed graph data set data structure. The transformed graph data set data structure has a reduced dimensionality from that of the input graph data structure but represents characteristics of the original graph data set. Moreover, the mechanisms perform an application specific operation on the transformed graph data set data structure to generate an output of a closest similarity record in the transformed graph data set to a target component.

Abstract translation: 提供了用于将原始图形数据集变换为具有较小维数原始图形数据集的代表形式的机制。 该机制基于输入图形数据结构生成图形变换基础结构。 这些机制基于图形变换基础结构和输入图形数据结构的交点进一步变换原始图形数据集，从而生成变换图形数据集数据结构。 变换后的图形数据集数据结构具有与输入图形数据结构的维度相当的维度，但表示原始图形数据集的特征。 此外，机构对变换的图形数据集数据结构执行应用程序特定的操作，以在转换的图形数据集中产生最接近的相似度记录的输出到目标分量。

公开(公告)号：US08650213B2

公开(公告)日：2014-02-11

申请号：US11752708

申请日：2007-05-23

Applicant: Charu C. Aggarwal ,  Philip Shi-Lung Yu

Inventor： Charu C. Aggarwal ,  Philip Shi-Lung Yu

IPC: G06F7/00

CPC classification number: G06F17/30539 ,  G06F21/6245 ,  G06F2216/03 ,  Y10S707/99931 ,  Y10S707/99932

Abstract: Distributed privacy preserving data mining techniques are provided. A first entity of a plurality of entities in a distributed computing environment exchanges summary information with a second entity of the plurality of entities via a privacy-preserving data sharing protocol such that the privacy of the summary information is preserved, the summary information associated with an entity relating to data stored at the entity. The first entity may then mine data based on at least the summary information obtained from the second entity via the privacy-preserving data sharing protocol. The first entity may obtain, from the second entity via the privacy-preserving data sharing protocol, information relating to the number of transactions in which a particular itemset occurs and/or information relating to the number of transactions in which a particular rule is satisfied.

Abstract translation: 提供分布式隐私保护数据挖掘技术。 分布式计算环境中的多个实体的第一实体通过隐私保护数据共享协议与多个实体的第二实体交换摘要信息，使得保留摘要信息的隐私，与 与实体存储的数据相关的实体。 然后，第一实体可以至少基于通过隐私保护数据共享协议从第二实体获得的摘要信息来挖掘数据。 第一实体可以通过隐私保护数据共享协议从第二实体获得与特定项目集出现的交易数量有关的信息和/或与其中满足特定规则的交易数量有关的信息。

公开(公告)号：US08311959B2

公开(公告)日：2012-11-13

申请号：US13400863

申请日：2012-02-21

Applicant: Charu C Aggarwal ,  Philip S Yu

Inventor： Charu C Aggarwal ,  Philip S Yu

IPC: G06F15/18

CPC classification number: G06N99/005 ,  G06K9/6267

Abstract: An object and attributes that describe that object are identified. The attributes are grouped into attribute patterns, and classification classes are identified. For each identified class a sketch table containing a plurality of parallel hash tables is created. For the object to be classified, each attribute pattern is processed using the all of the hash functions for each sketch table, resulting in a plurality of values under each sketch table for a single attribute pattern. The lowest value is selected for each sketch table. The distribution of values across all sketch tables is evaluated for each attribute pattern, producing a discriminatory power for each attribute pattern. Attribute patterns having a discriminatory power above a given threshold are selected and added to the associated sketch table values. The sketch table with the largest overall sum is identified, and the associated class is assigned to the object belonging to the attribute patterns.

Abstract translation: 识别描述该对象的对象和属性。 这些属性被分组成属性模式，并且识别分类类。 对于每个识别的类，创建包含多个并行哈希表的草图表。 对于要分类的对象，使用每个草图表的所有散列函数处理每个属性模式，从而在单个属性模式的每个草图表下产生多个值。 为每个草图表选择最低值。 对每个属性模式评估所有草图表中的值的分布，为每个属性模式产生歧视性的权力。 选择具有高于给定阈值的辨别力的属性模式并将其添加到关联的草图表值。 识别具有最大总和的草图表，并将关联的类分配给属于属性模式的对象。

公开(公告)号：US20120269200A1

公开(公告)日：2012-10-25

申请号：US13091244

申请日：2011-04-21

Applicant: Charu C. Aggarwal

Inventor： Charu C. Aggarwal

IPC: H04L12/56

CPC classification number: H04L47/00

Abstract: Techniques for determining a shortest path in a disk-based network are provided. The techniques include creating a compressed representation of an underlying disk resident network graph, wherein creating a compressed representation of an underlying disk resident network graph comprises determining one or more dense regions in the disk resident graph and compacting the one or more dense regions into one or more compressed nodes, associating one or more node penalties with the one or more compressed nodes, wherein the one or more node penalties reflect a distance of a sub-path within a compressed node, and performing a query on the underlying disk resident network graph using the compressed representation and one or more node penalties to determine a shortest path in the disk-based network to reduce the number of accesses to a physical disk.

Abstract translation: 提供用于确定基于磁盘的网络中的最短路径的技术。 所述技术包括创建底层磁盘驻留网络图的压缩表示，其中创建底层磁盘驻留网络图的压缩表示包括确定磁盘驻留图中的一个或多个密集区域并将一个或多个密集区域压缩为一个或多个密集区域 更多的压缩节点将一个或多个节点惩罚与一个或多个压缩节点相关联，其中所述一个或多个节点惩罚反映了压缩节点内的子路径的距离，并且使用 压缩表示和一个或多个节点惩罚，以确定基于磁盘的网络中的最短路径，以减少对物理磁盘的访问次数。

公开(公告)号：US20120218908A1

公开(公告)日：2012-08-30

申请号：US13036083

申请日：2011-02-28

Applicant: Charu C. Aggarwal

Inventor： Charu C. Aggarwal

IPC: H04L12/26

CPC classification number: H04L51/32 ,  H04L51/14

Abstract: Techniques for optimizing steady state flow of a network are provided. The techniques include determining a first set of two or more nodes in a network, computing a steady-state flow probability of the first set of two or more nodes, and iteratively interchanging nodes from a second set of two or more nodes into the first set of two or more nodes to determine an optimum total steady state flow of the network, wherein determining an optimum total steady-state flow of the network comprises iteratively interchanging nodes until no additional improvements in steady-state flow over the computed steady-state flow probability can be obtained.

Abstract translation: 提供了优化网络稳态流的技术。 这些技术包括确定网络中的两个或更多个节点的第一组，计算第二组两个或多个节点的稳态流概率，以及将节点从第二组两个或多个节点迭代地交换到第一组中 以确定网络的最佳总稳态流，其中确定网络的最佳总稳态流包括迭代交换节点，直到在所计算的稳态流概率上没有对稳态流的额外改进 可以获得。

公开(公告)号：US20110074786A1

公开(公告)日：2011-03-31

申请号：US12568719

申请日：2009-09-29

Applicant: Charu C. Aggarwal

Inventor： Charu C. Aggarwal

IPC: G06T11/20

CPC classification number: G06F17/30572 ,  G06T11/206

Abstract: Mechanisms are provided for transforming an original graph data set into a representative form having a smaller number of dimensions that the original graph data set. The mechanisms generate a graph transformation basis structure based on an input graph data structure. The mechanisms further transform an original graph data set based on an intersection of the graph transformation basis structure and the input graph data structure to thereby generate a transformed graph data set data structure. The transformed graph data set data structure has a reduced dimensionality from that of the input graph data structure but represents characteristics of the original graph data set. Moreover, the mechanisms perform an application specific operation on the transformed graph data set data structure to generate an output of a closest similarity record in the transformed graph data set to a target component.

Abstract translation: 提供了用于将原始图形数据集变换为具有较小维数原始图形数据集的代表形式的机制。 该机制基于输入图形数据结构生成图形变换基础结构。 这些机制基于图形变换基础结构和输入图形数据结构的交点进一步变换原始图形数据集，从而生成变换图形数据集数据结构。 变换后的图形数据集数据结构具有与输入图形数据结构的维度相当的维度，但表示原始图形数据集的特征。 此外，机构对变换的图形数据集数据结构执行应用程序特定的操作，以在转换的图形数据集中产生最接近的相似度记录的输出到目标分量。

公开(公告)号：US07890510B2

公开(公告)日：2011-02-15

申请号：US11243727

申请日：2005-10-05

Applicant: Charu C. Aggarwal ,  Philip Shi-Lung Yu

Inventor： Charu C. Aggarwal ,  Philip Shi-Lung Yu

IPC: G06F7/00 ,  G06N5/00

CPC classification number: G06Q10/00

Abstract: Improved techniques are disclosed for detecting patterns of interaction among a set of entities and analyzing community evolution in a stream environment. By way of example, a technique for processing data from a data stream includes the following steps/operations. A data point of the data stream representing an interaction event is obtained. An interaction graph is updated on-line based on the data point representing the interaction event. The updated interaction graph is stored in a nonvolatile memory. An interaction evolution is determined off-line from the updated interaction graph stored in the nonvolatile memory.

Abstract translation: 公开了用于检测一组实体之间的交互模式并分析流环境中的社区进化的改进的技术。 作为示例，用于从数据流处理数据的技术包括以下步骤/操作。 获得表示交互事件的数据流的数据点。 基于表示交互事件的数据点，在线更新交互图。 更新的交互图存储在非易失性存储器中。 从存储在非易失性存储器中的更新的交互图中离线确定交互演进。

公开(公告)号：US07739284B2

公开(公告)日：2010-06-15

申请号：US11110079

申请日：2005-04-20

Applicant: Charu C. Aggarwal ,  Philip Shi-Lung Yu

Inventor： Charu C. Aggarwal ,  Philip Shi-Lung Yu

IPC: G06F7/00

CPC classification number: G06F17/30592 ,  G06F17/30516 ,  G06F17/30539 ,  G06K9/6221

Abstract: A technique for processing a data stream includes the following steps/operations. A cluster structure representing one or more clusters in the data stream is maintained. A set of projected dimensions is determined for each of the one or more clusters using data points in the cluster structure. Assignments are determined for incoming data points of the data stream to the one or more clusters using distances associated with each set of projected dimensions for each of the one or more clusters. Further, the cluster structure maybe used for classification of data in the data stream.

Abstract translation: 一种用于处理数据流的技术包括以下步骤/操作。 保持表示数据流中的一个或多个簇的簇结构。 使用集群结构中的数据点为一个或多个集群中的每一个确定一组投影尺寸。 使用与每个一个或多个聚类的每一组的每个投影维度相关联的距离来确定数据流的输入数据点到一个或多个聚类的分配。 此外，集群结构可以用于数据流中的数据分类。

公开(公告)号：US07716154B2

公开(公告)日：2010-05-11

申请号：US11841221

申请日：2007-08-20

Applicant: Charu C. Aggarwal ,  Philip Shi-Lung Yu

Inventor： Charu C. Aggarwal ,  Philip Shi-Lung Yu

IPC: G06N5/00

CPC classification number: G06K9/6282 ,  G06F17/3061 ,  G06F2216/03 ,  Y10S707/99936

Abstract: Methods and apparatus are provided for generating a decision trees using linear discriminant analysis and implementing such a decision tree in the classification (also referred to as categorization) of data. The data is preferably in the form of multidimensional objects, e.g., data records including feature variables and class variables in a decision tree generation mode, and data records including only feature variables in a decision tree traversal mode. Such an inventive approach, for example, creates more effective supervised classification systems. In general, the present invention comprises splitting a decision tree, recursively, such that the greatest amount of separation among the class values of the training data is achieved. This is accomplished by finding effective combinations of variables in order to recursively split the training data and create the decision tree. The decision tree is then used to classify input testing data.

Abstract translation: 提供了用于使用线性判别分析生成决策树并且在分类（也称为分类））中实现这样的决策树的方法和装置。 数据优选地以多维对象的形式，例如包括决策树生成模式中的特征变量和类变量的数据记录，以及仅包括决策树遍历模式中的特征变量的数据记录。 例如，这种创造性的方法创建更有效的监督分类系统。 通常，本发明包括分解决策树，递归地分割，使得实现训练数据的类值之间的最大分离量。 这是通过找到变量的有效组合来实现的，以便递归地分割训练数据并创建决策树。 然后使用决策树对输入测试数据进行分类。

公开(公告)号：US07487167B2

公开(公告)日：2009-02-03

申请号：US11756227

申请日：2007-05-31

Applicant: Charu C. Aggarwal ,  Philip Shi-Lung Yu

Inventor： Charu C. Aggarwal ,  Philip Shi-Lung Yu

IPC: G06F7/00

CPC classification number: G06F17/30516 ,  G06F17/30598 ,  Y10S707/99942 ,  Y10S707/99943

Abstract: A technique for classifying data from a test data stream is provided. A stream of training data having class labels is received. One or more class-specific clusters of the training data are determined and stored. At least one test instance of the test data stream is classified using the one or more class-specific clusters.

Abstract translation: 提供了一种从测试数据流中分类数据的技术。 接收具有类标签的训练数据流。 确定并存储训练数据的一个或多个类特定的簇。 测试数据流的至少一个测试实例使用一个或多个类特定簇进行分类。