公开(公告)号：US07565369B2

公开(公告)日：2009-07-21

申请号：US10857030

申请日：2004-05-28

申请人： Wei Fan ,  Haixun Wang ,  Philip S. Yu

发明人： Wei Fan ,  Haixun Wang ,  Philip S. Yu

IPC分类号： G06F17/30

CPC分类号： G06N99/005 ,  Y10S707/99943 ,  Y10S707/99945

摘要： A general framework for mining concept-drifting data streams using weighted ensemble classifiers. An ensemble of classification models, such as C4.5, RIPPER, naive Bayesian, etc., is trained from sequential chunks of the data stream. The classifiers in the ensemble are judiciously weighted based on their expected classification accuracy on the test data under the time-evolving environment. Thus, the ensemble approach improves both the efficiency in learning the model and the accuracy in performing classification. An empirical study shows that the proposed methods have substantial advantage over single-classifier approaches in prediction accuracy, and the ensemble framework is effective for a variety of classification models.

摘要翻译： 采用加权综合分类器挖掘概念漂移数据流的一般框架。 分类模型的集合，例如C4.5，RIPPER，朴素贝叶斯等，是从数据流的连续块中训练出来的。 根据其在时间不断变化的环境下的测试数据的预期分类精度，合理地加权集合中的分类器。 因此，综合方法提高了学习模型的效率和执行分类的准确性。 实证研究表明，所提出的方法在预测精度方面具有优于单分类器方法的优势，并且整体框架对于各种分类模型是有效的。

公开(公告)号：US20060010093A1

公开(公告)日：2006-01-12

申请号：US10880913

申请日：2004-06-30

申请人： Wei Fan ,  Haixun Wang ,  Philip Yu

发明人： Wei Fan ,  Haixun Wang ,  Philip Yu

IPC分类号： G06F17/30

CPC分类号： G06F17/30017 ,  G06F2216/03 ,  Y10S707/99931 ,  Y10S707/99935

摘要： In connection with the mining of time-evolving data streams, a general framework that mines changes and reconstructs models from a data stream with unlabeled instances or a limited number of labeled instances. In particular, there are defined herein statistical profiling methods that extend a classification tree in order to guess the percentage of drifts in the data stream without any labelled data. Exact error can be estimated by actively sampling a small number of true labels. If the estimated error is significantly higher than empirical expectations, there preferably re-sampled a small number of true labels to reconstruct the decision tree from the leaf node level.

摘要翻译： 与挖掘时间不断变化的数据流有关的一般框架，即从具有未标记实例的数据流或有限数量的标记实例中挖掘变更和重建模型。 特别地，这里定义了扩展分类树的统计分析方法，以便在没有任何标记数据的情况下猜测数据流中漂移的百分比。 可以通过主动抽取少量真实标签来估计精确误差。 如果估计的误差明显高于经验期望值，则最好重新采样少量的真实标签，以从叶节点级别重建决策树。

公开(公告)号：US20050146708A1

公开(公告)日：2005-07-07

申请号：US10510858

申请日：2002-04-11

申请人： Xunqing Shi ,  Zhiping Wang ,  Jason Pickering ,  Wei Fan

发明人： Xunqing Shi ,  Zhiping Wang ,  Jason Pickering ,  Wei Fan

IPC分类号： G01B11/16 ,  G01N21/88 ,  G01R31/311 ,  G01L1/24

CPC分类号： G01B11/162 ,  G01N21/88 ,  G01R31/311

摘要： A system for the real-time and in-situ macro and micro measurement of in-plane deformations of a microelectronic package or the like comprises a closed environmental chamber (3) within which a test sample may be subjected to thermal cycle loading and/or humidity loading, an incoherent white light source (6) for illuminating the sample, a long-working-distance microscope (2) and image acquisition means (7) for capturing speckle patterns from the surface of the sample during loading, and a control (8) for automating the co-ordination of the various components and for analysing the speckle images using digital image speckle correlation.

摘要翻译： 用于微电子封装等的面内变形的实时和原位宏观和微观测量的系统包括封闭的环境室（3），其中测试样品可以经受热循环加载和/或 湿度加载，用于照射样品的非相干白光源（6），用于在加载期间从样品表面捕获散斑图案的长距离显微镜（2）和图像获取装置（7），以及控制 8），用于使各种组件的协调自动化并且使用数字图像散斑相关性来分析斑点图像。

公开(公告)号：US20140346378A1

公开(公告)日：2014-11-27

申请号：US13977480

申请日：2011-12-21

申请人： Chin Hock Kua ,  Zhenfeng Wang ,  Wei Fan ,  Cong Zhi Leon Chan ,  Zhiping Wang

发明人： Chin Hock Kua ,  Zhenfeng Wang ,  Wei Fan ,  Cong Zhi Leon Chan ,  Zhiping Wang

IPC分类号： F16K99/00

CPC分类号： F16K99/0015 ,  F16K99/0061 ,  F16K2099/0084

摘要： An improved microfluidic system with an improved microfluidic valve module is disclosed. The microfluidic system includes a microfluidic chip and one or more valve modules. The microfluidic chip has microfluidic channels and one or more cavities formed in the chip, each of the one or more cavities designed to receive one of the one or more valve modules. Each of the one or more valve modules includes a first layer, a control layer and one or more second layers. The first layer includes a deformable material. The control layer has a microfluidic control chamber formed in a portion of it. The control layer is also located adjoining the first layer and the deformable material of the first layer forms a deformable surface of the control chamber. The one or more second layers include an input microfluidic channel and an output microfluidic channel. The input microfluidic channel and the output microfluidic channel are fluidically coupled to the microfluidic control chamber, and fluid flow through the input microfluidic channel, the microfluidic control chamber and the output microfluidic channel is controlled in response to a force deforming the deformable material of the first layer at least a predetermined amount.

摘要翻译： 公开了具有改进的微流体阀模块的改进的微流体系统。 微流体系统包括微流体芯片和一个或多个阀模块。 微流体芯片具有微流体通道和在芯片中形成的一个或多个空腔，所述一个或多个空腔中的每一个被设计成容纳一个或多个阀模块中的一个。 一个或多个阀模块中的每一个包括第一层，控制层和一个或多个第二层。 第一层包括可变形材料。 控制层具有形成在其一部分中的微流控制室。 控制层也邻接第一层并且第一层的可变形材料形成控制室的可变形表面。 一个或多个第二层包括输入微流体通道和输出微流体通道。 输入微流体通道和输出微流体通道流体耦合到微流控制室，并且通过输入微流体通道，微流控制室和输出微流体通道的流体流动被响应于使第一 层至少预定量。

公开(公告)号：US20130151543A1

公开(公告)日：2013-06-13

申请号：US13316178

申请日：2011-12-09

申请人： Wei Fan ,  Jing Gao ,  Srinivasan Parthasarathy ,  Deepak Turaga

发明人： Wei Fan ,  Jing Gao ,  Srinivasan Parthasarathy ,  Deepak Turaga

IPC分类号： G06F17/30

CPC分类号： G06F17/30598 ,  G11B27/32

摘要： A horizontal anomaly detection method includes receiving at plurality of objects described in a plurality of information sources, wherein each individual information source captures a plurality of similarity relationships between the objects, combining the information sources to determine a similarity matrix whose entries represent quantitative scores of similarity between pairs of the objects, and identifying at least one horizontal anomaly of the objects within the similarity matrix, wherein the horizontal anomalies are anomalous relationships across the plurality of information sources.

摘要翻译： 水平异常检测方法包括在多个信息源中描述的多个对象处接收，其中每个单独的信息源捕获对象之间的多个相似关系，组合信息源以确定其条目表示相似度的定量分数的相似性矩阵 在所述对象之间，并且识别所述相似性矩阵内的对象的至少一个水平异常，其中所述水平异常是所述多个信息源之间的异常关系。

公开(公告)号：US08462516B2

公开(公告)日：2013-06-11

申请号：US12741582

申请日：2008-10-21

申请人： Chee Khuen Stephen Wong ,  Hock Lye John Pang ,  Wei Fan ,  Haijing Lu ,  Boon Keng Lok

发明人： Chee Khuen Stephen Wong ,  Hock Lye John Pang ,  Wei Fan ,  Haijing Lu ,  Boon Keng Lok

IPC分类号： H05K7/02 ,  H05K1/16 ,  H05K7/20 ,  H05K1/09 ,  B29C59/00

CPC分类号： H01L24/13 ,  B81C1/00095 ,  H01L24/11 ,  H01L24/16 ,  H01L24/81 ,  H01L25/0657 ,  H01L2224/05568 ,  H01L2224/05573 ,  H01L2224/056 ,  H01L2224/1147 ,  H01L2224/11474 ,  H01L2224/11902 ,  H01L2224/11903 ,  H01L2224/13012 ,  H01L2224/13013 ,  H01L2224/13014 ,  H01L2224/13015 ,  H01L2224/13017 ,  H01L2224/13018 ,  H01L2224/13019 ,  H01L2224/1308 ,  H01L2224/13082 ,  H01L2224/13144 ,  H01L2224/13147 ,  H01L2224/13155 ,  H01L2224/32145 ,  H01L2224/81193 ,  H01L2224/81203 ,  H01L2224/81801 ,  H01L2224/8182 ,  H01L2224/81894 ,  H01L2225/06517 ,  H01L2924/00013 ,  H01L2924/01005 ,  H01L2924/01006 ,  H01L2924/01022 ,  H01L2924/01024 ,  H01L2924/01029 ,  H01L2924/01033 ,  H01L2924/01074 ,  H01L2924/01076 ,  H01L2924/01078 ,  H01L2924/01079 ,  H01L2924/01082 ,  H01L2924/01327 ,  H01L2924/014 ,  H01L2924/09701 ,  H01L2924/10253 ,  H01L2924/15787 ,  H01L2924/30105 ,  H01L2924/30107 ,  H01L2924/3011 ,  Y10T29/49149 ,  H01L2924/00014 ,  H01L2224/13099 ,  H01L2224/29099 ,  H01L2924/00 ,  H01L2924/00012

摘要： An interconnect structure, an interconnect structure for interconnecting first and second components, an interconnect structure for interconnecting a multiple component stack and a substrate, and a method of fabricating an interconnect structure. The interconnect structure comprising a base portion formed on a mounting surface of a first component; a pillar portion extending from the base portion and substantially perpendicularly to the mounting surface; and a head portion formed on the pillar portion and having larger lateral dimensions than the pillar portion; wherein the base portion and the pillar portion are integrally formed of a homogeneous material.

摘要翻译： 互连结构，用于互连第一和第二组件的互连结构，用于互连多组分堆叠和衬底的互连结构，以及制造互连结构的方法。 所述互连结构包括形成在第一部件的安装表面上的基部; 从所述基部延伸并基本上垂直于所述安装表面的柱部; 以及头部，形成在所述柱部上并且具有比所述柱部更大的横向尺寸; 其中所述基部和所述柱部由均质材料一体地形成。

公开(公告)号：US07904397B2

公开(公告)日：2011-03-08

申请号：US12690502

申请日：2010-01-20

申请人： Wei Fan ,  Haixun Wang ,  Philip S. Yu

发明人： Wei Fan ,  Haixun Wang ,  Philip S. Yu

IPC分类号： G06F15/18 ,  G06N3/00 ,  G06N3/12

CPC分类号： G06N99/005

摘要： A method (and structure) for processing an inductive learning model for a dataset of examples, includes dividing the dataset of examples into a plurality of subsets of data and generating, using a processor on a computer, a learning model using examples of a first subset of data of the plurality of subsets of data. The learning model being generated for the first subset comprises an initial stage of an evolving aggregate learning model (ensemble model) for an entirety of the dataset, the ensemble model thereby providing an evolving estimated learning model for the entirety of the dataset if all the subsets were to be processed. The generating of the learning model using data from a subset includes calculating a value for at least one parameter that provides an objective indication of an adequacy of a current stage of the ensemble model.

摘要翻译： 一种用于处理实例的数据集的感应学习模型的方法（和结构），包括将示例的数据集划分成多个数据子集，并使用计算机上的处理器生成使用第一子集的示例的学习模型 的多个数据子集的数据。 为第一子集生成的学习模型包括用于整个数据集的演进聚合学习模型（集合模型）的初始阶段，从而为整个数据集提供演进的估计学习模型，如果所有子集 被处理。 使用来自子集的数据生成学习模型包括计算至少一个参数的值，所述参数提供对所述集合模型的当前阶段的充分性的客观指示。

公开(公告)号：US07565346B2

公开(公告)日：2009-07-21

申请号：US10858541

申请日：2004-05-31

申请人： Wei Fan ,  Haixun Wang ,  Philip S. Yu

发明人： Wei Fan ,  Haixun Wang ,  Philip S. Yu

IPC分类号： G06F17/30

CPC分类号： G06K9/6215 ,  Y10S707/99936

摘要： Unlike traditional clustering methods that focus on grouping objects with similar values on a set of dimensions, clustering by pattern similarity finds objects that exhibit a coherent pattern of rise and fall in subspaces. Pattern-based clustering extends the concept of traditional clustering and benefits a wide range of applications, including e-Commerce target marketing, bioinformatics (large scale scientific data analysis), and automatic computing (web usage analysis), etc. However, state-of-the-art pattern-based clustering methods (e.g., the pCluster algorithm) can only handle datasets of thousands of records, which makes them inappropriate for many real-life applications. Furthermore, besides the huge data volume, many data sets are also characterized by their sequentiality, for instance, customer purchase records and network event logs are usually modeled as data sequences. Hence, it becomes important to enable pattern-based clustering methods i) to handle large datasets, and ii) to discover pattern similarity embedded in data sequences. There is presented herein a novel method that offers this capability.

摘要翻译： 与传统的集群方法不同，传统的集群方法集中在对一组维度上具有类似值的对象进行分组，通过模式相似性进行聚类可以找到在子空间中呈现一致的上升和下降模式的对象。 基于模式的群集扩展了传统群集的概念，受益于广泛的应用，包括电子商务目标营销，生物信息学（大规模科学数据分析）和自动计算（Web使用分析）等。然而，状态 基于图案的聚类方法（例如，pCluster算法）只能处理数千条记录的数据集，这使得它们不适合许多现实生活中的应用。 此外，除了巨大的数据量之外，许多数据集的特征还在于它们的顺序性，例如，客户购买记录和网络事件日志通常被建模为数据序列。 因此，重要的是启用基于图案的聚类方法i）处理大数据集，以及ii）发现嵌入在数据序列中的模式相似性。 这里提供了一种提供这种能力的新颖方法。

公开(公告)号：US20060026110A1

公开(公告)日：2006-02-02

申请号：US10903336

申请日：2004-07-30

申请人： Wei Fan ,  Haixun Wang ,  Philip Yu

发明人： Wei Fan ,  Haixun Wang ,  Philip Yu

IPC分类号： G06F15/18

CPC分类号： G06N99/005 ,  Y10S707/99931

摘要： Most recent research of scalable inductive learning on very large streaming dataset focuses on eliminating memory constraints and reducing the number of sequential data scans. However, state-of-the-art algorithms still require multiple scans over the data set and use sophisticated control mechanisms and data structures. There is discussed herein a general inductive learning framework that scans the dataset exactly once. Then, there is proposed an extension based on Hoeffding's inequality that scans the dataset less than once. The proposed frameworks are applicable to a wide range of inductive learners.

摘要翻译： 对最大流式数据集的可伸缩归纳学习的最新研究着重于消除记忆限制并减少顺序数据扫描的次数。 然而，最先进的算法仍然需要对数据集进行多次扫描，并使用复杂的控制机制和数据结构。 这里讨论了一般的归纳学习框架，该框架一次扫描数据集。 然后，提出了一种基于Hoeffding不等式的扩展，可以扫描数据集不止一次。 提出的框架适用于广泛的归纳学习者。

公开(公告)号：US10347559B2

公开(公告)日：2019-07-09

申请号：US13049498

申请日：2011-03-16

申请人： Wei Fan ,  Xiang Liu ,  John Mariner

发明人： Wei Fan ,  Xiang Liu ,  John Mariner

IPC分类号： B32B9/00 ,  H01L23/373 ,  H01L23/36

摘要： A high thermal conductivity/low coefficient of thermal expansion thermally conductive composite material for heat sinks and an electronic apparatus comprising a heat sink formed from such composites. The thermally conductive composite comprises a high thermal conductivity layer disposed between two substrates having a low coefficient of thermal expansion. The substrates have a low coefficient of thermal expansion and a relatively high modulus of elasticity, and the composite exhibits high thermal conductivity and low coefficient of thermal expansion even for composites with high loadings of the thermally conductive material.