公开(公告)号：US07755509B2

公开(公告)日：2010-07-13

申请号：US11869372

申请日：2007-10-09

Applicant: Dmitriy Bespalov ,  Ali Shokoufandeh

Inventor： Dmitriy Bespalov ,  Ali Shokoufandeh

IPC: G08G1/09

CPC classification number: G08G1/0104

Abstract: Actual traffic conditions of a roadway segment are predicted by providing a plurality of historical roadway condition patterns of the roadway segment in a database, obtaining an electronic representation of a current roadway condition pattern of the roadway segment, identifying one or more of the historical roadway condition patterns that closely matches the current roadway condition pattern, and predicting the future actual traffic conditions of the roadway segment by using the conditions associated with the one or more identified historical patterns.

Abstract translation: 通过在数据库中提供道路段的多个历史道路条件模式来预测道路段的实际交通状况，获得道路段的当前道路状况模式的电子表示，识别历史道路状况中的一个或多个 与当前道路条件模式紧密匹配的模式，以及通过使用与一个或多个所识别的历史模式相关联的条件来预测道路段的未来实际交通状况。

公开(公告)号：US08972192B2

公开(公告)日：2015-03-03

申请号：US11860918

申请日：2007-09-25

Applicant: Dmitriy Bespalov ,  James F. Carroll ,  Dean Zimmerman

Inventor： Dmitriy Bespalov ,  James F. Carroll ,  Dean Zimmerman

IPC: G01V15/00 ,  G08G1/01

CPC classification number: G08G1/0125 ,  G06F17/30241 ,  G08G1/0104 ,  G08G1/0129

Abstract: Actual conditions of a roadway segment are estimated by providing roadway condition data to a processor for the roadway segment from a plurality of different types of sources of the roadway condition data, assigning a quality to each of the plurality of different types of sources of the roadway condition data, and estimating in the processor the actual conditions of the roadway segment by using the roadway condition data and the quality of each of the plurality of different types of sources of the roadway data. The quality determines weightings given to each of the plurality of different types of sources.

Abstract translation: 通过从道路状态数据的多种不同类型的源提供道路状况数据到道路段的处理器，估计道路段的实际条件，为道路的多种不同类型的源分配质量 条件数据，以及通过使用道路状况数据和道路数据的多个不同类型的源的质量来在处理器中估计道路段的实际状况。 质量确定给予多个不同类型的源中的每一个的权重。

公开(公告)号：US08266079B2

公开(公告)日：2012-09-11

申请号：US13185532

申请日：2011-07-19

Applicant: William C. Regli ,  Ali Shokoufandeh ,  Dmitriy Bespalov

Inventor： William C. Regli ,  Ali Shokoufandeh ,  Dmitriy Bespalov

IPC: G06F15/18

CPC classification number: G06F17/30542 ,  G06F15/18

Abstract: A scale-Space feature extraction technique is based on recursive decomposition of polyhedral surfaces into surface patches. The experimental results show that this technique can be used to perform matching based on local model structure. Scale-space techniques can be parameterized to generate decompositions that correspond to manufacturing, assembly or surface features relevant to mechanical design. One application of these techniques is to support matching and content-based retrieval of solid models. Scale-space technique can extract features that are invariant with respect to the global structure of the model as well as small perturbations that 3D laser scanning may introduce. A new distance function defined on triangles instead of points is introduced. This technique offers a new way to control the feature decomposition process, which results in extraction of features that are more meaningful from an engineering viewpoint. The technique is computationally practical for use in indexing large models.

Abstract translation: 尺度空间特征提取技术基于多面体表面递归分解成表面斑块。 实验结果表明，该技术可以用于基于局部模型结构进行匹配。 尺度空间技术可以被参数化以产生对应于与机械设计相关的制造，组装或表面特征的分解。 这些技术的一个应用是支持实体模型的匹配和基于内容的检索。 尺度空间技术可以提取相对于模型的全局结构不变的特征以及3D激光扫描可能引入的小扰动。 介绍了三角形而不是点定义的新距离函数。 这种技术提供了一种控制特征分解过程的新方法，从而从工程角度出发，提取更有意义的特征。 该技术在计算上可用于索引大型模型。

公开(公告)号：US20120136860A1

公开(公告)日：2012-05-31

申请号：US13185532

申请日：2011-07-19

Applicant: WILLIAM C. REGLI ,  ALI SHOKOUFANDEH ,  DMITRIY BESPALOV

Inventor： WILLIAM C. REGLI ,  ALI SHOKOUFANDEH ,  DMITRIY BESPALOV

IPC: G06F17/30

CPC classification number: G06F17/30542 ,  G06F15/18

Abstract: A scale-Space feature extraction technique is based on recursive decomposition of polyhedral surfaces into surface patches. The experimental results show that this technique can be used to perform matching based on local model structure. Scale-space techniques can be parameterized to generate decompositions that correspond to manufacturing, assembly or surface features relevant to mechanical design. One application of these techniques is to support matching and content-based retrieval of solid models. Scale-space technique can extract features that are invariant with respect to the global structure of the model as well as small perturbations that 3D laser scanning may introduce. A new distance function defined on triangles instead of points is introduced. This technique offers a new way to control the feature decomposition process, which results in extraction of features that are more meaningful from an engineering viewpoint. The technique is computationally practical for use in indexing large models.

Abstract translation: 尺度空间特征提取技术基于多面体表面递归分解成表面斑块。 实验结果表明，该技术可以用于基于局部模型结构进行匹配。 尺度空间技术可以被参数化以产生对应于与机械设计相关的制造，组装或表面特征的分解。 这些技术的一个应用是支持实体模型的匹配和基于内容的检索。 尺度空间技术可以提取相对于模型的全局结构不变的特征以及3D激光扫描可能引入的小扰动。 介绍了三角形而不是点定义的新距离函数。 这种技术提供了一种控制特征分解过程的新方法，从而从工程角度出发，提取更有意义的特征。 该技术在计算上可用于索引大型模型。

公开(公告)号：US20090079586A1

公开(公告)日：2009-03-26

申请号：US11869372

申请日：2007-10-09

Applicant: Dmitriy Bespalov ,  Ali Shokoufandeh

Inventor： Dmitriy Bespalov ,  Ali Shokoufandeh

IPC: G08G1/09

CPC classification number: G08G1/0104

Abstract: Actual traffic conditions of a roadway segment are predicted by providing a plurality of historical roadway condition patterns of the roadway segment in a database, obtaining an electronic representation of a current roadway condition pattern of the roadway segment, identifying one or more of the historical roadway condition patterns that closely matches the current roadway condition pattern, and predicting the future actual traffic conditions of the roadway segment by using the conditions associated with the one or more identified historical patterns.

Abstract translation: 通过在数据库中提供道路段的多个历史道路条件模式来预测道路段的实际交通状况，获得道路段的当前道路状况模式的电子表示，识别历史道路状况中的一个或多个 与当前道路条件模式紧密匹配的模式，以及通过使用与一个或多个所识别的历史模式相关联的条件来预测道路段的未来实际交通状况。

公开(公告)号：US20130080443A1

公开(公告)日：2013-03-28

申请号：US13557918

申请日：2012-07-25

Applicant: WILLIAM C. REGLI ,  ALI SHOKOUFANDEH ,  DMITRIY BESPALOV

Inventor： WILLIAM C. REGLI ,  ALI SHOKOUFANDEH ,  DMITRIY BESPALOV

IPC: G06F17/30

CPC classification number: G06F16/2468 ,  G06N20/00 ,  G06T19/00

Abstract: A scale-Space feature extraction technique is based on recursive decomposition of polyhedral surfaces into surface patches. The experimental results show that this technique can be used to perform matching based on local model structure. Scale-space techniques can be parameterized to generate decompositions that correspond to manufacturing, assembly or surface features relevant to mechanical design. One application of these techniques is to support matching and content-based retrieval of solid models. Scale-space technique can extract features that are invariant with respect to the global structure of the model as well as small perturbations that 3D laser scanning may introduce. A new distance function defined on triangles instead of points is introduced. This technique offers a new way to control the feature decomposition process, which results in extraction of features that are more meaningful from an engineering viewpoint. The technique is computationally practical for use in indexing large models.

Abstract translation: 尺度空间特征提取技术基于多面体表面递归分解成表面斑块。 实验结果表明，该技术可以用于基于局部模型结构进行匹配。 尺度空间技术可以被参数化以产生对应于与机械设计相关的制造，组装或表面特征的分解。 这些技术的一个应用是支持实体模型的匹配和基于内容的检索。 尺度空间技术可以提取相对于模型的全局结构不变的特征以及3D激光扫描可能引入的小扰动。 介绍了三角形而不是点定义的新距离函数。 这种技术提供了一种控制特征分解过程的新方法，从而从工程角度出发，提取更有意义的特征。 该技术在计算上可用于索引大型模型。

公开(公告)号：US20120253792A1

公开(公告)日：2012-10-04

申请号：US13424900

申请日：2012-03-20

Applicant: Dmitriy Bespalov ,  Bing Bai ,  Yanjun Qi

Inventor： Dmitriy Bespalov ,  Bing Bai ,  Yanjun Qi

IPC: G06F17/27

CPC classification number: G06F16/353

Abstract: A method for sentiment classification of a text document using high-order n-grams utilizes a multilevel embedding strategy to project n-grams into a low-dimensional latent semantic space where the projection parameters are trained in a supervised fashion together with the sentiment classification task. Using, for example, a deep convolutional neural network, the semantic embedding of n-grams, the bag-of-occurrence representation of text from n-grams, and the classification function from each review to the sentiment class are learned jointly in one unified discriminative framework.

Abstract translation: 使用高阶n克的文本文档的情感分类方法利用多级嵌入策略将n-gram投影到低维潜在语义空间中，其中投影参数与监视分类任务一起被训练 。 使用例如深卷积神经网络，n-gram的语义嵌入，n-gram中的文本的行为表示，以及从每个评论到情感类的分类函数，在一个统一的 歧视性框架

公开(公告)号：US08015125B2

公开(公告)日：2011-09-06

申请号：US11847942

申请日：2007-08-30

Applicant: William C. Regli ,  Ali Shokoufandeh ,  Dmitriy Bespalov

Inventor： William C. Regli ,  Ali Shokoufandeh ,  Dmitriy Bespalov

IPC: G06F15/18

CPC classification number: G06F17/30542 ,  G06F15/18

Abstract: A scale-Space feature extraction technique is based on recursive decomposition of polyhedral surfaces into surface patches. The experimental results show that this technique can be used to perform matching based on local model structure. Scale-space techniques can be parameterized to generate decompositions that correspond to manufacturing, assembly or surface features relevant to mechanical design. One application of these techniques is to support matching and content-based retrieval of solid models. Scale-space technique can extract features that are invariant with respect to the global structure of the model as well as small perturbations that 3D laser scanning may introduce. A new distance function defined on triangles instead of points is introduced. This technique offers a new way to control the feature decomposition process, which results in extraction of features that are more meaningful from an engineering viewpoint. The technique is computationally practical for use in indexing large models.

Abstract translation: 尺度空间特征提取技术基于多面体表面递归分解成表面斑块。 实验结果表明，该技术可以用于基于局部模型结构进行匹配。 尺度空间技术可以被参数化以产生对应于与机械设计相关的制造，组装或表面特征的分解。 这些技术的一个应用是支持实体模型的匹配和基于内容的检索。 尺度空间技术可以提取相对于模型的全局结构不变的特征以及3D激光扫描可能引入的小扰动。 介绍了三角形而不是点定义的新距离函数。 这种技术提供了一种控制特征分解过程的新方法，从而从工程角度出发，提取更有意义的特征。 该技术在计算上可用于索引大型模型。

公开(公告)号：US20090080973A1

公开(公告)日：2009-03-26

申请号：US11860918

申请日：2007-09-25

Applicant: Dmitriy Bespalov ,  James F. Carroll ,  Dean Zimmerman

Inventor： Dmitriy Bespalov ,  James F. Carroll ,  Dean Zimmerman

IPC: E01C11/00

CPC classification number: G08G1/0125 ,  G06F17/30241 ,  G08G1/0104 ,  G08G1/0129

Abstract: Actual conditions of a roadway segment are estimated by providing roadway condition data to a processor for the roadway segment from a plurality of different types of sources of the roadway condition data, assigning a quality to each of the plurality of different types of sources of the roadway condition data, and estimating in the processor the actual conditions of the roadway segment by using the roadway condition data and the quality of each of the plurality of different types of sources of the roadway data. The quality determines weightings given to each of the plurality of different types of sources.

Abstract translation: 通过从道路状态数据的多种不同类型的源提供道路状况数据到道路段的处理器，估计道路段的实际条件，为道路的多种不同类型的源分配质量 条件数据，以及通过使用道路状况数据和道路数据的多个不同类型的源的质量来在处理器中估计道路段的实际状况。 质量确定给予多个不同类型的源中的每一个的权重。

公开(公告)号：US20080215510A1

公开(公告)日：2008-09-04

申请号：US11847942

申请日：2007-08-30

Applicant: WILLIAM C. REGLI ,  ALI SHOKOUFANDEH ,  DMITRIY BESPALOV

Inventor： WILLIAM C. REGLI ,  ALI SHOKOUFANDEH ,  DMITRIY BESPALOV

IPC: G06F15/18

CPC classification number: G06F17/30542 ,  G06F15/18

Abstract: A scale-Space feature extraction technique is based on recursive decomposition of polyhedral surfaces into surface patches. The experimental results show that this technique can be used to perform matching based on local model structure. Scale-space techniques can be parameterized to generate decompositions that correspond to manufacturing, assembly or surface features relevant to mechanical design. One application of these techniques is to support matching and content-based retrieval of solid models. Scale-space technique can extract features that are invariant with respect to the global structure of the model as well as small perturbations that 3D laser scanning may introduce. A new distance function defined on triangles instead of points is introduced. This technique offers a new way to control the feature decomposition process, which results in extraction of features that are more meaningful from an engineering viewpoint. The technique is computationally practical for use in indexing large models.

Abstract translation: 尺度空间特征提取技术基于多面体表面递归分解成表面斑块。 实验结果表明，该技术可以用于基于局部模型结构进行匹配。 尺度空间技术可以被参数化以产生对应于与机械设计相关的制造，组装或表面特征的分解。 这些技术的一个应用是支持实体模型的匹配和基于内容的检索。 尺度空间技术可以提取相对于模型的全局结构不变的特征以及3 D激光扫描可能引入的小扰动。 介绍了三角形而不是点定义的新距离函数。 这种技术提供了一种控制特征分解过程的新方法，从而从工程角度出发，提取更有意义的特征。 该技术在计算上可用于索引大型模型。