公开(公告)号：US08577663B2

公开(公告)日：2013-11-05

申请号：US13113835

申请日：2011-05-23

Applicant: Tsai-Ching Lu ,  Yilu Zhang ,  Alejandro Nijamkin ,  David L. Allen ,  Hankyu Moon ,  Mutasim A. Salman

Inventor： Tsai-Ching Lu ,  Yilu Zhang ,  Alejandro Nijamkin ,  David L. Allen ,  Hankyu Moon ,  Mutasim A. Salman

IPC: G06F17/50

CPC classification number: G05B23/0235 ,  B60W50/0205 ,  B60W50/045 ,  G06F11/0739 ,  G06F11/079 ,  G06F11/3013 ,  G06F11/3093

Abstract: A system and method for identifying a monitoring point in an electrical and electronic system (EES) in a vehicle. The method includes defining a network model of the EES where potential monitoring point locations in the model are identified as targets, such as nodes. The method then computes a betweenness centrality metric for each target in the model as a summation of a ratio of a number of shortest paths between each pair of targets in the model that pass through the target whose betweenness centrality metric is being determined to a total number of shortest paths between each pair of targets. The method identifies which of the betweenness centrality metrics are greater than a threshold that defines a minimum acceptable metric and determines which of those targets meets a predetermined model coverage. The monitoring point is selected as the target that best satisfies the minimum metric and the desired coverage.

Abstract translation: 一种用于识别车辆中电气和电子系统（EES）中的监测点的系统和方法。 该方法包括定义EES的网络模型，其中将模型中的潜在监测点位置识别为诸如节点的目标。 该方法然后计算模型中每个目标的中间性中心度量，作为模型中每对目标之间的最短路径数之和的比值，该模型中通过目标之间的最小路径的比率，该目标的中间性中心度量被确定为总数 每对目标之间的最短路径。 该方法识别哪个中间中心度量大于定义最小可接受度量的阈值，并确定哪些目标满足预定的模型覆盖。 选择监测点作为最适合最小度量和所需覆盖范围的目标。

公开(公告)号：US07739213B1

公开(公告)日：2010-06-15

申请号：US11715068

申请日：2007-03-06

Applicant: Krzysztof W. Przytula ,  Tsai Ching Lu

Inventor： Krzysztof W. Przytula ,  Tsai Ching Lu

IPC: G06N5/02

CPC classification number: G06N7/005

Abstract: A method and computer program product to capture expert knowledge and data using probabilistic models. A custom layered structure and nodes reduce the complexity of the model, allowing for representation of the model using tables. An editor is used for entry and verification of expert knowledge and data into tables and a probabilistic model is generated from the tables.

Abstract translation: 一种使用概率模型捕获专家知识和数据的方法和计算机程序产品。 定制分层结构和节点降低了模型的复杂性，允许使用表格来表示模型。 编辑器用于将专家知识和数据输入和验证到表中，并从表中生成概率模型。

公开(公告)号：US09483729B1

公开(公告)日：2016-11-01

申请号：US13600101

申请日：2012-08-30

Applicant: David L. Allen ,  Tsai-Ching Lu

Inventor： David L. Allen ,  Tsai-Ching Lu

IPC: G06N5/02

CPC classification number: G06N5/02 ,  G06N5/022 ,  G06Q10/06 ,  G06Q50/01

Abstract: Described is a system for detecting group behaviors in dynamic relational data by monitoring individual events of interest. Data is collected from a domain of interest at predetermined time intervals. Examples of domains of interest include internet data, video behavior analysis, social networks, and diagnosis and prognosis. The data is then monitored for at least one local event of interest defined by a user. The system is configured to analyze a relationship between at least two monitored local events of interest. Finally, a visual representation of the relationship between the monitored local events of interest is generated and presented to the user for further analysis. Also described is a method and computer program product for detecting group behaviors in data.

Abstract translation: 描述了通过监视感兴趣的个人事件来检测动态关系数据中的组行为的系统。 以预定的时间间隔从感兴趣的域收集数据。 感兴趣的领域的例子包括互联网数据，视频行为分析，社交网络，以及诊断和预后。 然后，监视由用户定义的至少一个感兴趣的本地事件的数据。 该系统被配置为分析至少两个被监视的感兴趣的本地事件之间的关系。 最后，生成并监视本地感兴趣的本地事件之间的关系的视觉表示，以供用户进一步分析。 还描述了一种用于检测数据中的组行为的方法和计算机程序产品。

公开(公告)号：US09147273B1

公开(公告)日：2015-09-29

申请号：US13029073

申请日：2011-02-16

Applicant: David L. Allen ,  Tsai-Ching Lu ,  David J. Huber ,  Hankyu Moon

Inventor： David L. Allen ,  Tsai-Ching Lu ,  David J. Huber ,  Hankyu Moon

IPC: G06T11/20 ,  G06F19/26

CPC classification number: G06T11/206 ,  G06F19/12 ,  G06F19/26

Abstract: The present invention is directed to a data processing apparatus and a computer implemented method for modeling and analyzing relational data represented in a network that includes a plurality of nodes and a plurality of connections between the nodes. The method includes assigning at least one weight to a connection between two nodes in the network. A set of possible dendrograms is then generated for the network, and a likelihood of each dendrogram in the set is determined. The determination of the likelihood is based on at least the one weight of the connection. One of the dendrograms from the set is selected as an optimal dendrogram based on the determined likelihood. The selected dendrogram is then output via an output device. The dendrogram may be used to predict missing links or identify any possible false-positive (noisy) links within a relational dataset.

Abstract translation: 本发明涉及一种数据处理装置和计算机实现的方法，用于对包括多个节点和节点之间的多个连接的网络中表示的关系数据进行建模和分析。 该方法包括为网络中的两个节点之间的连接分配至少一个权重。 然后为网络生成一组可能的树状图，并确定集合中每个树形图的可能性。 可能性的确定至少基于连接的一个重量。 根据确定的可能性，将集合中的一个树形图选择为最佳树形图。 然后通过输出设备输出所选的树形图。 树状图可用于预测遗漏链接或识别关系数据集内任何可能的假阳性（嘈杂）链接。

公开(公告)号：US08874584B1

公开(公告)日：2014-10-28

申请号：US12660320

申请日：2010-02-24

Applicant: Yang Chen ,  Swarup Medasani ,  David L. Allen ,  Qin Jiang ,  Yuri Owechko ,  Tsai-Ching Lu

Inventor： Yang Chen ,  Swarup Medasani ,  David L. Allen ,  Qin Jiang ,  Yuri Owechko ,  Tsai-Ching Lu

IPC: G06F17/30

CPC classification number: G06F17/30805 ,  G06F17/30811

Abstract: Described is a system for content recognition, search, and retrieval in visual data. The system is configured to perform operations of receiving visual data as an input, processing the visual data, and extracting distinct activity-agnostic content descriptors from the visual data at each level of a hierarchical content descriptor module. The resulting content descriptors are then indexed with a hierarchical content indexing module, wherein each level of the content indexing module comprises a distinct set of indexed content descriptors. The visual data, generated content descriptors, and indexed content descriptors are then stored in a storage module. Finally, based on a content-based query by a user, the storage module is searched, and visual data containing the content of interest is retrieved and presented to the user. A method and computer program product for content recognition, search, and retrieval in visual data are also described.

Abstract translation: 描述了用于视觉数据中的内容识别，搜索和检索的系统。 该系统被配置为执行接收视觉数据作为输入，处理可视数据以及从分层内容描述符模块的每个级别的视觉数据中提取不同的活动不可知内容描述符的操作。 所得到的内容描述符然后用分层内容索引模块进行索引，其中内容索引模块的每个级别包括不同的索引内容描述符集合。 然后将可视数据，生成的内容描述符和索引的内容描述符存储在存储模块中。 最后，基于用户的基于内容的查询，搜索存储模块，并且检索包含感兴趣内容的视觉数据并呈现给用户。 还描述了用于视觉数据中的内容识别，搜索和检索的方法和计算机程序产品。

公开(公告)号：US09361523B1

公开(公告)日：2016-06-07

申请号：US12841078

申请日：2010-07-21

Applicant: Yang Chen ,  Swarup Medasani ,  Qin Jiang ,  David L. Allen ,  Tsai-Ching Lu

Inventor： Yang Chen ,  Swarup Medasani ,  Qin Jiang ,  David L. Allen ,  Tsai-Ching Lu

IPC: G06K9/03 ,  G06K9/00

CPC classification number: G06K9/00758 ,  G06K9/00711 ,  G06K9/00718 ,  G06K9/00744 ,  G06K9/4676 ,  G06T2207/10016 ,  G06T2210/00

Abstract: A method and system for video-content based retrieval is described. A query video depicting an activity is processed using interest point selection to find locations in the video that are relevant to that activity. A set of spatio-temporal descriptors such as self-similarity and 3-D SIFT are calculated within a local neighborhood of the set of interest points. An indexed video database containing videos similar to the query video is searched using the set of descriptors to obtain a set of candidate videos. The videos in the video database are indexed hierarchically using a vocabulary tree or other hierarchical indexing mechanism.

Abstract translation: 描述了基于视频内容的检索的方法和系统。 使用兴趣点选择来处理描绘活动的查询视频，以查找视频中与该活动相关的位置。 在一组感兴趣点的本地邻域内计算一组空间 - 时间描述符，例如自相似性和3-D SIFT。 使用该组描述符搜索包含与查询视频类似的视频的索引视频数据库，以获得一组候选视频。 视频数据库中的视频使用词汇树或其他分层索引机制分层索引。

公开(公告)号：US20130325203A1

公开(公告)日：2013-12-05

申请号：US13488502

申请日：2012-06-05

Applicant: TSAI-CHING LU ,  DAVID L. ALLEN ,  YILU ZHANG ,  MUTASIM A. SALMAN

Inventor： TSAI-CHING LU ,  DAVID L. ALLEN ,  YILU ZHANG ,  MUTASIM A. SALMAN

IPC: G06F7/00

CPC classification number: G05B23/0229

Abstract: Methods and systems are provided for monitoring a vehicle. In one embodiment, the method includes, but is not limited to, receiving traffic data from a vehicle communication bus. The method further includes, but is not limited to, identifying, by a processor, net-motifs from the traffic data. The method still further includes, but is not limited to, detecting a mode of components of the vehicle based on the net-motifs.

Abstract translation: 提供了用于监测车辆的方法和系统。 在一个实施例中，该方法包括但不限于从车辆通信总线接收交通数据。 该方法还包括但不限于由处理器从业务数据识别网络主题。 该方法还包括但不限于基于网络图案来检测车辆的部件的模式。

公开(公告)号：US08213709B1

公开(公告)日：2012-07-03

申请号：US12590110

申请日：2009-11-03

Applicant: Swarup Medasani ,  Yuri Owechko ,  Tsai-Ching Lu ,  Deepak Khosla ,  David L. Allen

Inventor： Swarup Medasani ,  Yuri Owechko ,  Tsai-Ching Lu ,  Deepak Khosla ,  David L. Allen

IPC: G06K9/62

CPC classification number: G06K9/6278 ,  G06K9/00671 ,  G06K9/6263 ,  G06N7/005

Abstract: A method and system for a directed area search using cognitive swarm vision and cognitive Bayesian reasoning is disclosed. The system comprises a domain knowledge database, a top-down reasoning module, and a bottom-up module. The domain knowledge database is configured to store Bayesian network models comprising visual features and observables associated with various sets of entities. The top-down module is configured to receive a search goal, generate a plan of action using Bayesian network models, and partition the plan into a set of tasks/observables to be located in the imagery. The bottom-up module is configured to select relevant feature/attention models for the observables, and search the visual imagery using a cognitive swarm for the at least one observable. The system further provides for operator feedback and updating of the domain knowledge database to perform better future searches.

Abstract translation: 公开了一种使用认知群体视觉和认知贝叶斯推理的定向区域搜索的方法和系统。 该系统包括域知识数据库，自上而下推理模块和自下而上模块。 域知识数据库被配置为存储包括与各组实体相关联的视觉特征和可观察性的贝叶斯网络模型。 自顶向下模块被配置为接收搜索目标，使用贝叶斯网络模型生成行动计划，并将计划分成一组要在图像中的任务/可观察值。 自下而上模块被配置为选择可观察的相关特征/关注模型，并且使用用于至少一个可观察的认知群搜索视觉图像。 该系统进一步提供操作者反馈和更新领域知识数据库以执行更好的未来搜索。

公开(公告)号：US20150312123A1

公开(公告)日：2015-10-29

申请号：US14425116

申请日：2012-09-05

Applicant: Yilu ZHANG ,  Xinyu DU ,  Mutasim A. SALMAN ,  Tsai-Ching LU ,  David L. ALLEN ,  Shengbing JIANG

Inventor： Yilu ZHANG ,  Xinyu DU ,  Mutasim A. SALMAN ,  Tsai-Ching LU ,  David L. ALLEN ,  Shengbing JIANG

IPC: H04L12/26 ,  H04L29/08

CPC classification number: H04L43/0847 ,  B60W50/0225 ,  B60W2050/0045 ,  G06F11/0739 ,  G06F11/0745 ,  H04L43/0817 ,  H04L67/12

Abstract: A controller area network (CAN) has a plurality of CAN elements including a communication bus and controllers. A method for monitoring the controller area network CAN includes identifying active and inactive controllers based upon signal communications on the communication bus and identifying a candidate fault associated with one of the CAN elements based upon the identified inactive controllers.

Abstract translation: 控制器局域网（CAN）具有包括通信总线和控制器的多个CAN元件。 用于监视控制器区域网络CAN的方法包括基于通信总线上的信号通信识别有源和非活动控制器，并且基于所识别的非活动控制器来识别与CAN元件之一相关联的候选故障。

公开(公告)号：US20120303348A1

公开(公告)日：2012-11-29

申请号：US13113835

申请日：2011-05-23

Applicant: Tsai-Ching Lu ,  Yilu Zhang ,  Alejandro Nijamkin ,  David L. Allen ,  Hankyu Moon ,  Mutasim A. Salman

Inventor： Tsai-Ching Lu ,  Yilu Zhang ,  Alejandro Nijamkin ,  David L. Allen ,  Hankyu Moon ,  Mutasim A. Salman

IPC: G06G7/62

CPC classification number: G05B23/0235 ,  B60W50/0205 ,  B60W50/045 ,  G06F11/0739 ,  G06F11/079 ,  G06F11/3013 ,  G06F11/3093

Abstract: A system and method for identifying a monitoring point in an electrical and electronic system (EES) in a vehicle. The method includes defining a network model of the EES where potential monitoring point locations in the model are identified as targets, such as nodes. The method then computes a betweenness centrality metric for each target in the model as a summation of a ratio of a total number of shortest paths between each pair of targets and a number of shortest paths that pass through the target whose betweenness centrality metric is being determined. The method identifies which of the betweenness centrality metrics are greater than a threshold that defines a minimum acceptable metric and determines which of those targets meets a predetermined model coverage. The monitoring point is selected as the target that best satisfies the minimum metric and the desired coverage.

Abstract translation: 一种用于识别车辆中电气和电子系统（EES）中的监测点的系统和方法。 该方法包括定义EES的网络模型，其中将模型中的潜在监测点位置识别为诸如节点的目标。 该方法然后将模型中的每个目标的中间性中心度量计算为每对目标之间的最短路径的总数与通过其中心中心度量被确定的目标的最短路径的数量之和的总和 。 该方法识别哪个中间中心度量大于定义最小可接受度量的阈值，并确定哪些目标满足预定的模型覆盖。 选择监测点作为最适合最小度量和所需覆盖范围的目标。