专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

US09779504B1 Method and system for identifying anomalies in medical images especially those including one of a pair of symmetric body parts 有权
公开(公告)号：US09779504B1
公开(公告)日：2017-10-03
申请号：US15140746
申请日：2016-04-28
申请人： ATTI International Services Company, Inc.
发明人： William Biagiotti , Eli Levi , David Levi
IPC分类号： G06T7/00 , G06T7/60 , G06K9/62 , G06K9/52 , G06K9/46 , G06K9/00 , G06T7/40 , G06F19/28 , G06F19/00 , G06F17/30
CPC分类号： G06T7/0014 , G06F3/04842 , G06F17/30256 , G06F19/00 , G06F19/28 , G06F19/321 , G06K9/6215 , G06K9/6284 , G06K2209/05 , G06T7/0044 , G06T7/0085 , G06T7/408 , G06T7/60 , G06T7/68 , G06T11/60 , G06T2207/10072 , G06T2207/20104 , G06T2207/30004 , G06T2207/30016
摘要： Method for locating anomalous features in medical images in which medical images are supplied by an external source. A sequence of specific measurements is executed on the supplied data to obtain image-related metrics. The metrics are compared to corresponding values in a database resulting in an anomalous/not anomalous determination. Anomalous determinations are presented to the test operator for analysis along with supplemental historical data. In application to all types of medical imagery, potential anomalies are located resulting in an efficient and accurate diagnosis. For paired body parts having symmetrical properties, as a pre-screening stage, a line of symmetry between the body parts is determined and symmetric regions of the two body parts on opposite sides of the determined line of symmetry are analyzed for differences. The metric comparison using the database is performed between both symmetric regions only when differences between the symmetric regions of the subject medical image are present.

12. 发明申请

US20170228432A1 AUTOMATED OUTLIER DETECTION 审中-公开
公开(公告)号：US20170228432A1
公开(公告)日：2017-08-10
申请号：US15385085
申请日：2016-12-20
申请人： International Business Machines Corporation
发明人： Charu Aggarwal , Yanjie Fu , Srinivasan Parthasarathy , Deepak Turaga
IPC分类号： G06F17/30
CPC分类号： G06F17/30477 , G06F17/30539 , G06F17/30554 , G06F17/3056 , G06K9/6215 , G06K9/623 , G06K9/6232 , G06K9/6284
摘要： An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.

13. 发明申请

US20170220857A1 IMAGE-BASED QUALITY CONTROL 审中-公开
公开(公告)号：US20170220857A1
公开(公告)日：2017-08-03
申请号：US15010901
申请日：2016-01-29
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： KAMIL SZOSTAK
IPC分类号： G06K9/00 , G06T7/40 , G06K9/62 , G06T7/00 , G06T7/60 , G06F17/30 , G06K9/52 , G06K9/46
CPC分类号： G06K9/00442 , G06F17/3028 , G06F17/30991 , G06K9/00208 , G06K9/00228 , G06K9/00664 , G06K9/00892 , G06K9/03 , G06K9/2018 , G06K9/4652 , G06K9/52 , G06K9/6201 , G06K9/6284 , G06K2009/4666 , G06T7/0079 , G06T7/11 , G06T7/194 , G06T7/408 , G06T7/60 , G06T7/90 , G06T2207/20144 , G06T2207/30168 , G06T2207/30201
摘要： Aspects of the technology described herein detect visible abnormalities within a webpage or other document. The technology improves computing accuracy by identifying data and/or programing errors that cause the abnormalities. The abnormalities are detected through image analysis of portions of a document. Initially, a portion of a webpage associated with a particular feature is identified and then converted to a digital image. The digital image can capture the website as it would appear to a user viewing the website, for example, in a web browser application. The image is then analyzed against an established feature-pattern for the feature to determine whether the image falls outside of a normal range. When the image of a portion of the webpage falls outside of the normal range, a notification can be communicated to a person associated with the webpage, such as a system administrator.

14. 发明申请

US20170192872A1 INTERACTIVE DETECTION OF SYSTEM ANOMALIES 审中-公开
公开(公告)号：US20170192872A1
公开(公告)日：2017-07-06
申请号：US15325847
申请日：2014-12-11
申请人： Hewlett Packard Enterprise Development LP
发明人： Morad Awad , Gil Elgrably , Mani Fischer , Renato Keshet , Mike Krohn , Alina Maor , Ron Maurer , Igor Nor , Olga Shain , Doron Shaked
IPC分类号： G06F11/34 , G06F17/18
CPC分类号： G06F11/3476 , G06F3/04842 , G06F11/3072 , G06F11/3452 , G06F16/24568 , G06F17/18 , G06F17/40 , G06F2201/86 , G06K9/00543 , G06K9/6284
摘要： Interactive detection of system anomalies is disclosed. One example is a system including a data processor, an anomaly processor, and an interaction processor. Input data related to a series of events and telemetry measurements is received by the data processor. The anomaly processor detects presence of a system anomaly in the input data, the system anomaly indicative of a rare situation that is distant from a norm of a distribution based on the series of events and telemetry measurements. The interaction processor is communicatively linked to the anomaly processor and to an interactive graphical user interface. The interaction processor displays, via the interactive graphical user interface, an output data stream based on the presence of the system anomaly, receives, from the interactive graphical user interface, feedback data associated with the output data stream, and provides the feedback data to the anomaly processor for operations analytics based on the feedback data.

15. 发明申请

US20170076576A1 ACTIVITY MONITORING METHOD AND SYSTEM 审中-公开
标题翻译：活动监测方法和系统
公开(公告)号：US20170076576A1
公开(公告)日：2017-03-16
申请号：US15308949
申请日：2015-05-01
申请人： SEOW LOONG TAN
发明人： SEOW LOONG TAN
IPC分类号： G08B21/04 , G06K9/00
CPC分类号： G08B21/0423 , G06K9/00771 , G06K9/6284 , G08B21/0476 , G08B21/0492
摘要： Human activity monitoring systems are mainly used for tracking and monitoring of activities of people. Constant monitoring is required in order to ensure that proper care is provided for each person when faced with events such as sudden health issues and the like emergencies. Existing systems require constant monitoring and are non-adaptive to constant habitual changes or peculiarities of an individual. Described herein is an activity monitoring method that generates activity data from the activities of a person within a defined area before analyzing the activity data to identify presence of anomaly therein based on recognizing deviation of the activity data from activity profile. The activity profile is indicative of the expected activity and behavior of the person
摘要翻译：人类活动监测系统主要用于跟踪和监测人的活动。需要不断的监测，以确保在遇到诸如突发性健康问题等突发事件时为每个人提供适当的照顾。现有系统需要不断的监控，并且不适应于个体的不断的习惯性变化或特殊性。这里描述的是一种活动监视方法，其基于识别活动数据与活动简档的偏差，在分析活动数据以识别其中的异常现象之前，从定义区域内的人的活动中生成活动数据。活动简介表示该人的预期活动和行为

16. 发明授权

US09576031B1 Automated outlier detection 有权
标题翻译：自动异常值检测
公开(公告)号：US09576031B1
公开(公告)日：2017-02-21
申请号：US15018016
申请日：2016-02-08
申请人： International Business Machines Corporation
发明人： Charu Aggarwal , Yanjie Fu , Srinivasan Parthasarathy , Deepak Turaga
IPC分类号： G06F17/30
CPC分类号： G06F17/30477 , G06F17/30539 , G06F17/30554 , G06F17/3056 , G06K9/6215 , G06K9/623 , G06K9/6232 , G06K9/6284
摘要： An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.
摘要翻译：自动异常值检测系统实现无监督的一组过程以从数据集中确定特征子空间; 确定候选探索动作，其中每个候选探索动作是特征子空间和异常值检测算法的参数化实例的特定组合; 并确定一组优化的探索性行动，以推荐在候选人探索行动中对数据集执行。处理作为执行该优化探索动作的结果获得的异常值得到一个或多个异常值视图，使得每个异常值视图通过与该异常值视图相对应的每个最优探索动作代表离群值的一致表征。

17. 发明授权

US09537954B2 Method and apparatus for biologically inspired autonomous infrastructure monitoring 有权
标题翻译：用于生物灵感的自主式基础设施监测的方法和装置
公开(公告)号：US09537954B2
公开(公告)日：2017-01-03
申请号：US14716852
申请日：2015-05-19
申请人： EpiSys Science, Inc.
发明人： Nadeesha Oliver Ranasinghe , Bong Kyun Ryu , Wei-Min Shen
IPC分类号： G07C5/02 , H04L29/08 , H04W76/04 , H04W72/04 , H04W24/10 , H04W4/02 , H04W76/02 , G07C5/08 , H04W40/24 , H04W84/18 , H04W84/00 , G05D1/00 , G06K9/62
CPC分类号： H04L67/12 , G05D1/00 , G05D1/104 , G06K9/00664 , G06K9/6284 , G06K9/6296 , G06K9/6297 , G07C5/02 , G07C5/08 , H04W4/021 , H04W4/023 , H04W24/10 , H04W40/248 , H04W72/0406 , H04W76/11 , H04W76/25 , H04W84/005 , H04W84/18
摘要： A method and apparatus are provided for autonomously detecting and reporting anomalies in actions of an autonomous mobile node, or in behaviors of a swarm of autonomous mobile nodes to an operator. The autonomous mobile node may experience anomalies or unexpected situations due to various failures or external influence (e.g. natural weather phenomena, enemy threats). During a training phase a prediction model and a structured model may be established from measurement data received from one or more sensors of an autonomous mobile node or a swarm of nodes while executing an action or behavior under normal circumstances. A prediction model forecasts the expected outcome of an action or behavior, and structured model helps quantify the similarity of a learned action or behavior to the currently observed situation. Based on the measurement data applicable models can be used for an action or behavior for anomaly detection in the action or behavior.
摘要翻译：提供了一种方法和装置，用于自主地检测和报告自主移动节点的动作中的异常，或者对于运营商的自治移动节点群的行为。由于各种故障或外部影响（例如自然天气现象，敌人威胁），自主移动节点可能会经历异常或意外情况。在训练阶段期间，可以在正常情况下执行动作或行为时，从自主移动节点或节点群的一个或多个传感器接收的测量数据建立预测模型和结构化模型。预测模型预测行动或行为的预期结果，结构化模型有助于量化学习动作或行为与当前观察到的情境的相似性。基于测量数据，适用的模型可以用于动作或行为中异常检测的动作或行为。

18. 发明申请

US20160314174A1 DATA MINING METHOD 审中-公开
标题翻译：数据采矿方法
公开(公告)号：US20160314174A1
公开(公告)日：2016-10-27
申请号：US15100533
申请日：2014-12-10
申请人： CHINA UNIONPAY CO., LTD.
发明人： Jun Wang , Hongchao Yang
IPC分类号： G06F17/30
CPC分类号： G06F16/2465 , G06F16/2462 , G06F16/285 , G06K9/6267 , G06K9/6278 , G06K9/6284
摘要： The present invention proposes a method for data mining, the method comprising: making statistics of the feature vectors of each target object according to the records in a target data set so as to constitute a rough data set, each of the feature vectors including the value of at least one attribute data of the target objects corresponding thereto; screening the feature vectors which correspond to all known the first type of target objects from the rough data set, and performing a filter operation onto the screened feature vectors to obtain samples; and building a regression model based on the samples, and then using the built regression model to determine whether each of all known the second type of target objects potentially belongs to the first type of target objects. The method for data mining disclosed in the present invention is capable of mining and classifying the target objects according to the comprehensive features of the target objects.
摘要翻译：本发明提出了一种数据挖掘方法，该方法包括：根据目标数据集中的记录，对每个目标对象的特征向量进行统计，构成粗略数据集，每个特征向量包括值与其对应的目标对象的至少一个属性数据; 从粗略数据集筛选与所有已知的第一类型的目标对象相对应的特征向量，并对筛选的特征向量执行滤波操作以获得样本; 并基于样本建立回归模型，然后使用内建的回归模型来确定所有已知的第二类型的目标对象中的每一个是否潜在地属于第一类型的目标对象。本发明公开的数据挖掘方法能够根据目标对象的综合特征对目标对象进行挖掘和分类。

19. 发明授权

US09443201B2 Systems and methods for learning of normal sensor signatures, condition monitoring and diagnosis 有权
标题翻译：用于学习正常传感器特征，状态监测和诊断的系统和方法
公开(公告)号：US09443201B2
公开(公告)日：2016-09-13
申请号：US13703156
申请日：2011-05-12
申请人： Heiko Claussen , Justinian Rosca , Hans-Gerd Brummel , Edward David Thompson
发明人： Heiko Claussen , Justinian Rosca , Hans-Gerd Brummel , Edward David Thompson
IPC分类号： G06N99/00 , G06K9/62
CPC分类号： G06N99/005 , G06K9/6284
摘要： Systems and methods to monitor a signal from an apparatus are disclosed. A feature extracted from the signal is automatically defined. Signals are received over a period of time wherein the apparatus is in a normal operational mode. Features are classified in a learning mode and are applied to create a reference model that defines a within-normal operational mode. In a testing mode a signal generated by the apparatus is received, a feature is extracted and classified. Instantaneous data generated in operational mode by the apparatus is classified by the system as abnormal if it does not lie within boundaries of the reference model or contains information/structure in an orthogonal subspace. A learned reference model is augmented by a user or automatically. In one illustrative example the apparatus is a power generation equipment and the signal is an acoustic signal.
摘要翻译：公开了一种监视来自装置的信号的系统和方法。自动定义从信号中提取的特征。在设备处于正常操作模式的一段时间内接收信号。功能被分类为学习模式，并被应用于创建定义正常工作模式的参考模型。在测试模式中，接收由设备产生的信号，提取和分类特征。如果设备在操作模式下生成的瞬时数据被分类为异常，如果它不在参考模型的边界内或在正交子空间中包含信息/结构。学习的参考模型由用户增强或自动增强。在一个说明性示例中，该装置是发电设备，并且该信号是声信号。

20. 发明申请

US20160258748A1 Anomaly Detection Method, Program, and System 有权
公开(公告)号：US20160258748A1
公开(公告)日：2016-09-08
申请号：US15153090
申请日：2016-05-12
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
IPC分类号： G01B21/30
CPC分类号： G06F17/18 , G01B21/30 , G06K9/00536 , G06K9/6267 , G06K9/6284 , G06K9/6298
摘要： A method providing an analytical technique introducing label information into an anomaly detection model. The method includes the steps of: inputting measurement data having an anomalous or normal label and measurement data having no label as samples; determining a similarity matrix indicating the relationship between the samples based on the samples; defining a penalty based on the similarity matrix and calculating parameters in accordance with an updating equation having a term reducing the penalty; and calculating a degree of anomaly based on the calculated parameters. The present invention also provides a program and system for detecting an anomaly based on measurement data.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式