-
公开(公告)号：US20170011008A1
公开(公告)日：2017-01-12
申请号：US15273301
申请日：2016-09-22
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
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. Effective utilization of label information is based on introducing the degree of similarity between samples. Assuming, for example, there is a degree of similarity between normally labeled samples and no similarity between normally labeled and abnormally labeled samples. Also each sensor value is generated by the linear sum of a latent variable and a coefficient vector specific to each sensor. However, the magnitude of observation noise is formulated to vary according to the label information for the sensor values, and set so that normal label unlabeled anomalously labeled. A graph Laplacian is created based on the degree of similarity between samples, and determines the optimal linear transformation matrix according to a gradient method. A optimal linear transformation matrix is used to calculate an anomaly score for each sensor in the test samples.
摘要翻译： 一种提供将标签信息引入异常检测模型的分析技术的方法。 标签信息的有效利用是基于引入样本之间的相似度。 例如，假设通常标记的样品之间存在一定程度的相似性，并且在正常标记和异常标记的样品之间没有相似性。 此外，每个传感器值由潜变量和每个传感器特有的系数矢量的线性和产生。 然而，观察噪声的大小被制定为根据传感器值的标签信息而变化，并且使得正常标签未标记为异常标记。 基于样本之间的相似度创建图形拉普拉斯算子，并根据梯度法确定最优线性变换矩阵。 最优线性变换矩阵用于计算测试样本中每个传感器的异常分数。
-
公开(公告)号：US10133703B2
公开(公告)日：2018-11-20
申请号：US15273301
申请日：2016-09-22
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
摘要： A method providing an analytical technique introducing label information into an anomaly detection model. Effective utilization of label information is based on introducing the degree of similarity between samples. Assuming, for example, there is a degree of similarity between normally labeled samples and no similarity between normally labeled and abnormally labeled samples. Also each sensor value is generated by the linear sum of a latent variable and a coefficient vector specific to each sensor. However, the magnitude of observation noise is formulated to vary according to the label information for the sensor values, and set so that normal label≤unlabeled≤anomalously labeled. A graph Laplacian is created based on the degree of similarity between samples, and determines the optimal linear transformation matrix according to a gradient method. A optimal linear transformation matrix is used to calculate an anomaly score for each sensor in the test samples.
-
公开(公告)号：US09805002B2
公开(公告)日：2017-10-31
申请号：US15152867
申请日：2016-05-12
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
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.
-
公开(公告)号：US20160258748A1
公开(公告)日：2016-09-08
申请号：US15153090
申请日：2016-05-12
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.
-
公开(公告)号：US09824069B2
公开(公告)日：2017-11-21
申请号：US15153090
申请日：2016-05-12
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
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.
-
公开(公告)号：US09495330B2
公开(公告)日：2016-11-15
申请号：US13916744
申请日：2013-06-13
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
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. Effective utilization of label information is based on introducing the degree of similarity between samples. Assuming, for example, there is a degree of similarity between normally labeled samples and no similarity between normally labeled and abnormally labeled samples. Also each sensor value is generated by the linear sum of a latent variable and a coefficient vector specific to each sensor. However, the magnitude of observation noise is formulated to vary according to the label information for the sensor values, and set so that normal label≦unlabeled≦anomalously labeled. A graph Laplacian is created based on the degree of similarity between samples, and determines the optimal linear transformation matrix according to a gradient method. A optimal linear transformation matrix is used to calculate an anomaly score for each sensor in the test samples.
摘要翻译： 一种提供将标签信息引入异常检测模型的分析技术的方法。 标签信息的有效利用是基于引入样本之间的相似度。 例如，假设通常标记的样品之间存在一定程度的相似性，并且在正常标记和异常标记的样品之间没有相似性。 此外，每个传感器值由潜变量和每个传感器特有的系数矢量的线性和产生。 然而，观察噪声的大小被制定为根据传感器值的标签信息而变化，并且设置使得正常标签≤未标记≤异常标记。 基于样本之间的相似度创建图形拉普拉斯算子，并根据梯度法确定最优线性变换矩阵。 最优线性变换矩阵用于计算测试样本中每个传感器的异常分数。
-
公开(公告)号：US20160258747A1
公开(公告)日：2016-09-08
申请号：US15152867
申请日：2016-05-12
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.
摘要翻译： 一种提供将标签信息引入异常检测模型的分析技术的方法。 该方法包括以下步骤：输入具有异常或正常标签的测量数据和没有标签的测量数据作为样本; 基于样本确定指示样本之间的关系的相似性矩阵; 基于所述相似性矩阵来定义惩罚，并且根据具有减少惩罚的项的更新方程来计算参数; 并基于所计算的参数来计算异常程度。 本发明还提供了一种用于基于测量数据检测异常的程序和系统。
-
公开(公告)号：US20130338965A1
公开(公告)日：2013-12-19
申请号：US13916744
申请日：2013-06-13
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
IPC分类号： G06F17/18
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. Effective utilization of label information is based on introducing the degree of similarity between samples. Assuming, for example, there is a degree of similarity between normally labeled samples and no similarity between normally labeled and abnormally labeled samples. Also each sensor value is generated by the linear sum of a latent variable and a coefficient vector specific to each sensor. However, the magnitude of observation noise is formulated to vary according to the label information for the sensor values, and set so that normal label unlabeled anomalously labeled. A graph Laplacian is created based on the degree of similarity between samples, and determines the optimal linear transformation matrix according to a gradient method. A optimal linear transformation matrix is used to calculate an anomaly score for each sensor in the test samples.
摘要翻译： 一种提供将标签信息引入异常检测模型的分析技术的方法。 标签信息的有效利用是基于引入样本之间的相似度。 例如，假设通常标记的样品之间存在一定程度的相似性，并且在正常标记和异常标记的样品之间没有相似性。 此外，每个传感器值由潜变量和每个传感器特有的系数矢量的线性和产生。 然而，观察噪声的大小被制定为根据传感器值的标签信息而变化，并且使得正常标签未标记为异常标记。 基于样本之间的相似度创建图形拉普拉斯算子，并根据梯度法确定最优线性变换矩阵。 最优线性变换矩阵用于计算测试样本中每个传感器的异常分数。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.016 秒)
