公开(公告)号：US20080201278A1

公开(公告)日：2008-08-21

申请号：US10568217

申请日：2004-08-17

申请人： Klaus-Robert Muller ,  Pavel Laskov ,  David Tax ,  Christin Schafer

发明人： Klaus-Robert Muller ,  Pavel Laskov ,  David Tax ,  Christin Schafer

IPC分类号： G06F15/18

CPC分类号： G06K9/6284

摘要： The invention is concerned with a method for automatic online detection and classification of anomalous objects in a data stream, especially comprising datasets and/or signals, wherein a) the detection of at least one incoming data stream containing normal and anomalous objects, b) automatic construction of a geometric representation of normality the incoming objects of the data stream at a time t1 subject to at least one predefined optimality condition, especially the construction of a hypersurface enclosing a finite number of normal objects, c) online adaptation of the geometric representation of normality in respect to received at least one received object at a time t2, which is greater than t1, the adaptation being subject to at least one predefined optimality condition, d) online determination of a normality classification for received objects at t2 in respect to the geometric representation of normality, e) automatic classification of normal objects and anomalous objects based on the generated normality classification and generating a data set describing the anomalous data for further processing, especially a visual representation.

摘要翻译： 本发明涉及一种用于数据流中异常对象的自动在线检测和分类的方法，特别是包括数据集和/或信号，其中a）检测包含正常和异常对象的至少一个输入数据流，b）自动 构造正态分布的数字流的传入对象，受到至少一个预定义的最优条件的影响，特别是包含有限数量正常对象的超曲面的构造，c ）在大于t 1的时间t 2 2处对于接收到的至少一个接收对象的正态几何表示的在线适应，适应受 至少一个预定义的最优性条件，d）关于正常几何表示的t 2处的接收对象的正态分类的在线确定，e）n的自动分类 基于所产生的正态分类并产生描述用于进一步处理的异常数据的数据集，特别是视觉表示的数据集。