METHOD FOR PATTERN DISCOVERY IN A MULTIDIMENSIONAL

专利名称：METHOD FOR PATTERN DISCOVERY IN A

MULTIDIMENSIONAL NUMERICAL DATASET

发明人：MEREDITH, David,WIGGINS,

Geraint,LEMSTROM, Kjell

申请号：EP02726327.6申请日：20020523公开号：EP1402400A2公开日：20040331

摘要：This invention provides methods for pattern discovery, pattern matching anddata compression in multidimensional numerical datasets. The invention can usefully beapplied in any domain in which information represented in the form of multidimensionaldatasets needs to be retrieved, compared, analysed or compressed. Such domainsinclude 2D images, audio and video data, biomolecular data, seismic, meteorological andfinancial data. The method allows maximal matches for a query pattern to be found in adataset by computing the inter-datapoint vectors between datapoints in the pattern anddatapoints in the dataset. The method allows maximal recurring pattern in a the datasetto be found by computing inter-datapoint vectors between datapoints in the dataset. Anextension of the method allows all occurrences of all maximal recurring patterns in adataset to be found. This extension to the method can be used to compute a

compressed (i.e. space-efficient) representation of a dataset from which the dataset canbe reconstructed by multiple translations of an optimal set of generating patterns.

申请人：City University London

地址：Northampton Square London EC1V 0HB GB

国籍：GB

代理机构：Langley, Peter James

更多信息请下载全文后查看