ABNORMALITY CANDIDATE EXTRACTION PROGRAM, ABNORMALITY CANDIDATE EXTRACTION METHOD AND ABNORMALITY CANDIDATE EXTRACTION APPARATUS

摘要

To recognize a change corresponding to an abnormality in unsupervised time series data analysis.SOLUTION: An extraction apparatus generates a plurality of Betti series composed of Betti numbers obtained by persistent homology converting a plurality of pseudo attractors generated from plural pieces of time series data. The extraction apparatus generates a plurality of converted Betti series in which an area having a large radius is weighted than an area having a small radius when generating a Betti number from the plurality of Betti series. The extraction apparatus extracts an abnormal candidate from the plural pieces of time series data based on the Betti number in the plurality of converted Betti series.SELECTED DRAWING: Figure 1