RPAA:A Time Property-based Representation for Time Series
Wang Yuan · 2007
PAA(Piecewise Aggregate Approximation)is a method for representing time series by sliding an equal-width window on the data and dividing the data into segments.An improved representation method RPAA(Reversed Piecewise Aggregate Approximation)is presented by preserving the time property that different segments may play different role on the data in time series.RPAA assigns different influence factors to different segments and is of linear time complexity.It is proved that RPAA satisfies the lower-bounding lemma,so search on RPAA is practical.The experiments show the effectiveness of the method.