Supporting Fast Search in Time Series for Movement Patterns in Multiple Scales

An important investigation of time series involves searching for \movement" patterns, such as \going up" or \going down" or some combinations of them. Movement patterns can be in various scales: a large scale pattern may cover a long time period, while a small scale pattern usually covers a short time period. This paper considers such scale requirement. More speci cally, a pattern is de ned as a regular expression of letters, where each letter describes a movement direction and covers a speci ed length of time (called pattern unit length). To nd if a time series (or a part of it) matches a pattern, the time series is rst partitioned into consecutive sub-series of the unit length, and for each subseries, the direction of its best tting line is taken as the movement direction of the sub-series if the distance between the best tting line and the sub-series is within a speci ed tolerance (tolerance requirement). A direct implementation of pattern search will undoubtedly yie...

• Type: Conference
• Year: 1998
• Where: CIKM
• Authors: Yunyao Qu, Changzhou Wang, Xiaoyang Sean Wang
• Keywords: CIKM 1998, Information Management, Movement Directions, Scale Pattern, Time Series