p844 - Detecting Time Series Motifs Under Uniform Scaling...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Detecting Time Series Motifs Under Uniform Scaling Dragomir Yankov, Eamonn Keogh, Jose Medina, Bill Chiu, Victor Zordan Dept. of Computer Science & Eng. University of California, Riverside, USA { dyankov, eamonn, medinaj, bill, vzb } @cs.ucr.edu ABSTRACT Time series motifs are approximately repeated patterns found within the data. Such motifs have utility for many data min- ing algorithms, including rule-discovery, novelty-detection, summarization and clustering. Since the formalization of the problem and the introduction of efficient linear time al- gorithms, motif discovery has been successfully applied to many domains, including medicine, motion capture, robotics and meteorology. In this work we show that most previous applications of time series motifs have been severely limited by the defini- tion’s brittleness to even slight changes of uniform scaling, the speed at which the patterns develop. We introduce a new algorithm that allows discovery of time series motifs with invariance to uniform scaling, and show that it pro- duces objectively superior results in several important do- mains. Apart from being more general than all other motif discovery algorithms, a further contribution of our work is that it is simpler than previous approaches, in particular we have drastically reduced the number of parameters that need to be specified. Categories and Subject Descriptors H.2.8 [ DATABASE MANAGEMENT ]: Database Ap- plications — Data mining General Terms Algorithms Keywords Time Series, Motifs, Random Projection, Uniform Scaling 1. INTRODUCTION Time series motifs are approximately repeated patterns found within the data. For many data mining areas the detection of such repeated patterns is of essential impor- tance. A few tasks, among others, that utilize time series Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. KDD’07, August 12–15, 2007, San Jose, California, USA. Copyright 2007 ACM 978-1-59593-609-7/07/0008 ... $ 5.00. motif detection are for example rule-discovery [21], novelty- detection, clustering and summarization [26]. Motif discov- ery has been successfully applied throughout a large range of domains too, such as medicine [2][3], motion-capture [8][22], robotics, video surveillance [13] and meteorology [21]. Here, we show that the existing approaches for motif detection are limited to discovering pattern occurrences of the same length, failing to capture similarities when the occurrences are uniformly scaled along the time axis. To motivate the need for such uniform-scaling invariant motif discovery we will examine a synthetic time series (synthetic data is used here for ease of exposition, real-world examples are studied...
View Full Document

This note was uploaded on 12/27/2011 for the course CMPSC 290a taught by Professor Vandam during the Fall '09 term at UCSB.

Page1 / 10

p844 - Detecting Time Series Motifs Under Uniform Scaling...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online