Survey on Time Series Motif Discovery

Last decades witness a huge growth in medical applications, genetic analysis,and in performance of manufacturing technologies and automatised productionsystems. A challenging task is to identify and diagnose the behavior of suchsystems, which aim to produce a product with desired quality. In order to con-trol the state of the systems, various information is gathered from differenttypes of sensors (optical, acoustic, chemical, electric, and thermal). Time seriesdata are a set of real-valued variables obtained chronologically. Data miningand machine learning help derive meaningful knowledge from time series.Such tasks include clustering, classification, anomaly detection andmotif discov-ery. Motif discovery attempts tofind meaningful, new, and unknown knowledgefrom data. Detection of motifs in a time series is beneficial for, e.g., discovery ofrules or specific events in a signal. Motifs provide useful information for theuser in order to model or analyze the data. Motif discovery is applied to variousareas as telecommunication, medicine, web, motion-capture, and sensornetworks. This contribution provides a review of the existing publications intime series motif discovery along with advantages and disadvantages of existingapproaches. Moreover, the research issues and missing points in thisfield arehighlighted. The main objective of this focus article is to serve as a glossary forresearchers in thisfield.