Monday, February 1, 2016 - 4:30pm
Location:8102 Gates & Hillman Centers
Speaker:DANIEL Y.T. CHINO, Ph.D. Student http://chinodyt.github.io/
For More Information, Contact:epapalex @ cs.cmu.edu
Finding previously unknown patterns that frequently occur on time series is a core task of mining time series. These patterns are known as time series motifs and are essential to associate events and meaningful occurrences within the time series. In this work we propose a method based on a trie data structure, that allows a fast and accurate time series motif discovery. From the experiments performed on synthetic and real data we can see that our TrieMotif approach is able to efficiently find motifs even when the size of the time series goes longer, being in average 3 times faster and requiring 10 times less memory than the state of the art approach. As a case study on real data, we also evaluated our method using time series extracted from remote sensing images regarding sugarcane crops. Our proposed method was able to find relevant patterns, as sugarcane cycles and other land covers inside the same area.