Abstract
The present disclosure relates to a system and method for finding actionable information in time series based on motif locations. The method includes an analysis computer that obtains time series data. The analysis computer generates a plurality of motifs. For each motif of the plurality of motifs, the analysis computer determines identified locations in the time series data that match the motif and determines a plurality of motif type scores based on the identified locations of the motif. The analysis computer determines a selected motif of the plurality of motifs based on the plurality of motif type scores for each motif of the plurality of motifs.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
YEH, MICHAEL; ZHENG, YAN; and WANG, JUNPENG, "PRIMITIVE FOR FINDING ACTIONABLE INFORMATION IN TIME SERIES BASED ON MOTIF LOCATIONS", Technical Disclosure Commons, (July 01, 2026)
https://www.tdcommons.org/dpubs_series/10784