1887

Abstract

Summary

The paper investigates the task of optimal subsequence search in high dimension time series. Author proposes to use a search with distance function that is stable in case of local and global time warpings: dynamic time warping method. It presents a baseline for solving the task. its weighted modification improves the quality and adds new properties: method lets to analyze the most significant measures. The experiment holds on the synthetic data based on real human activity data. The experiment results let us to use the method on the real seismological data for patterns search.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.201900546
2019-03-25
2024-04-25
Loading full text...

Full text loading...

References

  1. GoncharovA.V., PopovaM.S., StrijovV.V.
    [2015] Metric times series classification with dynamic time warping relative to centroids of classes. Systems and meanings of informatics, 25(4), 52–64.
    [Google Scholar]
  2. GoncharovA.V. and StrijovV.V.
    [2016] Metric time series classification using weighted dynamic warping relative to centroids of classes. Informatics and applications, 10(2), 36–47.
    [Google Scholar]
  3. Ignatov A.D. and V. V.Strijov
    . [2015] Human activity types recognition using quasiperiodic sets of time series. Multimedia tools and applications, 1–14.
    [Google Scholar]
  4. PetitjeanF., ForestierG., Webb G.I., Nicholson A.E., ChenY., KeoghE.
    [2014] Dynamic Time Warping Averaging of Time Series allows Faster and more Accurate Classification. IEEE International Conference on Data Engineering (ICDE), 470–479.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.201900546
Loading
/content/papers/10.3997/2214-4609.201900546
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error