Intelligent Systems.
Theory and Applications

(Intellektual'nye Sistemy. Teoriya i Prilozheniya)

Symbolic, Numeric and Convolutional Methods for Time Series: Accuracy and Computation Time

Abstract

Seven time-series classifiers are compared on eight UCR datasets: ROCKET, MiniRocket and BOSS form the top group by mean rank (1.63, 1.81 and 2.56) with no significant differences within it by the Nemenyi test, and the total times of MiniRocket and BOSS in the CPU runs are 2.4 min and 11.6 h, respectively. Five models forecasting BTC and ETH prices had higher RMSE than Naive in all eight asset–horizon combinations.

Keywords: time series, classification, symbolic representation, BOSS, ROCKET, MiniRocket, computational cost, forecasting.

BibTeX
@article{IS-Zhuravlev-Kumskov2026,
  author  = {Zhuravlev, Georgy Valerievich and Kumskov, Mikhail Ivanovich},
  title   = {{Symbolic, Numeric and Convolutional Methods for Time Series: Accuracy and Computation Time}},
  journal = {Intelligent Systems. Theory and Applications},
  year    = {2026},
  volume  = {30},
  number  = {4},
  pages   = {353--356},
}
AMSBIB
\Bibitem{IS-Zhuravlev-Kumskov2026}
\by G.\,V.~Zhuravlev, M.\,I.~Kumskov
\paper Symbolic, Numeric and Convolutional Methods for Time Series: Accuracy and Computation Time
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 353--356
\lang In Russian
Published under Creative Commons Attribution 4.0 International (CC BY 4.0)

← Back to issue

× Issue cover