Revisiting WEASEL 2.0: Reproduction, Sensitivity, and an Adaptive Ensemble-Size Rule
This work reproduces WEASEL 2.0 on 114 UCR datasets and tests the sensitivity of four design choices: the downstream classifier, the absence of feature weighting, the maximum window-size rule, the maximum ensemble-size rule, and the maximum ensemble-size rule.
C. Higgins, Gerard Carrigan, Pinar Sungu Isiacik et al.
· 0 citations