Goto

Collaborating Authors

 self-rocket

Time series classification with random convolution kernels based transforms: pooling operators and input representations matter

Lo, Mouhamadou Mansour, Morvan, Gildas, Rossi, Mathieu, Morganti, Fabrice, Mercier, David

arXiv.org Artificial Intelligence

This article presents a new approach based on MiniRocket, called SelF-Rocket, for fast time series classification (TSC). Unlike existing approaches based on random convolution kernels, it dynamically selects the best couple of input representations and pooling operator during the training process. SelF-Rocket achieves state-of-the-art accuracy on the University of California Riverside (UCR) TSC benchmark datasets.

2409.01115
  Country:
  Genre: Research Report > New Finding (0.68)
  Technology: Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.31)

Add feedback