no code implementations • 28 Sep 2021 • Samuel Harford, Fazle Karim, Houshang Darabi
In this paper, we experimentally show that by substituting convolutions with OctConv, we significantly improve accuracy for time series classification tasks for most of the benchmark datasets.
no code implementations • 31 Mar 2020 • Samuel Harford, Fazle Karim, Houshang Darabi
Classification models for the multivariate time series have gained significant importance in the research community, but not much research has been done on generating adversarial samples for these models.
7 code implementations • 14 Jan 2018 • Fazle Karim, Somshubra Majumdar, Houshang Darabi, Samuel Harford
Over the past decade, multivariate time series classification has received great attention.
Ranked #1 on Time Series Classification on CharacterTrajectories