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 • 19 Jul 2021 • Emilia Apostolova, Fazle Karim, Guido Muscioni, Anubhav Rana, Jeffrey Clyman
In this work, we modify and apply self-supervision techniques to the domain of medical health insurance claims.
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.
2 code implementations • 27 Feb 2019 • Fazle Karim, Somshubra Majumdar, Houshang Darabi
In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models.
4 code implementations • 27 Feb 2019 • Fazle Karim, Somshubra Majumdar, Houshang Darabi
In this paper, we perform a series of ablation tests (3627 experiments) on LSTM-FCN and ALSTM-FCN to provide a better understanding of the model and each of its sub-module.
no code implementations • 19 Dec 2018 • Maryam Pishgar, Fazle Karim, Somshubra Majumdar, Houshang Darabi
Vocal disorders have affected several patients all over the world.
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
9 code implementations • 8 Sep 2017 • Fazle Karim, Somshubra Majumdar, Houshang Darabi, Shun Chen
We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification.
Ranked #2 on Outlier Detection on ECG5000