Insights Into LSTM Fully Convolutional Networks for Time Series Classification

Insights Into LSTM Fully Convolutional Networks for Time Series Classification

Long short-term memory fully convolutional neural networks (LSTM-FCNs) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve the state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (UCR) time series repository. However, there h...

Full description

Bibliographic Details
Main Authors: Fazle Karim, Somshubra Majumdar, Houshang Darabi
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Convolutional neural network
long short term memory recurrent neural network
time series classification
Online Access:https://ieeexplore.ieee.org/document/8713870/

Internet

https://ieeexplore.ieee.org/document/8713870/

Similar Items