LSTM Fully Convolutional Networks for Time Series Classification

By Fazle Karim, Somshubra Majumdar, Houshang Darabi, Shun Chen. IEEE Access, 2017

1,303 citations recorded by the source corpus.

Fully convolutional neural networks (FCNs) have been shown to achieve the state-of-the-art performance on the task of classifying time series sequences. We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification. Our proposed models significantly enhance the performance of fully convolutional networks with a nominal increase in model size and require minimal preprocessing of the data set. The proposed long short term memory fully convolutional network (LSTM-FCN) achieves the state-of-the-art performance compared with others. We also explore the usage of attention mechanism to improve time series classification with the attention long short term memory fully convolutional network (ALSTM-FCN). The attention mechanism allows one to visualize the decision process of the LSTM cell. Furthermore, we propose refinement as a method to enhance the performance of trained models. An overall analysis of the performance of our model is provided and compared with other techniques.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/a75da5376b48c0cc1c307561d14e0f177341afc0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Multivariate LSTM-FCNs for Time Series Classification (2018, methodology): “The LSTM block is identical to the block from the LSTM-FCN or ALSTMFCN models [31], comprising of either a LSTM layer or an Attention LSTM layer, which is followed by a dropout.”
A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data (2018, background): “This paper is also related to other time series applications such as clustering/classiﬁcation (Li and Prakash 2011; Hallac et al. 2017; Karim et al. 2018), segmentation (Keogh et al. 2001; Lemire 2007), and so on.”
UAV & satellite synergies for optical remote sensing applications: A literature review (2021, positive): “Since then, many architectures, either adapted to assign a label to each pixel (Fully Convolutional Networks and variants (Long et al., 2015)), to deal with unstructured data (Qi et al., 2017) or to time series for example (Fazle et al., 2017) have been proposed.”
TapNet: Multivariate Time Series Classification with Attentional Prototypical Network (2020, methodology): “In contrast, (Karim et al. 2018) recently proposed a model consisting of an LSTM layer and stacked CNN layer along with a Squeeze-and-Excitation block to generate latent features.”