IEEE Access· 2017Q1
LSTM Fully Convolutional Networks for Time Series Classification
- 1,452citations
- Q1SCImago
- 2017year
Short summary
LSTM-FCN models significantly improve time series classification accuracy over standard FCNs with minimal increase in model size and preprocessing.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces LSTM-FCN, combining FCNs with LSTM RNNs for time series classification.
- Achieves state-of-the-art performance, surpassing existing methods.
- Models show significant performance enhancement with minimal increase in size and preprocessing.
- Explores attention mechanisms (ALSTM-FCN) for visualizing LSTM decision processes.
- Proposes a refinement method to further boost trained model performance.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source. IEEE Access, 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science