LSTM Fully Convolutional Networks for Time Series Classification
LSTM Fully Convolutional Networks for Time Series Classification
复制标题
DOI：
10.1109/access.2017.2779939
复制
发表时间：
2018-01-01
期刊：
影响因子：
3.9
通讯作者：
Chen, Shun
中科院分区：
文献类型：
--
作者：
Karim, Fazle;Majumdar, Somshubra;Chen, Shun
全卷积神经网络（FCN）已被证明在对时间序列序列进行分类的任务上实现了最先进的性能。我们提出用长短期记忆递归神经网络（LSTM RNN）子模块增强全卷积网络，用于时间序列分类。我们提出的模型显着提高了全卷积网络的性能，模型大小略有增加，并且需要对数据集进行最少的预处理。提出的长短期记忆全卷积网络（LSTM-FCN）实现了最先进的性能与其他相比。我们还探索了使用注意力机制来改善时间序列分类与注意力长短期记忆完全卷积网络（ALSTM-FCN）。注意力机制允许人们可视化LSTM单元的决策过程。此外，我们提出细化作为增强训练模型性能的方法。我们的模型的性能进行了全面的分析，并与其他技术进行了比较。
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.