Deep Gated Recurrent and Convolutional Network Hybrid Model for Univariate Time Series Classification
This work addresses time series classification for researchers and practitioners, but it is incremental as it modifies an existing hybrid model by swapping LSTM with GRU.
The authors tackled the problem of univariate time series classification by proposing a GRU-fully convolutional network hybrid model (GRU-FCN) to replace LSTM-FCN, resulting in better performance on many datasets with fewer parameters and less training time.
Hybrid LSTM-fully convolutional networks (LSTM-FCN) for time series classification have produced state-of-the-art classification results on univariate time series. We show that replacing the LSTM with a gated recurrent unit (GRU) to create a GRU-fully convolutional network hybrid model (GRU-FCN) can offer even better performance on many time series datasets. The proposed GRU-FCN model outperforms state-of-the-art classification performance in many univariate and multivariate time series datasets. In addition, since the GRU uses a simpler architecture than the LSTM, it has fewer training parameters, less training time, and a simpler hardware implementation, compared to the LSTM-based models.