Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
This provides a strong, simple baseline for real-world time series classification applications and future research, though it is incremental as it builds on existing deep learning architectures.
The authors tackled time series classification by proposing a simple, end-to-end deep learning baseline without heavy preprocessing, achieving premium performance compared to state-of-the-art methods with their Fully Convolutional Network (FCN) and competitive results using ResNet structures.
We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy preprocessing on the raw data or feature crafting. The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and our exploration of the very deep neural networks with the ResNet structure is also competitive. The global average pooling in our convolutional model enables the exploitation of the Class Activation Map (CAM) to find out the contributing region in the raw data for the specific labels. Our models provides a simple choice for the real world application and a good starting point for the future research. An overall analysis is provided to discuss the generalization capability of our models, learned features, network structures and the classification semantics.