· 2017
Time series classification from scratch with deep neural networks: A strong baseline
- 2,034citations
- 2017year
Short summary
A novel Fully Convolutional Network (FCN) and ResNet-based deep neural networks achieve state-of-the-art performance for time series classification without manual feature engineering or heavy preprocessing.
AI-generated from the title and abstract; the full text is not read.
Key points
- Developed end-to-end deep neural networks (FCN and ResNet) for time series classification.
- Achieved state-of-the-art performance without requiring feature engineering or heavy preprocessing.
- Introduced Class Activation Maps (CAMs) via global average pooling to visualize contributing data regions.
- Models offer a simple, robust baseline for real-world applications and future research.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source., 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