All papers
ClassFormer: Transformers for Multivariate Time Series Classification
Simon Bührer, BSc Thesis, ETH Zürich, January 2024
Abstract
A Transformer for multivariate time-series classification. It uses continuous wavelet transforms to add frequency information, patch-wise embeddings to keep the sequence length manageable, and a three-stage attention that looks across time, channels, and frequency. On 18 UEA datasets it is competitive with eight standard baselines and best on several of them, including perfect accuracy on Epilepsy. A learned masking scheme adds a further accuracy gain and makes training more stable.
Tags
- Transformers
- Time-Series Modeling
- Attention Mechanisms