Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.00755 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912430926331904 |
|---|---|
| author | Tang, Xiaoya Berquist, Jake Steinberg, Benjamin A. Tasdizen, Tolga |
| author_facet | Tang, Xiaoya Berquist, Jake Steinberg, Benjamin A. Tasdizen, Tolga |
| contents | We propose a hierarchical Transformer for ECG analysis that combines depth-wise convolutions, multi-scale feature aggregation via a CLS token, and an attention-gated module to learn inter-lead relationships and enhance interpretability. The model is lightweight, flexible, and eliminates the need for complex attention or downsampling strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00755 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hierarchical Transformer for Electrocardiogram Diagnosis Tang, Xiaoya Berquist, Jake Steinberg, Benjamin A. Tasdizen, Tolga Machine Learning We propose a hierarchical Transformer for ECG analysis that combines depth-wise convolutions, multi-scale feature aggregation via a CLS token, and an attention-gated module to learn inter-lead relationships and enhance interpretability. The model is lightweight, flexible, and eliminates the need for complex attention or downsampling strategies. |
| title | Hierarchical Transformer for Electrocardiogram Diagnosis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2411.00755 |