ENCASE: An ENsemble ClASsifiEr for ECG classification using expert features and deep neural networks
We propose ENCASE to combine expert features and DNNs (Deep Neural Networks) together for ECG classification. We first explore and implement expert features from statistical area, signal processing area and medical area. Then, we build DNNs to automatically extract deep features. Besides, we propose a new algorithm to find the most representative wave (called centerwave) among long ECG record, and extract features from centerwave. Finally, we combine these features together and put them into ensemble classifiers. Experiment on 4-class ECG data classification reports 0.84 F1 score, which is much better than any of the single model.
PDFCode
Datasets
Results from the Paper
Ranked #1 on
Time Series Classification
on Physionet 2017 Atrial Fibrillation
(F1 (Hidden Test Set) metric)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Time Series Classification | Physionet 2017 Atrial Fibrillation | ENCASE | F1 (Hidden Test Set) | 0.825 | # 1 | |
| Arrhythmia Detection | The PhysioNet Computing in Cardiology Challenge 2017 | ResNet + Expert Features | F1 (Hidden Test Set) | 0.825 | # 1 |
