Papers › ENCASE: An ENsemble ClASsifiEr for ECG classification using expert features and deep...

ENCASE: An ENsemble ClASsifiEr for ECG classification using expert features and deep neural networks

24 Sep 20172017 Computing in Cardiology (CinC) 2017 9archive 2025-07-28

Shenda Hong, Meng Wu, Yuxi Zhou, Qingyun Wang, Junyuan Shang, Hongyan Li, Junqing Xie

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.

Paper PDF Code

Code

hsd1503/ENCASE tf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Arrhythmia Detection Classification ECG Classification General Classification Time Series Classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Arrhythmia Detection	The PhysioNet Computing in Cardiology Challenge 2017	ResNet + Expert Features	F1 (Hidden Test Set)	0.825	#5 of 5	Archive leaderboard	report
Time Series Classification	Physionet 2017 Atrial Fibrillation	ENCASE	F1 (Hidden Test Set)	0.825	#2 of 2	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections