Ecg Arrhythmia Classifier

--- license: apache-2.0 language: - tr - en tags: - ecg - arrhythmia - 12-lead - tflite - medical - time-series datasets: - adzetto/sph-ecg-arrhythmia metrics: - auc pipeline_tag: audio-classification --- # ECG Arrhythmia Classifier (12-Lead DS-CNN) Lightweight **Depthwise Separable 1D CNN** model for 12-lead ECG arrhythmia classification. Trained on the [Shaoxing People's Hospital (SPH) dataset](https://physionet.org/content/ecg-arrhythmia/1.0.0/) — 45,152 ECG recordings. ## Model Details | Property | Value | |---|---| | Architecture | Depthwise Separable 1D CNN | | Parameters | ~280K | | TFLite (INT8) size | ~350 KB | | Input | (1, 2500, 12) — 10s @ 250Hz, 12 leads | | Output | 49-class multi-label sigmoid | | Android latency | ~12ms (mid-range device) | ## Conditions (49 SNOMED-CT labels) 1AVB, 2AVB, 2AVB1, 2AVB2, 3AVB, ABI, ALS, APB, AQW, ARS, AVB, CCR, CR, ERV, FQRS, IDC, IVB, JEB, JPT, LBBB, LBBBB, LFBBB, LVH, LVQRSAL, LVQRSCL, LVQRSLL, MI, MIBW, MIFW, MILW, MISW, PRIE, PWC, QTIE, RAH, RBBB, RVH, STDD, STE, STTC, STTU, TWC, TWO, UW, VB, VEB, VFW, VPB, VPE ## Usage (Android TFLite) ```kotlin val classifier = EcgClassifier(context) val predictions = classifier.classify(ecgData12x2500) // predictions: List<EcgPrediction> (prob > 0.5) ``` ## Training ```bash python dataset/train_ecg_model.py ``` ## Project Part of the **Hayatın Ritmi** wearable ECG project — TÜBİTAK 2209-A research.

Source context: 0 downloads · 0 likes · Pipeline audio-classification · Repo adzetto/ecg-arrhythmia-classifier