ECG Data Analysis

Sept 2024 – Dec 2024

Processed and cleaned raw ECG signals in Python/Pandas, applying digital filters and performing feature engineering (time-domain and frequency-domain metrics) for anomaly detection.

PythonPandasscikit-learnSVMRandom ForestMatplotlibSeaborn

Highlights

  • Processed and cleaned raw ECG signals in Python/Pandas, applying digital filters and feature engineering (time-domain and frequency-domain metrics) for anomaly detection
  • Developed and validated machine learning classifiers (SVM, Random Forest) in scikit-learn to identify arrhythmias, achieving over 90% accuracy
  • Visualized results with Matplotlib and Seaborn for comprehensive analysis

Results

  • Achieved over 90% accuracy in arrhythmia classification

Links