Publications and Projects

Publications

  • ECG-biometrics-bench: A Unified Framework for Reproducible Benchmarking of ECG Biometrics

    Milad Parvan
    Preprint, 2026
    DOI: 10.5281/zenodo.19451889

    Electrocardiogram (ECG) biometrics have emerged as a promising modality for continuous, liveness-aware authentication in wearable systems. However, many prior studies report overly optimistic results due to data leakage and unrealistic evaluation protocols. In this work, we introduce ECG-biometrics-bench, a modular and reproducible benchmarking framework that standardizes preprocessing, segmentation, and evaluation across multiple public ECG datasets. We demonstrate the Random Split Fallacy and highlight performance degradation under realistic cross-session and open-set conditions.

  • Transfer Learning based Motor Imagery Classification Using Convolutional Neural Networks
    In 2019 27th Iranian Conference on Electrical Engineering (ICEE), IEEE
    [Google Scholar]
  • Deep Learning for ECG Biometrics: A Survey
    Preprint (in preparation), 2026
  • My Google Scholar Profile

Projects

  • Motor Imagery EEG Classification | Python, MATLAB
    Deep learning: DNN, CNN, LSTM, GRU, RNN, Transformers
    Machine learning: ELM, SVM, Contrastive Learning
    Feature extraction: CSP, FBCSP, Wavelet, FFT
  • EEG Data Augmentation | Python, MATLAB
    Methods: GANs, Autoencoders, Noise augmentation, Amplitude perturbation
  • User Identification using EEG Signals | Python
    Deep learning: CNN, LSTM, CNN-LSTM
    [Code]
  • Object Detection | Python
    Models: YOLO variants
    Application: vehicle detection and tracking dataset
  • Anomaly Detection | Python
    Models: Autoencoders, GANomaly, AnoGAN
    Datasets: MVTec + custom dataset
  • Audio Scene Classification | Python
    Models: CNN, GRU, CNN-GRU
    Dataset: LITIS Rouen
    [Code]
  • ECG Biometrics Framework | Python
    Reproducible pipeline covering preprocessing, feature extraction, and evaluation for ECG-based biometric systems
    [Code]
  • Iris Recognition Framework | Python
    Reproducible pipeline for iris-based biometric systems
    Developed at IEBI Lab, Università degli Studi di Milano
  • My GitHub Profile