Biometric Authentication with ECG Signals: A Secure Identification Model Based on Convolutional Autoencoders

Authors : Merve Akkuş, Murat Karabatak

Pages : 65-78

View : 38 | Download : 41

Publication Date : 2025-09-30

Article Type : Research Paper

Abstract :Electrocardiography (ECG) signals provide a unique opportunity for biometric identification by capturing individual electrical properties of the heart. This study explores ECG-based identity recognition using convolutional autoencoders (CAE). The proposed method efficiently extracts features from ECG signals, constructing a compact and meaningful representation for identification. Unlike traditional methods, CAE separates intervals with feature expansion and landmark detection, addressing limitations in existing literature. The study employs the MIT-BIH Arrhythmia ECG dataset, ensuring diverse and representative training data. By learning key features and reducing dimensionality, the model compresses and reconstructs input data for precise classification. Recognizing the sensitivity of personal medical data, robust data protection strategies, including encryption and compression, are implemented. Experimental results show a high accuracy of 98.46% in ECG-based identification, validating the approach as an effective biometric authentication method. The findings highlight the potential of cardiac electrical activity as a distinctive biometric identifier. The proposed model contributes to biometric recognition by integrating machine learning techniques and stringent security measures, offering a balanced approach between technological advancement and data privacy. This research paves the way for secure and reliable personal identification using ECG signals.
Keywords : Biyometrik kimlik doğrulama, Evrişimsel otokodlayıcılar (CAE), özellik çıkarma, sinyal sıkıştırma, gizlilik ve veri güvenliği.

ORIGINAL ARTICLE URL