Azab Mohamed AbdallaElsayed ( PhD Student, Faculty of Information Technology Security,
ITMO University, Saint Petersburg Russia
)
Korzhuk Viktoriia Mikhailovna (Associate Professor, Faculty of Information Technology Security,
ITMO University, Saint Petersburg Russia
)
| |
This paper presents an intelligent biometric authentication system based on electrocardiogram (ECG) signals and deep learning techniques. The system incorporates signal filtering, feature extraction, wavelet decomposition, and precise QRS complex detection. Noise robustness is enhanced through deviation modeling and threshold averaging. Classification is performed by an optimized neural network. Experimental validation using the ECG-ID dataset achieved 98% accuracy, 95% sensitivity, and a 10-second response time, with an AUC of 0.98. These results demonstrate the system's suitability for practical use and highlight future directions for improving selectivity and reducing false positives.
Keywords:biometrics, ECG, authentication, deep learning, ANN, wavelet decomposition, QRS complex, information security
|
|
| |
|
Read the full article …
|
Citation link:
Azab M. A., Korzhuk V. M. INTELLIGENT ECG-BASED BIOMETRIC AUTHENTICATION SYSTEM USING DEEP LEARNING TECHNIQUES // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2025. -№06. -С. 22-29 DOI 10.37882/2223-2966.2025.06.01 |
|
|
LEGAL
INFORMATION:
