Enhancing ECG-based authentication systems using VGG۱۶ model and transfer learning

This study explores a novel authentication algorithm leveraging ECG signals and deep learning models, specifically VGG۱۶, enhanced with transfer learning. Authentication systems were evaluated based on preparation time, response time, and accuracy, with biometric data utilized to increase security. Traditional deep learning models face challenges in retraining time when data changes, prompting the proposed algorithm to incorporate new users or modify access efficiently using transfer learning. Key findings included training the VGG۱۶ model on ECG data from ۴۸ individuals (MITDB dataset) with a ۹۹.۴۵% accuracy and ۱۲۰ seconds average training time. The transfer learning approach enabled adding or removing user data by adjusting SoftMax coefficients, reducing training time significantly to about ۱۲ seconds per user with accuracy exceeding ۹۹%. Removing a user followed a similar process with comparable results. Overall, the algorithm reduced retraining time by ۷۲.۸۹% while maintaining over ۹۹.۱۶% accuracy. Additionally, the system's response time for a new user was ۳۷ milliseconds, demonstrating practicality for real-time applications. The study highlights the proposed algorithm's efficiency in managing user data changes while ensuring high accuracy and reduced retraining time, making it a robust solution for modern authentication systems.

کلیدواژه ها:

Biometric Authentication System ، ECG Signals ، VGG۱۶ ، Transfer Learning ، Adding and Removing Users