Abstract

This paper introduces a framework for how to appropriately adopt and adjust Machine Learning (ML) techniques used to construct Electrocardiogram (ECG) based biometric authentication schemes. The proposed framework can help investigators and developers on ECG based biometric authentication mechanisms define the boundaries of required datasets and get training data with good quality. To determine the boundaries of datasets, use case analysis is adopted. Based on various application scenarios on ECG based authentication, three distinct use cases (or authentication categories) are developed. With more qualified training data given to corresponding machine learning schemes, the precision on ML-based ECG biometric authentication mechanisms is increased in consequence. ECG time slicing technique with the R-peak anchoring is utilized in this framework to acquire ML training data with good quality. In the proposed framework four new measure metrics are introduced to evaluate the quality of ML training and testing data. In addition, a Matlab toolbox, containing all proposed mechanisms, metrics and sample data with demonstrations using various ML techniques, is developed and made publicly available for further investigation. For developing ML-based ECG biometric authentication, the proposed framework can guide researchers to prepare the proper ML setups and the ML training datasets along with three identified user case scenarios. For researchers adopting ML techniques to design new schemes in other research domains, the proposed framework is still useful for generating ML-based training and testing datasets with good quality and utilizing new measure metrics.

Highlights

  • Because most application systems support Internet access for general users, identifying persons with their own body has become the trend for users to access application systems

  • Among various biometric authentication schemes such as fingerprint scanning and facial recognition, electrocardiogram authentication has the advantage of adopting live user body signals during authentication

  • Time slicing technique are introduced in the framework to prepare Machine Learning (ML)-based training datasets along with new measure metrics developed for authentication precision evaluation

Read more

Summary

INTRODUCTION

Because most application systems support Internet access for general users, identifying persons with their own body has become the trend for users to access application systems. Time slicing technique are introduced in the framework to prepare ML-based training datasets along with new measure metrics developed for authentication precision evaluation. The proposed core process currently supports both ECG reference database and trained Neural Network (NN) reference engine as the evaluation model for any ML-based ECG authentication mechanism to use them. An ECG based user authentication request associated with newly received ECG data is generated and the ECG data need to adopt data pre-process techniques to obtain filtered data with higher quality (less noise) first. The new Matlab toolbox with this paper contains all proposed mechanisms, metrics and sample data with demonstrations using various ML techniques This toolbox has been developed and publicly available for further investigation.

AUTHENTICATION CATEGORIZATION BASED ON USE CASES
TIME SLICING AND MACHINE LEARNING
DATA QUALITY MEASURES
MATLAB TOOLBOX
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call