Key result
An ECG biometric authentication scheme using Linear Prediction Coding provided similar security with lower computational complexity and communication overhead compared to the fuzzy vault scheme.
An LPC-based ECG biometric authentication scheme provides secure, low-complexity patient identification for e-healthcare systems.
May support efficient ECG biometrics for e-health authentication; leaves open clinical validation before practice adoption.
In this paper, we propose an electrocardiogram (ECG) biometric scheme that can authenticate patient identities in a healthcare system while protecting the privacy of their transmitted electrocardiogram signal. The presented algorithm is a new technique allowing the authentication device and the target application to share securely the ECG authentication features via an untrusted channel. The technique hides the ECG sensitive data based on the Linear Prediction Coding (LPC). This solution comes as an alternative to the fuzzy vault scheme. In fact we prove, by assessing the algorithm on ECG-Id physionet database, that concealing the features using the LPC technique ensures a similar security level while offering a low computational complexity and communication overhead compared with the fuzzy vault scheme. Moreover, we show that an acceptable recognition rate is preserved.
No takes yet. Share an insight, caveat, or question.
Zaghouani et al. (2017) studied ECG biometric authentication. ECG biometric scheme based on Linear Prediction Coding (LPC) vs. Fuzzy vault scheme was evaluated on Security level, computational complexity, communication overhead, and recognition rate. An ECG biometric authentication scheme using Linear Prediction Coding provided similar security with lower computational complexity and communication overhead compared to the fuzzy vault scheme.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: