الفهرس 
Chapter 1: IntroductionOnly 14 pages are availabe for public view
 |  | from | 192 |  |  |
| | | from | 192 | | |
Abstract
Biometric features are extensively employed for security purposes, but they
are vulnerable to threats and can be lost or compromised. Electrocardiogram
(ECG) has been utilized as one of the most favorable biometrics. Due to uniqueness
of electrocardiogram (ECG) is very high even in identical twins, so it can be used as
biometric signature. However, it contains confidential patient health information and
personal identification details. ECG needs to be encrypted before transmission
through public network to avoid the data being breached and hacked. On the other
hand, caregivers or doctors receive the encrypted ECG signal, which can be
decrypted using same key and analyze of patient’s ECG signal. Moreover, security
flaws take place in hacking scenarios. Therefore, original biometrics must be secured
by preventing them from being used in biometric databases. The enhanced security
trend in biometric authentication is cancelable biometrics. Cancelable biometric
systems can be built by generating regularly repeated distortions of biometric
features to secure the sensitive data of the users. When cancelable features are
disclosed, distortion parameters are modified, and new cancelable templates are
generated.
In this thesis, encryption technique based on convolution and substitution is
proposed. By taking random values of ECG signal and multiplying by random
number, then get an average of them to be encrypted. Finally, chaotic ECG signal is
completely different than original signal. The security of the proposed system will
depend on random kernel coefficients, substitution process and length of kernel
filter. Simulation results show that the proposed system is capable of encrypting
ECG signals for secure communication efficiently.
Cancelable ECG recognition system based on the 3D chaotic logistic
map encryption is also proposed, which has highly efficient random characteristics
with confusion and diffusion properties. Normal and abnormal ECG signals have
been used to test the proposed cancelable biometric recognition system, and good
access results have been obtained. The results of the simulation indicate that the
proposed system is secure, reliable, and practicable even with ECG signals for
patients.
For all the proposed systems, the experimental results on different datasets
prove that the proposed systems achieve high ability to efficiently encrypt different
biometric databases of normal ECG signals or abnormal ones that provide better
recognition performance with high efficiency. These results show that the proposed
systems are secure, reliable, feasible and also achieve high correlation rates with low
equal error rates (EER) that proved high security levels of the systems.