• DocumentCode
    190162
  • Title

    Pulse Active Transform (PAT): A non-invertible transformation with application to ECG biometric authentication

  • Author

    Safie, Sairul I. ; Nurfazira, H. ; Azavitra, Z. ; Soraghan, John J. ; Petropoulakis, Lykourgos

  • Author_Institution
    Malaysian Inst. of Ind. Technol. (MITEC), Univ. Kuala Lumpur, Johor Bahru, Malaysia
  • fYear
    2014
  • fDate
    14-16 April 2014
  • Firstpage
    667
  • Lastpage
    671
  • Abstract
    This paper presents a new transformation technique called the Pulse Active transform (PAT). The PAT uses a series of harmonically related periodic triangular waveforms to decompose a signal into a finite set of pulse active features. These features incorporate the signal´s information in the pulse active domain, and which are subsequently processed for some desired application. PAT is non-invertible thus ensuring complete security of the original signal source. In this paper PAT is demonstrated on an ECG signal and used for biometric authentication. The new transformation technique is tested on 112 PTB subjects. It is shown in this paper that the new transformation has a superior performance compared to the conventional characteristic based feature extraction methods with additional security to avoid recovery of the original ECG.
  • Keywords
    biometrics (access control); electrocardiography; feature extraction; medical signal processing; signal sources; ECG biometric authentication; ECG signal; PAT; PTB subjects; biometric authentication; characteristic based feature extraction methods; harmonically related periodic triangular waveforms; noninvertible transformation; pulse active features; pulse active transform; Authentication; Databases; Electrocardiography; Feature extraction; Region 10; Transforms; Biometric Authentication; Electrocardiogram; Pulse Active Transform;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Region 10 Symposium, 2014 IEEE
  • Conference_Location
    Kuala Lumpur
  • Print_ISBN
    978-1-4799-2028-0
  • Type

    conf

  • DOI
    10.1109/TENCONSpring.2014.6863117
  • Filename
    6863117