Open AccessAccess Control System with the Authentication Mechanism Implementation using Artificial Neural Network
Author(s) -
Ye. P. Belova,
Ирина Владимировна Машкина
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1488/1/012025
Subject(s) - biometrics , computer science , artificial neural network , access control , authentication (law) , network administrator , authorization , control (management) , system administrator , computer security , formant , artificial intelligence , vowel , speech recognition
Biometric access control system is presently one of the innovative Information Security (IS) technologies. The article shows a possibility to use this technology to control logical access as well as the technologies provided to administrator-users of Information Systems (IS). A method to compare biometric data of users who have administrator rights is proposed. Individuals’ unique voice parameters and Artificial Neural Networks (ANN) lay behind this method. The paper considers the specific ANN learning issues to solve the challenge over storing biometric patterns of users and authenticating them by values of the fourth formant characteristics as regard to the selected vowel phonemes as well as by additional voice qualities. The first and second type recognition errors are estimated. The architecture of the user authentication and authorization system that implements the method to monitor administrator-users of information systems has been designed.