User identification using Keystroke Dynamics

Traditional user authentication or identification systems are interested in something that you possess (like a key, an identification card, etc.) or something you already know (like a password, or a PIN). With biometrics, this interest has been shifted towards a different approach :something that are part of you (fingerprints or face) or something you make (e.g., handwritten signature or voice). Identification system works in such a way that the system obtains one sample and compares with each record in the database. This method is a comparison named “one-to-many. Behaviours and rhythms of the typing characters are used as a biometric authentication system named as Keystroke Dynamics. Unlike most identification systems that require specific hardware, keystroke dynamics requires only a keyboard. In the proposed approach, short fixed text is used like in the login approaches. The d-variate Gaussian, kNN and decision tree algorithms are tested on CMU keystroke database.