Browsing by Author "Lai, W. K."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Dynamic keystroke analysis using AR model(IEEE, 2004-12-08) Eltahir, Wasil E.; Salami, Momoh-Jimoh E.; Ismail, Ahmad F.; Lai, W. K.The design and development of a pressure sensor based typing biometrics authentication system (BAS) is discussed in this paper. The dynamic keystroke, represented by its time duration and force generates a waveform, which when concatenated results in a user's typing pattern for the typed password. The design of the BAS is in two stages, whereby the hardware comprising the pressure sensor and the associated data acquisition system (DAS) is first implemented. The system DAS has been designed using LabVIEW software. Furthermore several data preprocessing techniques have been used to improve the quality of the acquired waveforms. The second stage involves a classifier to authenticate the users. This paper discusses a new data classifier technique based on autoregressive signal modeling (AR), which has been developed so as to correctly identify and authenticate the users of the system. Some experiments have been conducted to show the validity of the overall BAS performance. The results obtained have shown that this proposed system is reliable with many potential applications for computer security.Item Hardware design, development and evaluation of a pressure-based typing biometrics authentication system(Proceedings of the Eighth Australian and New Zealand Intelligent Information Systems Conference (ANZIIS), 2003-12) Eltahir, Wasil E.; Lai, W. K.; Salami, Momoh-Jimoh E.; Ismail, A. F.The hardware design of a pressure based typing biometrics authentication system (BAS) is discussed in this paper. The dynamic keystroke is represented by its time duration (t) and force (F) applied to constitute a waveform, which when concatenated compose a complete pattern for the entered password. Hardware design is the first part in designing the complete pressure-based typing (BAS) in order to ensure that the best data to represent the keystroke pattern of the user is captured. The system has been designed using LabVIEW software. Several data preprocessing techniques have been used to improve the acquired waveforms. An experiment was conducted to show the validity of the design in representing keystroke dynamics and preliminary results have shown that the designed system can successfully capture password patterns.