User authentication based on keystroke analysis of long free texts with a reduced number of features

These days there are some papers about user classification and authentication based on keystroke patterns from typing long and free text. We suggest more accurate and convenient authentication model which is inspired by Pilsung et al. (2009). Unlike Gunetti and Picardi (2005), our model doesn't need any kind of user-defined parameters and isn't sensitive to noise. And the suggested model incorporates keystroke dynamics concepts more than Pilsung et al. (2009).