This dataset is described in the following paper that has recently been accepted for publication: Syed, Z.; Helmick, J.; Banerjee, S.; Cukic, B., "Touch Gesture-based Authentication on Mobile Devices: The Effects of User Posture, Device Size, Configuration, and Inter-session Variability," Journal of Systems and Software (Accepted Nov 13, 2018), https://doi.org/10.1016/j.jss.
The below table compares our dataset to four other currently publicly available datasets in this domain. The paper provides further analysis of the limitations and threats to validity stemming from collection limitations inherent
in each of these other datasets. The collection protocol used to create our dataset allows for efficient evaluation of hypotheses related to screen size (phones & tablets), manufacturer,
user posture (in-hand vs on a flat surface), screen orientation, intra-session variability, and inter-session variability. This design framework which controls the factors and includes replication of participants, improves
statistical validity, reliability, and replicability of the inferences. Although other works have contained subsets of these factors in various forms, none have exposed all participants to all of these factors in a controlled