Abstract
The main objective of this research study is to enhance the functionality of an Android pattern lock application by determining whether the time elements of a touch operation, in particular time on dot (TOD) and time between dot (TBD), can be accurately used as a biometric identifier. The three hypotheses that were tested through this study were the following–H1: there is a correlation between the number of touch stroke features used and the accuracy of the touch operation biometric system; H2: there is a correlation between pattern complexity and accuracy of the touch operation biometric system; H3: there is a correlation between user training and accuracy of the touch operation biometric system. Convenience sampling and a within-subjects design involving repeated measures were incorporated when testing an overall sample size of 12 subjects drawn from a university population who gave a total of 2,096 feature extracted data. Analysis was done using the Dynamic Time Warping (DTW) Algorithm. Through this study, it was shown that the extraction of one-touch stroke biometric feature coupled with user training was able to yield high average accuracy levels of up to 82%. This helps build a case for the introduction of biometrics into smart devices with average processing capabilities as they would be able to handle a biometric system without it compromising on the overall system performance. For future work, it is recommended that more work be done by applying other classification algorithms to the existing data set and comparing their results with those obtained with DTW.
Highlights
Mobile computing devices have been growing in popularity globally over the recent years
Once they added an additional two features, namely, finger size and pressure, the equal error rate value dropped to 12.2%, thereby concluding that more features extracted resulted in more accuracy. e extraction of multiple features resulted in low EER figures; it raises the potential challenge of keeping device processing overheads to a bare minimum as this is the only way biometric technology can successfully permeate all levels of smartphones irrespective of their technological capabilities
Is research study involves the use of two measurable touchstroke time variables, the finger-in-dot time and the finger-in-between-dot time, because the time element of a touch operation has been previously shown by the researchers such as Dhage et al [15] and Alghamdi and Elrefaei [9] to produce the most consistent and actionable information especially when calculating the false acceptance rates (FARs) and false rejection rates (FRRs). is was partially informed by the need to keep processing overheads to a bare minimum to make the system lucrative for any future integration with low-end smart devices. is approach differs from that of [9] who extracted a total of 31 features
Summary
Mobile computing devices have been growing in popularity globally over the recent years. Most of the mobile devices currently in use maintain the privacy and security of the device by authenticating a user at each login. Research by Sae-Bae et al [4] showed that the speed at which users type on flash glass, what is currently on smart mobile devices, was 31% slower that typing on a physical keyboard. E same research showed that users countered this problem by shortening their passwords which in turn led to a shorter login time and thereby resulted in an insecure mobile computing environment. It was inferred that login time was very critical on the part of the users when it came to authenticate them
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
