Learn More
—We propose a lightweight, and temporally and spatially aware user behaviour modelling technique for sensor-based authentication. Operating in the background, our data driven technique compares current behaviour with a user profile. If the behaviour deviates sufficiently from the established norm, actions such as explicit authentication can be triggered. To(More)
One of the main reasons why smartphone users do not adopt screen locking mechanisms is due to the inefficiency of entering a PIN/pattern each time they use their phone. To address this problem we designed a context-sensitive screen locking application which asked participants to enter a PIN/pattern only when necessary, and evaluated its impact on efficiency(More)
Modern mobile devices come with an array of sensors that support many interesting applications. However, sensors have different sampling costs (e.g., battery drain) and benefits (e.g., accuracy) under different circumstances. In this work we investigate the trade-off between the cost of using a sensor and the benefit gained from its use, with application to(More)
Current methods of behavioral data collection from mobile devices either require significant involvement from participants to verify the 'ground truth' of the data, or approximations that involve post-experiment comparisons to seed data. In this paper we argue that user involvement can be gracefully reduced by performing more intelligent seed comparisons.(More)
A majority of Stroke survivors have an arm impairment (up to 80%), which persists over the long term (>12 months). Physiotherapy experts believe that a rehabilitation Aide-Memoire could help these patients [25]. Hence, we designed, with the input of physiotherapists, Stroke experts and former Stroke patients, the Aide-Memoire Stroke (AIMS) App to help(More)
  • 1