A User-specific Machine Learning approach for improving touch accuracy on mobile devices
Daryl Weir; Simon Rogers; Roderick Murray-Smith; Markus Löchtefeld
In: Proceedings of the 25th ACM Symposium on User Interface Software and Technology. ACM Symposium on User Interface Software and Technology (UIST-12), October 7-10, Cambridge, Masachusetts, USA, ACM, 10/2012.
We present a flexible Machine Learning approach for learn- ing user-specific touch input models to increase touch ac- curacy on mobile devices. The model is based on flexible, non-parametric Gaussian Process regression and is learned using recorded touch inputs. We demonstrate that signifi- cant touch accuracy improvements can be obtained when ei- ther raw sensor data is used as an input or when the devices reported touch location is used as an input, with the latter marginally outperforming the former. We show that learned offset functions are highly nonlinear and user-specific and that user-specific models outperform models trained on data pooled from several users. Crucially, significant performance improvements can be obtained with a small (≈ 200) num- ber of training examples, easily obtained for a particular user through a calibration game or from keyboard entry data.