Short Paper

Sparse Selection of Training Data for Touch Correction Systems
Daryl Weir, University of Glasgow, UK
Daniel Buschek, University of Munich (LMU), Germany
Simon Rogers, University of Glasgow, UK
Time: Fri 11:36 - 11:48 | Session: Touch Screen Interaction and Multi-modal User Interfaces | Location: Gro├če Aula

Touch offset models which improve input accuracy on mobile touch screen devices typically require the use of a large num- ber of training points. In this paper, we describe a method for selecting training points such that high performance can be attained with fewer data. We use the Relevance Vector Machine (RVM) algorithm, and show that performance im- provements can be obtained with fewer than 10 training ex- amples. We show that the distribution of training points is conserved across users and contains interesting structure, and compare the RVM to two other offset prediction models for small training set sizes.

MobileHCI 2013 Proceedings in the ACM Digital Library.

Important Dates

ACM Logo
SIGCHI Logo
LMU Logo

Donors

Google Logo
Grand Logo
Intel Software Logo
Microsoft Research Logo
Nokia Logo
SMI Logo
Telefonica Logo
Yahoo! Labs Logo