Home > Research > Publications & Outputs > Robust Recognition of Reading Activity in Trans...

Electronic data

Links

Text available via DOI:

View graph of relations

Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Publication date2008
Host publicationLecture Notes in Computer Science: Pervasive Computing
EditorsJ. Indulska, D. J. Patterson, T. Rodden, M. Ott
PublisherSpringer
Pages19-37
Number of pages19
Volume5013
ISBN (print)978-3-540-79575-9
<mark>Original language</mark>English
EventPervasive Computing 2008 - Sydney, Australia
Duration: 1/05/2008 → …

Conference

ConferencePervasive Computing 2008
CitySydney, Australia
Period1/05/08 → …

Conference

ConferencePervasive Computing 2008
CitySydney, Australia
Period1/05/08 → …

Abstract

In this work we analyse the eye movements of people in transit in an everyday environment using a wearable electrooculographic (EOG) system. We compare three approaches for continuous recognition of reading activities: a string matching algorithm which exploits typical characteristics of reading signals, such as saccades and fixations; and two variants of Hidden Markov Models (HMMs) - mixed Gaussian and discrete. The recognition algorithms are evaluated in an experiment performed with eight subjects reading freely chosen text without pictures while sitting at a desk, standing, walking indoors and outdoors, and riding a tram. A total dataset of roughly 6 hours was collected with reading activity accounting for about half of the time. We were able to detect reading activities over all subjects with a top recognition rate of 80.2% (71.0% recall, 11.6% false positives) using string matching. We show that EOG is a potentially robust technique for reading recognition across a number of typical daily situations.