Robust Recognition of Reading Activity in Transit Using Wearable 
Electrooculography

Bulling, Andreas; Ward, Jamie A.; Gellersen, Hans; Tröster, Gerhard

doi:10.1007/978-3-540-79576-6_2

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Conference Paper

Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Bulling, A., Ward, J. A., Gellersen, H., & Tröster, G. (2008). Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography. In J. Indulska, D. J. Patterson, T. Rodden, & M. Ott (Eds.), Pervasive Computing. Berlin: Springer. doi:10.1007/978-3-540-79576-6_2.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0026-C3D2-9

Abstract

In this work we analyse the eye movements of people in transit in\u000A an everyday environment using a wearable electrooculographic (EOG)\u000A system. We compare three approaches for continuous recognition of\u000A reading activities: a string matching algorithm which exploits typical\u000A characteristics of reading signals, such as saccades and fixations;\u000A and two variants of Hidden Markov Models (HMMs) ‐ mixed Gaussian\u000A and discrete. The recognition algorithms are evaluated in an experiment\u000A performed with eight subjects reading freely chosen text without\u000A pictures while sitting at a desk, standing, walking indoors and outdoors,\u000A and riding a tram. A total dataset of roughly 6 hours was collected\u000A with reading activity accounting for about half of the time. We were\u000A able to detect reading activities over all subjects with a top recognition\u000A rate of 80.2% (71.0% recall, 11.6% false positives) using string\u000A matching. We show that EOG is a potentially robust technique for\u000A reading recognition across a number of typical daily situations.