eprintid: 1535735 rev_number: 21 eprint_status: archive userid: 608 dir: disk0/01/53/57/35 datestamp: 2017-01-14 22:03:05 lastmod: 2021-12-21 23:15:59 status_changed: 2018-08-03 07:39:12 type: proceedings_section metadata_visibility: show creators_name: Bulling, A creators_name: Ward, JA creators_name: Gellersen, H-W creators_name: Tröster, G title: Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography ispublished: pub divisions: UCL divisions: B02 divisions: C07 keywords: Hide Markov Model, Activity Recognition, String Match, Reading Activity, Baseline Drift note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. 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. date: 2008-05 date_type: published publisher: Springer, Berlin, Heidelberg official_url: https://doi.org/10.1007/978-3-540-79576-6_2 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1200831 doi: 10.1007/978-3-540-79576-6_2 lyricists_name: Ward, Jamie lyricists_id: JAWAR26 full_text_status: public series: Lecture Notes in Computer Science publication: PERVASIVE volume: 5013 place_of_pub: Sydney, Australia pagerange: 19-37 event_title: 6th International Conference on Pervasive Computing: Pervasive 2008 isbn: 978-3-540-79576-6 book_title: Proceedings of the 6th International Conference on Pervasive Computing: Pervasive 2008 citation: Bulling, A; Ward, JA; Gellersen, H-W; Tröster, G; (2008) Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography. In: Proceedings of the 6th International Conference on Pervasive Computing: Pervasive 2008. (pp. pp. 19-37). Springer, Berlin, Heidelberg: Sydney, Australia. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/1535735/1/Ward_BWGT08pervasive.pdf