Kumar, Gunjan, Jerbi, Houssem, Gurrin, CathalORCID: 0000-0003-2903-3968 and O'Mahony, Michael
(2014)
Towards activity recommendation from lifelogs.
In: 16th International Conference on Information Integration and Web-based Applications & Services (iiWAS2014), 406 Dec 2014, Hanoi, Vietnam.
With the increasing availability of passive, wearable sensor devices, digital lifelogs can now be captured for individuals. Lifelogs contain a digital trace of a person’s life, and are characterised by large quantities of rich contextual data. In this paper, we propose a content-based recommender sys- tem to leverage such lifelogs to suggest activities to users. We model lifelogs as timelines of chronological sequences of activity objects, and describe a recommendation framework in which a two-level distance metric is proposed to measure the similarity between current and past timelines. An ini- tial evaluation of our activity recommender performed using a real-world lifelog dataset demonstrates the utility of our approach.