Automatic event-based synchronization of multimodal data streams from wearable and ambient sensors

D. Bannach, O.D. Amft, P. Lukowicz

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

11 Citations (Scopus)
111 Downloads (Pure)

Abstract

A major challenge in using multi-modal, distributed sensor systems for activity recognition is to maintain a temporal synchronization between individually recorded data streams. A common approach is to use well defined ‘synchronization actions’ performed by the user to generate, easily identifiable pattern events in all recorded data streams. The events are then used to manually align data streams. This paper proposes an automatic method for this synchronization. We demonstrate that synchronization actions can be automatically identified and used for stream synchronization across widely different sensors such as acceleration, sound, force, and a motion tracking system. We describe fundamental properties and bounds of our event-based synchronization approach. In particular, we show that the event timing relation is transitive for sensor groups with shared members. We analyzed our synchronization approach in three studies. For a large dataset of 5 users and totally 308 data stream minutes we achieved a synchronization error of 0.3 s for more than 80% of the stream.
Original languageEnglish
Title of host publicationSmart sensing and context
EditorsP. Barnaghi, K. Moessner, M. Presser, S. Meissner
Place of PublicationBerlin
PublisherSpringer
Pages135-148
Number of pages14
ISBN (Print)978-3-642-04470-0
DOIs
Publication statusPublished - 2009
Eventconference; 4th European Conference, (EuroSSC 2009), Guildford, UK, September 16-18, 2009 -
Duration: 1 Jan 2009 → …

Publication series

NameLecture Notes in Computer Science
Volume5741
ISSN (Print)0302-9743

Conference

Conferenceconference; 4th European Conference, (EuroSSC 2009), Guildford, UK, September 16-18, 2009
Period1/01/09 → …
Other4th European Conference, (EuroSSC 2009), Guildford, UK, September 16-18, 2009

Fingerprint Dive into the research topics of 'Automatic event-based synchronization of multimodal data streams from wearable and ambient sensors'. Together they form a unique fingerprint.

  • Cite this

    Bannach, D., Amft, O. D., & Lukowicz, P. (2009). Automatic event-based synchronization of multimodal data streams from wearable and ambient sensors. In P. Barnaghi, K. Moessner, M. Presser, & S. Meissner (Eds.), Smart sensing and context (pp. 135-148). (Lecture Notes in Computer Science; Vol. 5741). Springer. https://doi.org/10.1007/978-3-642-04471-7_11