Smartwatch-based activity recognition: A machine learning approach

Smartwatches and smartphones contain accelerometers and gyroscopes that sense a user's movements, and can help identify the activity a user is performing. Research into smartphone-based activity recognition has exploded over the past few years, but research into smartwatch-based activity recogn...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) 2016-02, p.426-429
Hauptverfasser: Weiss, Gary M., Timko, Jessica L., Gallagher, Catherine M., Yoneda, Kenichi, Schreiber, Andrew J.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Smartwatches and smartphones contain accelerometers and gyroscopes that sense a user's movements, and can help identify the activity a user is performing. Research into smartphone-based activity recognition has exploded over the past few years, but research into smartwatch-based activity recognition is still in its infancy. In this paper we compare smartwatch and smartphone-based activity recognition, and smartwatches are shown to be capable of identifying specialized hand-based activities, such as eating activities, which cannot be effectively recognized using a smartphone (e.g., smartwatches can identify the "drinking" activity with 93.3% accuracy while smartphones achieve an accuracy of only 77.3%). Smartwatch-based activity recognition can form the basis of new biomedical and health applications, including applications that automatically track a user's eating habits.
ISSN:2168-2208
DOI:10.1109/BHI.2016.7455925