We demonstrate that a person's behavioral and environmental context can be automatically recognized by harnessing the sensors built into smartphones and smartwatches. We propose a generic system that can simultaneously recognize many contextual attributes from diverse behavioral domains. By fusing complementary information from different types of sensors our system successfully recognizes fine details of work and leisure activities, body movement, transportation, and more. Health monitoring, clinical intervention, aging care, personal assistance and many more applications will benefit from automatic, frequent and detailed context recognition.
from cs.AI updates on arXiv.org http://ift.tt/2dc8jsU
via IFTTT
No comments:
Post a Comment