| Literature DB >> 26737948 |
Javier Hernandez, Daniel J McDuff, Rosalind W Picard.
Abstract
The large-scale adoption of smartphones during recent years has created many opportunities to improve health monitoring and care delivery. In this work, we demonstrate that motion sensors available in off-the-shelf smartphones can capture physiological parameters of a person during stationary postures, even while being carried in a bag or a pocket. In particular, we develop methods to extract heart and breathing rates from accelerometer data and compare them with measurements obtained with FDA-cleared sensors. We evaluated their accuracy on 12 people across different still body postures (pre- and post- exercise) and were able to reach mean absolute errors of 1.16 beats per minute (STD: 3) and 0.26 breaths per minute (STD: 0.5) when considering different conditions. Furthermore, we evaluated the same methods during regular phone activities, such as when watching a video or listening to a conversation, yielding increased but still comparable error rates for some conditions.Entities:
Mesh:
Year: 2015 PMID: 26737948 DOI: 10.1109/EMBC.2015.7320048
Source DB: PubMed Journal: Conf Proc IEEE Eng Med Biol Soc ISSN: 1557-170X