eduzhai > Applied Sciences > Engineering >

Deep Multitask Learning for Pervasive BMI Estimation and Identity Recognition in Smart Beds

  • Save

... pages left unread,continue reading

Document pages: 11 pages

Abstract: Smart devices in the Internet of Things (IoT) paradigm provide a variety ofunobtrusive and pervasive means for continuous monitoring of bio-metrics andhealth information. Furthermore, automated personalization and authenticationthrough such smart systems can enable better user experience and security. Inthis paper, simultaneous estimation and monitoring of body mass index (BMI) anduser identity recognition through a unified machine learning framework usingsmart beds is explored. To this end, we utilize pressure data collected fromtextile-based sensor arrays integrated onto a mattress to estimate the BMIvalues of subjects and classify their identities in different positions byusing a deep multitask neural network. First, we filter and extract 14 featuresfrom the data and subsequently employ deep neural networks for BMI estimationand subject identification on two different public datasets. Finally, wedemonstrate that our proposed solution outperforms prior works and severalmachine learning benchmarks by a considerable margin, while also estimatingusers BMI in a 10-fold cross-validation scheme.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×