phat 15(2): e2

Research Article

Improving classification of posture based attributed attention assessed by ranked crowd-raters

Download180 downloads
  • @ARTICLE{10.4108/icst.pervasivehealth.2015.259171,
        author={Patrick Heyer and Jesus Rivas and Luis Sucar and Felipe Orihuela-Espina},
        title={Improving classification of posture based attributed attention assessed by ranked crowd-raters},
        journal={EAI Endorsed Transactions on Pervasive Health and Technology},
        volume={1},
        number={2},
        publisher={IEEE},
        journal_a={PHAT},
        year={2015},
        month={8},
        keywords={attention, adaptation, posture, neurorehabilitation, semi-supervised learning},
        doi={10.4108/icst.pervasivehealth.2015.259171}
    }
    
  • Patrick Heyer
    Jesus Rivas
    Luis Sucar
    Felipe Orihuela-Espina
    Year: 2015
    Improving classification of posture based attributed attention assessed by ranked crowd-raters
    PHAT
    EAI
    DOI: 10.4108/icst.pervasivehealth.2015.259171
Patrick Heyer1,*, Jesus Rivas1, Luis Sucar2, Felipe Orihuela-Espina2
  • 1: National Institute for Astrophysics, Optics and Electronics
  • 2: National Institute for Astrophysics, Optics and Electronics,
*Contact email: patrickhey@prodigy.net.mx

Abstract

Attribution of attention from observable body posture is plausible, providing additional information for affective computing applications. We previously reported a promissory 69. 72 ± 10. 50 (μ ± σ) of F-measure to use posture as a proxy for attributed attentional state with implications for affective computing applications. Here, we aim at improving that classification rate by reweighting votes of raters giving higher confidence to those raters that are representative of the raters population. An increase to 75. 35 ± 11. 66 in F-measure was achieved. The improvement in predictive power by the classifier is welcomed and its impact is still being assessed.