Applications for Future Internet. International Summit, AFI 2016, Puebla, Mexico, May 25-28, 2016, Revised Selected Papers

Research Article

Sensor Abstracted Extremity Representation for Automatic Fugl-Meyer Assessment

Download45 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-49622-1_17,
        author={Patrick Heyer and Felipe Orihuela-Espina and Luis Castrej\^{o}n and Jorge Hern\^{a}ndez-Franco and Luis Sucar},
        title={Sensor Abstracted Extremity Representation for Automatic Fugl-Meyer Assessment},
        proceedings={Applications for Future Internet. International Summit, AFI 2016, Puebla, Mexico, May 25-28, 2016, Revised Selected Papers},
        proceedings_a={AFI360},
        year={2017},
        month={1},
        keywords={Automatic motor dexterity assessment Gesture classification Gesture representation Sensor independent representation Automatic Fugl-Meyer},
        doi={10.1007/978-3-319-49622-1_17}
    }
    
  • Patrick Heyer
    Felipe Orihuela-Espina
    Luis Castrejón
    Jorge Hernández-Franco
    Luis Sucar
    Year: 2017
    Sensor Abstracted Extremity Representation for Automatic Fugl-Meyer Assessment
    AFI360
    Springer
    DOI: 10.1007/978-3-319-49622-1_17
Patrick Heyer1,*, Felipe Orihuela-Espina1, Luis Castrejón2, Jorge Hernández-Franco3, Luis Sucar1
  • 1: Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE)
  • 2: Hospital Universitario de la Benemérita Universidad Autónoma de Puebla (HU-BUAP)
  • 3: Instituto Nacional de Neurología y Neurocirugía (INNN)
*Contact email: patrickhey@prodigy.net.mx

Abstract

Given its virtually algorithmic process, the Fugl-Meyer Assessment (FMA) of motor recovery is prone to automatization reducing subjectivity, alleviating therapists’ burden and collaterally reducing costs. Several attempts have been recently reported to achieve such automatization of the FMA. However, a cost-effective solution matching expert criteria is still unfulfilled, perhaps because these attempts are sensor-specific representation of the limb or have thus far rely on a trial and error strategy for building the underpinning computational model. Here, we propose a sensor abstracted representation. In particular, we improve previously reported results in the automatization of FMA by classifying a manifold embedded representation capitalizing on quaternions, and explore a wider range of classifiers. By enhancing the modeling, overall classification accuracy is boosted to 87% (mean: 82% ± 4.53:) well over the maximum reported in literature thus far 51.03% (mean: 48.72 ± std: 2.10). The improved model brings automatic FMA closer to practical usage with implications for rehabilitation programs both in ward and at home.