• DocumentCode
    3756804
  • Title

    Ankle Rehabilitation System with Feedback from a Smartphone Wireless Gyroscope Platform and Machine Learning Classification

  • Author

    Robert LeMoyne;Timothy Mastroianni;Anthony Hessel;Kiisa Nishikawa

  • Author_Institution
    Dept. of Biol. Sci., Northern Arizona Univ., Flagstaff, AZ, USA
  • fYear
    2015
  • Firstpage
    406
  • Lastpage
    409
  • Abstract
    With the prevalence of traumatic brain injury and associated motor function impairment, an advance in the capacity to measure the efficacy of a rehabilitation strategy is a topic of considerable interest. For example, the development of a rehabilitation system that can quantify the efficacy to an ankle dorsiflexion therapy prescription would be beneficial. An ankle rehabilitation system is presented that amalgamates multiple technologies, such as a smartphone (iPhone) wireless gyroscope platform, machine learning, and 3D printing. The ankle rehabilitation system is produced by mostly 3D printing. A smartphone wireless gyroscope platform records the ankle rehabilitation system´s therapy usage with wireless transmission to the Internet as an email attachment. The gyroscope signal data is processed for machine learning. A support vector machine attains 97% classification between a hemiplegic affected ankle and unaffected ankle feature set while using the ankle rehabilitation system. The application can be readily applied to a homebound setting of the subject´s convenience.
  • Keywords
    "Gyroscopes","Wireless communication","Wireless sensor networks","Medical treatment","Communication system security","Support vector machines","Electronic mail"
  • Publisher
    ieee
  • Conference_Titel
    Machine Learning and Applications (ICMLA), 2015 IEEE 14th International Conference on
  • Type

    conf

  • DOI
    10.1109/ICMLA.2015.213
  • Filename
    7424346