Skip to main navigation Skip to search Skip to main content

Evolutionary Optimization of User Intent Recognition for Transfemoral Amputees

    • Cleveland State University
    • Cleveland VA Medical Center

    Research output: Contribution to journalArticlepeer-review

    Abstract

    Lower-limb prosthetic legs help amputees regain their walking ability. User intent recognition is utilized to infer human gait mode (fast walk, slow walk, etc.) so the controller can be adjusted depending on the detected gait mode. In this paper, mechanical sensor data is collected from an able-bodied subject and used for user intent recognition. Feature extraction, principal component analysis, correlation analysis, and K-nearest neighbor methods are used, modified, and optimized with an evolutionary algorithm for improved performance. The optimized system successfully classifies four different walking modes with an accuracy of 96%.

    Original languageAmerican English
    JournalBiomedical Circuits and Systems Conference (BioCAS), 2015 IEEE
    DOIs
    StatePublished - Jan 1 2015

    Keywords

    • user intent recognition; lower - limb prosthesis ; evolutionary algorithm ; K nearest neighbor

    Disciplines

    • Biomechanical Engineering
    • Electrical and Computer Engineering

    Cite this