Evolutionary Optimization of User Intent Recognition for Transfemoral Amputees

Authors

Gholamreza Khademi, Cleveland State University
Hanieh Mohammadi, Cleveland State University
Daniel J. Simon, Cleveland State UniversityFollow
Elizabeth C. Hardin, Cleveland VA Medical Center

Document Type

Article

Publication Date

2015

Publication Title

Biomedical Circuits and Systems Conference (BioCAS), 2015 IEEE

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%.

Comments

This research was supported by National Science Foundation Grant 1344954.

Repository Citation

Khademi, Gholamreza; Mohammadi, Hanieh; Simon, Daniel J.; and Hardin, Elizabeth C., "Evolutionary Optimization of User Intent Recognition for Transfemoral Amputees" (2015). Electrical and Computer Engineering Faculty Publications. 330.
https://engagedscholarship.csuohio.edu/enece_facpub/330

Original Citation

G. Khademi, H. Mohammadi, D. Simon and E. C. Hardin, "Evolutionary optimization of user intent recognition for transfemoral amputees," in Biomedical Circuits and Systems Conference (BioCAS), 2015 IEEE, 2015, pp. 1-4.

DOI

10.1109/BioCAS.2015.7348280