Download - This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry.

Transcript
Page 1: This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry.

This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry in persons with transtibial amputations. J Rehabil Res Dev. 2013;50(9):XXX–XXX. http://dx.doi.org/10.1682/JRRD.2012.12.0233

Slideshow ProjectDOI:10.1682/JRRD.2012.12.0233JSP

Classifying prosthetic use via accelerometry in persons with

transtibial amputations

Morgan T. Redfield, MSEE; John C. Cagle, BSE; Brian J. Hafner, PhD; Joan E. Sanders, PhD

Page 2: This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry.

This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry in persons with transtibial amputations. J Rehabil Res Dev. 2013;50(9):XXX–XXX. http://dx.doi.org/10.1682/JRRD.2012.12.0233

Slideshow ProjectDOI:10.1682/JRRD.2012.12.0233JSP

• Aim– Use 3-axis accelerometer to characterize activities and

body postures in transtibial amputation. • Relevance– How persons with amputation use their prostheses over

time may facilitate rehabilitation and enhance understanding of prosthesis functionality.

– Existing monitoring and classification systems are often limited, record data over short periods, and/or classify limited activities and body postures.

Page 3: This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry.

This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry in persons with transtibial amputations. J Rehabil Res Dev. 2013;50(9):XXX–XXX. http://dx.doi.org/10.1682/JRRD.2012.12.0233

Slideshow ProjectDOI:10.1682/JRRD.2012.12.0233JSP

Method• Accelerometers were mounted on prosthetic

pylons of 10 persons with transtibial amputation as they performed preset routine of actions.

• Accelerometer data was postprocessed with binary decision tree to:– Identify when prosthesis was being worn.– Classify use as movement, standing, or sitting.

• Classifications were compared to visual observation by study researchers.

Page 4: This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry.

This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry in persons with transtibial amputations. J Rehabil Res Dev. 2013;50(9):XXX–XXX. http://dx.doi.org/10.1682/JRRD.2012.12.0233

Slideshow ProjectDOI:10.1682/JRRD.2012.12.0233JSP

Results

• Classifier achieved average accuracy of 96.6%.

Page 5: This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry.

This article and any supplementary material should be cited as follows: Redfield MT, Cagle JC, Hafner BJ, Sanders JE. Classifying prosthetic use via accelerometry in persons with transtibial amputations. J Rehabil Res Dev. 2013;50(9):XXX–XXX. http://dx.doi.org/10.1682/JRRD.2012.12.0233

Slideshow ProjectDOI:10.1682/JRRD.2012.12.0233JSP

Conclusion

• Information provided by this system may:– Help clinicians in fitting prostheses, selecting

components, or training patients. – Be useful for automatic feedback control to adjust

prosthesis mechanisms based on activity and posture.