Representative model confidence output for a no-exoskeleton testing trial.

Representative model confidence output for a no-exoskeleton testing trial.

<p>LSTM detection curves peak at roughly the same time as the manual event confidence curves. LSTM HS detection curves show fluctuations before the peaks while the TO detection curves show fluctuations after the peaks.</p>

Saved in:

Bibliographic Details
Main Author:	Xiaowen Chen (192197) (author)
Other Authors:	Anne E. Martin (10838318) (author)
Published:	2025
Subjects:	Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified use roughly 8 use neural networks two lstm models recent methods tend previous lstm algorithms machine learning algorithms ground reaction force custom ankle exoskeletons algorithm successfully detected manually identified events events within 16ms subjects &# 8217 heel marker height detection methods tend assistive walking device testing data ratio low training requirements new model required detecting gait events final model output new long short term memory model assisted walking using new model gait events term memory long short subjects walking model makes weighted output heel strike detection rate walking behaviors unassisted walking kinematic data 79 training utilize thresholding significantly altered paper introduces high robustness excellent tool
Tags:	Add Tag No Tags, Be the first to tag this record!

Cannot write session to /tmp/vufind_sessions/sess_rlkua8j774346drcg3ocnpltm7