By Topic

Terrain recognition improves the performance of neural-machine interface for locomotion mode recognition

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Ding Wang ; Dept. of Electr., Comput., & Biomed. Eng., Univ. of Rhode Island, Kingston, RI, USA ; Lin Du ; He Huang

Neural-machine interface (NMI) for artificial limbs is a typical biomedical CPS that requires seamless integration of cyber components with physical systems (i.e. prostheses and users). In this paper we aimed to adopt a bio-inspired concept to improve the performance of a NMI for artificial legs by introducing additional information about the walking environment ahead of the prosthesis user. First, a terrain recognition module based on a portable laser distance sensor and an inertial measurement unit (IMU) was designed to accurately classify the terrain type in front of the prosthesis user. The output of this module was then modeled as prior probability and integrated into a Bayesian-based NMI system. The cyber algorithms were real-time implemented and evaluated on an able-bodied subject wearing a passive prosthetic leg in the laboratory environment. The preliminary results showed that the terrain recognition module can accurately recognize the type of terrain in front of the user, approximately half to one second before the critical timing for prosthesis control mode change. NMI with or without the terrain recognition module accurately predicted all the tested task mode transitions. However, the NMI with the terrain recognition module yielded approximately 5% higher classification accuracy rate in static state and 30~105 ms earlier prediction of mode transitions than the NMI without prior knowledge of environmental information. The preliminary results demonstrated the soundness of the bio-inspired concept and established CPS framework to further enhance the accuracy and response time of NMI for artificial leg control.

Published in:

Computing, Networking and Communications (ICNC), 2013 International Conference on

Date of Conference:

28-31 Jan. 2013