English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

To improve the control of wearable robotics for gait assistance, we presentan approach for continuous locomotion mode recognition as well as gait phaseand stair slope estimation based on artificial neural networks that includetime history information. The input features consist exclusively of processedvariables that can be measured with a single shank-mounted inertial measurementunit. We introduce a wearable device to acquire real-world environment testdata to demonstrate the performance and the robustness of the approach. Meanabsolute error (gait phase, stair slope) and accuracy (locomotion mode) weredetermined for steady level walking and steady stair ambulation. Robustness wasassessed using test data from different sensor hardware, sensor fixations,ambulation environments and subjects. The mean absolute error from the steadygait test data for the gait phase was 2.0-3.5 % for gait phase estimation and3.3-3.8{\deg} for stair slope estimation. The accuracy of classifying thecorrect locomotion mode on the test data with the utilization of time historyinformation was in between 98.51 % and 99.67 %. Results show high performanceand robustness for continuously predicting gait phase, stair slope andlocomotion mode during steady gait. As hypothesized, time history informationimproves the locomotion mode recognition. However, while the gait phaseestimation performed well for untrained transitions between locomotion modes,our qualitative analysis revealed that it may be beneficial to includetransition data into the training of the neural network to improve theprediction of the slope and the locomotion mode. Our results suggest thatartificial neural networks could be used for high level control of wearablelower limb robotics.

Continuous locomotion mode recognition and gait phase estimation based on a shank-mounted IMU with artificial neural networks