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/

Zendy Plus

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

Zendy Tools

Zendy Open

Repositioning of recording electrode array across repeated electromyographymeasurements may result in a displacement error in hand movement classificationsystems. In order to examine if the classifier re-training could reachsatisfactory results when electrode array is translated along or rotated aroundsubject's forearm for varying number of features, we recorded surfaceelectromyography signals in 10 healthy volunteers for three types of grasp and6 wrist movements. For feature extraction we applied principal componentanalysis and the feature set size varied from one to 8 principal components. Wecompared results of re-trained classifier with results from leave-one-outcross-validation classification procedure for three classifiers: LDA (LinearDiscriminant Analysis), QDA (Quadratic Discriminant Analysis), and ANN(Artificial Neural Network). Our results showed that there was no significantdifference in classification accuracy when the array electrode was repositionedindicating successful classification re-training and optimal feature setselection. The results also indicate expectedly that the number of principalcomponents plays a key role for acceptable classification accuracy ~90 %. Forthe largest dataset (9 hand movements), LDA and QDA outperformed ANN, while forthree grasping movements ANN showed promising results. Interestingly, we showedthat interaction between electrode array position and the feature set size isnot statistically significant. This study emphasizes the importance of testingthe interaction of factors that influence classification accuracy andclassifier selection altogether with their impact independently in order toestablish guiding principles for design of hand movement recognition system.Data recorded for this study are stored on Zenodo repository (doi:10.5281/zenodo.4039550).

Effect of the sEMG electrode (re)placement and feature set size on the hand movement recognition