A data-driven pipeline preprocesses EMG signals with low-pass filtering and Hilbert envelope, selects five features and six representative gestures via hierarchical clustering, and identifies Extra Trees and ANN as effective classifiers on the NINAPRO DB4 dataset for prosthetic applications.
A quan- titative taxonomy of human hand grasps,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unsupervised clustering and classification of upper limb EMG signals during functional movements: a data-driven
A data-driven pipeline preprocesses EMG signals with low-pass filtering and Hilbert envelope, selects five features and six representative gestures via hierarchical clustering, and identifies Extra Trees and ANN as effective classifiers on the NINAPRO DB4 dataset for prosthetic applications.