Learning Non-Euclidean Representations With SPD Manifold for Myoelectric Pattern Recognition

How to learn informative representations from Electromyography (EMG) signals is of vital importance for myoelectric control systems. Traditionally, hand-crafted features are extracted from individual EMG channels and combined together for pattern recognition. The spatial topological information betw...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on neural systems and rehabilitation engineering 2022, Vol.30, p.1514-1524
Hauptverfasser:	Xiong, Dezhen, Zhang, Daohui, Zhao, Xingang, Chu, Yaqi, Zhao, Yiwen
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Band-pass filters Channels Computer applications Computing costs Control systems Electromyography EMG Feature extraction Geometry Information processing Licenses Log-Euclidean metric Manifolds (mathematics) Measurement Myoelectric control Myoelectricity non-Euclidean Pattern recognition Performance evaluation Rank tests Representations SPD manifold Symmetric matrices System effectiveness
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!