Deep learning for waveform identification of resting needle electromyography signals

•Resting EMG discharges were classified by Mel-spectrogram conversion and deep-learning algorithms.•Data augmentation and use of pre-trained weights (transfer learning) increased the accuracy.•Waveform identification of clinical EMG testing might be possible by deep-learning algorithms. Given the re...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Clinical neurophysiology 2019-05, Vol.130 (5), p.617-623
Hauptverfasser:	Nodera, Hiroyuki, Osaki, Yusuke, Yamazaki, Hiroki, Mori, Atsuko, Izumi, Yuishin, Kaji, Ryuji
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural network Data augmentation Deep Learning Electromyography - methods Humans Muscle, Skeletal - physiology Needle electromyography Neural Networks, Computer Resting discharge
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!