sEMG-based hand gesture recognition with deep learning

Zanghieri, Marcello (2019) sEMG-based hand gesture recognition with deep learning. [Laurea magistrale], Università di Bologna, Corso di Studio in Fisica [LM-DM270]
Documenti full-text disponibili:
[img] Documento PDF (Thesis)
Disponibile con Licenza: Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0

Download (2MB)

Abstract

Hand gesture recognition based on surface electromyographic (sEMG) signals is a promising approach for the development of Human-Machine Interfaces (HMIs) with a natural control, such as intuitive robot interfaces or poly-articulated prostheses. However, real-world applications are limited by reliability problems due to motion artifacts, postural and temporal variability, and sensor re-positioning. This master thesis is the first application of deep learning on the Unibo-INAIL dataset, the first public sEMG dataset exploring the variability between subjects, sessions and arm postures, by collecting data over 8 sessions of each of 7 able-bodied subjects executing 6 hand gestures in 4 arm postures. In the most recent studies, the variability is addressed with training strategies based on training set composition, which improve inter-posture and inter-day generalization of classical (i.e. non-deep) machine learning classifiers, among which the RBF-kernel SVM yields the highest accuracy. The deep architecture realized in this work is a 1d-CNN implemented in Pytorch, inspired by a 2d-CNN reported to perform well on other public benchmark databases. On this 1d-CNN, various training strategies based on training set composition were implemented and tested. Multi-session training proves to yield higher inter-session validation accuracies than single-session training. Two-posture training proves to be the best postural training (proving the benefit of training on more than one posture), and yields 81.2% inter-posture test accuracy. Five-day training proves to be the best multi-day training, and yields 75.9% inter-day test accuracy. All results are close to the baseline. Moreover, the results of multi-day trainings highlight the phenomenon of user adaptation, indicating that training should also prioritize recent data. Though not better than the baseline, the achieved classification accuracies rightfully place the 1d-CNN among the candidates for further research.

Abstract
Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Zanghieri, Marcello
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Indirizzo
Curriculum E: Fisica applicata
Ordinamento Cds
DM270
Parole chiave
Electromyography,EMG,Surface electromyography,sEMG,Deep Learning,DL,Convolutional Neural Networks,CNN,Unibo-INAIL,Unibo-INAIL dataset,Machine Learning,ML,Python,PyThorch,Pattern Recognition,PR,Hand gesture recognition,Gesture recognition,Prosthetics,Biomedical signals,Automatic differentiation,Activation Potential,AP,Motor Unit Activation Potential,MUAP,Human-Machine Interface,HMI,Human-Computer Interface,HCI
Data di discussione della Tesi
22 Marzo 2019
URI

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento

^