Upper-Limb Electromyogram Classification of Reaching-to-Grasping Tasks Based on Convolutional Neural Networks for Control of a Prosthetic Hand

Abstract

In recent years, myoelectric interfaces using surface electromyogram (EMG) signals have been developed for assisting people with physical disabilities. Especially, in the myoelectric interfaces for robotic hands or arms, decoding the user’s upper-limb movement intentions is cardinal to properly control the prosthesis. However, because previous experiments were implemented with only healthy subjects, the possibility of classifying reaching-to-grasping based on the EMG signals from the residual limb without the below-elbow muscles was not investigated yet. Therefore, we aimed to investigate the possibility of classifying reaching-to-grasping tasks using the EMG from the upper arm and upper body without considering wrist muscles for prosthetic users. In our study, seven healthy subjects, one trans-radial amputee, and one wrist amputee were participated and performed 10 repeatable 12 reaching-to-grasping tasks based on the Southampton Hand Assessment Procedure (SHAP) with 12 different weighted (light and heavy) objects. The acquired EMG was processed using the principal component analysis (PCA) and convolutional neural network (CNN) to decode the tasks. The PCA–CNN method showed that the average accuracies of the healthy subjects were 69.4 ± 11.4%, using only the EMG signals by the upper arm and upper body. The result with the PCA–CNN method showed 8% significantly higher accuracies than the result with the widely used time domain and auto-regressive-support vector machine (TDAR–SVM) method as 61.6 ± 13.7%. However, in the cases of the amputees, the PCA–CNN showed slightly lower performance. In addition, in the aspects of assistant daily living, because grip force is also important when grasping an object after reaching, the possibility of classifying the two light and heavy objects in each reaching-to-grasping task was also investigated. Consequently, the PCA–CNN method showed higher accuracy at 70.1 ± 9.8%. Based on our results, the PCA–CNN method can help to improve the performance of classifying reaching-to-grasping tasks without wrist EMG signals. Our findings and decoding method can be implemented to further develop a practical human–machine interface using EMG signals.

Evaluation of Hand Action Classification Performance Using Machine Learning Based on Signals from Two sEMG Electrodes

“…Subsequently, two sEMG electrodes were attached to the right forearm at the belly of the flexor carpi radialis (medial electrode) and the extensor carpi radialis (lateral electrode) using double-sided adhesive, as shown in Figure 3 a. Electrode placement protocol was based on Surface ElectroMyoGraphy for the Non-Invasive Assessment of Muscles (SENIAM) recommendations [ 27 ], which describes optimal sEMG sensor application procedures. Electrode locations were selected in line with previous studies [ 28 , 29 , 30 ].…”

“…Electrode placement protocol was based on Surface ElectroMyoGraphy for the Non-Invasive Assessment of Muscles (SENIAM) recommendations [27], which describes optimal sEMG sensor application procedures. Electrode locations were selected in line with previous studies [28][29][30].…”

“…Electrode placement protocol was based on Surface ElectroMyoGraphy for the Non-Invasive Assessment of Muscles (SENIAM) recommendations [27], which describes optimal sEMG sensor application procedures. Electrode locations were selected in line with previous studies [28][29][30]. Following the electrode setup, each participant was instructed to sit and rest their forearms on a desk at an angle of approximately 45 • to create a 90 • elbow angle (Figure 3b).…”

Signal to Image Conversion and Convolutional Neural Networks for Physiological Signal Processing: A Review

“…Furthermore, [126] acquired EMG signals from the upper arm and upper body, specifically without considering wrist muscles from 7 healthy subjects (6 electrodes), 1 transradial amputee, and 1 wrist amputee using 8 surface electrodes. The signals were normalised and segmented.…”

Classification of deep vein thrombosis stages using convolutional neural network of electromyogram with vibrotactile stimulation toward developing an early diagnostic tool: A preliminary study on a pig model

“…The data preprocessing and feature extraction were performed according to the method which showed better performances in previous studies about myoelectric interfaces [35,44,45]. In the method, the acquired EMG data were sectioned into 400-sample segments with 200 overlapping samples.…”