Enhancing Classification Accuracy of Transhumeral Prosthesis: A Hybrid sEMG and fNIRS Approach

Abstract

Limited non-invasive transhumeral prosthesis control exists due to the absence of signal sources on amputee residual muscles. This paper introduces a hybrid brain-machine interface (hBMI) that integrates surface electromyography (sEMG) and functional near-infrared spectroscopy (fNIRS) signals to overcome the limits of existing myoelectric upper-limb prosthesis. This hybridization aims to improve classification accuracy (CA) to escalate arm movements' control performance for individuals who have transhumeral amputation. To evaluate the effectiveness of this hBMI, fifteen healthy and three transhumeral amputee subjects for six arm motions were participating in the experiment. Myo armband was used to acquire sEMG signals corresponding to four arm motions: elbow extension, elbow flexion, wrist pronation, and wrist supination. Whereas fNIRS brain imaging modality was used to monitor cortical hemodynamics response from the prefrontal cortex region for two hand motions: hand open and hand close. The average accuracy of 94.6 % and 74% was achieved for elbow and wrist motions by sEMG for healthy and amputated subjects, respectively. Simultaneously, the fNIRS modality showed an average accuracy of 96.9% and 94.5% for hand motions of healthy and amputated subjects. This study demonstrates the feasibility of hybridizing sEMG and fNIRS signals to improve the CA for transhumeral amputees, improving the control performances of multifunctional upper-limb prostheses.INDEX TERMS Classification accuracy, fNIRS, hybrid brain-machine interface, sEMG, transhumeral prosthesis.

An sEMG-Controlled Forearm Bracelet for Assessing and Training Manual Dexterity in Rehabilitation: A Systematic Review

“…The initial search yielded 108 articles. Once the duplicates were removed and eligibility criteria were applied, 10 articles with a total of 180 participants were included in the review [ 4 , 7 , 9 , 10 , 11 , 18 , 19 , 20 , 21 , 22 ]. The characteristics of included studies are shown in Table 2 and Table 3 .…”

“…One study (n = 19) included a sample of children with cerebral palsy (CP) with ages ranging from 8 to 18 years [ 22 ]. Three studies (n = 7) included patients with upper limb amputation: one of them did not specify the amputation level [ 4 ], another included transradial amputees [ 19 ] and the other transhumeral amputees [ 20 ]. Five studies (n = 31) examined patients with stroke [ 7 , 9 , 11 , 18 , 21 ]: three of them did not specify the characteristics of the impairment, one included people (n = 3) with mildly to severely impaired hand function [ 11 ], and the other included people (n = 4) with different levels of impairment [ 21 ].…”

“…All studies used semi-immersive VR. Six of them [ 4 , 11 , 18 , 19 , 20 , 21 ] implemented protocols designed to analyze the accuracy of the sEMG system. One of these used a protocol based on a dance game and added the Kinect ® sensor to track position in amputees, with the aim of knowing the time taken for each hand gesture to be detected by the system as well as its total operating time [ 4 ].…”

“…One of these used a protocol based on a dance game and added the Kinect ® sensor to track position in amputees, with the aim of knowing the time taken for each hand gesture to be detected by the system as well as its total operating time [ 4 ]. Another compared the accuracy of the information captured by the MYO Armband ® with functional near-infrared spectroscopy (fNIRS) and evaluated the effectiveness of the combination of both systems to obtain information about motor intention in patients with transhumeral amputation, which may be useful to improve the control of upper limb prostheses [ 20 ]. The other four studies [ 11 , 18 , 19 , 21 ] used different upper limb exercise protocols with or without visual feedback that allowed to calculate the accuracy of the MYO Armaband ® .…”

“…They used a software to apply mathematical formulations to the data collected from the sEMG, calculating the percentages of the accuracy of the system. Finally, two studies [ 18 , 20 ] used the sEMG signal to know the characteristics of the forearm muscle contraction performed by the participants. The second [ 20 ] also compared this signal with the data collected from another motion capture device and analyzed the effectiveness of combining both devices as an assessment approach.…”