Name
Title | ||
|---|---|---|
A Simple Method To Estimate Muscle Currents From Hd-Semg And Mri Using Electrical Network And Graph Theory |
Abstract | ||
|---|---|---|
In the last years the spread of hand prosthetics has fueled the research on the field of signal processing applied on physiologic data. At the state of the art there are different algorithms that allow a precise estimation of hand movements, the majority of whom work just on the electrode space. Even though there are signal processing methods that access single muscle information, they are still premature for a real application on prosthetics. We present a novel method that exploit the information extracted from a magnetic resonance image (MRI) and a single row of high-density surface electromyography (HD-sEMG) electrodes to estimate the muscles currents in the forearm, providing a first experimental application on two simple wrist movements to assess its performance. The results show that the proposed method is able to identify the correct muscle with a single muscle-contraction task, whereas for a 2 muscle task it shows a high variance in the results. The method models the signal propagation from muscles to electrodes using a simple resistive electrical network and uses the graph theory to calculate the muscle currents. It brings a considerably simpler muscle's current estimation method, significantly decreasing the problem complexity, and therefore becoming a potential effective approach for future prosthetics' control. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/EMBC.2019.8856616 | 2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) |
Field | DocType | Volume |
Graph theory,Computer vision,Signal processing,Electrical network,Resistive touchscreen,Computer science,Electromyography,Electric potential,Artificial intelligence,Problem complexity,Radio propagation | Conference | 2019 |
ISSN | Citations | PageRank |
1557-170X | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Enrico Piovanelli | 1 | 0 | 0.34 |
| D. Piovesan | 2 | 0 | 0.68 |
| Shouhei Shirafuji | 3 | 20 | 10.19 |
| Jun Ota | 4 | 527 | 109.77 |