Combining electromyography (EMG) and force myography (FMG) signals could help engineers build prosthetic limbs that better reproduce natural movements, according to a new study from the University of California, Davis. The work showed that the combination is more accurate at predicting hand movements than either method by itself.
“Using sensors and machine learning, we can recognize gestures based on muscle activity,” said Jonathon Schofield, PhD, professor of mechanical and aerospace engineering at the university and senior author of the paper.
EMG-based controls perform well in a lab setting and with limbs at rest. But if the arm is moved to a different position, or it grasps objects of different weights, the measurements change.
“In the real world, every time you move a limb and grasp something, the measurement is going to change,” said graduate student Peyton Young, first author on the paper. “The neutral position (where the limb is held passively next to the body) is very different to moving around.”
To address this, Young and Schofield experimented with FMG, which measures how muscles in the arm bulge as they contract, alone and in combination with EMG.
Young constructed a forearm cuff that includes both EMG and FMG sensors. He tested the device with a series of able-bodied volunteers in the lab who performed a series of arm gestures while holding different loads with different hand grasps. Data from the sensors was fed to a machine learning algorithm to classify the different movements (pinch, pick, fist, etc.).
For each experiment, the algorithm was trained on some of the data and scored on its ability to accurately classify the rest. The researchers found that position and loading affected the accuracy of classification of gestures.
Overall, a combination of EMG and FMG gave over 97 percent classification accuracy, compared to 92 percent for FMG alone and 83 percent for EMG alone.
Young is now working on a combined FMG/EMG sensor, and the team is working toward an experimental prosthetic limb that uses the technology.
Editor’s note: This story was adapted from materials provided by the University of California, Davis.
The open-access study, “The effects of limb position and grasped load on hand gesture classification using electromyography, force myography, and their combination,” was published in PLOS One.
