Classifiers and Adaptable Features Improve Myoelectric Command Accuracy in Trained Users
Bibliographic record
Abstract
A common challenge in myoelectric control is to create reliable human-machine interfaces. The aim of our study is to apply classifiers and adaptable features to electromyography (EMG) signals obtained from subjects who are trained to perform cursor-control tasks. We have developed a robust surface EMG command system that relies on training the human rather than training a classifier, thereby enabling the human to correct for signal changes. The purpose of the current study was to understand whether adding an adaptive timing feature and classifiers to our EMG interface could improve the performance of trained human subjects. Forty-eight subjects participated in the experiment, where they learned four different commands to control a cursor to select fixed targets on a computer screen, where each command was composed of a combination of short and long muscle contractions. A Command Accuracy Test assessed subject proficiency at producing commands when prompted. The command classification accuracy was calculated for a control condition and two conditions that reflected possible adaptive features: the timing between EMG signal inputs and a subject-specific classifier. The overall results showed significant improvements in command classification accuracy for both adaptive components (p<; 0.0001) compared to the control. However, some initially high performing subjects did not receive as much benefit. These results suggest that customizing the sEMG command system for individual subjects could improve their performance. Future work should investigate the effect of customizing the system for performance and co-adaptation, as well as using the adaptive features as a training tool to further improve command accuracy and efficiency.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".