The Use of an MEG/fMRI-Compatible Finger Motion Sensor in Detecting Different Finger Actions
Bibliographic record
Abstract
This paper explores the use of a novel device in detecting different finger actions among healthy individuals and individuals with stroke. The device is magnetoencephalography (MEG) and functional magnetic resonance imaging (fMRI) compatible. It was prototyped to have four air-filled chambers that are made of silicone elastomer, which contains low magnetizing materials. When an individual compresses the device with his/her fingers, each chamber experiences a change in pressure, which is detected by a pressure sensor. In a previous recent work, our device was shown to be MEG/fMRI compatible. In this study, our research effort focuses on using the device to detect different finger actions (e.g., grasping and pinching) in non-shielded rooms. This is achieved by applying a support vector machine to the sensor data collected from the device when participants are resting and executing the different finger actions. The total number of possible finger actions that can be executed using the device is 31. The healthy participants could perform all the 31 different finger actions and the average classification accuracy achieved is 95.53 ± 2.63%. The stroke participants could perform all the 31 different finger actions with their healthy hand and the average classification accuracy achieved is 83.13 ± 6.69%. Unfortunately, the functions of their affected hands are compromised due to stroke. Thus, the number of finger actions they could perform ranges from 2 to 24, depending on the level of impairments. The average classification accuracy for the affected hand is 83.99 ± 16.38%. The ability to identify different finger actions using the device can provide a mean to researchers to label the data automatically in MEG/fMRI studies. In addition, the sensor data acquired from the device provide sensorimotor--related information, such as speed and force, when the device is compressed. Thus, brain activations can be correlated with this information during different finger actions. Finally, the device can be used to assess the recovery of the sensory and motor functions of individuals with stroke when paired with fMRI.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".