Evaluation of Finger Flexion Classification at Reduced Lateral Spatial Resolutions of Ultrasound
Bibliographic record
Abstract
The objective of this paper is to investigate the effect that lateral spatial resolution of ultrasound has on finger flexion classification. The objective's purpose leads toward the development of a wearable human machine interface (HMI) using single-element ultrasonic sensors with non-focused ultrasound. Ultrasound radiofrequency (RF) signals were acquired using a linear array ultrasound probe in B-mode while performing the individual finger flexions from five healthy volunteers. Each B-mode frame is composed of 127 parallel ultrasound RF signals along the lateral direction within a 40-mm width. To reduce the lateral resolution of ultrasound data artificially, the RF signals were averaged into a reduced number of lateral columns. Across ten independent arm experiments the classification accuracy at 127 channels (full resolution) resulted in the first and third quartile to be 80-92%. Averaging into four RF signals (simulating 10-mm wide ultrasound beams from each channel) could achieve a median classification accuracy of 87% using the proposed feature extraction method with the discrete wavelet transform. Our results show low resolutions could achieve high accuracies to that of full resolution. We also conducted a preliminary study using a multichannel single-element ultrasound system with lightweight, flexible, and wearable ultrasonic sensors (WUSs) using non-focused ultrasound. Each WUS had an ultrasound sensing area of 20mm by 20mm. Three WUSs were attached on one subject's forearm and ultrasound RF signals were acquired during individual finger flexions. A mean classification accuracy of 98% was obtained with F1 scores ranging between 95 - 98% (across five finger flexions).
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".