Capturing finger positional data using portable and inexpensive markerless systems
Bibliographic record
Abstract
The understanding of human movement has been greatly enhanced through the use of kinematics, and it has provided a more sensitive metric to evaluate recovery following a stroke. Conventional acquisition techniques (e.g., Vicon, Optotrak) typically remain non feasible clinical options as they are immobile, expensive, and require long setup times. One alternative is using accelerometers, however movements recorded via accelerometers may be difficult to interpret as the axes shift with rotational movements. Advancements in sensor technologies have enabled kinematic acquisition without markers and portability, while effectively reducing costs. One such device is the LEAP sensor which enables the specific kinematic capture the hands and digits. Since this is a novel technology there remain questions regarding the validity of the kinematic measures and the feasibility of clinical use. Thus the purpose of this study was to test the validity and accuracy of LEAP compared to a gold standard system (Optotrak). Participants positioned their index finger at 15 different targets (located in vertical and horizontal planes on a monitor). Positional data was acquired using both systems. We compared the target coordinates of the two systems using correlations and measures of variability (constant error (CE), variable error (VE)). Our results demonstrate significant correlation between the systems (0.99 for horizontal and 0.95 for vertical direction) but the LEAP did not have the same precision (CE) as Optotrak; however variability (VE) was comparable. Overall these results suggest that the LEAP system could be adopted as a clinically feasible option to conventional kinematic capture systems.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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".