Detection of daily postures and walking modalities using a single chest-mounted tri-axial accelerometer
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This study presents a novel method for the detection and classification of a wide range of physical activities, including standing, sitting, lying, level walking, and walking upstairs and downstairs using a single chest-mounted accelerometer. The trunk inclination angle and variation of the gravitational component of the accelerometer recording were used for detection and classification of postural transitions and walking modalities. In addition, biomechanical features of each transition were used to reject false detections. To validate the accuracy of the presented method, two studies were performed, first in the (1) laboratory environment, where a motion capture system was the reference system (ten healthy subjects), and second (2) in the free-living environment where a handheld camera was the reference system (ten healthy subjects). The first study showed that the proposed method obtained higher accuracy, sensitivity, and specificity in detection of postural transitions and walking modalities compared to other methods in the literature when implemented on the same dataset. The second study obtained (1) the sensitivity and specificity of 100% for detection of sit-to-lie, lie-to-sit, and stand-to-sit, and 100% and 97%, respectively, for detection of sit-to-stand, and (2) the accuracy of 99%, 99%, and 95% for detection of slow, normal, and fast level walking, and 97% and 96% for detection of walking upstairs and downstairs. The proposed method enabled detection and classification of postural transitions and walking modalities with high sensitivity and specificity using only one chest-mounted accelerometer. This approach can be used for convenient and reliable assessment of physical activities in long-term.
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.
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 it