L-SFAN: Lightweight Spatially Focused Attention Network for Pain Behavior Detection
Bibliographic record
Abstract
Chronic low back pain (CLBP) afflicts millions globally, significantly impacting individuals’ well-being and imposing economic burdens on healthcare systems. Detecting protective behavior is essential for effective chronic pain management, as it can help prevent pain aggravation and disability. To reduce this burden, we could leverage sensor information and AI techniques to facilitate at-home patient follow-ups. Precisely, by utilizing motion sensors and surface electromyography (sEMG) sensors, we can continuously monitor movement patterns and muscle activity. This article introduces lightweight spatially focused attention network (L-SFAN), a lightweight convolutional neural network (CNN) architecture that innovatively models both spatial and temporal dimensions of multivariate time series to detect protective behavior. L-SFAN uses 2D CNN to capture spatial patterns from the 2-D matrix formed by the multivariate time series and uses self-attention to capture long-range temporal dependencies. Temporal average pooling (TAP) is used to emphasize spatial patterns. On the EmoPain dataset, L-SFAN outperforms state-of-the-art methods while reducing the number of parameters up to 94%, making it lightweight and embedded systems friendly. The ablation study underscores the importance of jointly modeling spatial-temporal information. The competitive performance and efficiency of our proposed method demonstrate its practicality for accessible chronic pain monitoring.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".