Deep Learning-based Temporal-Spatial Model for Stroke Rehabilitation Posture Estimation using StrokePoseNet
Bibliographic record
Abstract
Stroke rehabilitation plays a crucial role in restoring motor functions in patients suffering from neurological impairments. Accurate posture prediction and assessment during physiotherapy sessions are vital for tracking recovery and guiding therapeutic interventions. In this study, proposed StrokePoseNet(SPN) a novel temporal-spatial deep learning architecture designed to predict and classify rehabilitation postures based on joint coordinate sequences. Our approach combines 1D Convolutional Neural Networks (CNNs) to extract spatial features from individual frames and Long Short-Term Memory (LSTM) networks to capture temporal dependencies across sequences. Utilized the publicly available Toronto Rehabilitation Stroke Pose Dataset, which includes posture sequences of stroke patients performing various rehabilitation exercises. SPN was trained and evaluated using standard machine learning metrics, achieving a classification accuracy of 96.42% and a balanced F1-score of 95.99%. Comparative analysis with baseline models such as Random Forest, SVM, and standalone CNN or LSTM architectures confirmed StrokePoseNet’s superior performance. The outcomes reinforce that the model can be implemented in real-time scenarios in the clinical setting, proposing a data-based method to monitor stroke treatment through the form of intelligent physiotherapy frameworks.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".