Tai Chi Exercise Posture Detection and Assessment for the Elderly Using BPNN and 2 Kinect Cameras
Bibliographic record
Abstract
Exercise and recreation are beneficial to all genders and ages, exercise reduces stress and makes people healthy. Physical limitation among the elderly is the major concern and needed to be taking care for the elderly exercise. Low-impact exercises such as walking, slow jogging in the park, and Tai Chi are recommended for the elderly. Tai Chi is a slow and gentle exercise, which can help the circulatory system and dementia in the elderly; it also helps the elderly to get socialized and make new friends. Unfortunately, in the COVID-19 pandemic, people must stay in the house and avoid social activities including outdoor exercises and recreation. This paper aims to develop Tai Chi exercise posture detection and assessment system for helping the elderly to practice Tai Chi at home by themselves. The system provides Tai Chi video clips for demonstration and the graphics user interface (GUI) for capturing the movement of the elderly while they are exercising Tai Chi. The system will detect and assess the elderly's movement whether it is correct or not by using 2 Kinect cameras. The Kinect is used for joints detection and the series of joints movement will be used to compare with the correct Tai Chi postures stored in the system. The questionnaire, which was developed based on the usability criteria defined by the ISO 9241–11 and the users' experience, was used to evaluate the system. The precision, recall, F1-score, and accuracy of our system are 0.94, 0.98, 0.96, and 0.93 respectively.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".