Bibliographic record
Abstract
In recent years, because of an increasing aging population there are higher incidences of falling according to epidemiological reports. Because of this high frequency the prevention of falls becomes a major concern. Evidence of the high occurrence and significant cost of falls on health-related quality of life, significant financial load on the health care system, and on their social impact has been provided by various epidemiological studies. Falls are the second leading cause of traumatic brain injury (TBI), which is a major cause of death in many countries, especially the United States. Balance impairments are frequent and particularly high among people who suffer from stroke, TBI, incomplete spinal cord injuries, Parkinson’s disease, multiple sclerosis and diabetic peripheral neuropathy, and in general for people who suffer from different neurological disorders. For all of these groups, balance disorders have a major social and quality of life implications, which require attention and exploration of effective ways to evaluate risk and develop training programs that prevent falls. According to the literature, the most important factors for fall prevention are suitable training programs and the availability of feasible and cost-effective comprehensive risk measurement [1, 2]. This thesis describes the acquisition of acceleration data of a human body while maintaining balance on a balance board with three-axis accelerometers. Three different algorithms of balance region detection, the wavelet transform, and the neural network were developed to segment and classify the unstable regions of the accelerometer signal. To simplify the calculation of these algorithms vector processing technique was used. The experimental results show that arms have an effective role in the improvement of balance. From the balance region detection the duration and amount of activity can be found which will be good for prediction of falls. The wavelet transform is the best way to separate unstable periods from one another. For classification of stable and unstable parts of movements, the neural network is the best technique. It is effective to compare the amount of stable and unstable parts in more detail. The results suggest the specific role of the dominant and non-dominant arms.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 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) | 0.003 | 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".