Alphabet Recognition in Sign Language Using Deep Learning Algorithm with Bayesian Optimization
Bibliographic record
Abstract
Sign language, a vital medium for communication, particularly for individuals with speech and hearing impairments, is gaining recognition for its efficacy.To evaluate the efficacy of sign language alphabet recognition systems, three prominent image classification deep learning models-ResNeXt101, VGG19, and ViT-were chosen due to their established relevance and popularity in the field.The study aimed to identify the most effective model for accurate and efficient sign language classification using the NUS hand posture dataset-II.The study utilized Bayesian optimization for hyperparameter tuning, recognizing its superiority in systematically exploring the hyperparameter space compared to other optimization methods.This approach significantly enhanced the performance of the models by tailoring their configurations, leading to improved accuracy and robustness in sign language recognition across various experimental scenarios.While the findings consistently favored ResNeXt101 over VGG19, with a notable 2% higher F1 score, ViT also showcased comparable performance in certain experiments, achieving an impressive F1 score of 99%.Despite these successes, the study encountered limitations, including dataset bias and generalization challenges, which underscore the need for further research in this domain to address these complexities.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".