American Sign Language Translation Glove
Bibliographic record
Abstract
American Sign Language (ASL) is a widely used method of communication for the hearing impaired across North America and Canada. While ASL is a robust and elegant way of communication, there are many instances where the deaf and hearing may struggle to communicate with each other. Additionally, there exists the need for an educational tool to learn ASL. The goal of this project is to design an electronically aided translation device in conjunction with machine learning methods in hopes of aiding those wanting to communicate using ASL. The design utilizes a variety of low-cost sensors and modules integrated onto a glove and built for use on the Arduino platform. A signed letter, word or phrase is then output via a graphical user interface. Thus far, data was obtained from five individuals who repeatedly signed each letter of the ASL alphabet using our translation glove. This data was then pre-processed and sorted into a large database which was used to train a Random Forest machine learning classifier. The initial results show that this machine learning model has an accuracy score of 99.7%. As we continue to gather data and increase the vocabulary of the machine learning model, it is our aim to design a product that will bridge the communication gap between the hearing and hearing-impaired communities and provide the public access to an affordable and usable device that will ultimately improve the user's quality of life.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.044 | 0.022 |
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".