Convolutional Implementation Neural Network (CNN) on the System and Introduction Sign Language to Support Communication with People with Disabilities
Bibliographic record
Abstract
The results of this study are based on verifying communication solutions for deaf and hard of hearing participants in Indonesia, the majority of whom use the Indonesian Sign Language System (SIBI). The goal is to design an accurate and efficient system for detecting and recognizing sign language using Convolutional Neural Network (CNN) and accessible in real-time on mobile devices to support more inclusive communication. This study uses a quantitative approach and uses deep learning techniques by utilizing a SIBI image dataset totaling 5,280 images (24 classes without the letters J and Z) with a division of 80% for training data and 20% for validation data. This research process starts from image preprocessing, designing a CNN architecture consisting of convolution, pooling, and fully connected layers, implementing it systematically with Python–TensorFlow, and integrating it into the Flutter application through APIs. Evaluation was conducted using Intersection over Union (IoU) metrics and measured algorithm performance with precision, recall, and mean Average Precision (mAP). The model is capable of achieving a precision of 0.97, a recall of 1.00 and a high mAP in a wide range of backgrounds and lighting.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 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".