Recognition of Illegible Digits on Indonesian Election C1 Forms Using Convolutional Neural Network for Recapitulation Information System (SIREKAP)
Bibliographic record
Abstract
The General Election (PEMILU) in Indonesia utilizes the Recapitulation Information System (SIREKAP) to accelerate and improve the accuracy of vote counting.However, the system often fails to recognize numbers on C1 sheets due to handwriting variations, low image quality, and visual disturbances.This study develops a Convolutional Neural Network (CNN) to classify digits 0-9 and the letter X, which are frequently misread.The dataset was collected from 300 respondents who rewrote numbers with seven variations: bold, right italic, left italic, crumpled paper, subscript, superscript, and upside down.A total of 3,850 images were generated and divided into 70% training, 15% validation, and 15% testing.Four CNN configurations were compared: standard, with L1 regularization, L2 regularization, and Elastic Net (L1+L2).The standard CNN achieved 94.92% training accuracy, 72.91% validation, and 69.88% testing.The L1 model showed overfitting with 91.99% training but only 59.72% testing accuracy.L2 regularization improved results with 92.47% training and 75.84% testing accuracy.Elastic Net achieved the best balance, reaching 95.51% training, 71.74% validation, and 77.89% testing accuracy.These findings highlight the effectiveness of Elastic Net in enhancing generalization and reducing misclassification, thereby supporting more reliable election vote recapitulation.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".