Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Electronics, Electromedical Engineering, and Medical Informatics Information Technology Education Journal
Shaifudin Zuhdi
Department Of Informatics, Sebelas Maret University
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Indonesian Automated Essay Scoring: A Comparative Study of Pretrained Transformer Models Pulung Hendro Prastyo; Eddy Tungadi; Shaifudin Zuhdi
Information Technology Education Journal Vol. 4, No. 2, May (2025)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/intec.v4i2.8069

Abstract

Manual essay scoring is often characterized by inefficiency and inconsistency. This process is notably time-consuming, leading to delayed feedback and increased susceptibility to evaluator fatigue and subjective bias, thereby posing significant challenges. Automated Essay Scoring (AES) offers a scalable, robust, and consistent solution to these issues. However, the performance of AES models can vary considerably depending on the specific application. Therefore, this study evaluated ten Indonesian pretrained transformer models from Hugging Face for AES tasks, using 300 essay responses from a Research Methodology quiz at Politeknik Negeri Ujung Pandang. Performance was assessed using Root Mean Square Error (RMSE) and Quadratic Weighted Kappa (QWK). Among the evaluated models, Indobenchmark/indobert-base-p2 (BERT-02) demonstrated superior performance. It achieved the lowest RMSE of 5.664 and the highest QWK score of 0.6745. The findings suggest that BERT-02 is the most effective model for Indonesian AES tasks. Future research could explore larger datasets and different models to further enhance the performance and understanding of Indonesian AES systems.
Efficient VGA-Net Modification Using ConvNeXt-Tiny and GATv2 for Retinal Vessel Segmentation Billie Zandra Widiyanto; Wiharto Wiharto; Shaifudin Zuhdi
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 8 No 3 (2026): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v8i3.1747

Abstract

Retinal blood vessel segmentation plays a crucial role in the early detection of ocular diseases such as diabetic retinopathy, glaucoma, and macular degeneration. Existing hybrid architectures, such as VGA-Net, suffer from high computational complexity due to the VGG-16 backbone and limited attention expressiveness due to its static GAT module, yet no prior work has examined replacing both components within a patch-based graph architecture in which backbone feature quality directly conditions graph attention effectiveness. This study aims to improve the computational efficiency and topological modeling of VGA-Net by replacing VGG-16 with ConvNeXt-Tiny and substituting GAT with GATv2. The primary contribution is a 55% parameter reduction through the ConvNeXt-Tiny backbone substitution and improved vessel topology modeling through GATv2's dynamic attention mechanism, which produces fully dynamic attention coefficients per query node. Experiments were conducted on the DRIVE and STARE datasets using a consistent preprocessing pipeline, one-factor-at-a-time hyperparameter tuning, and a unified evaluation protocol across all compared methods. The proposed model achieves the lowest parameter count (5.3M) and GFLOPs (3.2443), with a competitive inference time of 61.00 ms per image, among all compared methods, while achieving competitive performance in sensitivity and topological continuity. On the DRIVE dataset, the model achieved the highest sensitivity of 0.8718 and the highest clDice of 0.8446. On the STARE dataset, the model achieved the highest sensitivity of 0.9383 and the highest clDice of 0.9055. These results demonstrate that the proposed model achieves a favorable efficiency-performance trade-off, leading to sensitivity and topological continuity at the lowest computational cost among all compared methods, at the expense of lower specificity, accuracy, Dice, and MCC relative to certain compared methods.
Co-Authors Billie Zandra Widiyanto Eddy Tungadi Pulung Hendro Prastyo Wiharto Wiharto