Article Per Year (5 Year)
p-Index From 2021 - 2026
1.768
P-Index
This Author published in this journals
All Journal ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Riset Informatika Indonesian Community Journal Jurnal Pengabdian Masyarakat BATIK: Jurnal Pengembangan dan Pengabdian Masyarakat Multikultural Scientific Journal of Informatics
Angel Metanosa Afinda
Telkom University
Religion Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Public Health Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Benchmarking YOLOv12 Variants for Indonesian Traditional Cuisine Detection Fauzan Firdaus; Lidya Ningsih; Aminah Indahsari Marsuki; Angel Metanosa Afinda
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12625

Abstract

YOLOv12 is one of the latest YOLO versions currently. Several studies have proven that YOLOv12 has better performance compared to previous versions. YOLOv12 itself has five model variants based on its architectural complexity, namely nano, small, medium, large and extra larges. This study tests the performance of YOLOv12 model variants (n, s, m, l, x) for traditional Indonesian culinary detection using a domain-specific object detection dataset. The dataset contains 718 images with 720 bounding-box instances annotated across 20 culinary classes, divided into 418/150/150 images for training/validation/testing. Data processing was performed in Roboflow with automatic orientation and stretching resizing to 640×640, while the training split was enriched using augmentation (horizontal and vertical flips) to increase sample diversity. All YOLOv12 variants were trained with the same configuration and environment, for 50 epochs using the Ultralytics framework with default hyperparameters on an NVIDIA A100-SXM4 80GB GPU. On the validation set, all variants achieved high detection accuracy (mAP@0.5 = 0.985–0.991), while differences emerged under a more stringent localization criterion (mAP@0.5:0.95). The best overall localization performance was achieved by YOLOv12-L (mAP@0.5:0.95 = 0.874), while YOLOv12-N provided the fastest inference (0.8 ms/image) with competitive accuracy (mAP@0.5:0.95 = 0.822). These findings provide preliminary guidance for selecting YOLOv12 variants based on the trade-off between accuracy and speed.
Leveraging Assistive Image Captioning on VizWiz through Multi-Caption Supervision Fauzan Firdaus; Ema Rachmawati; Angel Metanosa Afinda; Edward Ferdian; Muhammad Maulana Yusuf
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026 (In progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7472

Abstract

Most image captioning datasets provide several human captions for the same image, yet model training is frequently carried out in a way that effectively treats each image as having only one caption. Our study revisits this mismatch by examining the impact of training with multiple captions per image on caption generation performance. For this purpose, we utilized the VizWiz-Captions dataset, which reflects a real assistive scenario with images taken by blind or visually impaired users with five reference captions per image. We evaluated two conventional CNN-based encoder–decoder models, namely CNN–LSTM and CNN–GRU. In both models, the visual encoder was fixed using InceptionV3 image features, while the recurrent decoder was varied between LSTM and GRU. We performed experiments by using training data by varying the number of captions used per image from one to five (k = 1–5), while keeping the overall pipeline unchanged. The models were evaluated using standard multi-reference metrics (BLEU-1 to BLEU-4, CIDEr, and SPICE). Across both baselines, performance generally improves when more captions are included in training, although the gains are not perfectly monotonic for every metric. The strongest results are observed at k = 5. For CNN–LSTM, the best setting achieved BLEU-4 = 0.175, CIDEr = 0.206, and SPICE = 0.120. On the other hand, CNN–GRU achieved BLEU-4 = 0.192, CIDEr = 0.226, and SPICE = 0.119. These findings suggest that, even without architectural changes, simply leveraging the available caption diversity during training can provide a practical boost for VizWiz-style captioning tasks.
Co-Authors Adiwijaya AMINAH INDAHSARI MARSUKI Ardiansyah Ramadhan Astri Novianty Bayu Satrio Wibowo Darryl Satria Wibowo Diedrick Darrell Darmadi Donni Richasdy Edward Ferdian Ema Rachmawati Fauzan Firdaus Febriyani, Widia I Kadek Nuary Trisnawan Iga Narendra Pramawijaya Indah Novitasari Dwi Saputro Indah Novitasari Dwi Saputro Isman Kurniawan Kenneth Matthew Yonathan Kevin Radinka Lidya Ningsih Muhammad Alfi Syahrin Muhammad Faris Ruriawan Muhammad Farrel Ahadi Tama Muhammad Maulana Yusuf Muhammad Maulana Yusuf Nungki Selviandro Nur Ghaniaviyanto Ramadhan Nurul Izzah Abdussalam Zahra Raditya Ghifari Aljabbar Reza Rendian Septiawan Salma Safira Ramandha Salma Zanuba Surya Michrandi Nasution Surya Micrandi Nasution