Article Per Year (5 Year)
p-Index From 2021 - 2026
1.922
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Informasi Proceedings of KNASTIK Journal of ICT Research and Applications JUITA : Jurnal Informatika PAX HUMANA Indonesian Journal of Artificial Intelligence and Data Mining JurTI (JURNAL TEKNOLOGI INFORMASI) Indonesian Journal of Computing and Modeling Jurnal Riset Informatika CCIT (Creative Communication and Innovative Technology) Journal Jurnal SITECH : Sistem Informasi dan Teknologi Aiti: Jurnal Teknologi Informasi Journal of Business and Technology Jurnal Pengabdian Papua BACA: Jurnal Dokumentasi dan Informasi International Journal of Information Technology and Business JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Radius Tanone
Universitas Kristen Satya Wacana
Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Earth & Planetary Sciences Education Languange, Linguistic, Communication & Media Library & Information Science Mathematics Medicine & Pharmacology Social Sciences Other

Published : 32 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 32 Documents
Search

 1   2   3   4 
Implementation of MobileNetV2 and OpenCV in a Real-Time Sign Language Recognition System Marcellinus Ronan Narendra; Radius Tanone
Journal of Business and Technology Vol 6, No 1: April 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/jbt.v6i1.14500

Abstract

The main means of communication for the deaf is sign language, although communication hurdles are frequently caused by a lack of public comprehension. The goal of this project is to use the OpenCV library and MobileNetV2 architecture to create a real-time American Sign Language (ASL) recognition system. The ASL Alphabet from Kaggle, which has over 87,000 photos in 29 classes, is the dataset that was used. Convolutional Neural Networks (CNNs) based on MobileNetV2 with picture preprocessing and data augmentation were used to train the model. OpenCV was then used to combine the CNN with a camera for real-time implementation.The evaluation results indicate an average F1-score of 83.6, recall of 83.8, and precision of 83.5. The system is responsive for direct interaction because it can operate at 18–22 frames per second (FPS) on a typical laptop. The system still has issues with complicated backdrops, low light levels, and gesture similarities between some letters. Overall, this study demonstrates the efficacy of MobileNetV2 and OpenCV in developing a lightweight, efficient real-time sign language recognition system that facilitates inclusive communication for individuals with hearing impairments.
Bridging Vision and Graph Attention Learning Using Swin Transformer for Brain Tumor Classification Radius Tanone; Yos Richard Beeh; Pratyaksa Ocsa Nugraha Saian; Agus Cahyo Nugroho
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1839

Abstract

Accurate brain tumor classification from MRI images is crucial for supporting clinical diagnosis. This study proposes a hybrid framework that integrates a Swin Transformer and Graph-based learning to enhance feature representation and relational modeling. The Swin Transformer, known for its linear computational complexity and multi-scale attention mechanism, serves as a hierarchical feature extractor. The Graph module, on the other hand, captures structural dependencies among the extracted features. The model is evaluated on a four-class brain MRI dataset using 5-Fold cross-validation. Experimental results consistently demonstrate high performance, with the best accuracy of 0.9907. The model achieves sensitivity and specificity of 0.9903 and 0.9970, respectively. Notably, all folds maintain accuracy above 0.9500, indicating strong robustness and generalization capability. The proposed approach effectively reduces misclassification across tumor categories and outperforms baseline methods, underscoring its potential for reliable brain tumor classification.
Co-Authors Adi Nugroho Adib Luqman Azhari Agus Cahyo Nugroho Andreas A. Sukmana Arnold B Emmanuel Azhari, Adib Luqman Benny Kurniawan Betty E. Kristiani Budhi Kristianto Daniel Ritchie Indriyanto Supatra Daniel Tanudjaja Danny Manongga Dharmaputra Palekahelu Dodi Vebri Wicahyo Dwi Anggono Winarso Suparjo Putra Enggar Krisnada, Filian Erwien Christianto Evangs Mailoa Filian Enggar Krisnada George Richard Payara Hanita Yulia Hanna Prillysca Chernovita Hindriyanto Dwi Purnomo Irma Iswara Anatasia Komala Sari Jihot Lumban Gaol Johan Jimmy Carter Tambotoh Julios Gibral Ragananta Kresna Prasmadewa Kresna Prasmadewa, Kresna Krismiyati Kristoko Dwi Hartomo Kurniawan, Theofilus Li Hua Li Lumban Gaol, Jihot Marcellinus Ronan Narendra Markus Permadi Nadya Salsabila Mustafa Nina Setiyawati Palpialy, Revian Payara, George Richard Permadi, Markus Pratyaksa Ocsa Nugraha Saian Purwanto - Purwanto Purwoko, Agus Raynaldo Raynaldo Raynaldo Raynaldo, Raynaldo Revian Palpialy Riko Yudistira Robert William Ruhulessin Roosevelt Joshua Gunadi Rudy Latuperissa Saputri, Yuvika Sahid Saraswati, Fauzia Puspa Sri Kasmiyati Suprihadi Sushendra Ipol Sushendra Ipol, Sushendra Tanudjaja, Daniel Teguh I. Bayu Teguh Indra Bayu Vita Tantriyati Viviliani Viviliani Viviliani, Viviliani Wijaya, Yan Rigid Yan Rigid Wijaya Yos Richard Beeh Yudistira, Riko Yuliana T. B. Tacoh Yuvika Sahid Saputri