Article Per Year (5 Year)
p-Index From 2021 - 2026
4.041
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Journal of Information Technology and Computer Science Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Tirana Noor Fatyanosa, Tirana Noor
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 32 Documents
Search

 1   2   3   4 
Leveraging Stacked Vessel Segment and Channels of Fundus Image for Eye Disease Detection using Hybrid U-Net-Residual Convolutional Candra Dewi; Novanto Yudistira; Daffa Izzuddin; Nazura Wirayuda Tama; Fatyanosa, Tirana Noor
Journal of Information Technology and Computer Science Vol. 10 No. 2: August 2025
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2025102928

Abstract

Fundus images can be used to identify symptoms of various eye diseases. However, a limitation of using fundus images for classification is the generalization of information from the entire image, which can reduce recognition accuracy. To address this, this study proposes a combination of RGB channels from fundus images and segmented images for the identification process. Segmentation is performed using U-Net, which produces a segmentation of the blood vessels from the retinal image. The combined image is then used as input for the identification process with different ResNet models, including ResNet18, ResNet34, ResNet50, ResNet101, and ResNet152. Three model tuning scenarios are explored to obtain an optimal hybrid segmentation and classification model: learning using ResNet without U-Net (nounet), learning using a ResNet model with a frozen U-Net model (frozenunet), and learning using both the U-Net and ResNet models (hotunet). Testing is carried out to recognize normal, cataract, and glaucoma classes. The results show that the highest accuracy of 0.82 is achieved with the hybrid U-Net and ResNet152 model using frozenunet learning. This indicates that the addition of segmented images can improve identification results, with the best performance for glaucoma having a precision of 0.90, recall of 0.86, and F1-score of 0.88.
Analisis Dampak Panjang Dimensi Embedding Matryoshka Terhadap Kualitas Hasil dan Waktu Eksekusi dalam Sistem Pencarian Pakar Rafsandjani, Moch. Gustav Ali; Perdana, Rizal Setya; Fatyanosa, Tirana Noor
Jurnal Pengembangan Teknologi dan Ilmu Komputer Vol 10 No 7 (2026): Juli 2026
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pencarian pakar akademis berperan penting dalam membantu proses verifikasi kebenaran informasi. Pendekatan pencarian berbasis dokumen secara konvensional menggunakan representasi vektor semantik berdimensi tetap, yang dapat menimbulkan tantangan kompromi antara efisiensi komputasi dan kekayaan semantik. Penelitian ini menerapkan metode Matryoshka Representation Learning (MRL) pada arsitektur pencarian dua tahap guna mengeksplorasi trade-off kinerja pencarian pakar. Pengujian dilakukan menggunakan 100 kueri uji benchmark yang dievaluasi secara otomatis oleh juri Large Language Model (LLM) berbasis sistem penilaian Elo. Hasil eksperimen menunjukkan bahwa variasi panjang dimensi embedding memengaruhi latensi pencarian dengan nilai statistik F sebesar 3,9255 serta tingkat signifikansi p-value sebesar 0,0037. Pemangkasan dimensi hingga level 128 dimensi memotong waktu eksekusi rata-rata sebesar 36,02 persen dan disertai penurunan rata-rata kualitas hasil pencarian sebesar 4,97 persen jika dibandingkan dengan baseline dimensi 768 dimensi. Melalui pemetaan batas efisiensi, dimensi 128 diidentifikasi sebagai konfigurasi yang dinilai seimbang untuk penerapan sistem pencarian pakar secara praktis.
Co-Authors Achmad Ridok Adam, Muhammad Herdi Agus Wahyu Widodo, Agus Wahyu Aji, Alham Fikri Al Hafiz Akbar Maulana Siagian Al Kautsar, Prima Daffa Amadeo, Yoel Ananta, Hizkia Jeremmy Krisna Andreas Nugroho Sihananto Aqil Aldiyan, Rizky Aranda, Achmad Fauzi Athaya, Haikal Thoriq Azhari, Muhammad Rizqi Azzam, Ja'far Shidqul Brata, Gede Indra Adi Candra Dewi Candra Dewi Daffa Izzuddin Eman, Eleazar Tadeo Fidian, Diagne Alya Fitra Abdurrachman Bachtiar Gusti Ahmad Fanshuri Alfarisy, Gusti Ahmad Fanshuri Hafiz Rizky Nurwachid Hakim, Gibran Hakim, Muhammad Yasin Hanggara, Buce Trias Hilmi, Fadhilah Kusuma, Satrio Condro Lailil Muflikhah Lazuardi, Muhammad Dzakwan Bintang Lina, Femi Novia M Shochibul Burhan, M Shochibul Mahendra Data Marchelo, Nalendra Marji Maulana, Muhammad Taufik Murnastiti, Nurul Annisa Nazura Wirayuda Tama Niken Fitria Apriani Novanto Yudistira Nurwachid, Hafiz Rizky Pratama, Naufal Romero Putra Prima Zulvarina, Prima Putra Pandu Adikara Putra, Hanif Fermanda Raditya, Gavin Rafsandjani, Moch. Gustav Ali Raisaputri, Dayang Alyssa Raka Dimas Saputra Ravindra Rahman, Azka Reansyah, Javier Aahmes Rian Nopiardi Rizal Setya Perdana Sagala, Revaldo Gemino Kantana Saladin, Abid Faiz Sari, Irawati Nurmala Satrio Condro Kusuma Shidiq Al Hakim SIAGIAN, AL HAFIZ AKBAR MAULANA Tanaya, I Putu Paramaananda Taqiyassar, Kenzie Wayan Firdaus Mahmudy Winata, Jaya Zenatmaja, I Wayan Ivan