Article Per Year (5 Year)
p-Index From 2021 - 2026
1.399
P-Index
This Author published in this journals
All Journal Abdi Masyarakat Jurnal Pengabdian kepada Masyarakat Nusantara Jurnal Pengabdian Kepada Masyarakat Jurnal Algoritma Scientific Journal of Informatics Jurnal ilmiah teknologi informasi Asia
Safitri, Pima Hani
Unknown Affiliation
Arts Humanities Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Nursing Public Health Social Sciences Veterinary Other

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Algoritma

 1 
Rancang Bangun Prototipe Sistem Deteksi Dini Retinopathic Diabetic Berbasis Website Muhajir, Daud; Mustaqim, Tanzilal; Safitri, Pima Hani; Oktavia, Vessa Rizky
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2255

Abstract

Diabetic Retinopathic (DR) is one of the retinal disorders caused by high blood sugar levels. There are fewer ophthalmologists available, and treating DR patients manually is a time-consuming process. Therefore, there is a need for an automatic DR early detection method using Deep Learning. The purpose of this research is to build a web-based DR early detection prototype with retinal image classification using the DenseNet121 Deep Learning model and the Stochastic Gradient Descent (SGD) optimizer to improve the accessibility and efficiency of screening. The software development method used in this research is waterfall which consists of analysis phase, design phase, implementation phase, and testing phase. To ensure the prototype runs as planned, black-box testing is carried out on each of its features to ensure system functionality in accordance with predetermined specifications. This research produces a RD early detection prototype that has been tested with all 16 test cases and has a suitable status. Future research can be carried out further system development by involving real users such as ophthalmologists and can be applied in hospitals.
Analisis Perbandingan Metode Preprocessing untuk Citra Retinopati Diabetik Menggunakan Deep learning Safitri, Pima Hani; Mustaqim, Tanzilal; Muhajir, Daud
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2324

Abstract

Retinopati diabetik adalah gejala yang disebabkan oleh komplikasi diabetes yang menyerang mata penderitanya. Bercak-bercak pada retina penderita menjadi ciri gejalanya. Semakin banyak bercak, maka semakin parah retinopati diabetik yang diderita. Upaya peneliti untuk mendeteksi retinopati diabetik dengan citra retina sudah mulai dikembangkan dengan teknologi kecerdasan buatan, salah satunya berbasis deep learning. Kesulitan selanjutnya adalah kualitas citra retina yang kurang baik, sehingga mengakibatkan hasil deteksi yang kurang baik. Oleh karena itu, penelitian ini mengusulkan analisis perbandingan teknik untuk meningkatkan akurasi pengolahan citra deteksi retinopati diabetik berbasis deep learning. Data yang digunakan adalah data APTOS2019, yang terdiri dari 5 kelas berdasarkan tingkat keparahan penyakit. Ada tiga teknik yang digunakan: CLAHE, gamma correction, dan Retinex. Arsitektur deep learning yang digunakan adalah DenseNet121 dan EfficientNetB0 karena telah banyak digunakan pada data citra medis. Hasilnya, kombinasi gamma correction dan DenseNet121 menghasilkan akurasi tertinggi yaitu 81,4%. Sedangkan akurasi terendah diperoleh dari kombinasi menggunakan Retinex. Arsitektur terbaik secara keseluruhan adalah EfficientNetB0, dengan rata-rata akurasi sebesar 81,9%. Selanjutnya, penelitian ini dapat digunakan untuk memperbaiki citra retinopati diabetik sehingga deteksi dapat dilakukan sedini mungkin.
Peningkatan Sensitivitas Deteksi Diabetic Retinopathy melalui Mekanisme Hierarchical Self-Attention pada Swin Transformer Mustaqim, Tanzilal; Safitri, Pima Hani; Oktavia, Vessa Rizky
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2986

Abstract

Diabetic Retinopathy (DR) is a complication of diabetes that can cause blindness if not detected early. CNN has limitations in capturing scattered lesions due to its narrow receptive field, while Vision Transformers are generally less computationally efficient. The objective of this study is to develop an approach that can capture long-range spatial dependencies while maintaining computational efficiency for resource-limited clinical applications. The Swin Transformer-Tiny was implemented with a shifted window-based hierarchical self-attention mechanism on the APTOS 2019 dataset (3,663 retinal images), with pre-processing (CLAHE, gamma correction, Gaussian filtering) and data augmentation. The model was trained using SGD with CosineAnnealingLR and evaluated based on accuracy, precision, recall, and F1-score with a focus on minimizing false negatives. Swin Transformer-Tiny achieved an accuracy of 84.99%, precision of 84.89%, and recall of 84.99%, surpassing EfficientNet-B0 by 1.32% in F1-score and outperforming ResNet50 by 5.60%. The attention mechanism reduces false negatives by 1.28% compared to conventional CNNs while maintaining linear computational complexity. This research contributes to showing that hierarchical self-attention in Swin Transformer effectively improves DR detection sensitivity by overcoming the limitations of CNN receptive fields, while maintaining computational efficiency for clinical implementation.
Co-Authors Ahmad Wali Satria Bahari Johan Alqis Rausanfita Ardian Yusuf Wicaksono Arip Ramadan Desita Nur Rachmaniar DEWI RAHMAWATI Fauzi, Muhammad Dzulfikar Firdaus, Raihan Krishna Lokajaya, Gabriel Azarya Muhajir, Daud Muhammad Ilham Alhari Putra, Muhammad Alifian Rahmawati, Dyah Putri Saputra, Ananda Bintang Sebastian, Gerrard Tanzilal Mustaqim Vessa Rizky Oktavia Yulianto, Ilham