Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi JPEMAS: Jurnal Pengabdian Kepada Masyarakat
Rafli Filano
Unknown Affiliation
Humanities Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
FEW-SHOT LEARNING FOR AML CELL CLASSIFICATION USING PROTOTYPICAL NETWORKS Dirgayussa, I Gde Eka; Herman, Kevin Elfancyus; Nugroho, Doni Bowo; Sekar Asri Tresnaningtyas; Meita Mahardianti; Nurul Maulidiyah; Rafli Filano; Rudi Setiawan; Muhammad Artha Jabatsudewa Maras; Yohanssen Pratama
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 11 No. 2 (2025): Volume 11 Nomor 2 Tahun 2025
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/mtk.v11i2.4650

Abstract

Accurate blood cell classification is crucial for diagnosing Acute Myeloid Leukemia (AML) but limited medical data poses challenges for traditional machine learning models. This study presents a Few-Shot Learning (FSL) framework utilizing a Prototypical Network architecture with a ResNet-34 backbone to classify AML blood cell types from microscopic images. In this study, we utilize datasets consisting of 15 morphologically distinct cell classes. A 15-way, 5-shot, 5-query episodic setup was adopted to simulate data-scarce conditions. Evaluation via 5-fold cross-validation yielded strong performance, with an average accuracy of 97.76%, precision of 98.78%, recall of 96.55%, and F1-score of 97.76%. FSL training times were consistent (4.22–4.26 minutes per fold), and t-SNE along with confusion matrices confirmed the model’s ability to distinguish similar cell types. To validate the approach, its performance was compared with a conventional supervised CNN using the same ResNet-34 backbone. The FSL model outperformed the CNN across all metrics such as accuracy (98.32% vs. 77.25%), precision (98.55% vs. 76.87%), recall (98.31% vs. 78.66%), and F1-score (98.33% vs. 75.26%), while also requiring far less training time (~4.24 min/fold vs. ~420 min total). These results highlight the promise of FSL based methods for accurate, efficient, and scalable hematologic diagnostics in data limited settings.
FEW-SHOT LEARNING FOR AML CELL CLASSIFICATION USING PROTOTYPICAL I Gde Eka Dirgayussa; Kevin Elfancyus Herman; Doni Bowo Nugroho; Sekar Asri Tresnaningtyas; Meita Mahardianti; Nurul Maulidiyah; Rafli Filano; Rudi Setiawan; Muhammad Artha Jabatsudewa Maras; Yohanssen Pratama
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 11 No. 2 (2025): Volume 11 Nomor 2 Tahun 2025
Publisher : Universitas Methodist Indonesia

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

Abstract

Accurate blood cell classification is crucial for diagnosing Acute Myeloid Leukemia (AML) but limited medical data poses challenges for traditional machine learning models. This study presents a Few-Shot Learning (FSL) framework utilizing a Prototypical Network architecture with a ResNet-34 backbone to classify AML blood cell types from microscopic images. In this study, we utilize datasets consisting of 15 morphologically distinct cell classes. A 15-way, 5-shot, 5-query episodic setup was adopted to simulate data-scarce conditions. Evaluation via 5-fold cross-validation yielded strong performance, with an average accuracy of 97.76%, precision of 98.78%, recall of 96.55%, and F1-score of 97.76%. FSL training times were consistent (4.22–4.26 minutes per fold), and t-SNE along with confusion matrices confirmed the model’s ability to distinguish similar cell types. To validate the approach, its performance was compared with a conventional supervised CNN using the same ResNet-34 backbone. The FSL model outperformed the CNN across all metrics such as accuracy (98.32% vs. 77.25%), precision (98.55% vs. 76.87%), recall (98.31% vs. 78.66%), and F1-score (98.33% vs. 75.26%), while also requiring far less training time (~4.24 min/fold vs. ~420 min total). These results highlight the promise of FSL based methods for accurate, efficient, and scalable hematologic diagnostics in data limited settings.
Peningkatan Kesehatan Mental Dini untuk Pencegahan Bullying di Kuttab Anas Bin Malik Retno Maharsi; Aldi Herbanu; Asy Syifa Labibah; Rafli Filano; Sekar Asri Tresnaningtyas; Dwi Susanti; Nova Resfita; Nurul Maulidiyah; Seiswondyshu Hannoudzaky Sonefisal; Rilensya Rahma Suci
JPEMAS: Jurnal Pengabdian Kepada Masyarakat Vol. 4 No. 2 (2026): JPEMAS: Jurnal Pengabdian Kepada Masyarakat
Publisher : Yayasan Pendidikan Tanggui Baimbaian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71456/adc.v4i2.1782

Abstract

Kegiatan Pengabdian kepada Masyarakat (PkM) yang dilaksanakan oleh Program Studi Teknik Biomedis ITERA di Kuttab Anas bin Malik bertujuan untuk meningkatkan kesadaran dan pengetahuan siswa mengenai pentingnya kesehatan mental sebagai faktor yang memengaruhi cara berpikir, berperilaku, dan berinteraksi sosial. Latar belakang kegiatan ini didasarkan pada meningkatnya permasalahan kesehatan mental pada anak dan remaja serta adanya perilaku bullying di lingkungan pendidikan yang berdampak negatif terhadap kondisi emosional, kepercayaan diri, dan perkembangan sosial akademik siswa. Selain itu, keterbatasan pemahaman siswa terkait pengelolaan emosi dan interaksi sosial positif, serta belum adanya program edukasi kesehatan mental yang terstruktur, menjadi dasar pelaksanaan kegiatan ini. Metode yang digunakan berupa pendekatan edukatif dan interaktif melalui penyampaian materi mengenai empati, bullying dan dampaknya, serta pembiasaan perilaku sosial positif dengan teknik role play, drama, presentasi interaktif, dan lagu edukatif yang dilaksanakan dalam tiga tahap, yaitu pra-sosialisasi, sosialisasi, dan pasca-sosialisasi. Hasil kegiatan menunjukkan adanya peningkatan pemahaman siswa terhadap kesehatan mental serta terbentuknya perilaku sosial yang lebih positif. Kegiatan ini juga berkontribusi dalam menciptakan lingkungan sekolah yang lebih aman, nyaman, dan kondusif serta mendukung upaya pencegahan bullying secara efektif.
Co-Authors Aldi Herbanu Asy Syifa Labibah Dirgayussa, I Gde Eka Doni Bowo Nugroho Doni Bowo Nugroho Dwi Susanti Herman, Kevin Elfancyus I Gde Eka Dirgayussa Kevin Elfancyus Herman Meita Mahardianti Muhammad Artha Jabatsudewa Maras Nova Resfita Nurul Maulidiyah Retno Maharsi Rilensya Rahma Suci Rudi Setiawan Seiswondyshu Hannoudzaky Sonefisal Sekar Asri Tresnaningtyas Yohanssen Pratama