Article Per Year (5 Year)
p-Index From 2020 - 2025
0.882
P-Index
This Author published in this journals
All Journal ELKHA : Jurnal Teknik Elektro METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Jurnal Pendidikan dan Teknologi Indonesia Jurnal Fisika
Dirgayussa, I Gde Eka
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Physics

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Perancangan, Implementasi Monitoring dan Kontrol Alat Pemanggang Kopi Tampubolon, Friyogi; Pratama, Yohanssen; Dirgayussa, I Gde Eka
ELKHA : Jurnal Teknik Elektro Vol. 12 No. 2 October 2020
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v12i2.41188

Abstract

Coffee roasting is the process of removing the water that is exist in the coffee beans. Roasted coffee beans will change weight and give a nice aroma and taste. The longer the coffee beans are roasted, the color of the coffee beans will continue getting darker blackish brown. The roasting level of coffee beans is determined from the change in color of coffee beans starting from light, medium and dark. Roasting coffee beans that develop on a home industry scale is still manual, that is, using more human labor in its operation. Therefore, this research will be made an automatic coffee roasting machine using a heater to heating the coffee beans, a DC motor to stir roasted coffee beans and a webcam to monitor changes in the color of coffee beans when roasted. Components of heating elements and motors controlled by Arduino Mega 2560 microcontroller while the webcam is connected with Raspberry Pi 3. As a component of performance that has been met with sensors as data collectors, microcontrollers as data processors and actuators as control systems. In this researh 3D modeling for a roasting container is done using SketchUp 3D design software. The results of the coffee roasting machine can meet the requirements of the system designed in accordance with the roasting level desired by the user and the thermocoupel give a better result in reading the temperature parameter compared to infrared thermometer. In 4,5 minutes the difference reading in temperature reach 27,50C between two sensors.
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.
Klasifikasi Spesies Nyamuk Berbasis Few-Shot Learning Prototypical Network dengan ResNet-34 untuk Mendukung Sistem Pengendalian Vektor Dirgayussa, I Gde Eka; Pratama, Yohanssen; Apriana Susanti, Ni Wayan Puspa; Santoso, Budi
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 10 (2025): JPTI - Oktober 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.1356

Abstract

Klasifikasi spesies nyamuk secara cepat dan akurat merupakan aspek penting dalam upaya pengendalian berbagai penyakit seperti demam berdarah, chikungunya, dan filariasis. Metode klasifikasi berbasis pembelajaran mesin konvensional umumnya membutuhkan dataset berukuran besar yang relatif sulit untuk didapatkan. Untuk mengatasi kendala tersebut, penelitian ini mengusulkan pendekatan Few-Shot Learning (FSL) dengan menggunakan arsitektur Prototypical Network yang didukung oleh deep visual embeddings berbasis backbone ResNet-34. Model dilatih secara episodik dengan sedikit data per kelas menggunakan citra dari tiga spesies nyamuk utama yaitu Aedes aegypti, Aedes albopictus, dan Culex quinquefasciatus. Evaluasi kinerja model dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian ini  menunjukkan bahwa model dapat mencapai akurasi rata-rata sebesar 96,33% dengan deviasi antar-fold yang rendah serta stabilitas dan kemampuan generalisasi yang tinggi. Selain akurat, model ini juga efisien secara komputasi dengan waktu pelatihan rata-rata sebesar 0,83 detik per episode. Visualisasi menggunakan Grad-CAM menunjukkan bahwa model secara konsisten dapat memfokuskan perhatian pada area morfologis penting seperti toraks dan abdomen sehingga meningkatkan interpretabilitas dari proses klasifikasi. Secara keseluruhan, penelitian ini memberikan kontribusi penting dalam pengembangan sistem surveilans vektor berbasis kecerdasan buatan di wilayah dengan keterbatasan data dan sumber daya.
The Future Direction of Radiology: The Role of Artificial Intelligence and Augmented Reality in Medical Visualization Putra, Damianus Dinata; Nisa, Dila Fadilatu; Affan Alfarabi; Dirgayussa, I Gde Eka; Filano, Raffli
Jurnal Fisika Vol. 15 No. 2 (2025): Jurnal Fisika 15 (2) 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jf.v15i2.23310

Abstract

The rapid advancement of digital technologies has significantly influenced the field of medical imaging, particularly through the integration of Artificial Intelligence (AI) and Augmented Reality (AR). These technologies offer transformative potential in improving diagnostic accuracy, enhancing surgical planning, and addressing the limitations of traditional radiological methods. This study aims to evaluate the roles and effectiveness of AI and AR in radiology by analyzing their applications in medical diagnosis and surgical visualization, with a focus on increasing diagnostic speed, precision, and accessibility, especially in resource-limited settings. A systematic literature review was conducted by examining 45 peer-reviewed articles published between 2017 and 2025, selected based on relevance, innovation, and applicability. Thematic analysis revealed that AI—especially models using convolutional neural networks—has demonstrated high accuracy in detecting lung disease, breast cancer, and brain tumors. Meanwhile, AR has shown potential in enhancing spatial understanding and accuracy in surgical procedures. Despite these benefits, several challenges were identified, including integration difficulties with existing hospital systems, algorithmic bias, regulatory constraints, and high costs. In conclusion, the integration of AI and AR represents a promising direction for the future of radiology. However, further research is needed to develop cost-effective systems, ensure ethical and inclusive AI training, and establish standardized protocols for implementation. This study provides a foundational overview for healthcare stakeholders aiming to adopt these technologies in pursuit of more equitable and efficient medical imaging practices.
Advancements and Challenges of Deep Learning in Diagnostic Radiology: A Systematic Literature Review Affan Alfarabi; Filano, Rafli; Dirgayussa, I Gde Eka; Akbar, Ridho Lailatul; Zakiah, Hafizah
Jurnal Fisika Vol. 15 No. 2 (2025): Jurnal Fisika 15 (2) 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jf.v15i2.27967

Abstract

The rapid integration of Deep Learning (DL) in medical imaging is revolutionizing radiology and addressing critical challenges in diagnostic accuracy and healthcare delivery. In Indonesia and other developing countries, the shortage of radiologists and uneven distribution of healthcare services underline the urgency of exploring DL applications as potential solutions. This study aims to systematically review recent trends, effectiveness, and challenges of DL in diagnostic radiology, as well as to provide insights into its potential adaptation in the Indonesian healthcare system. Using a systematic literature review of peer-reviewed articles (2020–2025) from PubMed, IEEE Xplore, ScienceDirect, and Google Scholar, we identified and synthesized evidence on DL applications across multiple imaging modalities, including CT, MRI, X-ray, and ultrasound. Results show that DL achieves radiologist-level accuracy in tasks such as disease detection, segmentation, and automated report generation, while also improving workflow efficiency and clinical decision-making. However, challenges remain in terms of data availability, model interpretability, ethical issues, and clinical integration. This study provides recommendations for advancing DL adoption in radiology, emphasizing the need for standardized validation, clinician training, and context-specific implementation strategies in Indonesia. The findings highlight both the global and local significance of DL in enhancing healthcare access and equity.
Co-Authors Affan Alfarabi Akbar, Ridho Lailatul Apriana Susanti, Ni Wayan Puspa Doni Bowo Nugroho Dwi Budi Santoso Filano, Raffli Herman, Kevin Elfancyus Meita Mahardianti Muhammad Artha Jabatsudewa Maras Nisa, Dila Fadilatu Nurul Maulidiyah Pratama, Yohanssen Putra, Damianus Dinata Rafli Filano Rafli Filano Rudi Setiawan Sekar Asri Tresnaningtyas Tampubolon, Friyogi Yohanssen Pratama Zakiah, Hafizah