Article Per Year (5 Year)
p-Index From 2021 - 2026
3.757
P-Index
This Author published in this journals
All Journal Jurnal Matematika Jurnal Sains dan Teknologi Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JIEET (Journal of Information Engineering and Educational Technology) JUTIK : Jurnal Teknologi Informasi dan Komputer JOURNAL OF APPLIED INFORMATICS AND COMPUTING SINTECH (Science and Information Technology) Journal Jurnal Matematika UNAND Jurnal Ekonomi Manajemen Sistem Informasi Jurnal Cahaya Mandalika Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Pendidikan dan Teknologi Indonesia Jurnal Locus Penelitian dan Pengabdian Jurnal Pengabdian Informatika (JUPITA) International Journal of Applied Mathematics and Computing. Konstanta : Jurnal Matematika dan Ilmu Pengelatuan Alam
Wijayakusuma, I Gusti Ngurah Lanang
Universitas Udayana
Aerospace Engineering Humanities Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Immunology & microbiology Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

Published : 33 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 33 Documents
Search

 1   2   3   4 
Mathematical Model of COVID-19 with Aspects of Community Compliance to Health Protocols Gautama, I Putu Winada; Wijayakusuma, IGN Lanang; Swastika, Putu Veri; Dwipayana, I Made Eka
Jurnal Matematika UNAND Vol. 14 No. 2 (2025)
Publisher : Departemen Matematika dan Sains Data FMIPA Universitas Andalas Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jmua.14.2.154-166.2025

Abstract

COVID-19 infection is still a health problem in various countries. Some people who recover from COVID-19 still experience some symptoms. Therefore, it is essential to implement health protocols to minimize transmission of the COVID-19 virus. Based on this, a mathematical model of COVID-19 with aspects of community compliance with health protocols is presented. The population is divided into three subpopulations: the susceptible subpopulation, the exposed subpopulation, and the infected subpopulation. The basic reproduction number, $R_0$, determines whether there are disease-free and endemic equilibrium points. When $R_0$ is less than 1, the disease-free equilibrium is locally asymptotically stable. Conversely, when $R_0$ is greater than 1, the endemic equilibrium point is locally stable. Numerical simulations will demonstrate how COVID-19 spreads, taking into account community adherence to health guidelines. The results of numerical simulations indicate that an increase in public adherence to health protocols leads to a decrease in the number of COVID-19 infections.
Intelligent Web-Based Application for Personalized Obesity Management Wijayakusuma, I Gusti Ngurah Lanang; Sudarma, Made; I Ketut Gede Darma Putra; Oka Sudana; Minho Jo
Journal of Applied Informatics and Computing Vol. 9 No. 3 (2025): June 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i3.9151

Abstract

Obesity is a serious global problem due to its association with various chronic diseases. This study explores the utilization of machine learning in particular deep learning technology to predict Body Mass Index (BMI) from individual photos to create an efficient solution for assessing obesity. Using the ResNet152 model and K-Fold Cross Validation, this application integrates filters on individual photos to improve prediction accuracy. The application was developed using React JS for the front end, PHP and MySQL for the backend and database management, and Python as the core of the machine learning system. The application that tested using blackbox method, to see all features is functioning and the web application prototipe is passed all the test scenario.
Klasifikasi Subtipe Leukemia Limfoblastik Akut (LLA) pada Citra Mikroskopis Sel Darah Menggunakan Arsitektur EfficientNet-B3 dengan Dataset Seimbang Agustina, Ni Putu Dina; Wijayakusuma, I Gusti Ngurah Lanang
Jurnal Locus Penelitian dan Pengabdian Vol. 4 No. 6 (2025): JURNAL LOCUS: Penelitian & Pengabdian
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/locus.v4i6.4321

Abstract

Acute Lymphoblastic Leukemia (ALL) is one of the most common types of blood cancer that affects children and requires fast and accurate diagnosis. This study proposes a classification model for subtypes of acute lymphoblastic leukemia (ALL) based on microscopic blood cell images using the EfficientNet-B3 architecture. With a transfer learning approach and a balanced dataset, the model achieves a testing accuracy of 97.50% and an average F1-Score of 0.97. Overall, the macro average and weighted average values show consistent results, with precision and recall of 0.98 and an F1-Score of 0.97. This indicates that the model excels not only in one or two classes but demonstrates uniform performance across all classes, making it a robust classification tool for automatic leukemia diagnosis applications.
Dendritic ShuffleNetV2 Model for Alzheimer’s Disease Imaging Classification Riandika Fathur Rochim; I Gusti Ngurah Lanang Wijayakusuma
Journal of Applied Informatics and Computing Vol. 9 No. 4 (2025): August 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i4.9742

Abstract

This study investigates the integration of a dendritic neural model (DNM) into the ShuffleNetV2 architecture to enhance Alzheimer’s stage classification from MRI scans. The proposed “Dendritic ShuffleNetV2” retains the original network’s computational cost (0.31 GFLOPs) while incurring only a 1.6% increase in parameter count (from 2.48 M to 2.52 M) and achieves faster convergence (15 epochs versus 22 epochs). Experiments were conducted on a four‑class Alzheimer’s MRI dataset comprising Non‑Demented, Very Mild Demented, Mild Demented, and Moderate Demented categories. Compared to the baseline ShuffleNetV2, the Dendritic variant yielded an average accuracy improvement of 0.79%, with corresponding gains of approximately 0.8% in weighted precision, recall, and F1‑score. Confusion matrix analysis revealed persistent overlap between the Very Mild and Mild Demented classes, although overall discrimination—particularly for the majority and early‑stage classes—remained robust. Training stability was maintained without significant overfitting.
Eye Disease Classification Using EfficientNet-B0 Based on Transfer Learning Pratiwi Tentriajaya, I Dewa Ayu Pradnya; Wijayakusuma, I Gusti Ngurah Lanang
Journal of Applied Informatics and Computing Vol. 9 No. 4 (2025): August 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i4.9743

Abstract

This study focuses on developing and evaluating a deep learning approach employing EfficientNet-B0 based on transfer learning to classify retinal fundus images into four categories: Cataract, Diabetic Retinopathy, Glaucoma, and Normal. The model was trained using a retinal image dataset and demonstrated stable training performance, indicated by a consistent decrease in both training and validation loss without signs of overfitting. The training accuracy reached 92%, while the validation accuracy ranged between 94–95%. Model performance evaluation using a confusion matrix and classification report showed excellent classification results, particularly for the Diabetic Retinopathy class, with an F1-Score of 0.98. The Cataract and Normal classes also achieved high performance, with F1-Scores of 0.94 and 0.92, respectively. However, classification accuracy slightly declined for the Glaucoma class, which experienced some misclassification with the Normal class. Overall, the model achieved a classification accuracy of 94% on the test dataset, indicating good generalization capability. These findings suggest that the model holds strong potential for implementation in automated medical image-based diagnostic support systems. Nonetheless, performance improvement in classes with relatively higher misclassification rates is still required to ensure model reliability in clinical practice.
Implementation of Convolutional Neural Networks (CNN) for Breast Cancer Detection Using ResNet18 Architecture Siden, Hagia Sofia; Wijayakusuma, I Gusti Ngurah Lanang
Journal of Applied Informatics and Computing Vol. 9 No. 4 (2025): August 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i4.9746

Abstract

Early detection of breast cancer is crucial for improving patient survival rates. This study implements a Convolutional Neural Network (CNN) architecture based on ResNet18 using a transfer learning approach to classify breast ultrasound (USG) images into three categories: normal, benign, and malignant. The dataset, comprising 1,578 grayscale images collected from Baheya Hospital in Egypt, underwent preprocessing steps including image conversion, normalization, and augmentation. The ResNet18 model was fine-tuned using selective layer unfreezing to better adapt to the medical imaging domain. Evaluation was conducted using stratified 5-fold cross-validation and assessed with accuracy, precision, recall, F1-score, and AUC metrics. The best results were achieved by fine-tuning layer2, layer3, and the fully connected layer, yielding 95% accuracy, a macro F1-score of 0.93, and an AUC of 0.9906. The findings demonstrate that ResNet18, when properly fine-tuned with transfer learning, delivers high performance in breast cancer detection via ultrasound and holds strong potential as a reliable clinical decision-support tool.
Perbandingan Kinerja IndoBERT dan MBERT Untuk Deteksi Berita Hoaks Politik dalam Bahasa Indonesia Tobing, Charlotte Jocelynne L; IGN Lanang Wijayakusuma; Luh Putu Ida Harini
JST (Jurnal Sains dan Teknologi) Vol. 14 No. 1 (2025): April
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jstundiksha.v14i1.92126

Abstract

Berita hoaks menjadi tantangan besar dalam era digital, terutama dalam ranah politik di Indonesia, karena dapat memengaruhi opini publik dan stabilitas demokrasi. Penelitian ini bertujuan untuk membandingkan kinerja model IndoBERT dan Multilingual BERT (MBERT) dalam mendeteksi berita hoaks berbahasa Indonesia. Model dilatih menggunakan pendekatan fine-tuning pada dataset berita politik yang telah diberi label sebagai fakta atau hoaks. Evaluasi dilakukan menggunakan metrik akurasi, presisi, recall, F1-score, dan ROC-AUC. Hasil penelitian menunjukkan bahwa IndoBERT lebih unggul dibandingkan MBERT dalam mendeteksi berita hoaks, dengan performa yang lebih tinggi pada semua metrik evaluasi. Keunggulan IndoBERT disebabkan oleh pelatihannya yang spesifik pada korpus bahasa Indonesia, memungkinkan model memahami struktur dan pola bahasa dengan lebih baik dibandingkan MBERT yang bersifat multibahasa. Temuan ini menegaskan pentingnya model berbasis bahasa lokal dalam tugas klasifikasi teks yang spesifik. Implikasi dari penelitian ini menunjukkan bahwa penggunaan model berbasis bahasa lokal dapat meningkatkan efektivitas deteksi berita hoaks, serta dapat menjadi dasar pengembangan lebih lanjut untuk sistem otomatis dalam memverifikasi informasi di era digital.
Perbandingan Metode Transfer Learning untuk Identifikasi Tumbuhan Herbal Berbasis Lontar Usada Taru Pramana Desak Made Sidantya Amanda Putri; G K Gandhiadi; I GN Lanang Wijayakusuma
JST (Jurnal Sains dan Teknologi) Vol. 14 No. 1 (2025): April
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jstundiksha.v14i1.92414

Abstract

Indonesia dikenal memiliki keanekaragaman hayati yang melimpah, termasuk tumbuhan herbal yang dimanfaatkan dalam pengobatan tradisional, seperti di Bali yang beberapa masyarakatnya masih menggunakan tumbuhan herbal sebagai bahan pengobatan.  Namun, identifikasi dan klasifikasi tumbuhan herbal masih menjadi tantangan karena kesamaan morfologi antarspesies, yang dapat memengaruhi efektivitas pengobatan. Oleh karena itu, penelitian ini menganalisis dan mengembangkan metode klasifikasi tumbuhan herbal dengan pendekatan transfer learning menggunakan arsitektur Convolutional Neural Network (CNN), yaitu MobileNet-V2 dan ResNet-50 V2, guna meningkatkan akurasi klasifikasi. Penelitian ini menggunakan dataset TPHerbleaf yang berisi 1000 citra dari 50 jenis daun tumbuhan herbal yang tercatat dalam Lontar Usada Taru Pramana. Data diproses dengan teknik augmentasi dan fine-tuning, kemudian model diuji dengan membandingkan arsitektur usulan dengan penelitian terdahulu. Hasilnya, MobileNet-V2 mencapai akurasi 98,65%, sedangkan ResNet-50 V2 mencapai 98,48%, menunjukkan peningkatan signifikan dibanding model sebelumnya. MobileNet-V2 lebih efisien dalam penggunaan sumber daya, sementara ResNet-50 V2 lebih stabil dalam pelatihan jaringan yang dalam. Penelitian ini berkontribusi pada pengembangan metode klasifikasi tanaman herbal berbasis CNN yang lebih akurat dan aplikatif, serta dapat digunakan untuk mendukung pemanfaatan tanaman herbal secara lebih luas.
Perbandingan Metode LSTM dan TCN untuk Prediksi Gelombang Laut Berdasarkan Enam Parameter Oseanografi Ni Nyoman Bintang Marscelina; I GN Lanang Wijayakusuma; Putu Veri Swastika
JST (Jurnal Sains dan Teknologi) Vol. 14 No. 1 (2025): April
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jstundiksha.v14i1.92590

Abstract

Perubahan kondisi oseanografi seperti variabilitas gelombang laut mengancam keselamatan pengguna pantai dan aktivitas maritim di Pantai Mooloolaba, Australia. Penelitian ini dilatarbelakangi oleh kebutuhan mendesak untuk mengembangkan model prediksi yang mampu menangkap pola temporal jangka panjang dari parameter oseanografi secara akurat. Oleh karena itu, penelitian ini membandingkan dua pendekatan deep learning, yaitu long short-term memory (LSTM) dan temporal convolutional network (TCN), guna mengoptimalkan prediksi perilaku gelombang laut berdasarkan enam parameter oseanografi. Menggunakan metode kuantitatif dengan desain komparatif eksperimental, penelitian ini memanfaatkan data sekunder dari Queensland Government Data dengan interval pengukuran 30 menit (20 April 2000 – 31 Agustus 2024). Setelah pra-pemrosesan, data dibagi menjadi 80% pelatihan dan 20% pengujian. Hasil evaluasi menunjukkan bahwa TCN memiliki nilai RMSE lebih rendah dibandingkan LSTM pada semua parameter, baik pada data latih maupun uji. Oleh karena itu, TCN lebih unggul dalam menangkap pola temporal jangka panjang dan lebih efektif untuk mitigasi risiko kondisi laut ekstrem.
Comparing Data Preprocessing Strategy on T5 Architecture to Classify ICD-10 Diagnosis Lanang Wijayakusuma, I Gusti Ngurah; Sudarma, Made; Darma Putra, I Ketut Gede; Sudana, Oka; Astutik, Dian
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 5 (2025): October 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i5.6919

Abstract

Manual ICD-10 coding in healthcare systems remains time-consuming, error-prone, and inefficient, particularly in resource-constrained settings. This study investigates the effect of various preprocessing strategies on the performance of the Text-to-Text Transfer Transformer (T5) model for primary diagnosis classification using structured clinical data. A total of 7,263 clinical records were collected from two high-density regions in Bali (Badung and Gianyar) between January 2023 and March 2024, then converted into descriptive text prompts for model training. Four experimental scenarios combined variations of input features and label configurations, comparing T5 with Oversampling against T5 with Easy Data Augmentation (EDA) plus Oversampling. Results showed that T5 with Random Oversampling consistently outperformed the EDA-based configuration across all scenarios, with performance gaps ranging from 8% to 19%. Scenario 4, which excluded body system features and the semantically overlapping E860 label, achieved the highest balance, reaching 84.7% accuracy, 85.1% precision, 84.7% recall, and 84.3% F1-score. Conversely, the EDA-based approach reduced training time by up to 72%, indicating a clear trade-off between performance and efficiency. Both configurations frequently misclassified semantically similar codes within the same ICD-10 categories, underscoring the difficulty of distinguishing clinically related diagnoses. Overall, the results suggest that careful selection of preprocessing strategies can enhance transformer-based medical text classification, while striking a balance between model performance and training efficiency. This work may serve as an initial reference for developing more efficient semi-automated medical coding systems in the Indonesian regional healthcare context.
Co-Authors Agustina, Ni Putu Dina Anak Agung Kompiang Oka Sudana Arta Wiguna, I Putu Chandra Astutik, Dian Br Sebayang, Virna Dalira Chandra, Veronica Celine Damayanthi, Ni Wayan Rita Desak Made Sidantya Amanda Putri Driyandita, Bernadeta EKA N. KENCANA Fransisca Emmanuella Aryossi G K Gandhiadi I Gusti Ayu Made Srinadi I ketut Gede Darma Putra I Ketut Restu Wiranata I KOMANG GDE SUKARSA I MADE EKA DWIPAYANA I Nyoman Widana I Putu Eka Nila Kencana I PUTU WINADA GAUTAMA I Putu Winada Gautama I WAYAN SUMARJAYA IM Suyana Utama Isabel Divya Georgiana Walewangko Jocelynne, Charlotte Karina Maharani Bernis Kencana, Eka N. Ketut Jayanegara Khairunisa, Mutiara Komang Dharmawan LUH PUTU IDA HARINI LUH PUTU IDA HARINI Made Sudarma Manurung, Mikael Triartama Maylianti, Ni Putu Minho Jo Ni Kadek Emik Sapitri Ni Luh Putu Suciptawati Ni Nyoman Bintang Marscelina Ni Putu Leony Putri Paramita Pratama, Halim Meliana Pratiwi Tentriajaya, I Dewa Ayu Pradnya Putri, Desak Putri, Desak Made Sidantya Amanda Putri, Made Ayu Asri Oktarini Putu Veri Swastika Raharja, Made Agung Ratna Sari Widiastuti Riandika Fathur Rochim Sagun Chandra Yowani Siden, Hagia Sofia Swastika, Putu Veri Tobing, Charlotte Jocelynne L Ulfatun Farika Novitasari Widiastuti, Ratna Sari Yohanes Kristianto Kristianto