Mahajaya, Nyoman Sarasuartha
Unknown Affiliation

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

Found 3 Documents
Search

Classification of Lung Diseases in X-Ray Images Using Transformer-Based Deep Learning Models Mahajaya, Nyoman Sarasuartha; Putu Desiana Wulaning Ayu; Roy Rudolf Huizen
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI Vol. 13 No. 3 (2024)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v13i3.81425

Abstract

This research evaluates the performance of two Transformer models, the Vision Transformer (ViT) and Swin Transformer, in the analysis of thoracic X-ray images. The study's objective is to determine whether Transformer models can enhance diagnostic accuracy for lung diseases, considering challenges such as early symptom variability and similar radiological signs. The dataset includes 21,165 X-ray images, featuring 3,616 COVID-19 cases, 10,192 normal images, 6,012 images of Lung Opacity, and 1,345 pneumonia images. Model development involved tuning hyperparameters such as epoch numbers and optimizer choice. The results indicate that using the AdamW and Adamax optimizers achieves an optimal balance between computational efficiency and accuracy. The Swin Transformer model, using the Adamax optimizer, reached the highest testing accuracy of 96.10% in 33,802.70 seconds, while the Vision Transformer achieved a testing accuracy of 95.10% in 33,503.10 seconds.
PELATIHAN DAN PENDAMPINGAN PENGGUNAAN ALAT PENGENALAN PROVINSI DI INDONESIA MENGGUNAKAN MIKROKONTROLER PADA SDN 1 SEMPIDI BADUNG BALI Desnanjaya, I Gusti Made Ngurah; Nugraha, I Made Aditya; Mahajaya, Nyoman Sarasuartha
Jurnal Widya Laksmi: Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 2 (2025): Jurnal WIDYA LAKSMI (Jurnal Pengabdian Kepada Masyarakat)
Publisher : Yayasan Lavandaia Dharma Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59458/jwl.v5i2.189

Abstract

Pembelajaran geografi di tingkat sekolah dasar di Indonesia seringkali terkendala oleh metode konvensional yang monoton, berdampak pada rendahnya pemahaman dan minat siswa, khususnya dalam mengenali provinsi-provinsi di Indonesia. SDN 1 Sempidi di Badung, Bali, menghadapi tantangan ini akibat keterbatasan media pembelajaran interaktif. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk merancang, mengimplementasikan, dan mengevaluasi efektivitas media pembelajaran berupa peta interaktif berbasis mikrokontroler untuk meningkatkan pemahaman geografis dan minat belajar siswa. Metode pelaksanaan menggunakan pendekatan participatory action research yang melibatkan lima tahapan sistematis: (1) identifikasi kebutuhan bersama mitra, (2) pengembangan alat peraga berbasis mikrokontroler AtMega 2560, (3) pelatihan dan pendampingan guru, (4) implementasi di dalam kelas, dan (5) evaluasi dampak menggunakan instrumen pre-test dan post-test pada 28 siswa kelas 6. Hasil evaluasi menunjukkan peningkatan signifikan dalam pengetahuan siswa. Persentase siswa dengan pemahaman "Baik" dan "Sangat Baik" melonjak dari 39,7% pada pre-test menjadi 89,3% pada post-test. Sebaliknya, kategori "Tidak Baik" menurun drastis dari 50% menjadi hanya 7,1%. Peta interaktif terbukti menjadi solusi pedagogis yang efektif untuk mengatasi kesenjangan pembelajaran. Pendekatan multi-sensori (visual, auditori, taktil) berhasil meningkatkan keterlibatan dan pemahaman siswa secara signifikan. Program ini juga berhasil membangun kapasitas guru untuk keberlanjutan pemanfaatan teknologi di sekolah.
Stock Control-Based Personal Protective Equipment Inventory System for Work Safety Santika, Komang Yuli; Putri, Putu Chrisdayanti Suada; Sridyantari, Luh Verra; Anggara, Komang Drei Bayu; Permana, Putu Adi Guna; Mahajaya, Nyoman Sarasuartha
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3842

Abstract

Effective management of Personal Protective Equipment (PPE) is crucial for ensuring worker safety in hazardous environments. However, manual PPE management often leads to issues, such as discrepancies between recorded stock and actual quantities and challenges in tracking tool distribution. As a result, there is a need for an inventory system that can effectively monitor and control PPE stock levels. This research aims to design a web-based inventory system capable of managing PPE with integrated stock control using the Economic Order Quantity (EOQ), Safety Stock, and Reorder Point (ROP) methods. The methodology used in this study is a Research and Development (R&D) approach with a prototyping model. The research includes the design of data structures and system process flows, as well as the implementation of key features, including a dashboard, inventory management, and PPE distribution. The data used consists of employee data, supplier information, PPE types, and existing stock, all of which are analyzed to support the stock control system. The results show that the developed system can record and monitor PPE stock levels more systematically than manual methods. Additionally, the system allows for accurate monitoring of PPE distribution to employees. In conclusion, the web-based PPE inventory system can significantly improve stock management efficiency and support workplace safety by ensuring the timely availability of appropriate PPE. Future research is recommended to test the system with real operational data and assess its impact on managing occupational safety risks.