Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal JIKO (Jurnal Informatika dan Komputer) Informatik : Jurnal Ilmu Komputer Advanced Journal of STEM Education (AJOSED)
Neny Rosmawarni
Universitas Pembangunan Nasional "Veteran" Jakarta
Computer Science & IT Education Other

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

Found 3 Documents
Search

 1 
Augmented Reality Markerless Implementation Method in Benign Education Application for Prostatic Mobile-Based Hyperplasia (BPH) Muhammad Fari Abiyyudhiya; Neny Rosmawarni; Hamonangan Kinantan Prabu
Advanced Journal of STEM Education Vol. 4 No. 1 (2026): Advanced Journal of STEM Education (AJOSED)
Publisher : Research Synergy Foundation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31098/ajosed.v4i1.3306

Abstract

Technological developments in recent years have brought significant changes in education, particularly through the integration of Information and Communication Technology (ICT). ICT enables broader and more flexible access to learning resources through distance learning, educational applications, and digital platforms. One notable innovation is Augmented Reality (AR), which integrates two-dimensional (2D) and three-dimensional (3D) virtual objects into real-world environments in real time, providing more interactive and concrete learning experiences. This study aims to develop a mobile-based educational application using markerless Augmented Reality to improve the general population's understanding of Benign Prostatic Hyperplasia (BPH). This common health condition remains poorly understood. The research methodology adopts the Multimedia Development Life Cycle (MDLC), which consists of concept, design, material collection, assembly, testing, and distribution stages. The application was developed using Unity and Vuforia SDK and implemented on mobile devices. The findings show that the developed application functions properly, as demonstrated by black-box testing and markerless distance testing. Questionnaire and knowledge test results indicate that users' understanding of BPH improved after using the application. Users also provided positive feedback regarding usability, visual quality, and the effectiveness of AR-based learning. In conclusion, the proposed markerless AR educational application is an effective interactive learning medium for increasing public awareness, supporting early understanding, and encouraging timely treatment of Benign Prostatic Hyperplasia.
Developing a Machine Learning Model to Shorten Emergency Department Length of Stay: Model Testing and Nurses Acceptance Laksita Barbara; Neny Rosmawarni; Arief Wahyudi Jadmiko
Informatik : Jurnal Ilmu Komputer Vol 22 No 1 (2026): April 2026
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52958/iftk.v22i1.13031

Abstract

This study aimed to develop and evaluate a portfolio of ML models to predict ED LoS and examine nurses’ acceptance of AI-based clinical decision support. Secondary data from two public hospitals in Jakarta were analysed using three ML algorithms Random Forest, Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM) to classify ED LoS into short, medium, and prolonged categories. Predictor variables included triage level, arrival time, referral source, disposition, number of diagnostic tests, and consultations. Model performance was assessed using precision, recall, and F1-scores across training, testing, and blind validation datasets. Additionally, nurses’ readiness to adopt ML tools was evaluated using a survey. Across 687 ED cases, XGBoost achieved the best overall performance (precision, recall, and F1-score = 1.00), indicating excellent discrimination and balance between sensitivity and specificity. SVM also demonstrated strong external validation (blind-test F1 = 1.00), confirming robust generalisation across hospital sites. High-performance metrics across all models indicate consistent accuracy and calibration. Most nurses (89.3%) expressed high performance expectancy, and 95.7% high effort expectancy toward technology adoption. The developed ML framework accurately predicts ED LoS in Jakarta’s hospital settings, providing a foundation for data-driven resource management.
PERBANDINGAN DENSENET201, EFFICIENTNETB0, DAN MOBILENETV2 UNTUK KLASIFIKASI TUBERKULOSIS DAN PNEUMONIA PADA PARU Muhammad Alif Nadin Putra; Neny Rosmawarni; Kraugusteeliana Kraugusteeliana; Faiz Firstian Nugroho; Nisaul Husna
JURNAL INFORMATIKA DAN KOMPUTER Vol 10, No 2 (2026): Juni 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v10i2.2686

Abstract

Penelitian ini bertujuan membandingkan performa DenseNet201, EfficientNetB0, dan MobileNetV2 untuk klasifikasi citra X-ray dada pada tiga kelas, yaitu TBC, pneumonia, dan normal, sebagai respons terhadap keterbatasan tenaga radiolog dan tingginya kebutuhan diagnosis cepat. Dataset berjumlah 5.312 citra (2.494 TBC, 2.100 pneumonia, 718 normal) dibagi menjadi 70% data latih, 15% validasi, dan 15% data uji. Tahap praproses mencakup resize citra menjadi 224×224 piksel, normalisasi sesuai model, serta augmentasi data berupa horizontal/vertical flip, rotasi, zoom 15%, dan shear 15%. Ketiga arsitektur dilatih menggunakan transfer learning berbobot awal ImageNet, kemudian fine-tuning pada 15 lapisan terakhir dengan optimizer Adam. Evaluasi dilakukan menggunakan confusion matrix, akurasi, precision, recall, F1-score, dan AUC. Hasil menunjukkan DenseNet201 memberikan kinerja terbaik dengan akurasi 96,86% (precision 97%, recall 96%, F1-score 96%), diikuti EfficientNetB0 dengan akurasi 95,61%, sedangkan MobileNetV2 mencapai 89,21%. Temuan ini menunjukkan DenseNet201 paling efektif untuk klasifikasi TBC dan pneumonia pada citra X-ray dada, dengan tantangan utama berupa ketidakseimbangan data pada kelas normal yang masih memengaruhi konsistensi prediksi model.
Co-Authors Arief Wahyudi Jadmiko Faiz Firstian Nugroho Hamonangan Kinantan Prabu Kraugusteeliana Kraugusteeliana Laksita Barbara Muhammad Alif Nadin Putra Muhammad Fari Abiyyudhiya Nisaul Husna