cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
I Gede Surya Rahayuda
Contact Email
igedesuryarahayuda@unud.ac.id
Phone
+6289672169911
Journal Mail Official
jnatia@unud.ac.id
Editorial Address
Sekretariat JNATIA Gedung FMIPA Lantai 1, Program Studi Informatika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Udayana
Location
Kota denpasar,
Bali
INDONESIA
Jurnal Nasional Teknologi Informasi dan Aplikasinya
Published by Universitas Udayana
ISSN : 29863929     EISSN : 30321948     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Engineering
JNATIA (Jurnal Nasional Teknologi Informasi dan Aplikasinya) adalah jurnal yang berfokus pada teori, praktik, dan metodologi semua aspek teknologi di bidang ilmu komputer, informatika dan teknik, serta ide-ide produktif dan inovatif terkait teknologi baru dan teknologi informasi. Jurnal ini memuat makalah penelitian asli yang belum pernah diterbitkan. JNATIA (Jurnal Teknologi Informasi dan Aplikasinya) diterbitkan empat kali setahun (Februari, Mei, Agustus, November).
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 49 Documents
 1   2   3   4   5 
Analisis Komparatif Arsitektur CNN dan VGG16 pada Klasifikasi Genre Musik Komang Indra Pradnya; Made Agung Raharja
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 4 (2025): JNATIA Vol. 3, No. 4, Agustus 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v03.i04.p19

Abstract

Music genre classification based on spectrogram images is an important task in music information retrieval. This study compares the performance of a custom Convolutional Neural Network (CNN) architecture and VGG-16 for classifying five music genres from the GTZAN dataset: blues, classical, hiphop, metal, and reggae. A total of 500 audio files were converted into spectrogram images for training and testing. The custom CNN was designed and trained from scratch, while VGG-16 utilized pretrained weights with fine-tuning applied to the fully connected layers. Experimental results show that the custom CNN achieved 75% test accuracy and a macro F1- score of 0.74, outperforming VGG-16 which achieved 68.75% accuracy and a macro F1-score of 0.67. These findings demonstrate the advantage of using a tailored architecture for spectrogram- based music genre classification and provide directions for future research, including full fine- tuning of pretrained models, hybrid architectures, and integration of temporal features.
Analisis Visual Clutter Antarmuka Aplikasi Belanja Online Menggunakan Metode System Usability Scale Anak Agung Yoga Aditya Putra; Cokorda Pramartha
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p14

Abstract

This study investigates the phenomenon of visual clutter in mobile online shopping applications, a growing concern given the rapid expansion of the e-commerce industry and increasing reliance on mobile devices for shopping activities. Visual clutter, characterized by an overly dense, unfocused, or excessive display, can disrupt user interaction, heighten cognitive load, and diminish the effectiveness of visual search. The research specifically analyzes the degree of visual clutter within a selected online shopping application interface, representing a mobile e-commerce platform. The System Usability Scale (SUS) method was employed to quantitatively assess user perceptions of the application's usability. The findings are expected to offer valuable insights for developing more structured and user-friendly online shopping application interfaces.
Optimasi Hyperparameter CART Menggunakan Particle Swarm Optimization (PSO) untuk Klasifikasi Penyakit Stroke I Putu Agus Wahyu Wirakusuma Putra; I Putu Gede Hendra Suputra; Ida Bagus Gede Sarasvananda
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p18

Abstract

Stroke is a leading cause of death and disability worldwide, including in Indonesia, making early diagnosis crucial. This study aims to enhance the accuracy of stroke classification using the Classification and Regression Tree (CART) algorithm optimized with Particle Swarm Optimization (PSO). A primary challenge in stroke classification is the prevalence of imbalanced datasets. To address this issue, the hybrid sampling technique SMOTEENN (Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors) was applied to balance the class distribution. The standard CART model (baseline) was first evaluated, achieving an accuracy of 94.41%. Subsequently, PSO was implemented to find the optimal hyperparameter combination for the CART model. The PSO optimization results improved the model's performance; the optimized CART model achieved an accuracy of 94.84%, an increase of 0.43% compared to the baseline model. This improvement demonstrates that the combination of the SMOTEENN method for handling imbalanced data and PSO for hyperparameter optimization is an effective and promising approach to enhance the accuracy of stroke classification models.
Implementasi Algoritma Rule-Based dalam Penentuan Tata Letak Sanggah Merajan Ni Kadek Rika Dwi Utami; I Wayan Supriana
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p10

Abstract

Balinese traditional architecture holds deep philosophical and spatial meanings, particularly in the design of sacred family shrines known as merajan. However, the complexity of applying Asta Kosala Kosali principles often poses challenges, especially for the younger generation unfamiliar with traditional spatial knowledge. This research aims to develop a web-based simulator that assists users in designing merajan layouts by implementing a rule-based algorithm derived from literature and expert interviews. The simulator processes user inputs such as land dimensions and traditional measurement units to generate an automated visual layout that aligns with cultural rules. The methodology includes knowledge acquisition, rule formulation, system architecture design, and functional implementation. Functional testing confirms that the system can accurately position sacred structures according to the Sanga Mandala zoning concept and calculate distances based on customary units like alengkat and limang nyari. Usability testing involving 38 respondents using the System Usability Scale (SUS) method results in a high usability rating, indicating the system’s ease of use and usefulness. This research contributes to the digital preservation and dissemination of Balinese spatial wisdom and provides a foundation for future development of interactive cultural heritage tools.
Analisis Perbandingan K-Means++, Mini Batch K-Means, dan Fuzzy C-Means pada Segmentasi Pelanggan I Putu Satria Dharma Wibawa; Made Agung Raharja
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p19

Abstract

Customer segmentation is a crucial process for optimizing marketing strategies This study aims to implement and compare three clustering algorithms on customer transaction data using RFMT (Recency, Frequency, Monetary, and Tenure) features. The dataset, obtained from the UCI Machine Learning Repository, underwent several preprocessing stages, including data cleaning, feature extraction, outlier handling, and normalization. Optimal cluster numbers were determined using the elbow method and validated using silhouette score and davies-bouldin index. The results show that mini batch k-means outperforms the other algorithms with the highest silhouette score of 0.4011 and the lowest davies-bouldin index of 0.9521. K-means++ demonstrated better computation time but slightly lower clustering quality, while fuzzy c-means produced less distinct segmentation
Klasifikasi Berita Berdasarkan Kategori Menggunakan Convolutional Neural Network dengan IndoBERT Jonathan Federico Tantoro; I Dewa Made Bayu Atmaja Darmawan
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 4 (2025): JNATIA Vol. 3, No. 4, Agustus 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v03.i04.p20

Abstract

The advancement of technology information has led to a significant increased the volume of digital news, that makes needs for automatic news classification. This study aims to design a model capable of caterogizing Indonesian language news articles into six predefined categories, such as News, Money, Bola, Health, Tekno, and Tren. To achieve this goal, the method used combines IndoBERT as the embedding technique with Convolutional Neural Network (CNN) as the classification algorithm. The dataset consists of 3.000 news articles collected from Kompas.com and is divided into training data and testing data using four different data split ratios: 60:40, 70:30 80:20, and 90:10 . The evaluation results show that the best performance was achieved using the 80:20 ratio, where the model reached an accuracy of 91%, along with high precision, recall, and F-1 Score These result prove that the combination of IndoBERT and CNN is effective for the automatic classification of Indonesian new texts.
Analisis Sentimen Kebijakan Insentif Mobil Listrik Menggunakan TF-IDF dan Naïve Bayes Yande Pramana Yustika Pradeva; I Made Widiartha; I Putu Satwika
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p20

Abstract

This study aims to analyze public sentiment regarding the Indonesian government’s electric vehicle (EV) incentive policy using YouTube comments as the data source. The research applies text preprocessing steps including cleaning, normalization, stopword removal, tokenization, and stemming to prepare the textual data. The cleaned data is transformed into numerical representation using the Term Frequency-Inverse Document Frequency (TF-IDF) method and classified using the Multinomial Naïve Bayes algorithm. To address class imbalance in the dataset, Synthetic Minority Over-sampling Techique (SMOTE) is applied. The model evaluation metrics include accuracy, precision, recall, and F1-score. Based on the evaluation, the model achieves an accuracy of 71%. The model performs better in classifying negative comments, as shown by a higher recall and F1-score in the negative class compared to the positive class. These findings indicate that public responses to the EV incentive policy tend to be more critical. This study provides insights into public opinion that can serve as a valuable reference for policymakers in designing more effective and well-communicated incentive strategies for promoting electric vehicle adoption in Indonesia.
Model Penerjemah Bahasa Isyarat SIBI Statis Berbasis Convolutional Neural Network Ni Made Wipra Ranum Ratnayu; I Dewa Made Bayu Atmaja Darmawan; I Putu Gede Hendra Suputra
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p21

Abstract

This study addresses the communication gap between deaf and hearing communities by developing an optimal sign language recognition system for Indonesian Sign Language System (SIBI) static gestures. A comprehensive comparative analysis was conducted on four VGG architecture variants (VGG-11, VGG-13, VGG-16, and VGG-19) using a dataset across 10 SIBI word classes. The research employed systematic methodology including data extraction from video sources, preprocessing with augmentation techniques, model training over 25 epochs, and comprehensive evaluation using accuracy, precision, recall, and F1-score metrics. Results demonstrate that VGG-16 achieves superior performance with 83.4% accuracy, 85.2% precision, 83.4% recall, and 82.9% F1-score, establishing optimal balance between model complexity and generalization capability. The study reveals diminishing returns phenomenon in VGG-19 despite increased architectural complexity. Computational efficiency analysis shows VGG-11 provides highest efficiency score (10.46 GFLOPs) while VGG-16 maintains optimal accuracy-efficiency trade-off. These findings provide crucial insights for developing effective assistive technology solutions that bridge communication barriers for the Indonesian deaf community.
Implementasi Pipeline CI/CD dengan Github Actions dalam Mengurangi Downtime pada Aplikasi Berbasis Web I Komang Wahyu Pranata; I Wayan Santiyasa
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p15

Abstract

This research focuses on optimizing the application deployment process to minimize prolonged downtime, which is often caused by the architecture that don’t supports automation of program code to the deployment server. To overcome this problem, Continuous Integration/Continuous Deployment (CI/CD) pipeline using GitHub Workflow is implemented by involving three main components: local development server, GitHub (repository and actions), and deployment server. The pipeline design includes three types of branches in the GitHub repository: dev, staging, and master. The workflow process starts from local development to the dev branch, then integrated to staging for integration testing, and finally to master which triggers automatic deployment actions to the server using the FTP protocol. From the results of the system testing, the metrics used are downtime and deployment time. The results show that the implementation of the pipeline successfully achieved zero downtime (0 seconds) both in the initial deployment and the deployment of changes. However, the deployment time is still relatively long due to the use of the FTP protocol. Although the application does not experience downtime, the long deployment time has the potential to make the application not optimally usable during the deployment process.
Implementasi Logistic Regression dan SMOTE dalam Analisis Sentimen Ulasan Wondr by BNI Komang Krisna Jaya Nova Antara; Ngurah Agus Sanjaya ER
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v04.i01.p22

Abstract

Rapid innovation in Indonesia’s digital banking, evidences by digital transactions reaching Rp7,492.93 trillion by September 2024 and the launch of Wondr by BNI by PT. Bank Negara Indonesia, which has 5.3 million active users and 397 thousand reviews on Google Play Store by June 2025, presents a challenge for manual sentiment analysis of reviews due to its inefficiency. This study addresses this issue by employing a machine learning approach, utilizing the Logistic Regression algorithm for sentiment analysis. A total of 8000 review data from Kaggle were used, with sentiment labeled based on rating scores (1-3 negative, 4-5 positive). The methodology included data preprocessing, feature weighting using Term Frequency-Inverse Document Frequency (TF-IDF), and balancing training data with Synthetic Minority Oversampling (SMOTE). The Logistic Regression model was trained after parameter optimization via grid search, yielding the optimal combination of C=1, penalty=’l2’, and solver=’newton-cg’. Evaluation using a confusion matrix revealed an overall accuracy of 93.54%. For negative sentiment, the model achieved 71.89% precision, 91.5% recall, and 80.52% F1-score, while for positive sentiment, it reached 98.48% precision, 93.89% recall, and 96.13% F1-score.

Page 4 of 5 | Total Record : 49

 1   2   3   4   5 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 4 No. 1 (2025): JNATIA Vol. 4, No. 1, November 2025 Vol. 3 No. 4 (2025): JNATIA Vol. 3, No. 4, Agustus 2025