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 Perbandingan XGBoost dan LightGBM dalam Prediksi Penjualan Ritel Walmart Store Sales I Gusti Ayu Riyani Astarani; I Gede Surya Rahayuda
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.p01

Abstract

Sales prediction is a crucial aspect in the retail industry for optimizing business strategies and inventory management. As a global retail company with a large-scale operation, Walmart faces significant challenges in efficiently managing its supply chain and inventory. This study conducts a comparative analysis between the Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) algorithms in the context of retail sales prediction using the Walmart Store Sales dataset. The dataset consists of 6,436 records with 8 attributes. The research methodology implements a comprehensive machine learning approach, including data preprocessing, feature selection, dataset splitting (80:20), model training, and evaluation using standard metrics. The analysis results show that LightGBM provides superior prediction performance, with an MSE of 0.0341, MAE of 0.1120, RMSE of 0.1847, and R² of 0.9663. In comparison, XGBoost yields an MSE of 0.0408, MAE of 0.1194, RMSE of 0.2021, and R² of 0.9596. The consistent superiority of LightGBM across all evaluation metrics indicates that this algorithm is more optimal for the Walmart sales prediction case. Additionally, feature analysis shows that the variable Store contributes the most to the predictive model, while Fuel Price has a relatively minor impact. This study emphasizes that selecting the appropriate machine learning algorithm significantly affects optimal prediction outcomes, particularly in a complex, data-driven retail industry.
Analisis UX pada Aplikasi Pemutar Video Animasi dengan Metode Usability Testing I Gusti Ngurah Esa Nandana; I Gede Arta Wibawa
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.p02

Abstract

A popular animation streaming platform requires a structured User Experience (UX) evaluation to ensure its ease of use. This study aims to analyze the usability level of an animation video player application using a mixed-method Usability Testing approach. The test was conducted on 5 active users, where performance data (success rate, time efficiency, error rate) and perceptual data (satisfaction level) were collected through task-based observation sessions and a post-test questionnaire. The results indicate a perfect task success rate (100%) and a high user satisfaction level (88%), but also reveal a significant error rate of 60%. The primary source of errors was identified as the ambiguity of iconography without text labels on certain features. In conclusion, the application is proven to be functional and satisfying, but it is recommended to improve the clarity of the interface design to minimize user errors and enhance the overall UX.
Klasifikasi Kematangan Tomat pada Citra Digital Menggunakan DeiT (Data-efficient Image Transformer) I Gede Made Widi Anditya; Gst. Ayu Vida Mastrika Giri
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.p03

Abstract

This study addresses the critical need for accurate and efficient tomato ripeness classification in agriculture and agribusiness, aiming to overcome the limitations of subjective manual methods. Leveraging advances in Computer Vision, this study implements a Data-efficient Image Transformer (DeiT) model for automatic classification of digital tomato images. DeiT, a Transformer-based architecture developed by Facebook AI Research, was chosen for its superior performance on small to medium-sized datasets, leveraging knowledge distillation. The model was trained using the Kaggle dataset, instrumented to enhance visual diversity, to classify tomatoes into “ripe” and “unripe” categories. Evaluation was performed using standard classification metrics including accuracy, F1-Score, and confusion matrix. The model demonstrated high performance, achieving an overall accuracy of 0.96 on the test dataset.
Analisis UX pada Aplikasi Komik Digital Menggunakan Metode Usability Testing Nanda Asmara Ramdhan Putra; I Gede Arta Wibawa
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.p02

Abstract

The shift to digital media has intensified competition among comic applications, making User Experience (UX) a critical determinant of success. This study evaluates a digital comic app's UX via Usability Testing with five users , measuring effectiveness, errors, learnability, and satisfaction.Results indicate a 100% task completion rate , yet a high error rate of 60% reveals significant usability issues. The "Change Notification" and "Download Offline" features were the primary sources of errors , scoring lowest in learnability. Interestingly, high user satisfaction contrasts with the high error rate , suggesting users encountered non-critical errors that hindered efficiency but did not spoil the overall experience. In conclusion, while functionally effective , the application requires a targeted redesign of its notification and download features to improve usability.
Evaluasi Usability Protoype Aplikasi Jemput Sampah Online Menggunakan Metode System Usability Scale Anak Agung Bagus Yoga Udiana; I Ketut Gede Suhartana; I Putu Satwika
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.p04

Abstract

In Indonesia, waste management is a big problem for the environment since not enough people are involved and there aren't any integrated systems. To solve this problem, a prototype mobile app called JEMPOL (Jemput Sampah Online Langsung) was made. It offers an online waste collecting service and instructional functions. The goal of this study was to evaluate the application of JEMPOL prototype. This stufy used the Design Thinking process to make sure that the application was user-centered.  The System Usability Scale (SUS) approach was used to evaluate the application with 20 people who are the intended users. The average SUS score was 70.38, which puts it in the "Acceptable" range on the Acceptability Range of SUS, gives it a "C" grade, and is rated "OK" to "Good" on the Adjective Rating scale. These results show that users generally like and can use the JEMPOL prototype, although the score differences suggest that some parts of the interface may be better. The application has a lot of promise for being used more to get more people involved in digital waste management.
Implementasi Algoritma Random Forest Regression dalam Sistem Prediksi Harga Rumah di Jabodetabek I Made Gede Aryadana Baraja Putra; I Ketut Gede Suhartana
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.p04

Abstract

Indonesia's rapid urbanization, particularly in the Jabodetabek region, has created a severe housing shortage with a backlog of 2.93 million units representing 30% of the national deficit. This imbalance between supply and demand necessitates accurate house price prediction systems to guide market participants. This research implements Random Forest Regression algorithm to predict house prices in the Jabodetabek region using comprehensive datasets covering land area, building area, geographical location, room quantities, facilities, and property characteristics across districts and cities. The methodology involves data preprocessing, model training using Random Forest Regression, and performance evaluation using established metrics. Results demonstrate great algorithm performance with RMSE of 0.3545, MAE of 0.2014, MAPE of 1.0184, and R² of 0.8751 confirming the model explains 87.51% of house price variance. The implementation successfully addresses the research objective of providing developers with a reliable algorithmic framework for property pricing strategies.
Evaluasi UX E‑Perpus UNUD Menggunakan UEQ (User Experience Questionnaire) Komang Andika Putra; I Wayan Santiyasa
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.p05

Abstract

The e-Perpus UNUD system serves as a digital library platform for managing academic documents at Udayana University. Previous studies using WebQual 3.0 and 4.0 methods reported suboptimal results, particularly in interface and user interaction quality. To provide a deeper and more emotional perspective on user experience, this study adopts the User Experience Questionnaire (UEQ) to evaluate the system across six UX dimensions: Attractiveness, Perspicuity, Efficiency, Dependability, Stimulation, and Novelty. Data were collected from 24 student respondents using the official UEQ format, and results were analyzed using the UEQ Data Analysis Tool. The findings show that Perspicuity and Dependability indicated slightly positive perceptions, while the remaining dimensions, especially Novelty, indicated negative perceptions. This study suggests a user interface redesign focusing on improving innovation, visual appeal, efficiency, and user stimulation, with future research encouraged to increase the sample size for more stable results.
Penerapan Support Vector Machine untuk Klasifikasi Tingkat Risiko Kebakaran Hutan I Komang Galih Agustan; I Gede Santi Astawa
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.p06

Abstract

Classifying forest fire risk levels is a critical step for disaster mitigation, yet it poses significant challenges due to data complexity and class imbalance. This study systematically applies and evaluates the performance of the Support Vector Machine (SVM) algorithm for the multi-class classification of fire risk (‘Low’,’Medium’,’High’) using the standard UCI Forest Fires dataset. The methodology involved a comprehensive preprocessing imbalance and hyperparameter optimization of C and gamma using GridSearchCV with cross-validation. Experimental results show that the final,optimized SVM model only achieved an accuracy of 50% and a macro-average F1-Score of 40% on the test set. This limited performance, particularly the model’s failure to reliably identify the ‘High’ risk class, indicates that the standard meteorological features within the dataset possess insufficient predictive power for the complex task of classifying fire severity, highlighting that model success is fundamentally dependent on feature richness over algorithmic optimization.
Desain Aplikasi MindSpare sebagai Media Literasi dan Dukungan Kesehatan Mental dengan Metode Design Thinking Asa Prameswari Karso; I Gede Surya Rahayuda
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.p11

Abstract

Mental health is a global issue that needs attention, especially for adolescents aged 16-24 years. Previous research shows that the mental health of adolescents of this age affects how their well-being is. Then, based on preliminary research that has been conducted on adolescents of that age, 83% of respondents have never used a mental health application with one of the reasons is that they feel they don't need the application. Therefore, in this study, a mental health application design was made as a medium of support for someone experiencing mental health problems and as a literacy medium for someone who is mentally healthy to be more aware of the surrounding environment. This research process is carried out using the Design Thinking method so that the application built can meet user needs. The design that has been made is tested using the UEQ scale and most aspects shows Excellent rating, with the highest score in the Attractiveness aspect, with an average value of 2.29.
Analisis Sentimen Fenomena FoMO Gaya Hidup Sehat Menggunakan Metode Naïve Bayes Classifier Putu Mahdalika Intan Pratiwi; Anak Agung Istri Ngurah Eka Karyawati
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.p07

Abstract

The development of social media has given rise to the Fear of Missing Out (FoMO) phenomenon which can affect healthy lifestyles among the community, especially the younger generation. This study aims to conduct a sentiment analysis of the FoMO phenomenon related to a healthy lifestyle using the Naïve Bayes Classifier method. Data were collected from Twitter social media using a crawling technique with certain keywords in the period from January 2024 to June 2025. The data was then processed through the preprocessing stage, sentiment labeling, data balancing using SMOTE, and feature weighting using TF-IDF. The model was trained using 2,364 training data and tested on 591 data. The evaluation results showed that the model achieved an accuracy of 84.09%, precision 85.66%, recall 84.09%, and F1-score 83.57%. Validation using 5-Fold Cross Validation also showed stable model performance with an average accuracy of 84.50%. This study proves that Naïve Bayes is effective in analyzing social media sentiment towards the FoMO phenomenon, with potential for development through dataset expansion and exploration of other algorithms

Page 1 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