Claim Missing Document
Check
Articles

Perancangan Model Ontologi untuk Representasi Pengetahuan Cagar Budaya Masa Kolonial di Indonesia I Gede Widiantara Mega Saputra; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 3 (2025): JNATIA Vol. 3, No. 3, Mei 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.i03.p04

Abstract

This study aims to develop an ontology model that represents knowledge about cultural heritage from the colonial era in Indonesia, an important effort in preserving and educating about cultural heritage. In the process, this ontology model is constructed using Protégé, a free and open-source ontology development platform that supports various formats including OWL (Web Ontology Language). By utilizing the Methontology methodology, this model ensures systematic and structured development. The structure of the ontology model includes one main class with four subclasses, which assists in the logical categorization of information and supports in-depth analysis. Testing the model using SPARQL queries confirms the accuracy and correctness of the data structure. The findings of this study indicate that the developed ontology successfully achieves its set objectives, not only in documenting information effectively but also in enriching methods of presenting and analyzing knowledge about cultural heritage. This opens the way for further research and practical applications in the preservation and education of cultural heritage, underlining the importance of digitalization in historical preservation. 
Klasifikasi Berita Berdasarkan Kategori Menggunakan Multinomial Naïve Bayes dengan K-Cross Validation dan Seleksi Fitur Chi-Squared Febrian Valentino Agape; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 2 (2025): JNATIA Vol. 3, No. 2, Februari 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.i02.p08

Abstract

Classifying news articles based on categories is an important challenge in text analysis and natural language processing. Most categorization of online news articles is often done manually, making it a complex and time-consuming process. To address this issue, the development of an automatic system capable of classifying news articles into various categories such as technology, sports, and entertainment is needed. The system is built using an approach to classify news articles into several appropriate categories using the Naïve Bayes method with TF-IDF weighting and feature selection using Chi-Squared. The Naïve Bayes model training uses the reduced feature results of 10,000 features from 54,091 features. Evaluation results show that the Naïve Bayes approach is able to produce a news classification model with good accuracy, with accuracy, precision, recall, and f1-score values of 96%. 
Rancang Bangun Website Sebagai Sarana Promosi Usaha Madu Kele-Kele di Desa Bongkasa Pertiwi Ni Made Desni Dwi Arisaputri; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 2 (2025): JNATIA Vol. 3, No. 2, Februari 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.i02.p09

Abstract

Kele-Kele Honey from Bongkasa Pertiwi Village is a superior product with large market potential but is still little known by the wider community. This research aims to develop a website as an effective promotional tool to increase awareness and sales of Kele-Kele honey. By implementing a Rapid Application Development (RAD) approach, website development is carried out quickly and iteratively, enabling active involvement of business owners in the development process and feature adjustments based on user feedback. The research results show that the website developed has succeeded in increasing public awareness about Kele-Kele honey and supporting the growth of local businesses. The practical implication of this research suggests that employing Rapid Application Development (RAD) in web development could be an effective strategy to enhance the sales and visibility of local products such as Kele-Kele honey. To further promote the growth of small and medium-sized enterprises, future studies could focus on developing new features and conducting a more comprehensive evaluation of the effectiveness of online promotions. 
Pengujian Prototipe Sistem Jasa Pengembangan Aplikasi Menggunakan Metode System Usability Scale I Kadek Agus Wijaya Kusuma; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 1 (2024): JNATIA Vol. 3, No. 1, November 2024
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.2024.v03.i01.p06

Abstract

The utilization of websites to spread information related to services is commonly used by service providers, including those in application development services. In developing a website, designing an interactive interface becomes an important aspect. This has an impact on the effectiveness and efficiency of the website, as well as the user experience. Therefore, the participation of users in designing the website, considering their needs and issues they face is essential. To ensure the website meets user’s standards and expectations, usability testing is conducted on the website prototype. This research uses the System Usability Scale (SUS) method. The SUS scores from the testing serve as a benchmark to evaluate the effectiveness, efficiency, and optimization of the user experience of the website prototype. To achieve high SUS scores, the website prototype must be capable of providing effective and efficient solutions to user’s issues while also supplying their needs. A website prototype with high scores can be considered to have met user’s standards and expectations, therefore it is ready for implementation. 
Perancangan Sistem Steganografi Berbasis Transformasi Wavelet Diskrit Terintegrasi Algoritma Rijndael dan QR-Code I Putu Rizky Pratama Putra; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 4 (2024): JNATIA Vol. 2, No. 4, Agustus 2024
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.2024.v02.i04.p04

Abstract

The advancement of technology has been the primary driving force behind the transformative shifts across various domains of human life, spanning from the era of industrial revolution to the present digital age. Within the digital epoch, the pivotal role of information and communication technology in shaping the global societal framework is unequivocal. Nonetheless, the rapid progression of technology introduces novel challenges such as safeguarding personal data integrity and combating unauthorized access to individual information. Addressing these challenges entails the adoption of sophisticated techniques, including compression methodologies like Discrete Wavelet Transform (DWT), renowned for its efficacy in multimedia data compression with high rates. Furthermore, cryptographic algorithms such as Rijndael offer viable solutions to enhance data security through a series of encryption operations, encompassing substitution, permutation, and iterative rounds applied to each block. The amalgamation of DWT and Rijndael culminates in data representation via QR codes. Additionally, this research encompasses the development of a user interface design to facilitate the seamless implementation and utilization of the system, ultimately aiming to fortify data security effectively. 
Deteksi Pneumonia dengan Ekstraksi Fitur Gray-Level Co-occurrence Matrix (GLCM) dan Support Vector Machine (SVM) I Gusti Bagus Sutha Arianata Putra; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 3 (2024): JNATIA Vol. 2, No. 3, Mei 2024
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.2024.v02.i03.p08

Abstract

Pneumonia, a prevalent lung disease globally, poses significant challenges in accurate diagnosis despite its severity. This paper proposes a novel approach leveraging Support Vector Machine (SVM) classification and Gray-Level Co-occurrence Matrix (GLCM) analysis on chest X-ray images to aid in pneumonia diagnosis. By extracting pneumonia-indicative features from digital X-ray images using Gray-Level Co-occurrence Matrix (GLCM) and employing Support Vector Machine (SVM) for classification, the study aims to enhance pneumonia diagnosis effectiveness, particularly crucial in regions with limited healthcare resources. The proposed method focuses on identifying characteristic patterns indicative of pneumonia in chest X-ray images and distinguishing between normal and pneumonia-affected images based on GLCM-extracted features. Furthermore, the study evaluates the impact of hyperparameter tuning using grid search on the proposed diagnostic system's performance, including accuracy, sensitivity, and specificity. By achieving these objectives, the research aims to contribute significantly to the development of more accurate and effective diagnostic tools for pneumonia, especially in resource-constrained areas. 
Klasifikasi Kualitas Buah dengan Menggunakan Convolutional Neural Network (CNN) Studi Kasus Dataset Fresh and Rotten Classification I Gede Diva Dwijayana; I Putu Fajar Tapa Mahendra; Ivan Luis Simarmata; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 2 No. 2 (2024): JNATIA Vol. 2, No. 2, Februari 2024
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.2024.v02.i02.p24

Abstract

This research aims to develop a deep learning model for fruit quality classification using Convolutional Neural Network (CNN) with the Fresh and Rotten Classification dataset. Two CNN models are compared, with the first model serving as the baseline and the second model resulting from parameter tuning based on the first model. The results indicate that increasing the number of epochs improves the model accuracy, as evidenced by the first model achieving 91% accuracy with 10 epochs and 93% accuracy with 15 epochs. Similar patterns are observed in the second model, with 87% accuracy at 10 epochs and 90% accuracy at 15 epochs. Despite the second model involving the addition of layers and parameters, its accuracy tends to be lower compared to the first model. The research emphasizes that increasing the number of epochs enhances model performance, while adding layers does not always lead to significant improvements, depending on the model's complexity and dataset characteristics. The first model, trained with 15 epochs, demonstrates the highest accuracy, approaching results from similar previous studies. This evaluation provides valuable insights for developing a CNN-based fruit classification model on the Fresh and Rotten Classification dataset. 
Klasifikasi Lagu Daerah di Indonesia dengan Metode Machine Learning Gst. Ayu Vida Mastrika Giri; Made Leo Radhitya
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 1 No. 3 (2023): JNATIA Vol. 1, No. 3, Mei 2023
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.2023.v01.i03.p29

Abstract

Keunikan dari lagu daerah yang mencerminkan daerah asal adalah diiringi dengan alat musik daerah dan dinyanyikan dengan bahasa daerah masing-masing. Ciri khas lagu daerah dapat dilihat dari fitur-fitur musik seperti spectral centroid dan Mel Frequency Cepstral Coefficients (MFCC) karena dimainkan dengan alat musik berbeda dan memiliki timbre yang berbeda pula. Dengan menggunakan fitur-fitur musik tersebut dan algoritma machine learning, lagu-lagu daerah dapat diklasifikasi berdasarkan daerah asalnya. Pada penelitian ini digunakan sebuah dataset lagu daerah Indonesia yang bernama IRSD: Indonesian Regional Song Dataset yang terdiri dari 67 fitur musik yang diantaranya adalah MFCC, energy, dan spectral centroid dari 500 lagu daerah dari 10 provinsi di Indonesia. Metode machine learning yang akan digunakan untuk klasifikasi adalah SVM dan K-NN untuk menghasilkan nilai klasifikasi yang baik dengan waktu eksekusi yang cepat. Dengan menggunakan nilai K=3 dan 5-fold cross validation, metode K-NN menghasilkan nilai akurasi 0,69. Klasifikasi dengan metode SVM menggunakan kernel RBF dan 5-fold cross validation menghasilkan nilai akurasi 0,73. Pada penelitian kali ini, metode SVM dapat mengklasifikasi lagu daerah lebih baik daripada metode K-NN. 
Implementasi Algoritma KNN Untuk Memprediksi Performa Siswa Sekolah I Made Ryan Prana Dhita; Gst. Ayu Vida Mastrika Giri
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 1 No. 3 (2023): JNATIA Vol. 1, No. 3, Mei 2023
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.2023.v01.i03.p06

Abstract

One of the factors that influences students graduation rates is their performance in learning. Predicting graduation rates based on student performance has the benefit of analyzing academically underperforming students and providing support to students who face difficulties in the learning process. There are several factors to consider in predicting students' graduation rates, such as academic grades, attitudes, and social factors. However, these factors alone are not sufficient to effectively predict students' performance, and educators also struggle to identify which factors affect students' performance.To predict the performance of school students, the KNearest Neighbor (KNN) method is utilized. The K-Nearest Neighbor method is often used in classifying students' performance due to its simplicity and ability to produce significant and competitive results. In this research, the prediction of students' graduation rates is carried out using the KNN method.The results of implementing the prediction of students' performance using the KNN method can serve as a reference for students to improve their achievements and assist educators in considering future teaching materials. 
Co-Authors Adi Guna, I Made Dirga Agus Harjoko Agus Muliantara Al Habib Muhammad Anak Agung Istri Ngurah Eka Karyawati Andika Putra, Ida Bagus Angriani, Husni Arianata Putra, I Gusti Bagus Sutha Dhita, I Made Ryan Prana Edo Krishnanda Aditya Febrian Valentino Agape Gede Agung Aji Andar Sakti Giri, I Nyoman Yusha Tresnatama Gusto Gibeon Ginting I Gede Arta Wibawa I Gede Arta Wibawa I Gede Diva Dwijayana I Gede Diva Dwijayana I Gede Laksmana Yudha I Gede Liyang Anugrah Oktapian I Gede Made Widi Anditya I Gede Santi Astawa I Gede Widiantara Mega Saputra I Gusti Bagus Sutha Arianata Putra I Gusti Ngurah Anom Cahyadi Putra I Kadek Agus Wijaya Kusuma I Ketut Gede Suhartana I Ketut Gede Suhartana I Komang Ari Mogi I Komang Ari Mogi I Made Rovan Puja Wardana I Made Ryan Prana Dhita I Made Widiartha I Made Yoga Mahendra I Nyoman Budhiarta Suputra I Putu Ananta Wijaya I Putu Fajar Tapa Mahendra I Putu Rizky Pratama Putra I WAYAN SANTIYASA I Wayan Supriana Ivan Luis Simarmata izmy alwiah musdar Jaya, I Nyoman Wiratma Kadek Nanda Banyu Permana Komang Arsa Wiguna Leo Radhitya, Made Luh Arida Ayu Rahning Putri Luh Gede Tresna Dewi Luh Ristiario Mega Saputra, I Gede Widiantara Muhammad Arief Budiman Ngurah Agus Sanjaya ER Ni Ketut Intan Setiawati Ni Made Desni Dwi Arisaputri Ni Made Elvina Aryadhika Putri Ni Putu Novia Ardiyanti Ni Putu Suci Paramita Nyoman Hendradinata Dharma Pasha Renaisan Prasetya, Putu Rikky Mahendra Pratama Putra, I Putu Rizky Putu Audy Cipta Pratiwi Putu Krisna Udayana Radhitya, Made Leo Raharja, Made Agung Siaka, Made Bayu Maha Krisna Sutanti, Putu Asri Sri Taruk, Medi Wiratama Putra, I Putu Andi Yoga, I Putu Harta