Article Per Year (5 Year)
p-Index From 2021 - 2026
2.994
P-Index
This Author published in this journals
All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Pendidikan Teknologi dan Kejuruan APTEKINDO Jurnal Sains dan Teknologi Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Edukasi dan Penelitian Informatika (JEPIN) Jurnal Informatika dan Teknik Elektro Terapan JUTIK : Jurnal Teknologi Informasi dan Komputer Journal of Educational Research and Evaluation Jurnal Teknologi Informasi dan Pendidikan INSERT: Information System and Emerging Technology Journal Jurnal Edukasi Citra Olahraga Jurnal Informatika Polinema (JIP) ALSYSTECH Journal of Education Technology Jurnal Edukasi Citra Olahraga
Ni Wayan Marti
Universitas Pendidikan Ganesha
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Public Health Social Sciences Other

Published : 36 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 36 Documents
Search

 1   2   3   4 
UNDIKSHA VIRTUAL ASSISTANT (SHAVIRA): INTEGRATION FREQUENCY ASKED QUESTION WITH RASA FRAMEWORK Resika Arthana, I Ketut; Dewi, Luh Joni Erawati; Seputra, Ketut Agus; Marti, Ni Wayan
JST (Jurnal Sains dan Teknologi) Vol. 10 No. 2 (2021)
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1084.369 KB) | DOI: 10.23887/jstundiksha.v10i2.39863

Abstract

Nowadays, the implementation of chatbots in information systems is getting popular to increase user experience. In our previous research, we developed Undiksha Virtual Assistant (Shavira). Shavira is a knowledge management system (KMS) as Frequency Asked Question (FAQ) system to facilitate users to get an answer about their questions. The challenge on the existing Shavira system is that the users must open a website and type queries to get a list of answers. The text query must match with the keyword in systems. To address this problem and to avoid cognitive load, in this research we implemented a chatbot in Shavira. The purpose of the chatbot implementation in Shavira is to make information easier to be accessed and to increase user experience. The users can ask a question in natural language and get an answer immediately on their chat application such as: Telegram, Facebook, or Messenger. We used Rasa Framework as a chatbot engine in Shavira. Rasa Framework is an open-source virtual assistant engine based on artificial intelligence. The challenge in conducting this research is in integrating the existing FAQ system with Rasa Framework. This research consists of four phases, they are: adaptation data structure in the existing FAQ with data structure requested by Rasa framework, data integration and mapper, and evaluation. The result of this research is a new Shavira that is integrated with a chatbot and can be accessed from chat applications such as Telegram.  We evaluated the accuracy of Shavira powered by Rasa Framework with ten topics about academic information. The results showed that the accuracy of Shavira is 90%. We also evaluated the usability of Shavira with Software Usability Scale (SUS) Questionnaire. The usability evaluation showed that Shavira satisfied users with value  81 (threshold 68) and categorized Excellent, Acceptable and Prometer.
Model Classifer Judul Berita Pariwisata Indonesia Berdasarkan Sentimen Dewi, Ni Luh Putu Risma; Wijaya, I Nyoman Saputra Wahyu; Purnamawan, I Ketut; Marti, Ni Wayan
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 1: Februari 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20241117617

Abstract

Kemajuan teknologi dan platform digital telah menyebabkan perubahan penting dalam industri pariwisata, termasuk penyebaran berita pariwisata. Artikel-artikel berita yang kerap dipublikasikan melalui portal media online dapat berdampak besar pada persepsi positif maupun negatif bagi pembaca. Oleh sebab itu, penelitian ini bertujuan untuk mengembangkan sebuah classifier yang mampu melakukan klasifikasi terhadap judul berita pariwisata berdasarkan sentimen. Sebelumnya, penelitian serupa biasanya lebih berfokus pada klasifikasi berita pariwisata Indonesia dengan menggunakan data dari platform Twitter. Namun, dalam penelitian ini, penulis melakukan pendekatan yang berbeda dengan menggunakan data dari portal berita online, dengan hanya mengambil judul berita sebagai sumber datanya. Penelitian berfokus pada analisis dan klasifikasi sentimen atau sikap emosional yang terkandung dalam judul-judul berita pariwisata. Dalam penelitian ini, digunakan metode machine learning Support Vector Machine (SVM). Data dikumpulkan dari situs berita Detik.com dan diberi label secara manual sesuai dengan sentimen yang terkandung dalamnya. Proses preprocessing teks digunakan untuk mempersiapkan data judul berita pariwisata Indonesia sehingga fiturnya dapat diekstraksi dengan pendekatan Binary Term Presence. Data penelitian dibagi menjadi dua bagian, yaitu 90% untuk proses pelatihan (training proses) dan 10% untuk pengujian, menerapkan teknik K-Fold Cross Validation untuk membagi data dalam proses pelatihan. Hasil penelitian menunjukkan bahwa pendekatan Binary Term Presence berhasil mencapai akurasi sebesar 87,80% dengan kernel RBF. Penelitian ini memberikan kontribusi penting dalam memahami respon publik terhadap topik atau isu pariwisata yang dipublikasikan oleh media. Metode dan pendekatan yang dikembangkan diharapkan dapat menjadi panduan dalam menganalisis sentimen terkini terkait industri pariwisata dan berita yang terkait dengannya.
THE IMPACT OF USING INTERACTIVE MULTIMEDIA IN TEACHING BASIC BADMINTON TECHNIQUES TO IMPROVE COGNITIVE LEARNING OUTCOMES AND SELF-REGULATED LEARNING OF PHYSICAL EDUCATION STUDENTS Ariani, Luh Putu Tuti; Marti, Ni Wayan
Jurnal Edukasi Citra Olahraga Vol. 4 No. 3 (2024): Jurnal Edukasi Citra Olahraga
Publisher : STKIP Citra Bakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38048/jor.v4i3.5004

Abstract

The learning process demands high-quality human resources that evolve with the times. Technological development is essential for the learning process in the form of media. Interactive multimedia is a tool equipped with controls that can be operated by users as desired. This Interactive Media can facilitate learning, making it a stimulus to improve learning outcomes and self-regulated learning. The purpose of this study is to determine the effect of using interactive multimedia in teaching basic badminton techniques to improve cognitive learning outcomes and self-regulated learning among Physical Education students at FOK Undiksha. This research uses an experimental design with The Posttest-Only Control Group Design. The sample was selected using simple random sampling through a lottery method. The instruments for measuring learning outcomes involved a test of basic badminton skills and a questionnaire for assessing self-regulated learning. Data analysis for hypothesis testing required precondition tests, namely normality and homogeneity/F-tests. After conducting these precondition tests, hypothesis testing was carried out using a difference test. The results showed that the use of interactive media had a high impact on cognitive learning outcomes and self-regulated learning in basic badminton techniques. In conclusion, there is a significant difference in the learning outcomes of basic badminton techniques and self-regulated learning between Physical Education students at FOK Undiksha who were taught using interactive multimedia and those who were taught using conventional methods.
KLASIFIKASI POSE YOGA SURYA NAMASKAR MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR VGG19 DAN RESNET-50 Wedatama, Made Restu; Dewi, Luh Joni Erawati; Marti, Ni Wayan
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 1 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i1.8824

Abstract

Penelitian ini bertujuan untuk membangun dan membandingkan kinerja model klasifikasi pose yoga Surya Namaskar menggunakan metode Deep Learning dengan arsitektur Convolutional Neural Network (CNN) VGG19 dan ResNet-50. Surya Namaskar merupakan rangkaian pose yoga yang populer, namun kesalahan postur tanpa pengawasan instruktur dapat berisiko cedera. Dataset yang digunakan terdiri dari 154 citra asli yang diaugmentasi menjadi 1.540 citra, terbagi dalam 7 kelas pose: Pranamasana, Hasta Utthanasana, Padahastasana, Ashwa Sanchalanasana, Parvatasana, Ashtanga Namaskara, dan Bhujangasana. Proses pelatihan dilakukan menggunakan optimizer Adam dengan variasi learning rate 0.0001, 0.00001, dan 0.00005. Hasil penelitian menunjukkan bahwa arsitektur ResNet-50 secara konsisten mengungguli VGG19. Kinerja terbaik dicapai oleh ResNet-50 pada learning rate 0.00005 dengan akurasi 85%, sedangkan akurasi terbaik VGG19 hanya mencapai 77% pada learning rate 0.0001. Penelitian menyimpulkan bahwa arsitektur ResNet-50 dengan residual connection lebih efektif dalam mengklasifikasikan pose yoga yang kompleks dibandingkan VGG19, meskipun masih terdapat tantangan dalam membedakan pose dengan kemiripan visual tinggi seperti Ashwa Sanchalanasana dan Bhujangasana.
IMPLEMENTASI SISTEM INFORMASI TOKO ONLINE PADA TOKO LOVELACE BALI Riswan Alfin Jaya Arsana; Kadek Yota Ernanda Aryanto; Ni Wayan Marti
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 1 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i1.9110

Abstract

Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem informasi toko online pada Toko LoveLace Bali sebagai solusi digital dalam menghadapi tantangan era modern. Metode yang digunakan adalah model pengembangan perangkat lunak Waterfall yang mencakup tahapan kebutuhan sistem, perancangan, implementasi dan pengujian, integrasi, serta pemeliharaan. Sistem dirancang menggunakan berbagai diagram seperti Use Case Diagram, Activity Diagram, Sequence Diagram, ERD, serta UI Wireframe dan arsitektur sistem. Teknologi yang diadopsi meliputi Laraveluntuk backend, ReactJS dengan InertiaJS untuk frontend, serta MySQL sebagai basis data. Pengujian dilakukan menggunakan metode Blackbox dan System Usability Scale (SUS) dengan melibatkan 23 responden. Hasil pengujian menunjukkan skor SUS sebesar 71,41 yang termasuk dalam kategori “baik”, menandakan bahwa sistem memiliki tingkat kegunaan yang tinggi dan dapat memberikan pengalaman pengguna yang memadai. Sistem ini mendukung operasional toko seperti manajemen produk, proses pemesanan, hingga promosi online. Dengan demikian, sistem informasi toko online ini berhasil memenuhi kebutuhan fungsional dan non-fungsional, serta dapat digunakan sebagai sarana untuk meningkatkan efisiensi dan efektivitas penjualan di Toko LoveLace Bali.
Synthetic Data Quantity in Animal Classification Fieter Brain Pasaribu; Luh Joni Erawati Dewi; I Nyoman Saputra Wahyu Wijaya; Ni Wayan Marti; Ni Putu Novita Puspa Dewi
Jurnal Teknologi Informasi dan Pendidikan Vol. 20 No. 1 (2027): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v20i1.1137

Abstract

The need for large datasets remains a challenge in deep learning-based classification models such as Convolutional Neural Networks. Limited data can lead to overfitting, where the model performs well on training data but poorly on testing data. To address this, numerous studies have been conducted using both traditional augmented data and synthetic data generated by Generative Adversarial Networks (GANs). GANs have proven effective across a wide range of dataset domains. However, no research has focused on the effect of the amount of synthetic data on model classification accuracy, leading to confusion about how much should be used to avoid overfitting. Therefore, this study will review the effectiveness of GANs by examining the effect of synthetic data ranging from small amounts to 20 times the original dataset size. The synthetic image results from GANs were then tested using them as supplementary datasets for MobileNetV2 and EfficientNetB0. The results show that the effectiveness of synthetic data fluctuates significantly. At certain amounts, the use of synthetic data can improve accuracy, such as in MobileNetV2, which increased from 73% to 77%. However, at certain amounts, the use of synthetic data also decreases accuracy from 73% as the baseline to 66%. This fluctuating condition is caused by the synthetic data from GANs not being consistent in representing the original data well. The lack of quality of GAN is caused by the architecture used, which is still too simple to capture data patterns with a wide variety of perspectives
Co-Authors Agus Aan Jiwa Permana Agus Seputra I Ketut Dewi, Ni Luh Putu Risma Dwi Prima Handayani Putri Fieter Brain Pasaribu Gede Rasben Dantes Gunawan, I Gede Made Deny Surya Gusti Michael Ferdinand I Gst Ayu Pradnya Saci Devi Sastrawan I Gusti Putu Suharta I Kadek Suranata I Ketut Purnamawan I Ketut Purnamawan I Ketut Resika Arthana I Komang Sudarma I Nyoman Putra Satya Natha I Nyoman Saputra Wahyu Wijaya I Nyoman Saputra Wahyu Wijaya I Nyoman Yoga Setyawan Juli, I Wayan Kadek Yota Ernanda Aryanto Ketut Agustini Komang Setemen Luh Joni Erawati Dewi Luh Putu Tuti Ariani Marcelino, Antonius Ni Ketut Kertiasih Ni Putu Novita Puspa Dewi Ni Putu Novita Puspa Dewi Pratama Putra, Gede Bakti Putu Hendra Suputra Riswan Alfin Jaya Arsana Satriawan, Putu Raditia Sugiantari, Kadek Feny Surya Mahedy, Kadek Tanok Arta Wijaya, Gede Utami Pramesti Indraswari, Putu Wedatama, Made Restu Wijaya, I Nyoman Saputra Wahyu