Article Per Year (5 Year)
p-Index From 2021 - 2026
5.659
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) International Journal of Advances in Applied Sciences Jurnal Pendidikan Teknologi dan Kejuruan KARMAPATI (Kumpulan Artikel Mahasiswa Pendidikan Teknik Informatika) ISSN: 2252-9063 Techno.Com: Jurnal Teknologi Informasi Pixel : Jurnal Ilmiah Komputer Grafis Jurnal Sarjana Teknik Informatika Jurnal Informatika dan Teknik Elektro Terapan Jurnal Eksplora Informatika SINTECH (Science and Information Technology) Journal International Journal of New Media Technology MULTINETICS Jurnal Pendidikan Sains dan Komputer Jurnal WIDYA LAKSMI (Jurnal Pengabdian Kepada Masyarakat) Journal of Artificial Intelligence and Digital Business Galuh International Journal of Community Service and Development
Ida Bagus Nyoman Pascima
Universitas Pendidikan Ganesha
Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Immunology & microbiology Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Physics Social Sciences Other

Published : 42 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 42 Documents
Search

 1   2   3   4   5 
Development of Automated Essay Scoring Using Retrieval Augmented Generation in SAGE I Gusti Nyoman Sapta Wiguna; Ida Bagus Nyoman Pascima; Luh Putu Eka Damayanthi
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 2 (2026): Mei-Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i2.8979

Abstract

Academic assessment through essay questions is a fundamental component of the educational ecosystem designed to measure students’ cognitive depth and critical reasoning. However, manual essay grading presents significant pedagogical and administrative challenges including high susceptibility to subjective bias and an overwhelming workload for educators. To address these critical issues this research develops the Smart Automated Grading Engine or SAGE, an advanced Learning Management System engineered to automate qualitative assessments. SAGE integrates large language models via the Gemini API with a robust Retrieval Augmented Generation architecture. By strictly grounding the artificial intelligence evaluation process in teacher curated reference documents and specific grading rubrics the system effectively neutralizes the risk of information hallucination. The system was empirically validated at SMAN 1 Blahbatuh involving 180 authentic essay responses from 36 eleventh grade students. The automated assessments were statistically compared against the manual evaluations of three expert history teachers. Comprehensive technical evaluations utilizing Black Box and White Box testing confirmed the platform absolute functional stability and architectural security. Crucially the accuracy testing demonstrated exceptional pedagogical reliability where the SAGE platform achieved a Quadratic Weighted Kappa coefficient of 0.9133 categorizing its performance as having almost perfect agreement. Furthermore, the system exhibited a remarkable precision rate of 94.44 percent within a stringent 10 point score tolerance. Ultimately the integration of this technology proves to be an effective objective and efficient solution capable of replicating human evaluation sharpness while significantly alleviating educator burnout.
Implementasi Algoritma Levenshtein Distance pada Sistem Evaluasi Keterbacaan Berbasis Speech-to-Text dalam Aplikasi Literasi Multisensori untuk Anak Disleksia I Made Aris Danuarta; I Nyoman Indhi Wiradika; Ida Bagus Nyoman Pascima
KARMAPATI (Kumpulan Artikel Mahasiswa Pendidikan Teknik Informatika) Vol. 15 No. 2 (2026): Karmapati Vol 15 No 2 Tahun 2026
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/karmapati.v15i2.113741

Abstract

Disleksia merupakan gangguan belajar spesifik yang menghambat kemampuan anak dalam mengenali kata secara akurat dan lancar. Salah satu kendala utama dalam intervensi literasi di Indonesia adalah keterbatasan alat bantu mandiri yang mampu memberikan umpan balik pengucapan secara real-time. Penelitian ini bertujuan untuk mengimplementasikan algoritma Levenshtein Distance pada modul Speech-to-Text (STT) sebagai sistem evaluasi keterbacaan otomatis dalam aplikasi multisensori "DyLearn". Metode pengembangan yang digunakan adalah ADDIE (Analysis, Design, Development, Implementation, Evaluation). Algoritma Levenshtein Distance diterapkan untuk menghitung jarak perbedaan antara string teks target dengan hasil transkripsi suara yang ditangkap melalui Google ML Kit STT. Sistem melakukan normalisasi teks sebelum menghitung bobot insertion, deletion, dan substitution untuk menghasilkan nilai persentase akurasi pembacaan. Pengujian sistem dilakukan melalui uji ahli isi (2 ahli, 2 tahap), uji ahli media (2 ahli, 2 tahap), uji black box (25 skenario), uji white box (16 skenario logika), dan analisis data sesi latihan STT berbasis Levenshtein Distance terhadap 90 sesi latihan membaca. Hasil menunjukkan seluruh skenario fungsional berhasil dieksekusi sesuai kriteria, dan algoritma mampu mengklasifikasikan kata dengan rata-rata akurasi 90,09% pada kondisi variasi input suara pengguna. Implementasi ini memungkinkan adanya sistem monitoring berbasis data bagi guru dan orang tua melalui web admin panel untuk memantau kemajuan literasi anak secara objektif.
Pengembangan Film Animasi 3 Dimensi Sebagai Edukasi Penangkaran Penyu dan Terumbu Karang Made Sevta Reyma Priyandika; I Gede Partha Sindu; Ida Bagus Nyoman Pascima
KARMAPATI (Kumpulan Artikel Mahasiswa Pendidikan Teknik Informatika) Vol. 15 No. 2 (2026): Karmapati Vol 15 No 2 Tahun 2026
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/karmapati.v15i2.114007

Abstract

Penelitian ini bertujuan untuk mengembangkan film animasi tiga dimensi sebagai media edukasi mengenai penangkaran penyu dan pelestarian terumbu karang. Latar belakang penelitian ini didasari oleh masih rendahnya pemahaman dan kesadaran masyarakat terhadap pentingnya konservasi ekosistem laut, khususnya penyu dan terumbu karang, akibat keterbatasan media edukasi yang menarik dan interaktif. Metode penelitian yang digunakan adalah Research and Development (R&D) dengan model pengembangan Multimedia Development Life Cycle (MDLC) yang meliputi enam tahapan, yaitu Concept, Design, Material Collecting, Assembly, Testing, dan Distribution. Produk yang dihasilkan berupa film animasi tiga dimensi yang menyajikan informasi proses penangkaran penyu, pelestarian terumbu karang, serta dampak aktivitas manusia terhadap ekosistem laut. Pengujian dilakukan melalui uji ahli isi, uji ahli media, dan uji respons pengguna. Hasil pengujian menunjukkan bahwa film animasi yang dikembangkan berada pada kualifikasi sangat valid dan memperoleh respons positif dari pengguna. Dengan demikian, film animasi tiga dimensi ini dinyatakan layak digunakan sebagai media edukasi untuk meningkatkan pemahaman dan kesadaran masyarakat terhadap pentingnya konservasi penyu dan terumbu karang.
Pengembangan Aplikasi Mobile Berbasis Android untuk Pembelajaran Basita Paribasa Bali Melalui Permainan Kuis Dua Pemain (QuizDuel) I Kadek Diwa Anjapuryana; Dewa Gede Hendra Divayana; Ida Bagus Nyoman Pascima
KARMAPATI (Kumpulan Artikel Mahasiswa Pendidikan Teknik Informatika) Vol. 15 No. 2 (2026): Karmapati Vol 15 No 2 Tahun 2026
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/karmapati.v15i2.114400

Abstract

Penelitian ini difokuskan pada pengembangan QuizDuel, sebuah aplikasi mobile berbasis Android yang dirancang untuk mengatasi rendahnya minat dan keterlibatan peserta didik pada mata pelajaran muatan lokal Bahasa Bali, khususnya materi Basita Paribasa Bali. Fenomena ini diidentifikasi sebagai dampak dari dominasi metode konvensional yang cenderung statis. Guna menciptakan pengalaman belajar yang dinamis, QuizDuel mengintegrasikan konsep game edukasi melalui mekanisme kuis kompetitif dua pemain secara real-time. Penelitian Research and Development (R&D) ini mengadopsi model Agile, dengan mengintegrasikan ekosistem teknologi modern meliputi framework Flutter untuk antarmuka, Laravel sebagai backend, serta Supabase untuk sinkronisasi data instan. Kualitas sistem divalidasi melalui pengujian BlackBox dan WhiteBox, serta terbukti memperoleh koefisien validitas sempurna (1,00) berpredikat “Sangat Valid” dari ahli isi dan media. Evaluasi pengalaman pengguna menggunakan instrumen User Experience Questionnaire (UEQ) terhadap 30 siswa mencetak hasil yang didominasi predikat Excellent (daya tarik 2,21; kejelasan 2,06; efisiensi 2,22; stimulasi 2,14; kebaruan 1,93) dan Good pada aspek ketepatan (1,68). Didukung oleh respons guru yang mencapai skor 49,0 (Sangat Praktis), QuizDuel dinyatakan sangat layak dan efektif diimplementasikan sebagai inovasi media interaktif yang mampu mendongkrak partisipasi aktif siswa dalam melestarikan budaya lokal melalui teknologi digital.
Preserving Balinese Folklore: The Development of 'The Origins of Buleleng and Singaraja' via Augmented Reality I Ketut Yudi Premana Giri; I Gede Mahendra Darmawiguna; Ida Bagus Nyoman Pascima
IJNMT (International Journal of New Media Technology) Vol 13 No 1 (2026): Vol 13 No 1 (2026): IJNMT (International Journal of New Media Technology)
Publisher : Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ijnmt.v13i1.3771

Abstract

This study presents the development and validation of an Augmented Reality (AR) application centered on the Balinese folklore "The Origins of Buleleng and Singaraja." Utilizing the Multimedia Development Life Cycle (MDLC) model, which includes six stages”concept, design, material collection, assembly, testing, and distribution”the research aims to enhance public engagement, awareness, and understanding of Balinese cultural heritage. The application underwent rigorous testing, including expert content validation, media expert assessment, and user response evaluation. The content and media tests, analyzed using Gregory's formula, yielded a perfect validity score of 1.00, indicating a "very high" level of accuracy and effectiveness in both historical narrative presentation and AR content delivery. User feedback, collected from 35 respondents, showed a 97.30% response rate in the "very positive" and "very good" categories, with the remaining 2.70% in the "good" category. These results demonstrate strong user approval and the potential of AR technology to preserve and promote Balinese folklore.
Performance Comparison of SARIMA and Prophet Models for Forecasting Indonesian Banking Stock Prices Syarifudin Abdullah; Ida Bagus Nyoman Pascima; I Nyoman Tri Anindia Putra
Pixel :Jurnal Ilmiah Komputer Grafis Vol. 19 No. 1 (2026): Pixel :Jurnal Ilmiah Komputer Grafis dan Ilmu Komputer
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/pixel.v19i1.3959

Abstract

This study compared the performance of SARIMA and Prophet models in forecasting daily close prices of three major Indonesian banking stocks: BBCA, BBRI, and BMRI, using data from January 2020 to March 2026. Data were retrieved via the yfinance library, preprocessed, and split into 80% training and 20% testing sets. SARIMA modeling followed the Box-Jenkins procedure, while Prophet was configured with a Lag-1 regressor, weekly and monthly seasonality, Indonesian public holidays, and log transformation. Model performance was evaluated using MAPE, MSE, and Dstat metrics. Results showed that SARIMA outperformed Prophet in MAPE and MSE across all six stock-variable combinations, with MAPE values ranging from 1.3368% to 1.9386% for SARIMA and 1.5992% to 2.2300% for Prophet. However, Prophet demonstrated marginally higher Dstat values in several series. Both models achieved "Very Good" forecasting accuracy. A web-based forecasting system was also developed using Streamlit to make the models accessible to investors.
Performance comparison of feature extraction methods for electroencephalogram-based recognition of Balinese script I Made Agus Wirawan; Ida Bagus Nyoman Pascima; Gede Surya Mahendra; I Made Candiasa; I Nyoman Sukajaya
International Journal of Advances in Applied Sciences Vol 15, No 1: March 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijaas.v15.i1.pp55-64

Abstract

Recognizing Balinese script from electroencephalogram (EEG) signals remains a challenging problem due to low signal amplitude, non-stationary dynamics, and significant inter-subject variability. Despite previous attempts, no single feature extraction method has been universally effective in addressing these limitations. To fill this gap, this study systematically evaluates five feature extraction techniques—differential entropy (DE), power spectral density (PSD), discrete wavelet transforms (DWT), Hjorth parameters, and statistical features—on the Balinese imagined spelling using electroencephalography (BISE) dataset, which contains EEG recordings specifically designed for Balinese script recognition. For classification, both artificial neural networks (ANN) and support vector machines (SVM) are applied, and their performance is validated across multiple experimental settings. Results demonstrate that DE consistently provides more stable and discriminative features than the other methods, achieving the highest classification accuracy when combined with ANN. These findings highlight the potential of DE-based approaches to advance electroencephalogram driven Balinese script recognition, offering a culturally significant contribution to brain-computer interface (BCI) research and supporting future applications in inclusive artificial intelligence, digital heritage preservation, and assistive technologies.
Optimalisasi Coverage Area Jaringan WiFi Di SMK N 1 Tegalalang Dengan Menggunakan NetSpot Yuda I Made Wedana Yuda Yana; Gede Arna Jude Saskara; Ida Bagus Nyoman Pascima
MULTINETICS Vol. 11 No. 02 (2025): MULTINETICS Nopember (2025)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v11i02.7904

Abstract

This study focuses on optimizing the Wi-Fi network coverage area at SMK Negeri 1 Tegalalang through mapping and analysis using the NetSpot application. Stable and evenly distributed internet connectivity is essential to support digital-based learning activities in schools. Preliminary observations revealed several blank spots and uneven signal distribution across classrooms and buildings, indicating the need for improvement in network infrastructure. The research employed an action research approach consisting of four stages: diagnosing, action planning, action taking, and evaluating. Data collection was conducted using both active and passive site surveys, measuring the Received Signal Strength Indicator (RSSI), and generating heatmap visualizations to illustrate signal distribution. The analysis emphasized three main aspects: wall attenuation factors, access point positioning, and potential channel interference that contributed to performance degradation. The findings provide a comprehensive signal coverage map along with recommendations for more strategic placement of access points. These recommendations resulted in improved coverage with a minimum RSSI target of –65 dBm and a service area of at least 80%. The outcomes of this study are expected to serve as a valuable reference for schools in designing and enhancing Wi-Fi infrastructure, ensuring reliable connectivity that supports the implementation of online and blended learning effectively.
Perbandingan Performa LLaMA-2 dan GPT-3.5 Turbo Menggunakan Metode Retrieval Augmented Few-shot pada Analisis Sentimen I Wayan Adi Maha Wiguna; Ida Bagus Nyoman Pascima; Luh Putu Eka Damayanti
Jurnal Sarjana Teknik Informatika Vol. 14 No. 1 (2026): Februari
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v14i1.31872

Abstract

Large Language Models (LLM) memerlukan metode tambahan untuk optimasi pada tugas spesifik seperti analisis sentimen. Penelitian ini membandingkan performa GPT-3.5 Turbo dan LLaMA-2 melalui penerapan metode Retrieval Augmented Few-shot (RAFS) pada domain pariwisata, dengan skenario Zero-shot sebagai baseline. Hasil eksperimen menunjukkan bahwa LLaMA-2 mengalami peningkatan performa yang jauh lebih signifikan dibandingkan GPT-3.5 Turbo setelah penerapan RAFS. Akurasi LLaMA-2 meningkat dari 0,833 menjadi 0,862, sementara GPT-3.5 Turbo hanya meningkat tipis dari 0,851 menjadi 0,856. Perbedaan substansial terlihat pada metrik kelas minoritas; f1-score GPT-3.5 hanya naik dari 0,555 ke 0,572, sedangkan LLaMA-2 melonjak drastis dari 0,462 ke 0,676 dengan kenaikan presisi dari 0,395 ke 0,844. Secara head-to-head, LLaMA-2 terbukti sedikit lebih unggul dibanding dengan GPT-3.5 Turbo dalam menghasilkan klasifikasi yang tepat dan seimbang. Meskipun GPT-3.5 memiliki baseline awal yang lebih tinggi, LLaMA-2 menunjukkan kemampuan adaptasi dan skalabilitas yang lebih baik terhadap augmentasi konteks. Temuan ini menegaskan bahwa model open-source dengan dukungan RAFS mampu menyamai, bahkan melampaui model proprieter dalam menangani kompleksitas sentimen ulasan pelanggan.
Pengembangan Sistem Penilaian Keaktifan Belajar Otomatis Berbasis Learning Management System (LMS) Dengan Retrieval-Augmented Generation (RAG) Putu Ryan Darmayasa; Ida Bagus Nyoman Pascima; Ketut Agustini
KARMAPATI (Kumpulan Artikel Mahasiswa Pendidikan Teknik Informatika) Vol. 14 No. 3 (2025)
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/karmapati.v14i3.102876

Abstract

Learning Management System (LMS) merupakan perangkat lunak berbasis internet yang digunakan untuk administrasi, dokumentasi, pencarian, dan penyampaian materi, pelaporan aktivitas pembelajaran daring, serta menyediakan berbagai fitur untuk mempermudah proses unggah dan berbagi materi, diskusi, kuis, survei, dan pelaporan. Meskipun Learning Management System (LMS) telah memberikan kemudahan dalam proses pembelajaran, kenyataannya sistem ini masih memiliki kelemahan, terutama pada aspek penilaian keaktifan belajar siswa yang masih dilakukan secara manual oleh guru. Tujuan dari penelitian ini adalah mengembangkan sistem yang mampu melakukan penilaian keaktifan belajar siswa secara otomatis dengan memanfaatkan Large Language Model (LLM) dan metode Retrieval-Augmented Generation (RAG), serta menganalisis hasil penilaiannya. Penelitian ini menggunakan pendekatan Research and Development (R&D) dengan metode System Development Life Cycle (SDLC) model Agile. Penelitian ini dilakukan melalui empat tahapan, yaitu Requirements, Design, Development, dan Testing. Pengujian sistem mencakup uji blackbox dan whitebox untuk mengukur fungsionalitas, serta uji akurasi menggunakan perhitungan Error Rate untuk membandingkan hasil penilaian sistem dengan guru. Hasil penelitian menunjukkan bahwa sistem mencapai tingkat akurasi sebesar 84,81%.
Co-Authors Alfiansyah Aristamy, I Gusti Ayu Agung Mas Arya Budhi Saputra, I Made Christina Purnama Yanti Darmika, I Wayan Dewa Gede Hendra Divayana, Dewa Gede Hendra Dewi Agustini Dharsika, Eka Edi Wijaya, Ikomang Fitriani, Rani Ligar Gede Aditra Pradnyana Gede Arna Jude Saskara Gede Surya Mahendra I Dewa Made Ditha Utama P I Gede Bendesa Subawa I Gede Mahendra Darmawiguna I Gusti Ayu Agung Diatri Indradewi I Gusti Lanang Agung Raditya Putra I Gusti Lanang Agung Raditya Putra I Gusti Nyoman Sapta Wiguna I Kadek Diwa Anjapuryana I Ketut Yudi Premana Giri I Komang Yuda Muliawan I Made Andhika Pramana Putra I Made Ardwi Pradnyana I Made Aris Danuarta I Made Candiasa I Made Edy Listartha I Nengah Eka Mertayasa I Nyoman Indhi Wiradika I Nyoman Sukajaya I Nyoman Tri Anindia Putra I Putu Dedy Wira Darmawan I Wayan Adi Maha Wiguna Iswardani, Putu Risanti Kadek Ayu Ariningsih Ketut Agustini Krisnayana, I Komang Bayu Luh Putu Eka Damayanthi Luh Putu Eka Damayanti M.Cs S.Kom I Made Agus Wirawan . Made Sevta Reyma Priyandika Mertayasa , I Nengah Eka Mohammad Rezzy Al Zamzammi Ni Kadek Nopiani Ni Komang Tri Witari Ni Nyoman Utami Januhari Ni Wayan Risa Rahayu Saraswati Nyoman Arta Ada Nyoman Sugihartini P. WAYAN ARTA SUYASA Pramudita, Putu Dimas Putra, I Komang Apriyatama Sukarma Putri, Ni Putu Meyka Pradnya Putu Riesty Masdiantini, Putu Riesty Putu Ryan Darmayasa Santoso, Erlinda Shirleen Sidiq, Maulana Sindu, I Gede Partha Sukarasa, Made Dwi Sukma Putri Novianti Supriatman, Rian Dwicahya suryani, rika Syarifudin Abdullah Thoyyibah, Luthfiyatun Wiguna, I Wayan Adi Maha Yogantara, Ketut Manik Yuda I Made Wedana Yuda Yana