Article Per Year (5 Year)
p-Index From 2020 - 2025
3.2
P-Index
This Author published in this journals
All Journal Litera Syntax Jurnal Informatika Indonesian Journal of Science and Technology JITK (Jurnal Ilmu Pengetahuan dan Komputer) JMM (Jurnal Masyarakat Mandiri) Indonesian Journal of Applied Informatics Jurnal Linguistik Komputasional Jurnal Abmas Brilliance: Research of Artificial Intelligence Academic Journal of Computer Science Research (AJCSR) Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Digital Transformation Technology (Digitech) JATIKOM: Jurnal Aplikasi dan Teori Ilmu Komputer Hipotenusa: Journal of Mathematical Society
Wibisono, Yudi
Universitas Pendidikan Indonesia
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 Mathematics Social Sciences Other

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
Penerapan Large Languange Models Dalam Pembaruan Artikel Biografi Wikipedia Dwiharani, Najma Qalbi; Yudi Wibisono; Yaya Wihardi
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 2 (2025): September 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i2.499

Abstract

Wikipedia merupakan sumber informasi daring yang sangat populer di Indonesia, namun pembaruan artikelnya masih sangat bergantung pada kontribusi penyunting. Pada kategori artikel biografi, pembaruan informasi secara berkala sangat penting karena adanya perkembangan karier dan peristiwa terkini dari tokoh yang bersangkutan. Penelitian ini bertujuan untuk mengeksplorasi penerapan Large Language Models (LLM) dalam menambahkan informasi baru ke artikel biografi Wikipedia Indonesia dengan referensi dari satu artikel berita daring. Model utama yang digunakan adalah Gemma 3 yang kemudian dibandingkan dengan model baseline Phi-3-mini. Penelitian ini juga menguji efektivitas lima strategi prompting yang berbeda, yaitu simple prompt, system prompt (en), system prompt (id), one-shot, dan prompt chaining untuk mengarahkan model dalam menghasilkan keluaran yang relevan dan sesuai dengan gaya Wikipedia. Proses fine-tuning dilakukan menggunakan data berbentuk kombinasi artikel Wikipedia sebelum diperbarui, artikel berita sebagai referensi, dan teks berisi informasi baru yang relevan untuk ditambahkan ke dalam artikel Wikipedia sebagai target keluaran. Evaluasi dilakukan dengan metrik ROUGE untuk mengukur kesamaan antara hasil keluaran model dan referensi dari penyunting Wikipedia. Hasil penelitian menunjukkan bahwa fine-tuning model Gemma 4B secara signifikan meningkatkan performa, khususnya pada strategi prompt chaining dengan rata-rata skor ROUGE-1 sebesar 0.3687. Dibandingkan dengan baseline Phi-3-mini, model Gemma memberikan hasil yang lebih konsisten dan relevan. Temuan ini menunjukkan bahwa pendekatan berbasis LLM dapat menjadi solusi potensial dalam membantu proses pembaruan artikel biografi Wikipedia.
Integrasi YOLOv11 dan Intersection-Based Method Untuk Estimasi Karakteristik Parkir Berdasarkan Parking Lot Surveillance Video Muhammad Kamal Robbani; Yudi Wibisono; Eddy Prasetyo Nugroho
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 2 (2025): September 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i2.502

Abstract

The rapid growth of vehicles without a corresponding increase in parking space availability has led to various issues such as traffic congestion, fuel waste, and excessive emissions. This study develops a computer vision-based parking analysis system using the YOLOv11 model to automatically detect vehicles in parking areas. The system integrates an intersection-based method and the BoT-SORT object tracking algorithm to classify parking spot availability. The classification results are then used to extract parking characteristic data. Video data were obtained from a publicly accessible livestream on YouTube in Kusatsu, Japan, and used for training and evaluating the model. The model achieved an mAP@50-95 of 0.926 under bright lighting conditions and 0.859 in low-light conditions. Additionally, estimation accuracy was evaluated using MAE and R² metrics, showing promising results, with MAE of 1.27 and R² of 0.989 during daytime, and MAE of 0.91 and R² of 0.91 at night.
Analisis Sentimen dan Pemodelan Topik pada Post tentang Merek Teknologi di X Menggunakan Fine-tuning IndoBERT dan BERTopic Muhammad Rayhan Nur; Yudi Wibisono; Rani Megasari
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 2 (2025): September 2025
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i2.508

Abstract

Media sosial telah menjadi wadah bagi konsumen untuk menyampaikan persepsi dan opini. Opini yang beredar tersebut berpotensi menjadi sumber data yang berharga bagi brand, termasuk Xiaomi, dalam memahami persepsi publik terhadap produk mereka. Penelitian ini bertujuan untuk menganalisis sentimen dan mengidentifikasi topik diskusi pada unggahan (post) mengenai merek teknologi Xiaomi di platform X (sebelumnya Twitter) dengan pendekatan berbasis Transformer. Dua metode utama yang digunakan adalah fine-tuning IndoBERT untuk model klasifikasi sentimen dan BERTopic untuk pemodelan topik. Data yang berhasil dikumpulkan sebanyak 10.130 post dari bulan Mei 2023 hingga Mei 2025 yang dilanjutkan menuju tahapan praproses serta pelabelan. Model klasifikasi dilatih dengan berbagai kombinasi konfigurasi hyperparameter, dengan hasil pengujian terbaik menghasilkan nilai accuracy 79,8%, precision 73,0%, recall 67,7%, dan f1-score (macro) sebesar 0,699. Distribusi sentimen dalam data menunjukkan dominasi sentimen netral, sedangkan BERTopic berhasil menghasilkan 16 cluster topik dengan rata-rata nilai coherence (C_v) sebesar 0,5437. Topik paling dominan dengan jumlah anggota cluster terbanyak membahas mengenai produk Xiaomi Series dan Poco. Sementara itu, topik dengan persentase sentimen negatif tertinggi berkaitan dengan layanan service center dan sentimen positif tertinggi mengenai produk komputer tablet (tab) Xiaomi. Penggabungan hasil analisis sentimen dan topik memberikan pemahaman yang lebih mendalam terhadap isu yang dibicarakan serta persepsi konsumen. Penelitian ini membuktikan bahwa kombinasi IndoBERT dan BERTopic efektif dalam menganalisis opini konsumen di media sosial serta memberikan wawasan strategis yang relevan bagi perusahaan untuk mengidentifikasi kekuatan dan potensi peningkatan yang dapat dilakukan.
Intelligent News Aggregation System with Automatic Classification, Clustering, and Summarization Zulfikar, Ihsan Ghozi; Wibisono, Yudi; Wahyudin, Asep
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6712

Abstract

The rapid growth of online news content has made it increasingly difficult for users to access relevant information efficiently. This study presents the development of an intelligent web-based news aggregation system that performs automatic classification, clustering, and summarization of Indonesian-language news articles. The system aims to enhance the news reading experience by organizing articles by category and topic, and by providing concise summaries. The system was built using the ADDIE development model, with each AI component trained and evaluated separately. News classification is handled by a BLSTM-2DCNN model trained on the IndoSum dataset, achieving 86% accuracy and an F1-score of 0.85. This model was also applied to classify 37,187 real-world articles scraped from Kompas and TribunNews during June 2025. Topic clustering is performed using K-means with entropy-weighted Bag-of-Words features over 5-day sliding windows. The clustering quality, evaluated using the Calinski-Harabasz Index, ranged from 5.21 to 525.44 with an average of 80.53, indicating varying cluster cohesion. For summarization, a fine-tuned BART model was used to summarize the article closest to each cluster’s centroid. The model achieved ROUGE scores of 0.6389 (ROUGE-1), 0.5458 (ROUGE-2), and 0.6017 (ROUGE-L). The integrated system automatically scrapes news, classifies and clusters articles, and displays generated summaries through a user-friendly web interface. The results show that combining deep learning and natural language processing offers an effective approach for intelligent news aggregation, helping users consume news faster and more meaningfully.
Development of an Academic Services Chatbot Based on Retrieval-Augmented Generation (RAG) Husain, Mohammad Labib; Wibisono, Yudi; Anisyah, Ani
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6719

Abstract

Higher education institutions struggle to provide accurate and accessible academic information. Traditional chatbots are often limited in capability, while standard Large Language Models (LLMs) pose a significant risk of factual "hallucinations," rendering them unsuitable for official university use where trustworthiness is paramount. This study aims to increase the accessibility and effectiveness of academic services by developing a trustworthy chatbot. The primary objective is to implement the Retrieval-Augmented Generation framework to create a reliable AI assistant that is factually grounded in a verified, domain-specific knowledge base. A knowledge base was constructed from official FPMIPA UPI documents and structured using hierarchical chunking. The system employs a multi-stage RAG pipeline featuring query contextualization and reranking before generation with Gemini 2.5 Pro. Performance was evaluated using metrics from the RAGAS framework on a 100-question dataset categorized into factual, reasoning, and out-of-context queries. The evaluation revealed strong performance on factual queries, achieving a Faithfulness score of 0.9100. A significant performance decrease was observed for reasoning tasks, with Context Recall dropping to 0.5926. Crucially, the system successfully handled 81.25% of out-of-context questions by correctly refusing to answer, thereby effectively preventing hallucination. The RAG framework provides a viable and empirically-validated blueprint for creating a trustworthy conversational AI for higher education. The model proves to be an effective tool for factual information delivery and has strong potential to modernize how student support and academic services are delivered.
Development of an Automatic Summarization System based on Large Language Models for Annual Report Analysis Rizki, Muhammad; Wibisono, Yudi; Nugroho, Eddy Prasetyo
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6772

Abstract

The increasing interest in stock market investment in Indonesia has highlighted a significant challenge for retail investors: the difficulty of analyzing lengthy and complex corporate annual reports. These documents, essential for fundamental analysis, are often hundreds of pages long and contain detailed narrative sections that require considerable time and effort to comprehend. This research addresses this issue by developing an automatic summarization system using a Large Language Model (LLM) to generate concise and insightful summaries of such reports. The primary objective was to develop and evaluate an LLM-based system specifically adapted for the structure and content of annual reports. The method involved creating a tailored dataset comprising 2,008 narrative text excerpts and their corresponding manual summaries sourced from the annual reports of companies listed on the Indonesia Stock Exchange (IDX). The open-source Llama-3.2-3B-Instruct model was then fine-tuned using the Parameter-Efficient Fine-Tuning (PEFT) technique, specifically Low-Rank Adaptation (LoRA). The research results demonstrated a significant improvement in the model's performance after fine-tuning. Quantitative evaluation using ROUGE metrics showed a relative increase of 18.63% in ROUGE-1, 44.45% in ROUGE-2, and 33.83% in ROUGE-L compared to the base model. Qualitative analysis confirmed that the fine-tuned model was capable of generating informative and relevant summaries aligned with the context of annual report analysis. In conclusion, this study demonstrates that fine-tuning LLMs with document-specific data is an effective approach for specialized tasks such as annual report summarization.
Non-Playable Characters Based On Large Language Models For Role Playing Games (RPG) Mulyana, Ade; Wibisono, Yudi; Anisyah, Ani
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6779

Abstract

Interactive dialogue is a central element in role-playing games (RPG), particularly those that emphasize storytelling and immersion. This study explores the development of a dynamic Non-Playable Character (NPC) system using a Large Language Model (LLM) to simulate responsive conversations in a fictional world. The objective of this research is to design an NPC dialogue system that can maintain contextual consistency with the game’s lore while adapting to player input dynamically. The method used is engineering-based development, involving prompt engineering and a Retrieval-Augmented Generation (RAG) approach to embed narrative context into the LLM prompts. The system is implemented in a 2D RPG titled Kage no Meiyaku: Shinobi no Michi, where players interact with multiple NPCs whose responses evolve based on both pre-defined lore and game progression. Evaluation is conducted using a Likert scale across four dialogue quality dimensions: coherence, emotional engagement, narrative relevance, and persona consistency. The results show that the system generates engaging and contextually accurate responses, with average scores ranging from 4.0 to 4.5. Some limitations are identified, such as occasional misspellings and generic responses in ambiguous inputs. However, the approach demonstrates strong potential for AI-assisted storytelling in games. This research contributes to expanding LLM applications in interactive fiction and opens future work toward feature-rich RPG elements such as transactional systems, branching narratives, and real-time battle interactions.
Co-Authors Acep Aris Mubarok Ade Mulyana, Ade Ade Rohayati Ananias Erlita Mamu Anisyah, Ani Arie Gunawan Asep Wahyudin Chairul Furqon, Chairul Christina Prilla Rosaria Ardyanti Dwiharani, Najma Qalbi Eddy Prasetyo Nugroho Eddy Prasetyo Nugroho Emilia Stefani Nurung Febyana Ramadhanti Fikry Al Farisi Muslim Husain, Mohammad Labib Ibrahim Zein Abdillah Ignasius Kevin Rinta Johan, Riche Cynthia Kristianus Viktor Pantaleon Lala Septem Riza Maharani, Fenny Feronika Makur, Alberta P Maulana R, M Rifky Maximus Tamur Mediayani, Melani Muhammad Fadhil Muhammad Kamal Robbani Muhammad Rayhan Nur Muhammad Rizki Munir Munir Niagara, Asep Indra Nikmah, Qoidatun Nurjanah . Nursalman, Muhammad Pantaleon, Kristianus Viktor Paulus Roldin Ganas Pérez, Alejandro Rosales Putra, Budi Lasono Putro, Budi Laksono Rani Megasari Rani Megasari Rosa Ariani Sukamto Setiadiputra, Dodi Siregar, Herbert Sobana, Aceng Tamur, Maximus Teti Suryati Tommy Tanu Wijaya Umar Syahid Aulia Rahman Wawan Setiawan Wawan Setiawan Wihardi, Yaya Yosefus Januarisky Berchmans Yudi Wahyudi Yuniarti Musa'adah Yupa Umigi Al-khairi Zulfikar, Ihsan Ghozi