cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yusmaniarti
Contact Email
yusmaniarti8@gmail.com
Phone
+6281368411554
Journal Mail Official
jurnaljdaics@gmail.com
Editorial Address
Perum Taman Asri 1 Blok C2 RT 31 RW 06 Palembang South Sumatra 30149
Location
Kota palembang,
Sumatera selatan
INDONESIA
Journal of Data Analytics, Information, and Computer Science (JDAICS)
Published by Yayasan Nuraini Ibrahim Mandiri
ISSN : -     EISSN : 30324696     DOI : https://doi.org/10.59407/jdaics.v1i2
Core Subject : Science, Education,
Computer Science & IT Decision Sciences, Operations Research & Management Mathematics Other
Journal of Data Analytics, Information, and Computer Science (JDAICS) is a national journal for scientific research Analytics, Artificial Intelligence, Bioinformatics, Big Data, Computational Linguistics, Cryptography & Information Security, Data Mining, Data Warehouse, E-Commerce / E-Health / E-Government, Internet of Things, Information Theory, Machine Learning, Multimedia & Image Processing, Software Engineering, Socio Informatics , Wireless & Mobile Computing, Data collection and integration, Data cleaning and preprocessing, Data analysis and exploration, Machine learning and predictive modelling, Data visualization and communication, Data-driven decision making, Ethical and privacy considerations, Designing data infrastructure and systems, Data pipeline development and management, Database design and management, Data integration and ETL (Extract, Transform, Load) processes
Arjuna Subject : Ilmu Komputer (semua kategori) - Teori Komputasi dan Matematika
Articles 82 Documents
 5   6   7   8   9 
CHATBOT AKADEMIK BERBASIS RAG UNTUK INFORMASI AKADEMIK MAHASISWA Ikharista Ayu Nusrotun Afifah; Sam Farisa Chaerul Haviana
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 2 (2026): April
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i2.3636

Abstract

This study aims to develop a Retrieval-Augmented Generation (RAG)-based academic chatbot to provide accurate, relevant, and official document-based academic information for students of the Informatics Engineering Study Program, FTI UNISSULA. The methods used include collecting and pre-processing academic documents, chunking processes, forming vector representations using the Sentence-BERT model, and storing them in the FAISS database to support semantic search. The RAG system integrates document retrieval results with the capabilities of the Large Language Model (LLM) in generating contextual responses. System evaluation was carried out using the ROUGE-1 and BLEU-4 metrics on 50 questions consisting of FAQ and non-FAQ categories. The test results showed that the system was able to respond to all questions given, with high performance in the FAQ category (ROUGE-1 of 0.957 and BLEU-4 of 0.877), and lower performance in the non-FAQ category due to paraphrasing variations in academic documents. These results indicate that the RAG approach is effective in improving the accuracy and relevance of academic chatbot answers, and is able to reduce the risk of misinformation compared to a purely generative approach.
EKSTRAKSI INFORMASI DAN KLASIFIKASI BERITA PEMERINTAHAN DAERAH MENGGUNAKAN FINE-TUNING INDOBERT Arfiana Maulidiyah; Mustafa
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 2 (2026): April
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i2.3714

Abstract

Pemanfaatan kebijakan berbasis penelitian (Evidence-Based Policy) semakin penting dalam mendukung pengambilan keputusan pemerintah daerah, khususnya pada sektor pendidikan, kesehatan, dan ketenagakerjaan di Provinsi Jawa Tengah. Tingginya volume berita berani yang dipublikasikan setiap hari menjadi tantangan bagi Organisasi Perangkat Daerah (OPD) dalam mengumpulkan dan menganalisis informasi secara manual. Penelitian ini bertujuan mengembangkan sistem ekstraksi informasi dan klasifikasi berita pemerintahan daerah secara otomatis menggunakan fine-tuning IndoBERT. Dataset terdiri dari 1.025 artikel berita yang dikumpulkan melalui web scraping dari empat media dare, kemudian diseleksi menjadi 377 data berlabel setelah melalui preprocessing, ekstraksi entitas Named Entity Recognition (NER), dan pelabelan semi-otomatis. Model IndoBERT disempurnakan untuk mengklasifikasikan berita ke dalam tiga kategori OPD: Dinas Pendidikan, Dinas Kesehatan, dan Dinas Ketenagakerjaan. Hasil evaluasi menunjukkan akurasi sebesar 88,16%, dengan presisi makro 0,88, recall makro 0,87, dan F1-score makro 0,87 pada pengujian data. Sistem ini diimplementasikan dalam dashboard Streamlit interaktif yang membantu OPD mengidentifikasi strategi isu secara cepat dan akurat, mendukung tata kelola pemerintahan berbasis data.
EVALUASI KINERJA PENGURUS LEMBAGA DAKWAH KAMPUS FAKULTAS SAINS DAN TEKNOLOGI BERBASIS SIMPLE ADDITIVE WEIGHTING Muhammad Rizki Hariyanto; Evy Nurmiati
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 2 (2026): April
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i2.3788

Abstract

Evaluasi kinerja pengurus LDKS FST menghadapi tantangan subjektivitas dan bias visibilitas akibat ketiadaan standar Key Performance Indicator (KPI). Penelitian ini bertujuan menerapkan Sistem Pendukung Keputusan (SPK) untuk menciptakan mekanisme evaluasi yang objektif menggunakan metode Simple Additive Weighting (SAW). Metode ini diimplementasikan terhadap 15 sampel pengurus dengan mengukur empat kriteria utama: kehadiran, penyelesaian jobdesc, inisiatif, dan tingkat indisipliner. Hasil analisis kuantitatif menunjukkan bahwa algoritma SAW mampu menghasilkan perangkingan kinerja secara presisi, di mana dua pengurus terbaik meraih nilai preferensi sempurna sebesar 1,000. Sistem ini terbukti efektif mendekonstruksi bias visibilitas dengan memberikan penalti otomatis pada fungsionaris yang memiliki catatan indisipliner tinggi hingga menyentuh nilai preferensi terendah sebesar 0,718, meskipun fungsionaris tersebut memiliki tingkat kehadiran fisik yang memadai. Implementasi sistem berhasil menggeser orientasi penilaian intuitif menuju keputusan berbasis data yang akuntabel. Penelitian ini memberikan kontribusi praktis dalam transformasi manajemen sumber daya manusia pada organisasi fungsionaris berbasis kerelawanan dengan mengintegrasikan prinsip etika teknologi dan keadilan proporsional ('adl)
DESIGN OF AN AUTOMATED CLASSIFICATION SYSTEM USING INDOBERT TRANSFORMERS AND LOCAL NEWS TEXT SUMMARIZATION WITH LLAMA 3 ON RADARTEGAL.COM Keisya Anazwa Octa Reviandy; Sam Farisa Chaerul Haviana
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 3 (2026): Juli
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i3.3659

Abstract

In the digital news production process, editorial teams face challenges in manually categorizing news articles and generating summaries, which are time-consuming, inefficient, and prone to inconsistencies that affect content management quality and Search Engine Optimization (SEO). This study aims to design and develop an automated system for news classification and summarization on the radartegal.com platform using the Transformer-based IndoBERT model for automatic news category classification and the Large Language Model (LLM) LLaMA 3 for abstractive text summarization. The research methodology consisted of problem identification, literature review, dataset collection, text preprocessing, IndoBERT fine-tuning, LLaMA 3 implementation, pipeline integration, and system evaluation. Classification performance was evaluated using accuracy, precision, recall, and F1-score, while summarization quality was evaluated using ROUGE metrics. Experimental results showed that the IndoBERT model achieved an accuracy of 84.00%, precision of 84.58%, recall of 84.00%, and F1-score of 83.95%. Meanwhile, the LLaMA 3 summarization module achieved ROUGE-1, ROUGE-2, and ROUGE-L scores of 0.4672, 0.2732, and 0.4122, respectively. The integrated system successfully automated editorial workflows, improved categorization consistency, generated informative summaries, and supported SEO optimization. These findings demonstrate that the proposed system can improve editorial efficiency while maintaining content quality in local digital news publishing.
IMPLEMENTATION OF INDOBERT IN AN EXTRACTIVE QUESTION ANSWERING CHATBOT FOR INFORMATION SERVICES AT LAZIS SULTAN AGUNG Ella Heriyawati; Sam Farisa Chaerul Haviana
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 2 (2026): April
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Advances in AI and Natural Language Processing (NLP) technology have facilitated the use of chatbots as a means of providing automated information in various sectors, including religious and social organizations. LAZIS Sultan Agung still operates its information services manually via WhatsApp and in-person interactions, which limits responsiveness due to time and staff availability. This research aims to create an Extractive Question Answering (EQA)-based information chatbot utilizing the IndoBERT model to automatically assist users in obtaining information about services, programs, zakat, and donations at LAZIS Sultan Agung. The approach used in this research involves TF-IDF for the context retrieval process and IndoBERT for the answer extraction step. The dataset was obtained from official documents and the LAZIS Sultan Agung knowledge base, which contains service information and frequently asked questions. This web-based system uses Flask and MySQL for data storage. The evaluation results show that the system achieved an Exact Match (EM) value of 0.5294, Cosine Similarity of 0.7875, Precision of 0.8059, Recall of 0.8244, and F1-Score of 0.8052. Furthermore, black box testing showed that the chatbot was able to provide appropriate answers to user questions and could reject questions outside the scope of the system. Thus, the developed chatbot can accelerate, automate, and improve the efficiency of the information receiving process of LAZIS Sultan Agung. Keyword : Chatbot, IndoBERT, Extractive Question Answering, TF-IDF, NLP.
A COMPARATIVE ANALYSIS OF DDR4 AND DDR5 MEMORY ARCHITECTURE Endita Layla Sulistiyowati; Aprillia Rahmasari Distiah; Nisa Ulin Ni'mah; Allifa Maulani; Aisyah Dwi Windarti; Noviara Zizi Amanda
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 3 (2026): Juli
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i3.4017

Abstract

The development of modern software demands high data transfer rates from the main memory. However, increasing conventional RAM speed is often hindered by thermal law limitations, triggering circuit temperature spikes due to forced clock speeds. This study aims to analyze DDR5 memory data bus path structural modifications in overcoming these semiconductor circuit physical limitations. The method employed is a literature study with a qualitative-descriptive approach, utilizing secondary data from Google Scholar, Garuda, and technical specification documents. The study scope is strictly confined to internal micro-architectural modifications, excluding memory capacity and density scaling parameters. Results indicate that increased data transfer rates in the DDR5 generation are achieved by restructuring the single 64-bit data bus path into a dual 32-bit sub-channel system. This modification combines with doubling the Burst Length value to BL16 to transmit large data packets simultaneously without frequent processor interruptions. In conclusion, this internal architectural engineering provides an effective solution to accelerate data transmission and maintain temperature stability without forcing memory physical frequency limits. Theoretically, these findings shift the memory optimization paradigm from frequency scaling to structural path efficiency, foundational for future scalable hardware designs.
INTEGRASI COMPUTER ASSISTED TEST DAN MANAJEMEN KESAMAPTAAN JASMANI PADA SISTEM PERSIAPAN SELEKSI KEDINASAN Bintang Augri Faris; Gugun Gunadi; Hilmy Aliy Andra Putra
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 3 (2026): Juli
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i3.4119

Abstract

Seleksi penerimaan taruna sekolah kedinasan dan instansi keamanan (TNI/Polri) menetapkan standar kompetensi kognitif dan fisik yang tinggi dengan rasio persaingan yang ketat. Permasalahan utama calon peserta adalah rendahnya efektivitas pemantauan kemajuan belajar karena sistem persiapan akademik dan latihan fisik (kesamaptaan) masih beroperasi secara parsial, manual, dan terisolasi (silo). Penelitian ini merancang sistem informasi pembelajaran berbasis web yang mengintegrasikan simulasi Computer Assisted Test (CAT) dengan manajemen data nilai kesamaptaan jasmani secara terpusat. Pengembangan perangkat lunak menerapkan System Development Life Cycle (SDLC) model Waterfall. Evaluasi fungsionalitas dan pengalaman pengguna dilakukan melalui Black Box Testing, User Acceptance Test (UAT), dan System Usability Scale (SUS) terhadap 30 responden target. Hasil penelitian menunjukkan fungsionalitas sistem berjalan 100% valid, termasuk algoritma auto-grading matriks skala 100 dan konversi nilai jasmani. Evaluasi kuantitatif UAT mencatat persentase penerimaan pengguna sebesar 92.5% (Sangat Layak), dan skor SUS mencapai 84.5 (Acceptable/Excellent). Integrasi data ke dalam satu dasbor rapor digital ini terbukti secara empiris meningkatkan efisiensi dan objektivitas calon peserta dalam memetakan parameter kesiapan kompetensi mereka secara komprehensif dan real-time.
PENGEMBANGAN SISTEM INFORMASI MANAJEMEN PETERNAKAN AYAM KAMPUNG BERBASIS WEB PADA SADELI FARM Dwi Apriansyah; Himmatul Miftah; Hilmy Aliy Andra Putra
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 3 (2026): Juli
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i3.4123

Abstract

Peternakan ayam kampung merupakan salah satu sektor usaha yang berperan penting dalam mendukung ketahanan pangan dan perekonomian masyarakat. Namun, sebagian besar peternakan skala kecil, termasuk Sadeli Farm di Bogor Selatan, masih menerapkan sistem pencatatan manual yang menyebabkan tingginya risiko kesalahan pencatatan, kesulitan dalam pemantauan data, serta keterlambatan penyusunan laporan operasional dan keuangan. Penelitian ini bertujuan untuk merancang dan mengembangkan Sistem Informasi Manajemen Peternakan Ayam Kampung berbasis web yang mengintegrasikan pengelolaan data ternak, pakan, produksi, dan keuangan dalam satu sistem terpusat. Metode pengembangan perangkat lunak yang digunakan adalah Waterfall dengan tahapan analisis kebutuhan, perancangan, implementasi, pengujian, dan pemeliharaan. Sistem dikembangkan menggunakan PHP Native, MySQL/MariaDB, Bootstrap 5, dan Chart.js. Pengujian fungsional dilakukan menggunakan metode Black Box Testing terhadap tujuh modul utama sistem dan menunjukkan tingkat keberhasilan sebesar 100%, sehingga seluruh fungsi berjalan sesuai dengan kebutuhan pengguna tanpa ditemukan kesalahan kritis. Evaluasi penerimaan pengguna dilakukan melalui User Acceptance Testing (UAT) terhadap 5 responden yang terdiri atas pemilik, anggota keluarga, dan pekerja kandang. Hasil evaluasi menunjukkan tingkat kepuasan pengguna sebesar 89,5% dengan kategori sangat baik, terutama pada aspek kemudahan penggunaan, keakuratan data, dan efisiensi waktu. Implementasi sistem mampu meningkatkan efisiensi proses pencatatan, mempercepat penyusunan laporan, serta menghasilkan informasi yang lebih terstruktur dan akurat untuk mendukung pengambilan keputusan operasional di Sadeli Farm. Dengan demikian, sistem yang dikembangkan
A COMPARATIVE ANALYSIS OF INFORMED SEARCH AND UNINFORMED SEARCH ALGORITHMS IN THE EFFICIENCY OF AI PROBLEM MODELING Boy Firmansyah
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 3 (2026): Juli
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i3.4170

Abstract

Search algorithms represent a core foundational component in intelligent system design for exploring state spaces to find optimal solutions. This article presents a theoretical comparative analysis between two primary search paradigms in Artificial Intelligence (AI): uninformed search (blind search) and informed search (heuristic search), with a specific focus on problem modeling computational efficiency. The scope of this study is focused on evaluating structural parameters and time-space complexity metrics across representative algorithms, including Breadth-First Search (BFS), Depth-First Search (DFS), Uniform-Cost Search (UCS), Greedy Best-First Search, and the A* algorithm. The qualitative comparative review demonstrates that while uninformed search offers model simplicity without requiring domain knowledge, it suffers from exponential complexity growth O(bd). Conversely, informed search leveraging admissible and consistent heuristic functions radically prunes search trees and optimizes resource consumption. The main scientific contribution of this study lies in a structured evaluation framework that maps the trade-offs between heuristic informativenes
SISTEM INFORMASI PENGAJUAN CUTI MAHASISWA PADA INSTITUT HASAN SULUR BERBASIS WEB Puput Talib; Basri Basri; Sapriadi Sapriadi
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 3 (2026): Juli
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i3.4184

Abstract

Prosedur pengajuan cuti mahasiswa di Institut Hasan Sulur saat ini masih menghadapi kendala administratif akibat sistem yang bersifat konvensional, sehingga memicu risiko kehilangan dokumen fisik, kurangnya transparansi status pengajuan, serta tidak tersedianya basis data yang terorganisir untuk pelaporan akademik. Penelitian ini bertujuan untuk merancang dan mengimplementasikan Sistem Informasi Pengajuan Cuti Mahasiswa berbasis web sebagai solusi digital atas permasalahan tersebut. Metode penelitian yang digunakan adalah Research and Development (R&D) dengan model pengembangan perangkat lunak Waterfall, meliputi analisis kebutuhan, desain, pengkodean, hingga pengujian. Arsitektur sistem dibangun menggunakan bahasa pemrograman PHP dan basis data MySQL, serta dilengkapi fitur visualisasi tren data untuk mendukung pengambilan keputusan manajerial. Tahap validasi dilakukan melalui pengujian fungsionalitas menggunakan metode Black Box Testing serta pengujian usability menggunakan instrumen System Usability Scale (SUS) terhadap 30 responden yang dipilih melalui teknik purposive sampling. Hasil pengujian pengguna memberikan nilai rata-rata SUS sebesar 81,5 (skala 0–100), yang mengindikasikan bahwa sistem berada dalam kategori sangat layak digunakan (Excellent). Implementasi sistem ini mampu mempercepat waktu pelayanan administrasi, menjamin keamanan kearsipan digital, dan menyediakan informasi yang akurat bagi pihak institusi dalam memantau dinamika akademik mahasiswa secara real-time..

Page 8 of 9 | Total Record : 82

 5   6   7   8   9 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 3 (2026): Juli Vol. 3 No. 2 (2026): April Vol. 3 No. 1 (2026): Januari Vol. 2 No. 4 (2025): Oktober Vol. 2 No. 3 (2025): Juli Vol. 2 No. 2 (2025): April Vol. 2 No. 1 (2025): Januari Vol. 1 No. 4 (2024): Oktober Vol. 1 No. 3 (2024): Juli Vol. 1 No. 2 (2024): April Vol. 1 No. 1 (2024): January More Issue