cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ahmad Homaidi
Contact Email
jurnalinformatika@ibrahimy.ac.id
Phone
+6285258824038
Journal Mail Official
jurnalinformatika@ibrahimy.ac.id
Editorial Address
Jl. KHR. Syamsul Arifin No. 01-02 Sukorejo Situbondo PO.BOX. 2 Telp. 0338-451307 Faks. 0338-45306
Location
Kab. situbondo,
Jawa timur
INDONESIA
Scientific Journal of Informatics
Published by Universitas Ibrahimy
ISSN : 25497480     EISSN : 25496301     DOI : https://doi.org/10.35316/jimi
Core Subject : Science,
Computer Science & IT
Topics cover the following areas (but are not limited to): 1. Information Technology (IT) a. Software engineering b. Game c. Information Retrieval d. Computer network e. Telecommunication f. Internet g. Wireless technology h. Network security i. Multimedia technology j. Mobile Computing k. Parallel/Distributed Computing 2. Information Systems Engineering a. Development, management and utilization of Information Systems b. Organizational Governance c. Enterprise Resource Planning d. Enterprise Architecture Planning e. e-Bbusinnes f. e-Commerce 3. Business Intelligence a. Data mining b. Text mining c. Data warehouse d. Online Analytical Processing e. Artificial Intelligence f. Decision Support System g. Machine Learning
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 158 Documents
 12   13   14   15   16 
EKSTRAKSI FITUR MENGGUNAKAN VGG-19 UNTUK CLUSTERING TINGKAT KERUSAKAN BANGUNAN PASCA BENCANA ALAM BERBASIS PCA Ahmad Jailani; Agung Teguh Wibowo Almais; Usman Pagalay; Mokhamad Amin Hariyadi; Fresy Nugroho
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.9429

Abstract

Penilaian kerusakan bangunan pascabencana alam merupakan tugas kritis yang memerlukan kecepatan dan akurasi tinggi. Metode manual memiliki keterbatasan dari segi waktu, risiko keselamatan, dan subjektivitas. Penelitian ini mengeksplorasi pemanfaatan arsitektur Convolutional Neural Network (CNN) VGG19 untuk mengekstraksi fitur visual dari citra bangunan yang rusak. Fitur hierarkis yang dihasilkan, mulai dari tepi, retakan, hingga deformasi struktural, kemudian dianalisis menggunakan Principal Component Analysis (PCA) untuk reduksi dimensi. Hasil penelitian menunjukkan bahwa PCA berhasil mempertahankan sekitar 95% total varians data hanya dengan tiga komponen utama (PC1, PC2, PC3). Visualisasi dalam ruang dua dimensi mengindikasikan bahwa fitur dari VGG19 secara alami mampu memisahkan karakteristik kerusakan bangunan menjadi dua kelompok utama berdasarkan nilai PC1 negatif dan positif. Dengan demikian, kombinasi VGG19 dan PCA menawarkan fondasi yang efektif untuk sistem penilaian kerusakan bangunan otomatis yang lebih cepat, objektif, dan aman, meskipun validasi lebih lanjut dengan data lapangan masih diperlukan.
PENDEKATAN NON-INVASIF UNTUK DETEKSI KOLESTEROL MENGGUNAKAN PENGOLAHAN CITRA IRIS DAN MACHINE LEARNING Rifki Rohidin; Rizal Rachman
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.9542

Abstract

High cholesterol levels are a major risk factor for cardiovascular disease, making early detection highly important. However, limited access to healthcare services and the high cost of laboratory examinations hinder routine screening within the community. This study aims to develop an Artificial Intelligence (AI)-based cholesterol detection system through iris image analysis as a practical and efficient solution. The Gray-Level Co-occurrence Matrix (GLCM) method is used to extract texture features from iris images, while Support Vector Machine (SVM) is applied to classify cholesterol levels. The system is designed as a web-based platform to improve accessibility, especially for communities in areas with limited healthcare facilities. Uploaded iris images are analyzed to produce cholesterol level classifications along with follow-up recommendations when high-risk conditions are detected. The expected outcomes of this research include a scientific article published in a nationally accredited Sinta 3 journal and Intellectual Property Rights in the form of copyright protection for the web application. The targeted Technology Readiness Level (TRL) is level 3 through experimental testing. This research is expected to contribute to improving access to innovative and sustainable early cholesterol detection.
SISTEM SKORING WOODBALL BERBASIS WEB DENGAN PERHITUNGAN OTOMATIS MENGGUNAKAN METODE WATERFALL Nurun Nihayatur Rifqiyah Aulia; Arie Nugroho; Anita Sari Wardani
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.9557

Abstract

The score recording process in woodball competitions is still commonly carried out manually using paper sheets, causing recording errors, delays in score recapitulation, and difficulties in managing match data. This study aims to develop a web-based woodball scoring system with automatic calculation to improve the accuracy and efficiency of score management during competitions. The system was developed using the Waterfall method and implemented using PHP, MySQL, HTML, CSS, JavaScript, and Bootstrap. The application provides features such as player management, match management, real-time score input, automatic score calculation, ranking generation, and match result reporting. Based on Black Box Testing results, all system features functioned properly according to user requirements. The developed system is able to reduce manual calculation errors, accelerate score recapitulation, and support real-time monitoring of match results. Therefore, the system can be used as an effective digital solution for woodball match scoring and management.
PENGEMBANGAN APLIKASI MOBILE SISTEM LAPORAN WARGA MENGGUNAKAN METODE MOBILE APPLICATION DEVELOPMENT LIFE CYCLE (MADLC) (STUDI KASUS : DESA GANGGANG PANJANG) Nico Mayharis; Wildan Suharso; Briansyah Setio Wiyono
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.9592

Abstract

The citizen reporting system in Ganggang Panjang Village is still conducted manually, requiring residents to visit the village office directly to report infrastructure issues, public facility problems, and emergency conditions. This condition causes delays in response, loss of documentation, and low transparency in complaint handling. This study aims to design, implement, and evaluate a mobile-based citizen reporting application using the Mobile Application Development Life Cycle (MADLC) methodology, which consists of seven phases: Identification, Design, Development, Prototyping, Testing, Deployment, and Maintenance. The application was developed using the Flutter framework and Supabase backend, featuring GPS-based reporting, real-time status tracking, an analytics dashboard, and two-way notifications. Functional testing using Black Box Testing on 18 test scenarios showed a 100% success rate. Usability testing using the System Usability Scale (SUS) with 15 respondents resulted in an average score of 82.08, categorized as Excellent. These results demonstrate that MADLC with iterative prototyping phases produces an application that is functional, user-friendly, and suitable for rural communities with varying levels of digital literacy.
RANCANGAN MODEL ASISTEN VIRTUAL BERBASIS RETRIEVAL-AUGMENTED GENERATION UNTUK MENDUKUNG PEMBELAJARAN MAHASISWA DI PERGURUAN TINGGI Jumar; Farhan Mahendra; Raul Mahya Komaran; Shaffira Vulkanietta Lusiana; Budi Tjahjono
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.9596

Abstract

Pemanfaatan kecerdasan buatan generatif di perguruan tinggi semakin dekat dengan aktivitas belajar mahasiswa, terutama ketika mahasiswa membutuhkan penjelasan tambahan, bahan pendukung, atau arahan awal dalam memahami materi. Di sisi lain, pemanfaatan AI generatif masih menimbulkan persoalan terkait akurasi jawaban, keterlacakan sumber, integritas akademik, dan kecenderungan mahasiswa menerima jawaban secara instan tanpa proses telaah yang memadai. Artikel ini bertujuan merumuskan rancangan model asisten virtual berbasis Retrieval-Augmented Generation (RAG) sebagai pendamping belajar mahasiswa di perguruan tinggi. Metode yang digunakan adalah kajian konseptual melalui studi pustaka dan perancangan model sistem. Literatur yang ditelaah mencakup chatbot pendidikan, RAG, generative AI di pendidikan tinggi, AI dalam pembelajaran pemrograman, serta isu etika penggunaan AI. Model yang diusulkan mencakup pengelolaan dokumen pembelajaran, prapemrosesan, chunking, embedding, basis data vektor, retrieval, konstruksi prompt, generasi jawaban, dan evaluasi respons. Hasil kajian menunjukkan bahwa RAG berpotensi memberi jawaban yang lebih kontekstual karena respons diarahkan pada dokumen akademik yang telah ditentukan. Kontribusi artikel ini berupa rancangan konseptual, alur pemanfaatan, serta indikator evaluasi yang dapat dijadikan dasar pengembangan prototipe asisten virtual pembelajaran secara lebih terukur.
PERBANDINGAN METODE TRANSFER LEARNING DALAM KLASIFIKASI PENYAKIT DAUN PADI Aldi Daffa Arisyi; Muhammad Aidil Saputra; Muhammad Rafif Hanif; Anindita Septiarini; Akhmad Irsyad
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.9611

Abstract

This study compares four transfer learning-based CNN models, namely VGG19, ResNet152, MobileNetV2, and DenseNet121, for the classification of 10 classes of rice leaf diseases. Evaluation results on the test dataset show that ResNet152 achieves the best performance with an accuracy of 0.9553, precision of 0.9589, recall of 0.9553, and F1-score of 0.9558, followed by DenseNet121 (accuracy 0.9433), MobileNetV2 (0.9353), and VGG19 (0.9247). ResNet152 excels in recognizing complex features through its skip connection mechanism, while DenseNet121 is more efficient with the lowest validation loss. MobileNetV2 is the lightest and fastest model, making it suitable for resource-limited devices. Based on the confusion matrix analysis, all models are able to classify the neck blast class perfectly; however, misclassifications still occur among visually similar classes such as brown spot, narrow brown spot, and leaf blast. Overall, transfer learning is proven effective for rice leaf disease classification, with ResNet152 and DenseNet121 being the most recommended models.
IMPLEMENTASI PEMBELAJARAN DIGITAL BERBASIS WEB DALAM MENINGKATKAN KEMAMPUAN BELAJAR MAHASISWA MAGISTER PENDIDIKAN AGAMA ISLAM DI UNIVERSITAS ISLAM ZAINUL HASAN GENGGONG Muhammad Ichsan; Moh. Fadel; Umi Diantika Susilowati; Anisa Nurul Wilda; Wahyu Nofiyan Hadi; Rojil Ghufron; Arya Dwi Nugraha; Syifa Ayu Via Mika Bahrul; Muhammad Mutawakkil Alallah
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.10016

Abstract

Penelitian ini bertujuan untuk mendeskripsikan implementasi pembelajaran digital berbasis web dalam meningkatkan kemampuan belajar mahasiswa Program Magister Pendidikan Agama Islam Pascasarjana Universitas Islam Zainul Hasan Genggong Probolinggo. Penelitian ini menggunakan pendekatan kualitatif deskriptif, dengan pengumpulan data melalui observasi, wawancara mendalam, dan dokumentasi yang melibatkan dosen serta sepuluh mahasiswa program magister. Hasil penelitian menunjukkan bahwa pembelajaran digital berbasis web diimplementasikan melalui pemanfaatan Learning Management System (LMS), situs web interaktif, bahan ajar digital, penugasan daring, serta platform komunikasi akademik digital. Implementasi tersebut berkontribusi terhadap peningkatan pemahaman konseptual mahasiswa, kemandirian belajar, keterampilan digital, partisipasi aktif, serta kemampuan mengintegrasikan materi Pendidikan Agama Islam dengan teknologi. Faktor pendukung implementasi meliputi ketersediaan LMS, komitmen dosen, kebutuhan akademik mahasiswa, dan budaya belajar yang adaptif. Adapun faktor penghambat meliputi tingkat literasi digital yang beragam, pemanfaatan fitur LMS yang belum optimal secara interaktif, kesiapan dosen yang bervariasi, serta kendala teknis pada jaringan internet. Penelitian ini memberikan implikasi bahwa pembelajaran digital berbasis web dapat dikembangkan sebagai strategi pedagogis yang integratif dalam penyelenggaraan pendidikan pada Program Magister Pendidikan Agama Islam.
ANALISIS PERBANDINGAN KINERJA APLIKASI LARAVEL DENGAN DAN TANPA REDIS CACHING DI LINGKUNGAN DENGAN BEBAN TINGGI M. BAHRIL ILMI; Hengki Dwiyan Hermawan
Jurnal Ilmiah Informatika Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/.v11i1.9575

Abstract

Laravel-based web applications are susceptible to significant performance degradation when user traffic increases, primarily due to the repeated execution of identical database queries that put excessive stress on MySQL. This study investigates the extent to which Redis, used as an in-memory caching layer, can offset this stress and measures the performance improvements achieved compared to a baseline configuration without caching. Load testing was conducted using k6s against a Docker-based containerized environment to ensure identical and fully reproducible test conditions. The tests included four concurrent user scenarios: 50, 100, 200, and 500 users, each sustained for 60 seconds. The application stack consisted of Laravel 11.x running PHP 8.3, MySQL 8.0 as the primary data store, and Redis 7.2 as the caching layer. The implemented caching strategies included query caching, route caching, and configuration caching. Observed metrics included response times at the P50, P95, and P99 percentiles, throughput in requests per second, server-side CPU and memory utilization, and error rates. The results showed that Redis reduced response times by 92% on average and increased throughput by up to 947% in a scenario with 500 concurrent users, while error rates remained below 1% across all test scenarios. The performance gap between configurations with and without caching widened consistently as load increased, with the most significant differences becoming apparent in scenarios with 100 users and above. These findings confirm that Redis is a highly effective caching solution for increasing the scalability of Laravel applications and is highly recommended for any deployment serving more than 100 concurrent users. Future research could investigate Redis's behavior under more extreme load conditions and explore adaptive cache invalidation strategies for handling high-frequency data writes.

Page 16 of 16 | Total Record : 158

 12   13   14   15   16 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 1 (2026): Jurnal Ilmiah Informatika Vol. 10 No. 2 (2025): Jurnal Ilmiah Informatika Vol. 10 No. 1 (2025): Jurnal Ilmiah Informatika Vol. 9 No. 2 (2024): Jurnal Ilmiah Informatika Vol. 9 No. 1 (2024): Jurnal Ilmiah Informatika Vol. 8 No. 2 (2023): Jurnal Ilmiah Informatika Vol. 8 No. 1 (2023): Jurnal Ilmiah Informatika Vol. 7 No. 2 (2022): Jurnal Ilmiah Informatika Vol. 7 No. 1 (2022): Jurnal Ilmiah Informatika Vol. 6 No. 2 (2021): Jurnal Ilmiah Informatika Vol. 6 No. 1 (2021): Jurnal Ilmiah Informatika Vol. 5 No. 2 (2020): Jurnal Ilmiah Informatika Vol. 5 No. 1 (2020): Jurnal Ilmiah Informatika Vol. 4 No. 2 (2019): Jurnal Imliah Informatika Vol. 4 No. 1 (2019): Jurnal Imliah Informatika Vol. 3 No. 2 (2018): Jurnal Ilmiah Informatika Vol. 3 No. 1 (2018): Jurnal Imliah Informatika Vol. 2 No. 2 (2017): Jurnal Imliah Informatika Vol. 2 No. 1 (2017): Jurnal Imliah Informatika Vol. 1 No. 1 (2016): Jurnal Imliah Informatika More Issue