cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Sularno
Contact Email
soelarno@unidha.ac.id
Phone
+6282173060361
Journal Mail Official
jurnal.gsp@gmail.com
Editorial Address
Jl. Bhakti Abri, Koto Panjang Ikua Koto, Kecamatan Koto Tangah, Kota Padang
Location
Kota padang,
Sumatera barat
INDONESIA
Jurnal Ilmu Komputer dan Informatika
Published by Global Scients Publisher
ISSN : -     EISSN : 30639026     DOI : https://doi.org/10.62379/jiki
Core Subject : Science, Education, Engineering,
Computer Science & IT Electrical & Electronics Engineering Engineering Mathematics
Jurnal Ilmu Komputer dan Informatika (E-ISSN : 3063-9026 )adalah jurnal ilmiah yang diterbitkan oleh GLOBAL SCIENTS PUBLISHER. Jurnal Ilmiah Komputer dan Informatika diterbitkan secara berkala yaitu 4 kali dalam setahun (pada bulan januari, april, juli dan oktober) yang bertujuan untuk menyebarluaskan berbagai jenis hasil riset dibidang Komputer dan Informatika kepada publik. Saat ini Jurnal Ilmu Komputer dan Informatika menerima kiriman artikel hasil riset dibidang komputer dan informatika yang ditulis dalam Bahasa Indonesia .
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 89 Documents
 5   6   7   8   9 
Analisis Dinamika Kesejahteraan Regional di Sumatera Barat Menggunakan Pooled Clustering K-Means Nurfiah; Anggi Hadi Wijaya
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 2 No. 4 (2026): April - Juni
Publisher : GLOBAL SCIENTS PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62379/jiki.v2i4.1632

Abstract

Ketimpangan kesejahteraan antarwilayah di Provinsi Sumatera Barat memerlukan pemetaan yang akurat sebagai dasar perumusan kebijakan yang tepat sasaran. Penelitian ini bertujuan untuk mengelompokkan tingkat kesejahteraan 19 kabupaten dan kota menggunakan algoritma K-Means Clustering berbasis pendekatan pooled data historis selama periode 2021–2025. Data sekunder bersumber dari Badan Pusat Statistik (BPS) meliputi empat indikator makro, yaitu Indeks Pembangunan Manusia (IPM), Persentase Penduduk Miskin, Tingkat Pengangguran Terbuka (TPT), dan Pengeluaran per Kapita disesuaikan. Melalui evaluasi Elbow Metho diperoleh segmentasi paling optimal yang terbagi menjadi tiga kelompok yaitu Klaster 0 diberi label Daerah Maju, Klaster 1 diberi label Daerah Berkembang, dan Klaster 2 diberi label Daerah Rentan. Pendekatan pooled data yang diterapkan berhasil memetakan transisi positif dari empat wilayah yang sukses naik kelas menuju Klaster 0. Selain itu ditemukan anomali ketenagakerjaan, yang mana daerah maju justru mencatat angka TPT tertinggi akibat fenomena pengangguran terdidik, sementara daerah rentan memiliki TPT terendah akibat tingginya gejala setengah pengangguran di sektor informal. Penelitian ini menyimpulkan bahwa intervensi pembangunan pemerintah daerah harus bersifat asimetris. Daerah maju perlu berfokus pada perluasan investasi sektor kreatif, sedangkan daerah rentan memprioritaskan pengentasan isolasi geografis.
Analisis Komparatif Teknik Quantization (INT4 vs INT8 vs FP16) terhadap Kualitas Output Large Language Model Berbasis Instruksi Ridwan Mahenra; Mahendra Dewantoro
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 3 No. 1 (2026): Juli - September
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

Quantization is a model compression technique that reduces the numerical precision of Large Language Model (LLM) weights to lower memory requirements and accelerate inference. This study presents a comparative analysis of three widely used quantization schemes—INT4, INT8, and FP16—using the Mistral-7B-Instruct-v0.2 model as the subject of study. Evaluation was conducted across five output quality dimensions: BLEU score, ROUGE-L score, perplexity, BERTScore, and average inference latency. Testing utilized 200 instruction prompts covering four task categories: text summarization, factual question answering, code generation, and logical reasoning. The analysis results indicate that INT8 offers the best balance between computational efficiency and output quality, showing an average performance degradation of 2.3% compared to FP16 while achieving a 48% reduction in memory requirements. INT4 exhibited a more significant degradation of 7.8% in logical reasoning tasks, despite successfully reducing memory usage by 74%. These findings provide practical guidance for researchers and practitioners in selecting a quantization scheme suited to available computational resources.
Implementasi Struktur Data Queue pada Sistem Antrian di Puskestren Salafiyah Safi’iyah Alsunil Arobiy; Abd Ghofur; Ach Yusril Ihza Mahendra; Ainur Yakin
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 3 No. 1 (2026): Juli - September
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

Effective healthcare services require a queue management system that can organize service order systematically to minimize patient waiting time. At Puskestren Salafiyah Syafi'iyah, the queuing process is still carried out in a simple manner, which has the potential to cause disorder, service delays, and errors in calling patients. This study aims to implement the Queue data structure as the basis for managing the patient queuing system in order to make the service process more organized, efficient, and fair. The research employs a descriptive approach by analyzing the patient service workflow and applying the First In First Out (FIFO) concept to the queuing system. The implementation of the Queue data structure enables patients who arrive first to receive service first according to their order of arrival. The results indicate that the implementation of the Queue data structure improves the organization of the queuing process, facilitates patient data management, reduces the potential for errors in calling patients, and enhances the efficiency of healthcare services at Puskestren Salafiyah Syafi'iyah. Therefore, the implementation of the Queue data structure can serve as an effective solution to support a more optimal healthcare service system.
Analisis Kinerja Support Vector Machine dalam Memprediksi Pembayaran Kredit Usaha Rakyat Rizcki Dwi Darmawan
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 3 No. 1 (2026): Juli - September
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

The People's Business Credit (KUR) program is vulnerable to Non-Performing Loan (NPL) risks [1]. Conventional credit scoring often fails to objectively map the complex financial variables of customers. This research aims to analyze the performance of the Support Vector Machine (SVM) algorithm in predicting KUR payment feasibility by comparing four kernel functions: Linear, Radial Basis Function (RBF), Polynomial, and Sigmoid. The dataset comprises 398 financial records from Bank XYZ with an extreme class imbalance (80:20). The model was trained using 9 initial financial capacity features, Z-score standardization, and GridSearchCV optimization [9]. Performance evaluation focused on the Confusion Matrix to detect the Accuracy Paradox on imbalanced data [6]. The results showed that the Polynomial Kernel achieved the highest Accuracy (73.75%) and F1-Score (84.67%) but suffered from the Accuracy Paradox by failing to detect the minority class, misclassifying 14 Default customers as Eligible. Conversely, the RBF Kernel (C = 0.1, γ = 2) demonstrated the best and most rational performance, balancing the margin to correctly detect 6 Default customers while maintaining high precision for the Eligible class.
Purwarupa Sistem Peringatan Dini Kebakaran Berbasis IoT dengan ESP32-CAM dan Notifikasi Telegram Andreas Jurdil Widiarsa
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 3 No. 1 (2026): Juli - September
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

Warehouses that store cardboard boxes carry a high fire risk because the stored material is highly flammable and a fire can spread quickly once it starts. Monitoring in many such warehouses still relies on periodic human checks, so the appearance of smoke or flame is often noticed late, which can increase the resulting loss. This study designs and builds an Internet of Things (IoT)-based prototype that detects fire indications, issues an early warning, and performs an initial suppression action in a cardboard box warehouse. The prototype uses an MQ-2 sensor to sense smoke and a flame sensor to sense fire directly, both connected to an ESP32-CAM acting as the main controller. Once a hazard is detected, the ESP32-CAM switches on a buzzer, drives a relay that activates a mini water pump, captures a photo through its onboard OV2640 camera, and forwards the photo together with a warning message to the user through a Telegram bot. Functional testing shows that the prototype detects smoke and flame accurately, triggers the buzzer and pump in under one second, and delivers the Telegram notification with photo within three to five seconds. These results indicate that the prototype can support faster fire detection and a quicker initial response in cardboard box warehouses.
Perancangan dan Pembangunan Sistem Informasi E-Surat RT/RW untuk Pelayanan Administrasi Surat Berbasis Web pada Kelurahan Padang Besi Muhammad Ikhsan
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 3 No. 1 (2026): Juli - September
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

Mail administration services in Padang Besi Village still rely on manual processes that require residents to come in person, submit physical documents, wait for verification, and then pick up their letters, resulting in long queues and poorly structured archives. This study designed and built a web-based RT/RW e-Mail Information System in Padang Besi Village to digitize the flow of letter submission, verification, and issuance. The system provides user registration, online letter submission, uploading required documents, verification by officers, letter data management, and automatic letter generation in PDF format using templates. Implementation and testing results indicate that the system makes it easier for residents to submit letters and assists RT/RW officers in managing, monitoring the process, and storing archives in a structured manner. Thus, it is hoped that mail administration services in Padang Besi Village will be faster, more effective, transparent, and digitally documented.
Rancang Bangun Aplikasi Kasir Sederhana Warung Makan Berbasis WEB Untuk Otomatisasi Transaksi Penjualan Mohamad Iqbal Ulumando
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 2 No. 4 (2026): April - Juni
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

Perkembangan teknologi informasi memberikan peluang besar dalam meningkatkan efisiensi pengelolaan usaha kecil, termasuk warung makan. Salah satu permasalahan yang sering dihadapi adalah proses transaksi penjualan yang masih dilakukan secara manual, sehingga berpotensi menimbulkan kesalahan pencatatan dan perhitungan. Penelitian ini bertujuan untuk merancang dan membangun aplikasi kasir sederhana warung makan berbasis web sebagai solusi untuk mengotomatisasi proses transaksi penjualan. Metode penelitian yang digunakan meliputi tahap analisis kebutuhan, perancangan sistem, implementasi, dan pengujian fungsional. Aplikasi dikembangkan menggunakan bahasa pemrograman PHP dengan basis data MySQL serta didukung oleh HTML dan CSS sebagai antarmuka pengguna. Hasil penelitian menunjukkan bahwa aplikasi yang dibangun mampu mengelola data menu makanan dan minuman, memproses transaksi penjualan, menghitung total pembayaran dan kembalian secara otomatis, serta menyimpan riwayat transaksi dengan baik. Dengan demikian, aplikasi kasir berbasis web ini dapat membantu meningkatkan efisiensi, ketelitian, dan kemudahan dalam pengelolaan transaksi penjualan pada warung makan.
Pengembangan Sistem Informasi Terintegrasi Untuk Manajemen Barbershop Berbasis Web Pada Styling House.Co Ahmad Fikri Fajri; Eka Iswandy
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 3 No. 1 (2026): Juli - September
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

The rapid development of information technology has encouraged businesses to implement information systems to improve service quality and operational efficiency, including barbershop businesses. Styling House.Co Barbershop still performs most of its business processes manually, including customer data management, service management, and reservation recording. These manual processes often lead to recording errors, difficulties in retrieving information, and inefficient customer service.This research aims to design and develop a web-based information system for Styling House.Co Barbershop using the CodeIgniter 4 framework and the Waterfall software development methodology. The development stages include requirements analysis, system design using Unified Modeling Language (UML), implementation using PHP, HTML, CSS, JavaScript, and MySQL database, followed by system testing using the Black Box Testing method.The developed system successfully improves customer data management, service management, employee management, online booking, payment processing, and report generation. Furthermore, the system provides customers with easier access to service information and online reservations, resulting in better service quality and more efficient business operations
Klasterisasi Citra Kucing dan Anjing Menggunakan Algoritma K-Means untuk Identifikasi Hewan Peliharaan Berbasis Visi Komputer Charisman Fajri Saputra; Intan Utnasari
Jurnal Ilmu Komputer dan Informatika | E-ISSN : 3063-9026 Vol. 3 No. 1 (2026): Juli - September
Publisher : GLOBAL SCIENTS PUBLISHER

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

Abstract

Automatic identification of pets, especially cats and dogs, is a challenge in the field of computer vision. K-Means Clustering can be utilized to classify cat and dog images based on visual features such as color, shape, and texture. This study aims to analyze the effectiveness of the K-Means algorithm in distinguishing between these two animal species. The methodology includes dataset collection consisting of 8 images (4 images of cats and 4 images of dogs), image preprocessing through normalization and color feature extraction, and K-Means implementation with K = 2 clusters. Evaluation is conducted using the Silhouette Score to measure clustering quality. The results indicate that K-Means achieves a classification accuracy of 100% due to the small dataset size and the distinct visual differences between the two animals. The findings suggest that K-Means can serve as an initial approach for automatic pet identification, but further validation with larger and more diverse datasets is needed. Improvements through advanced clustering techniques or integration with deep learning models are also recommended for higher accuracy.

Page 9 of 9 | Total Record : 89

 5   6   7   8   9 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2026): Juli - September Vol. 2 No. 4 (2026): April - Juni Vol. 2 No. 3 (2026): Januari - Maret Vol. 2 No. 2 (2025): Oktober - Desember Vol. 2 No. 1 (2025): Juli - September Vol. 1 No. 4 (2025): April - Juni Vol. 1 No. 3 (2025): Januari - Maret Vol. 1 No. 2 (2024): Oktober - Desember Vol. 1 No. 1 (2024): Jurnal Ilmu Komputer dan Informatika