cover
Contact Name
Errissya Rasywir
Contact Email
errissya.rasywir@gmail.com
Phone
+6285809949385
Journal Mail Official
errissya@unama.ac.ic
Editorial Address
Jl. Jendral Sudirman. Thehok. Kecamatan Jambi Selatan. 36138.Jambi City Jl. A. Tarmizi Kadir. No.04. RT 05. Kelurahan Pakuan Baru. Kecamatan Jambi Selatan. 36138.Jambi City
Location
Kota jambi,
Jambi
INDONESIA
Jurnal Informatika dan Rekayasa Komputer
ISSN : 28085469     EISSN : 28085000     DOI : https://doi.org/10.33998/jakakom.v3i1
Core Subject : Science,
Jurnal Informatika Dan Rekayasa Komputer (JAKAKOM) merupakan jurnal yang berada dibawah naungan Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) Universitas Dinamika Bangsa dan diterbitkan oleh Universitas Dinamika Bangsa Jambi. Jurnal Informatika Dan Rekayasa Komputer (JAKAKOM) menerbitkan jurnal 2 kali dalam setahun yaitu pada bulan September dan April. Misi dari Jurnal Informatika Dan Rekayasa Komputer (JAKAKOM) adalah untuk menyebarluaskan, mengembangkan dan memfasilitasi hasil penelitian bidang informatika dan rekayasa komputer.
Articles 234 Documents
Implementasi Data Mining Untuk Menentukan Persediaan Barang Di Mahkota Mart Menggunkan K-Means Dina Sunia; Jasmir Jasmir; Benni Purnama
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 1 (2026): JAKAKOM Vol 6 No 1 APRIL 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.1.2404

Abstract

Mahkota Mart is experiencing stock management problems. This minimarket often encounters mismatches between available stock and sales levels, leading to either shortages or excess inventory. To address this issue, data mining techniques using the K-Means Clustering method are needed to group sales data based on similar product characteristics, thereby facilitating more efficient stock management. The results of this research, processed using tools such as RapidMiner, show that the items in Mahkota Mart can be grouped into three clusters: Cluster 0 includes 61 items (21.40%), categorized as highly in-demand items; Cluster 1 includes 218 items (76.49%), categorized as moderately in-demand items; and Cluster 2 includes 6 items (2.11%), categorized as non-selling items. It is recommended to always replenish the stock of items in Cluster 0. For items in Cluster 1, stock should be added, but in smaller quantities than for Cluster 0. Items in Cluster 2 are recommended not to be restocked to avoid accumulation.
SLR Dengan Metode PRISMA: Perbandingan Sistem Keamanan Pada Sistem Operasi Windows Dan Linux : Comparison of Security Systems in Windows and Linux Operating Systems Meisya Amalia; Herbert Siregar
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 1 (2026): JAKAKOM Vol 6 No 1 APRIL 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.1.2407

Abstract

This study aims to compare the security systems of Windows and Linux operating systems using a Systematic Literature Review (SLR) method with the PRISMA approach. Literature from 2020 to 2025 was analyzed from four academic databases: Google Scholar, Scopus, IEEE Xplore, and ScienceDirect. The findings reveal that Linux is superior in security configuration flexibility, resource efficiency, and responsiveness to cyber threats through open-source community support. In contrast, Windows excels in integrated security automation and user-friendliness. These findings indicate that the effectiveness of security systems is highly influenced by the usage context and user understanding of the operating system. Therefore, Linux is more suitable for professional environments requiring high system control, while Windows is more user-friendly for general users.
Analysis of Educational Equity in Indonesia Based on Interactive Dashboard Visualization Mukhtada Billah Nasution; Tia Marcelin; Ismayani; Mutia Fadhila Putri; Pradita Eko Prasetyo Utomo
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 2 (2026): JAKAKOM Vol 6 No 2 SEPTEMBER 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.2.2425

Abstract

Educational inequality remains a major challenge in achieving equitable and inclusive education in Indonesia. Geographical disparities, uneven distribution of infrastructure, and low school participation rates hinder the nation's human capital development. This study aims to develop interactive dashboards using Tableau Public to visualize national education indicators and support data-driven decision-making. The method used is Exploratory Data Analysis (EDA) to extract patterns and trends from data. Three dashboards were designed: Education Profile, Educational Infrastructure, and Access and Equity in Education. The data, sourced from Indonesia's Central Statistics Agency (BPS), was processed through an ETL (Extract, Transform, Load) pipeline and visualized interactively. Results highlight significant disparities among provinces in terms of average years of schooling, facility availability, and school participation rates. The use of interactive dashboards proves effective in simplifying complex datasets into comprehensible, relevant, and actionable insights for stakeholders.
Implementasi Neural Networks Untuk Prediksi Seseorang Terjangkit Diabetes Dengan Keras Pramudityo Agung Nafianto; Firda Ayu Hassanah
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 1 (2026): JAKAKOM Vol 6 No 1 APRIL 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.1.2479

Abstract

Diabetes is a disease with a rising prevalence worldwide. Early prediction of diabetes can enable timely interventions and management, which in turn can help reduce the adverse impact of this disease. In this study, use employed a Machine Learning approach using Neural Network to predict whether an individual will develop diabetes within the next 5 years. The prediction process involved preprocessing stages such as filtering, normalization, handling missing data, and feature transformation if necessary. Subsequently, the dataset was divided into training and testing data. The training data was used to train the Neural Network model, while the testing data was used to evaluate the model's performance. Based on our study, after training the Neural Network model, we achieved an accuracy rate of 71%. The prediction was further tested on 10 sample data, where 7 out of 10 predictions matched the output in the dataset. These findings demonstrate the effectiveness of the Neural Network method in predicting diabetes data. This result has the potential to enhance our understanding of the risk factors contributing to the development of diabetes and contribute to the development of better predictive approaches in the prevention and management of this disease. With accurate early prediction, timely interventions and management can be implemented, thereby helping to mitigate the adverse impact of this disease.
Rancang Bangun Website E-Commerce Untuk UMKM Terintegrasi MIDTRANS Dan RajaOngkir (Studi Kasus : Ikobana Frozen Food) Muhammad Fadhlan Aziz; Intan Purnamasari, M.Kom; Carudin
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 1 (2026): JAKAKOM Vol 6 No 1 APRIL 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.1.2481

Abstract

Usaha Mikro, Kecil, dan Menengah (UMKM) memiliki peran penting dalam perekonomian Indonesia. Namun, banyak UMKM, seperti Ikobana Frozen Food, masih menghadapi kendala dalam pengelolaan pesanan dan jangkauan pasar karena proses pemesanan masih dilakukan secara manual. Penelitian ini bertujuan untuk merancang dan membangun website e-commerce terintegrasi untuk Ikobana Frozen Food guna mendukung digitalisasi proses bisnis. Sistem dikembangkan menggunakan metode Software Development Life Cycle (SDLC) dengan model Scrum untuk memungkinkan pengembangan iteratif dan adaptif. Teknologi yang digunakan meliputi Next.js (frontend), Golang (backend), dan PostgreSQL (database), serta layanan tambahan seperti Midtrans untuk integrasi pembayaran digital dan RajaOngkir untuk perhitungan ongkos kirim otomatis. Selain itu, fitur pengiriman gratis untuk wilayah tertentu juga diimplementasikan sebagai strategi peningkatan loyalitas pelanggan. Hasil pengujian menunjukkan bahwa sistem berjalan stabil dan sesuai dengan fungsionalitas yang dirancang. Pengujian dilakukan melalui metode white box testing dan black box testing untuk memastikan keandalan logika program dan validasi terhadap alur penggunaan sistem. Website ini berhasil menggantikan proses manual, meningkatkan efisiensi operasional, serta memperluas jangkauan pasar Ikobana Frozen Food. Penelitian ini membuktikan bahwa digitalisasi melalui pengembangan website e-commerce dapat menjadi solusi strategis bagi UMKM dalam menghadapi tantangan bisnis di era digital.
Design and Development of a Café Raw Material Inventory Management Information System Using Laravel and the Waterfall Method: A Case Study of Kafe Sugriwa Subali R. Fajar Dwi Novianto; Yudi Sutanto
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 2 (2026): JAKAKOM Vol 6 No 2 SEPTEMBER 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.2.2512

Abstract

Abstract Kafe Sugriwa Subali, a culinary SME in Kulon Progo, faces significant operational challenges due to its conventional inventory management system. The manual process of recording raw material stock directly impacts business operations, leading to frequent data errors, the risk of record loss, and delays in stock availability information. The most critical impact is the inability to consistently serve its menu, which can decrease customer satisfaction and hinder business growth. The research method employed to solve this problem is the Waterfall system development model. This process was executed through four structured and sequential stages: requirements analysis, system design, implementation using the Laravel framework, and system testing using the black box method to validate all its functionalities. The final result of this research is a functional and validated web-based information system for raw material stock management. Black box testing demonstrated that 100% of the system's functionalities, including the low-stock notification feature, perform successfully. The main contribution of this research is providing a ready-to-use technological solution to improve data accuracy and operational efficiency. These results can be directly utilized by the owner and staff of Kafe Sugriwa Subali and can serve as a reference for similar SMEs facing similar issues.
Perancangan Sistem Pengelolaan Penerimaan Beasiswa Berbasis Web Pada Universitas Batanghari Jambi Jatriyono; Facruddin; Sharipuddin; Gunardi
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 1 (2026): JAKAKOM Vol 6 No 1 APRIL 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.1.2567

Abstract

The purpose of this study is to develop and implement an internet-based scholarship management system at Batanghari University in Jambi. The previous manual process was considered inefficient, unclear, and difficult to access, especially for students outside the region. As a result, student engagement was low and the administrative burden increased. The main objective of this study is to improve convenience, effectiveness, and user experience during scholarship registration and monitoring. The methodology used is the Waterfall model, which includes needs analysis, design using UML diagrams, database structure, and implementation with PHP and MySQL. The system created includes features for online account registration, secure login, digital application and document submission, administrator verification, automatic selection, real-time announcement of results, and comprehensive reporting. The results of the study show that the system can digitize and simplify the scholarship admission process while increasing transparency and efficiency. Students, including those who do not live in Jambi, can easily register and monitor the status of their scholarships. Now, all data is stored in a MySQL database, which offers better governance. Therefore, this system helps universities realize smart campuses and provide equal access to education.
Perancangan Aplikasi Computer Vision Berbasis Convolutional Neural Network Untuk Deteksi Kematangan Kelapa Sawit Heri Setiawan; Kurniabudi; Sharipuddin; Gunardi
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 1 (2026): JAKAKOM Vol 6 No 1 APRIL 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.1.2568

Abstract

Manual determination of oil palm fruit maturity remains a significant challenge for farmers, leading to inefficiencies and reduced harvest quality. This research aims to design and implement a computer vision application based on Convolutional Neural Network (CNN) to automatically, objectively, and efficiently detect oil palm fruit maturity. The methodology involves web-based system development using the Waterfall model, integrating a modified YOLOv5s architecture enhanced with a Convolutional Block Attention Module (CBAM), C3 Transformer (C3TR), and Bidirectional Feature Pyramid Network (BiFPN). A dataset of 4160 oil palm fruit images underwent auto-orient, resize, color normalization, and data augmentation, then split into 70% training, 20% validation, and 10% test sets. Model training was conducted on Google Colab using an Nvidia A100 GPU for 21.36 minutes. Evaluation results demonstrate very high performance with a Precision of 0.9858, Recall of 0.9910, mAP@0.5 of 0.9941, and mAP@0.5:0.95 of 0.8544. The Confusion Matrix and Precision-Recall curve indicate excellent classification accuracy and strong model generalization capabilities. The web-based system allows farmers to upload images or videos and use a webcam for real-time detection. This application is expected to assist farmers in identifying oil palm fruit maturity more quickly and objectively, minimizing errors, and improving harvest quality and efficiency.
Comparison of Machine Learning Algorithms for Classifying Scientific Journal Article Titles in the Computer Science Field Muhammad Fadhillah; Dodo Zaenal Abidin; Jasmir
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 2 (2026): JAKAKOM Vol 6 No 2 SEPTEMBER 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.2.2591

Abstract

The increasing number of scientific publications in the computer science field poses challenges for automatic classification of article titles, which tend to be short, ambiguous, and contain domain-specific technical terms. This study aims to compare the performance of three machine learning algorithms—k-Nearest Neighbor (kNN), Naïve Bayes, and Random Forest—in classifying the titles of computer science journal articles into five main topics: AI & Machine Learning, UI/UX, IT Framework, IoT, and Cybersecurity. A dataset of 2,449 article titles was collected from the SINTA portal and underwent text preprocessing steps including tokenization, case normalization, stopword removal, and stemming, followed by numerical representation using TF-IDF weighting. Models were trained and tested using separate datasets and evaluated based on accuracy, precision, recall, and F1-score. The results show that kNN (k=51) achieved the highest accuracy of 89.61% with consistent precision, recall, and F1-score across all categories. Random Forest ranked second with 81.46% accuracy, showing strong performance in categories such as Cybersecurity and AI & Machine Learning, although it suffered a significant drop in recall for Cybersecurity. Naïve Bayes recorded the lowest accuracy (71.35%) but achieved the fastest execution time (12 seconds). These findings emphasize that algorithm selection should consider data characteristics, particularly for short-text classification such as article titles, and indicate that kNN is the most stable and accurate choice in this context.
Implementasi Sistem Pakar Pada Penyakit Kulit Menggunakan Metode Certainty Factor Rikardus Mbusa; Sebastianus Adi Santoso Mola; Arfan Yeheskiel Mauko
Jurnal Informatika Dan Rekayasa Komputer(JAKAKOM) Vol 6 No 1 (2026): JAKAKOM Vol 6 No 1 APRIL 2026
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jakakom.2026.6.1.2607

Abstract

Skin diseases in humans are disorders that affect the outermost layer of the body, characterized by symptoms such as itching, redness, and skin infections. These conditions may be caused by exposure to sunlight, viral infections, weakened immune systems, as well as the presence of fungi, bacteria, or parasites. This study aims to develop an expert system capable of diagnosing skin diseases based on the symptoms experienced by patients, using the Certainty Factor (CF) method. The Certainty Factor method itself is a technique used to measure the degree of uncertainty in knowledge-based systems, allowing for more accurate diagnostic outcomes. The system was tested using 100 test data entries encompassing various types of skin diseases, including morbus hansen, herpes zoster, contact dermatitis, tinea versicolor, tinea corporis, scabies, and psoriasis vulgaris. Each diagnosis is accompanied by a CF value that indicates the probability or confidence level. The results of the system testing showed an accuracy rate of 100%. With this optimal accuracy, the expert system is expected to serve as an early detection tool for skin diseases, providing reliable initial diagnoses and supporting treatment decision-making.