cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
jurnal@if.uinsgd.ac.id
Editorial Address
Gedung Fakultas Sains dan Teknologi Lt. 4 Jurusan Teknik Informatika Jl. A.H. Nasution No. 105 Cibiru Bandung 40614 Telp. (022) 7800525 / Fax (022) 7803936 Email : jurnal@if.uinsgd.ac.id
Location
Kota bandung,
Jawa barat
INDONESIA
JOIN (Jurnal Online Informatika)
Published by Universitas Islam Negeri Sunan Gunung Djati Bandung
ISSN : 25281682     EISSN : 25279165     DOI : 10.15575/join
Core Subject : Science,
Computer Science & IT
JOIN (Jurnal Online Informatika) is a scientific journal published by the Department of Informatics UIN Sunan Gunung Djati Bandung. This journal contains scientific papers from Academics, Researchers, and Practitioners about research on informatics. JOIN (Jurnal Online Informatika) is published twice a year in June and December. The paper is an original script and has a research base on Informatics.
Arjuna Subject : -
Articles 8 Documents
 1 
Search results for , issue "vol 11 no 2 (2026)" : 8 Documents clear
Integrating Portable Systems of Edge Computing Pocket Data Centers for Modernising MSME Services Norma Ningsih; Prima Kristalina; Bintang Desta Ramadhani
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1432

Abstract

Micro, Small, and Medium Enterprises (MSMEs) play a crucial role in local economic growth by generating employment opportunities. However, their digital transformation is often hindered by high server infrastructure costs and limited access to efficient computing resources. To address these challenges, this study develops an edge computing-based pocket data center system designed to process transactions efficiently, affordably, and portably. The system integrates virtualization technologies such as virtual machines, Docker, Kubernetes, Ubuntu, and the LAMP stack to support MSME applications. The HAProxy load balancer employs a round-robin algorithm to optimize workload distribution. Experimental testing over five minutes with 9,000 total requests demonstrated the system's capability to handle all user requests with a latency of 367 ms, a throughput of 29.4 requests per second, and a processing rate of 30 requests per second. The system also exhibited efficient power consumption at 9.01 watts while achieving a 100% success rate in request completion. Compared to conventional server solutions, this approach significantly enhances accessibility, cost-efficiency, and scalability for MSMEs. These findings highlight the potential of low-cost, portable data centers to modernize MSME operations, ensuring reliability and high performance in the digital economy.
Color Space Transformation to Identify the Disappearance of Syafaq as the Beginning of Isha Prayer Rusli; Niswatul Kariimah; Utiyah Hikmah; Ibnor Azli Ibrahim
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1621

Abstract

Early prayer times began to be widely discussed in the past few years, since several opinions said that the beginning of prayer isha’ and shubuh need to be corrected. This study focused on image processing approach to analyze the disappearance of syafaq rays as an early sign of the start of the Isha’ prayer. The imagery data were taken in Lombok and Masalembu then transformed into different color spaces. RGB data transform to YUV, YCbCr, and L*a*b* spaces. The main contribution is evaluating these models to establish an objective, sensor-based baseline. Conceptually, L*a*b* is superior because it isolates chromaticity from luminance*, allowing the a∗ channel to track the vanishing reddish hue without being obscured by total light fluctuations. From L*a*b* color spaces have sensitively identified the disappearance of syafaq. A uniform typology of graphs was obtained in 4 color spaces as a sign that the initial physical analysis of beginning isha’ times. A uniform graphic typology was obtained, where the Isha' time is marked by a plateau (flattening curve), indicating the rays have completely vanished. Results of the start of prayer times with color space transformation to identify the start of isha times close to the agreement in Indonesia.
Increasing Plaintext Indistinguishability in Honey Encryption using Context Relation-based Decoy Chat Message Yusril Firza; Ari Moesriami Barmawi
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1776

Abstract

General encryption method provides a low level of security against brute-force attacks, which attempt every possible key through the decryption process. The Honey Encryption (HE) method was developed to overcome these problems. However, the latest development of HE implemented in chat conversations results in conversations that do not correlate between one chat and another when the ciphertext is decrypted using the wrong key (decoy message). The absence of context relation in the decoy message results in the decryption results of the brute force attack becoming easy to analyze, which can make it possible for the adversary to obtain the correct decryption results and map the keys used. This study aims to improve the context relation or contextual naturalness between chats in HE decoy messages. This improvement is intended to generate contextually natural sentences such that an attacker cannot distinguish between messages decrypted using the correct key and those decrypted using the incorrect key. This process reduces the likelihood of success during a brute-force attack for obtaining the plaintext and the key.. A contextual naturalness decoy message is generated by utilizing keyword detection (KeyBERT) and keyword alternative mapping as key points for context generation. Additionally, the generated keywords are used in sentence generation with a Masked Language Model (in this study, Electra) for generating word candidates. The implementation of KeyBERT and Electra in this study shows that 22 out of 32 decoy chat messages can be categorized as natural conversations. Finally, it can be concluded that the proposed method has contextual relation between decoy chat messages.
Text Simplification Research: A Systematic Literature Review on Languages, Datasets, and Modeling Trends Lisnawita; Juhaida Abu Bakar; Ruziana Mohamad Rasli
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1792

Abstract

Text simplification (TS) is a Natural Language Processing (NLP) task that reduces linguistic complexity while preserving meaning and supports accessibility for different reader groups (e.g., children, second-language learners, and readers with cognitive or reading difficulties). TS studies are diverse in languages, datasets, and methods. Therefore, a consolidated overview is needed to summarize trends and guide future research. This study conducts a Systematic Literature Review (SLR) of TS research published from 2015 to 31 July 2025 to map trends in languages, target audiences, datasets/corpora, techniques, models/algorithms, and frameworks. Relevant literature was searched using IEEE Xplore, ScienceDirect (Elsevier), SpringerLink, and Google Scholar, applied predefined inclusion–exclusion criteria, and screened studies using a PRISMA-style process. The final set includes 75 primary studies. The results show that English dominates TS research, commonly used resources include Wikipedia-family datasets and Newsela, and modeling trends shift from rule-based and classical machine learning toward transformer-based architectures (e.g., BERT and Seq2Seq) and large language models (LLMs). This review offers: (1) a structured overview of TS research dimensions, (2) an evidence-based summary of key resources and modeling trends, and (3) recommendations for future research, particularly for low-resource languages and audience-specific evaluation.  
Static QR Code Indonesian Standard Protection using Visual Cryptography Aprianti Nanda Sari; Siti Dwi Setiarini; Eddy Bambang Soewono; Muhammad Reivan Naufal Mufid; Yazid Fauzan Prasatria
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1796

Abstract

The QR Code Indonesian Standard (QRIS) is widely used in digital payments across Indonesia, offering convenience but also introducing security risks such as quishing, QR code phishing, also known as quishing, attacks that redirect payments to fraudulent accounts. This study proposes a visual cryptography-based method to enhance the security of static QRIS. The proposed method employs a (2,2)-threshold visual cryptography scheme to split a static QRIS into two shares, held separately by the merchant and the customer, such that the original QR code can only be reconstructed when both shares are combined. A mobile-based prototype was implemented, incorporating fiducial marker detection, tilt correction, and image binarization to support accurate share reconstruction under real-world conditions. Experimental evaluation was conducted through 15 reconstruction trials using various smartphones and display conditions. The results show a reconstruction success rate of 80% (12 out of 15 trials), while 20% of attempts failed due to low camera resolution and complex background patterns that interfered with marker detection and binary conversion. Compared to existing QRIS security approaches that rely on dynamic QR codes or location-based verification, the proposed method offers a novel share-based protection mechanism specifically tailored to static QRIS. These findings indicate that visual cryptography can effectively mitigate quishing attacks on static QRIS, although its practical deployment remains dependent on environmental and device-related constraints.
EKF-LSTM for Hospital Pharmaceutical Demand Forecasting: A One-Step Ahead Hybrid Framework Andung Harjito; Wayan Firdaus Mahmudy; Mahendra Data
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1808

Abstract

Accurate pharmaceutical demand forecasting in hospitals is essential for optimization, as inaccurate demand predictions lead to drug shortages, overstocking, and increased operational costs. Although the integration of the Extended Kalman Filter (EKF) with Long Short-Term Memory (LSTM) has shown potential in various domains, its application to hospital pharmaceutical sales prediction remains underexplored. This study proposes a hybrid EKF-LSTM model that leverages recursive state estimation to stabilize learning during zero-demand periods, effectively handling non-linear and zero-inflated drug sales time-series. The model was evaluated on eight drug commodities (2022–2024) using time-series cross-validation with one-step-ahead forecasting and compared against LSTM, GRU, Random Forest, XGBoost, PatchTST, and ARIMA using MAE, MSE, RMSE and MAPE. EKF-LSTM achieved the lowest aggregate error (MAE: 78.33 ± 54.12 units; RMSE: 95.67 ± 68.45 units), yielding 51.7% lower RMSE than LSTM, the second-best method. For items with continuous demand, MAPE was as low as 18.16%. A Diebold-Mariano test confirmed a statistically significant superiority over PatchTST (p = 0.018). These findings indicate that the EKF-LSTM hybrid model provides a robust solution for hospital pharmaceutical inventory planning, reducing stockouts and overstocking while improving overall operational efficiency.
IoT-based Spatiotemporal Smart Air Quality Monitoring and Analysis System with a Machine Learning Approach Eddy Prasetyo Nugroho; Ani Anisyah; Yogi Prasetyo; Muhammad Nur Yasin Amadudin; Jason Rafif Pangestu Suryoatmojo; Franklin Impianro Turnip; Jidan Abdurahman Aufan; Deva Shofa Al Fathin
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1809

Abstract

Air quality plays an important role in the sustainability of life, especially for humans. Human activities, such as industry and motorised vehicles, have increased air pollution, particularly fine particulates (PM1.0, PM2.5, PM10) and carbon monoxide (CO), which have serious impacts on health. In Bandung City, the Environmental Agency recorded high levels of pollution, so a real-time air quality monitoring system is needed. This research aims to develop an Internet of Things (IoT)-based air pollution monitoring system in various locations in Bandung, focusing on spatial-temporal analysis during weekdays and weekends. The IoT sensors used are capable of detecting pollutants such as PM1.0, PM2.5, PM10, and CO, thus enabling continuous air quality monitoring. Based on the average Air Pollution Standard Index (ISPU) scores, the monitored locations show that CO pollution levels are higher than PM. Besides, PM particulates and CO are dominant on weekdays. The result of model prediction between LSTM and GRU model is GRU model having low value based on RSME and MRE indicator and making it a better model.  The system was successfully designed and implemented, allowing air quality data and analysis results to be accessed in real-time through a website that is easy to use by the public.  
Hybrid S-box Construction over GF(2⁸) Using Irreducible Polynomial and Affine Transformation Alamsyah; Yusuf Muhammad; Budi Prasetiyo; Yahya Nur Ifriza; Much Aziz Muslim; Shahrul Nizam Salahudin; Nur Atiqah Sia Abdullah; Yusuf Wisnu Mandaya
JOIN (Jurnal Online Informatika) Vol 11 No 2 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i2.1841

Abstract

The S-box, also known as the substitution box, is an essential component in symmetric encryption because it provides the nonlinear mapping required to transform input bits into output bits. The most widely used S-box is the AES S-box, which is constructed using the irreducible polynomial, an 8×8 affine matrix with the first row (10001111), and an 8-bit constant (01100011). This study presents a Hybrid S-box construction over GF(2⁸) that combines irreducible-polynomial arithmetic and affine transformation to obtain a secure and lightweight substitution mapping. The proposed method uses the irreducible polynomial, an 8×8 affine matrix with the first row (01010111), and an 8-bit constant (00000000). The originality of this research lies in combining polynomial-based finite-field inversion and affine bit mixing to produce a reproducible Hybrid S-box design that balances cryptographic strength and implementation efficiency. The resulting Hybrid S-box is evaluated using six standard cryptographic indicators: Nonlinearity (NL), Strict Avalanche Criterion (SAC), Bit Independence Criterion in terms of nonlinearity (BIC-NL) and avalanche (BIC-SAC), Differential Uniformity (DU), and Algebraic Degree (AD). The experimental results show that the proposed Hybrid S-box achieves NL = 112, SAC = 0.49756, BIC-NL = 112, BIC-SAC = 0.50119, DU = 4, and AD = 7. Compared with the AES S-box and recent S-box designs, the proposed Hybrid S-box attains AES-level nonlinearity and differential uniformity while producing SAC and BIC-SAC values closer to the ideal value of 0.5. These findings indicate that the proposed Hybrid S-box can enhance data security in Internet of Things devices, embedded controllers, and smart-card platforms. This work also supports Sustainable Development Goal 9 by contributing to secure, resilient, and resource-efficient digital infrastructure.  

Page 1 of 1 | Total Record : 8

 1 

Filter by Year

2026 2026


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