cover
Contact Name
Muhammad Yusuf Mappeasse
Contact Email
jtei@unm.ac.id
Phone
+628114946666
Journal Mail Official
jtei@unm.ac.id
Editorial Address
l. Dg. Tata Raya, Parangtambung, Makassar, Sulawesi Selatan Ged. Jurusan Pendidikan Teknik Elektro Lt.2, Fakultas Teknik, Universitas Negeri Makassar.
Location
Kota makassar,
Sulawesi selatan
INDONESIA
Journal of Electrical Engineering and Informatics
ISSN : -     EISSN : 3025213X     DOI : 10.59562
Journal of Electrical Engineering and Informatics is a scientific journal managed by a peer review process. The Journal of Electrical Engineering and Informatics is published by the Department of Electrical Engineering Education, Universitas Negeri Makassar. The Journal of Electrical Engineering and Informatics publishes research papers and literature reviews in the fields of Electrical Engineering, Informatics and Computer Engineering, and Control.
Articles 46 Documents
Literature Review: The Application of Deep Learning in Web Attack Detection Sapuan Sapuan
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12206

Abstract

This research is motivated by the increasing need for web security systems along with the rapid development of web-based applications and the rise of cyber threats such as Cross-Site Scripting (XSS), SQL Injection (SQLi), and HTTP manipulation. This study aims to review the application of Deep Learning methods in web attack detection with a focus on frequently used algorithms, model performance, and challenges faced. This study uses a systematic literature study approach by analyzing various relevant scientific publications. Data were collected from reliable literature sources and analyzed qualitatively to identify patterns, methods, and research gaps. The results of the study indicate that Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) algorithms are the most widely used methods and have good performance in detecting web attacks. However, several obstacles remain such as limited representative datasets, data imbalance, and high computational requirements. This study contributes in the form of a comprehensive synthesis of the application of Deep Learning in web security, as well as identifying research gaps and development opportunities to improve model effectiveness and efficiency, particularly in the implementation of real-time attack detection.
Design of Literacy and Numeracy Learning Website for Elementary School Students Using the OOAD Approach Ayu Tri Wardani Wardani; Alifya NFH
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12215

Abstract

This study designed an integrated web-based learning platform for literacy and numeracy that supports multiuser roles (students, teachers, and administrators) through interactive content, gamification, contextual assessment, and real-time learning analytics. This research and development study employed the object-oriented analysis and design (OOAD) methodology, focusing specifically on the micro process stages (identifying elements, defining collaborations, defining relationships, and detailing semantics). Data were collected through interviews with elementary school teachers, documentation of curriculum and learning materials, and literature studies. The study successfully produced a comprehensive system design featuring an integrated platform with learning content modules, gamification (games), interactive assessments with detailed question management, student progress tracking, and a teacher dashboard for learning analytics. The design includes a complete UML model, database structure, and modular 3-Tier MVC architecture that ensures scalability and maintainability. This study offers a novel contribution by providing a holistic, integrated OOAD-based website design specifically for elementary literacy and numeracy education in the Indonesian context. Unlike previous standalone digital media, this system combines gamification, contextual assessment with detailed question handling, and real-time analytics within a single modular platform.
Analysis of Voltage Drop and Power Loss in the 20 kV Medium Voltage Network of PT. PLN (PERSERO) ULP Panakkukang Uses ETAP Software Adrian Pratama; Al Imran; Haripuddin Haripuddin
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.11230

Abstract

In the modern era, electrical energy has evolved into an indispensable cornerstone of societal function, particularly in dense urban environments, where infrastructure demands are relentless. Ensuring both the effectiveness and efficiency of energy distribution from generation plants to end consumers is a paramount challenge for utility providers. A significant hurdle in this process is the inevitable phenomenon of energy loss, which degrades system performance and increases operational costs. This study provides a comprehensive analysis of power loss within the medium-voltage distribution network at PT. PLN (Persero) ULP Panakkukang. Several critical factors contribute to these inefficiencies, most notably the load imbalance between phases, which leads to neutral current flow and resistive heating generated within conductors. Furthermore, physical degradation, such as poor conductor connections, acts as a persistent impediment to seamless distribution. To quantify these issues, this research employs a dual-methodology approach: utilizing Electrical Transient Analyzer Program (ETAP) software alongside rigorous manual calculations to measure voltage drop and real power loss. These findings indicate that the losses fluctuate significantly in response to shifting load conditions throughout the day. Ultimately, this research serves as a vital technical reference for optimizing grid performance and enhancing the reliability of future electricity distribution systems.
Design and Development of an Android-Based Application for Receiving and Tracking Menu Orders in a Café Rama; Mustamin Tewa; Muhammad Iswal Burhan
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.11231

Abstract

This research aims to design and create  an Android-based order menu receiving and tracking application for Kopitawa X Empal Gepuk Cafe in Makassar to improve efficiency and accuracy in order management. Application development is carried out using  a waterfall approach  which consists of five main stages, namely, needs analysis, design, implementation, verification, and maintenance. The technology used includes the Dart programming language with the Flutter framework and Firebase as the database management system. Testing based on the ISO/IEC 25010 standard shows the application has a good level of feasibility. Functional suitability reaches 100%, indicating that all key features are functioning as needed. Optimal performance efficiency with 19% CPU usage and 81 MB of memory. Usability scored 77.9% in the "Good" category, while portability ensures that the app runs smoothly on various android devices including versions 10 to 14. This application can provide practical benefits by making it easier for café staff to manage orders, speed up the service process, and monitor sales performance. In addition, the application can also serve as a reference in the development of similar systems in the café and other restaurant business sectors, with the potential to continue to be developed through feature updates and improved data security.
Net Benefits of the Integrated Academic Information System for the Academic Community of the Department of Electrical Engineering Education, Universitas Negeri Makassar: An Evaluation Using the DeLone & McLean Model Hasrul Bakri
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12115

Abstract

Objectives: The JPTE Integrated Academic Information System (SIJUPE) was developed to address student data management problems at the Department of Electrical Engineering Education (JPTE), Faculty of Engineering, Universitas Negeri Makassar (FT UNM), which is one of the departments with the largest number of students. This study aims to evaluate the success of SIJUPE using the DeLone & McLean (2003) Information Systems Success Model, which encompasses three quality dimensions (system, information, service), use, user satisfaction, and net benefits. Methods: This research employed a quantitative approach with a survey method. The study population consisted of all SIJUPE users among the academic community, with samples taken using proportionate stratified random sampling. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with the assistance of SmartPLS software. Results:  The results show that user satisfaction has a positive and significant effect on net benefits, as does system use. Among the three quality dimensions, information quality is the most dominant factor influencing user satisfaction. These findings indicate that SIJUPE generally provides positive benefits to the academic community of JPTE FT UNM, although improvements in service quality are still needed. Novelty: This study contributes first empirical evidence on the successful implementation of a cloud computing-based academic information system in a higher education setting with a large student population, specifically in Eastern Indonesia, using an integrated DeLone & McLean framework.
Performance and Challenges of Deep Learning-Based Face Recognition Systems: A Systematic Review Khalis Khalis
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12479

Abstract

This research is motivated by the rapid development of Artificial Intelligence (AI) and the increasing use of face recognition systems in various fields such as security and education. Face recognition, as part of computer vision, enables systems to identify individuals based on unique facial characteristics. This study aims to review the application of Deep Learning methods in face recognition systems, with a focus on commonly used algorithms, model performance, and existing challenges. This study employs a systematic literature review approach by analyzing various relevant scientific publications. Data were collected from reliable academic sources and analyzed qualitatively to identify research trends, methods, and gaps. The results of the study indicate that Convolutional Neural Network (CNN) and its variants, such as FaceNet and VGG-Face, are the most widely used methods and demonstrate high performance in terms of accuracy and reliability. However, several challenges remain, including the need for large-scale datasets, variations in image conditions, and high computational complexity. This study contributes by providing a comprehensive synthesis of Deep Learning applications in face recognition and identifying research gaps and opportunities for future development to improve system effectiveness and efficiency.
Transient Stability Analysis of Inverter-Dominated Microgrids using Physics-Informed Deep Learning Andi Nur Faisal; Azizah Fauziah Misbahuddin; Andi Shridivia Nuran
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12490

Abstract

Inverter-dominated microgrids exhibit low rotational inertia and fast electromagnetic dynamics, making transient stability assessment significantly more challenging than in synchronous machine dominated systems. This paper proposes a physics informed deep learning (PIDL) framework to estimate post disturbance stability status and critical clearing time (CCT) directly from short window dynamic trajectories while embedding nonlinear inverter dynamics into model training. A total of 1200 disturbance scenarios were generated from reduced order time domain simulations of droop controlled inverter microgrids with randomized virtual inertia, droop damping, fault severity, clearing time, and stochastic renewable fluctuations. The proposed architecture combines a bidirectional temporal encoder with dual output heads and physics residual regularization, followed by two stage optimization (Adam and L-BFGS). On the held out test set, the model achieved 95.56% accuracy, 97.40% precision, 97.40% recall, and 97.40% F1-score for transient stability classification, with CCT error of 29.67 ms MAE and 45.55 ms RMSE. Inference speed reached 1.57 ms per sample, outperforming direct numerical simulation (8.37 ms per sample), and robustness testing under ±20% parameter scaling maintained 95.56% accuracy. These results indicate that integrating physical constraints with deep learning yields a practical and computationally efficient tool for real-time transient stability monitoring in inverter dominated microgrids.
Analysis of the Impact of Adding an Interposed Transformer on Distribution Transformer Protection Components on the Gontang Feeder at PT. PLN (Persero) ULP Mattoanging Reski Anugerah; Muhammad Yusuf Mappeasse; Andi Imran
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12590

Abstract

This research aims analyze of adding an inserted (interposing) transformer on the loading level of the distribution transformer as well as the performance and suitability of protective components, including Fuse Cut Out (FCO), No Fuse Breaker (NFB), and NH Fuse, on the Gontang feeder of PT PLN (Persero) ULP Mattoanging. The research method employed is quantitative descriptive, using a combination of manual calculations and simulation approaches with ETAP and Digsilent PowerFactory software, with data collected through documentation, observation, and interviews. The results indicate that the main transformer GT 0234, prior to the addition of the inserted transformer, experienced a loading level of approximately 92%, which is classified as overload as it exceeds the safe transformer loading limit of 80%. After the installation of the inserted transformer GT 0870 with a capacity of 160 kVA, the loading of the main transformer decreased to approximately 47–48%, while the loading of the inserted transformer ranged between 56–57%, resulting in normal operating conditions. The manual calculation results are consistent with the simulation results obtained from ETAP and Digsilent PowerFactory. Furthermore, the current flowing through the protective components decreased after the addition of the inserted transformer and remained within safer operating limits; however, discrepancies were still found between the installed protective component ratings and the results of the calculations and simulations. Therefore, an evaluation and adjustment of the protective component ratings are required to improve protection coordination and system reliability.
Real-Time Vehicle Stopping Duration Detection and Calculation System in Drop-Off Areas Based on CCTV Cameras Using YOLOv8 Ainun Jariyah; Nurul Khaerani Hamzidah; Syahrir Syahrir
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12492

Abstract

Objective: Campus drop-off areas often experience congestion due to vehicles stopping beyond the permitted duration without effective monitoring. This research aims to develop a real-time system for detecting and calculating vehicle stopping duration in campus drop-off areas using CCTV cameras and the YOLOv8 deep learning model. Method: This research applies a research and development (R&D) approach with a case study at the drop-off area of the Electrical Engineering Building, Campus 2, Ujung Pandang State Polytechnic (PNUP). The dataset, managed through Roboflow, comprises 803 images of cars and motorcycles (640×640 pixels), split into 78% training, 20% validation, and 2% test data. Model training and testing were conducted in Google Colab, while Visual Studio Code served as the main code editor. Results: The YOLOv8 model at epoch 42 of 50 achieved precision 90.8%, recall 98.5%, mAP50 94.5%, and mAP50-95 73.3%. The system successfully detects vehicles in real-time, recognizes drop-off boundaries, calculates stopping duration, and delivers voice notifications via speaker along with violation reports to a website dashboard and Telegram Bot. Novelty: This research integrates YOLOv8 object detection with polygon-based boundary recognition, automatic duration calculation, voice alerts, and dual monitoring through a website dashboard and Telegram Bot. The integration offers an automated solution for managing campus drop-off areas, reducing congestion and improving traffic efficiency.
Performance Evaluation of 4G LTE Networks Based on QoS Parameters at 2100 MHz and 2300 MHz Frequencies Asma Amaliah; Alfin Eka Riyanto; Kurniawan Harun; Sukriyah Buwarda; Mardhiyah Nas
Journal of Electrical Engineering and Informatics Vol. 3 No. 2 (2026): Journal of Electrical Engineering and Informatics
Publisher : Fakultas Teknik Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jeeni.v3i2.12505

Abstract

Objectives: This study aims to evaluate and compare data service performance of 4G LTE networks operating on the 2100 MHz (L2100) and 2300 MHz (L2300) frequency bands utilized by Indonesian mobile network providers, particularly Telkomsel. Methods: Field measurements were conducted at four purposively selected Base Transceiver Station (BTS) locations representing high-traffic urban environments in Makassar, Indonesia. At each BTS, speed tests were repeated five times per session across three different time periods, morning, afternoon, and evening, to ensure data reliability and minimize temporal bias. Packet loss was assessed using a dedicated network diagnostic application under real-world conditions. A total of 60 measurement sessions were recorded across all sites. Results: The L2300 band demonstrated superior throughput, achieving 49.7 Mbps at BTS UPD263 DMT ISAT Kassi-Kassi and 46.8 Mbps at BTS UPD057 MSC Pengayoman. The L2100 band yielded lower speeds of 34 Mbps at BTS UPD172 Kisel and 27.6 Mbps at BTS UPD248 Protelindo Baitul Rahman. Both bands maintained 0% packet loss across all measurement sessions. Novelty: This study contributes empirical, multi-temporal comparative data on 4G LTE performance across two frequency bands within Indonesian urban telecommunications infrastructure, providing actionable insights for network optimization and frequency band selection strategies.