cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
M. Miftach Fakhri
Contact Email
fakhri@unm.ac.id
Phone
+6282290603030
Journal Mail Official
wahid@unm.ac.id
Editorial Address
Program Studi Teknik Komputer, UNM Parangtambung, Daeng Tata Raya, Makassar, South Sulawesi, Indonesia
Location
Kota makassar,
Sulawesi selatan
INDONESIA
Journal of Embedded Systems, Security and Intelligent Systems
Published by Universitas Negeri Makassar
ISSN : 2745925X     EISSN : 2722273X     DOI : -
Core Subject : Science,
Computer Science & IT
The Journal of Embedded System Security and Intelligent System (JESSI), ISSN/e-ISSN 2745-925X/2722-273X covers all topics of technology in the field of embedded system, computer and network security, and intelligence system as well as innovative and productive ideas related to emerging technology and computer engineering, including but not limited to : Network Security System Security Information Security Social Network & Digital Security Cyber Crime Machine Learning Decision Support System Intelligent System Fuzzy System Evolutionary Computating Internet of Thing Micro & Nano Technology Sensor Network Renewable Energy Wearable Devices Embedded Robotics Microcontroller
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 13 Documents
 1   2 
Search results for , issue "Vol 7 No 1 (2026): March 2026" : 13 Documents clear
A Comparative Study of Decision Tree and Gradient Boosting Tree Algorithms for Predicting College Enrollment Decisions of High School Students Aras, Rezty Amalia; Utami Kusuma Dewi; Yabes Dwi Nugroho
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.10611

Abstract

The declining interest of high school students in pursuing higher education has become a major concern in Indonesia's education sector. This study aims to develop a data-driven predictive model to assist schools in identifying students’ decisions regarding further education. The study compares two popular classification algorithms, Decision Tree and Gradient Boosted Tree, using a dataset of 300 high school students comprising 10 attributes such as school accreditation, parental income, interest level, and residential status. The research method involves data preprocessing, model training, and performance evaluation using a confusion matrix to measure accuracy, precision, and recall. The results show that the Decision Tree algorithm achieved an accuracy of 76.67%, with a precision of 78.57% and a recall of 73.33% for the "college" class. Meanwhile, the Gradient Boosted Tree produced an accuracy of 73.33%, with a strength in recall for the "not attending college" class at 80%, but was less optimal in detecting students who pursued higher education. It can be concluded that the Decision Tree outperforms in terms of accuracy and interpretability, making it more suitable for use in school environments as a decision-support tool for early intervention, scholarship programs, and career counseling.
Comparative Performance Analysis of Web Caching and Load Balancing in Web-Based E-Learning Platforms Silamba, Yurico Ignasius May; Utomo, Muhammad Nur Yasir; Syamsuddin, Irfan
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2602

Abstract

Purpose – The increasing adoption of web-based E-learning platforms has introduced significant performance challenges under high user load, including elevated latency, degraded response time, and service downtime. While web caching and load balancing are commonly employed as mitigation strategies, empirical guidance on which technique better suits E-learning traffic characteristics remains limited. This study aims to provide a direct, controlled comparison between the two approaches.Design/methods/approach – An experimental methodology was employed using a Moodle-based E-learning platform deployed in a controlled virtualized environment.  Web caching was implemented with Varnish Cache and load balancing with HAProxy, each deployed on separate virtual machines running Moodle as the E-learning platform. Apache JMeter was used to simulate concurrent workloads ranging from 50 to 250 users, measuring latency, throughput, server response time, and failure rate.Findings – The results show that web caching consistently outperformed load balancing across all metrics. At 250 concurrent users, web caching reduced latency by 9.9%, improved throughput by approximately 4.5 times, decreased server response time by 96.6%, and lowered failure rate by 80.2% compared to load balancing. These findings indicate that caching more effectively mitigates backend overload in E-learning systems dominated by repetitive content access.Research implications/limitations – The experiments were conducted in a virtualized environment and focused primarily on static and semi-static content. Hybrid architecture combining both techniques were not evaluated.Originality/value – This study provides a head-to-head empirical comparison between web caching and load balancing under identical conditions, offering practical architectural guidance for infrastructure planning in academic environments.
Integrating Interface Design and Usability Evaluation in a Web-Based Zakat and Sadaqah Application Khasanah, Fata Nidaul
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2603

Abstract

Purpose – This study aims to design a user-centered interface for a web-based E-Zakat application to support the digital management of zakat and sadaqah by Mosque Prosperity Councils in the Industry 5.0 era. Design/methods/approach – The research adopts a user-centered design approach in developing the application interface. A usability evaluation was conducted using the Heuristic Evaluation method to assess the effectiveness, efficiency, and user experience of the designed interface. Findings – The results show that 80% of the interface design elements did not present any usability issues. However, two indicators were identified as cosmetic problems, indicating minor improvements are needed in future iterations. Research implications/limitations – This study is limited to interface design and usability evaluation using heuristic methods, without involving extensive user testing. Future research can expand by incorporating empirical user testing and system implementation to validate real-world effectiveness. Originality/value – This study contributes to the digital transformation of mosque financial management by providing a user-centered interface design specifically for E-Zakat systems, enhancing transparency, efficiency, and accessibility in managing zakat and sadaqah.
IoT-Based Smart Energy Management System for Air-Conditioning Energy Efficiency in Mosques Syaiful Amri; Rahmat Fajrul; Johny Custer; Murdani; Azizul
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2604

Abstract

Purpose – This study aims to develop and evaluate an Internet of Things (IoT)-based Smart Energy Management System (SEMS) to improve air-conditioning energy efficiency in mosque buildings. Design/methods/approach – The proposed system utilizes an infrared (IR) transmitter to replicate native air-conditioner remote signals, allowing implementation without modifying existing electrical installations. The system was implemented and tested at Taj-Al’ulum Mosque, Politeknik Negeri Bengkalis, under four operating modes: Default Manual, IoT Manual, Automatic, and Hybrid. Performance evaluation was conducted by comparing energy consumption across these modes and validating results through simulation and field testing. Findings – The results indicate that the Automatic mode achieved the highest energy savings, reducing energy consumption by 23.7% compared to the baseline, while also demonstrating the most stable operational performance. The Hybrid and IoT Manual modes also contributed to energy savings, although their effectiveness was influenced by user intervention and variations in mosque activities. Model validation showed strong agreement between simulation and real-world implementation, confirming system reliability. Research implications/limitations – This study is limited to a single case study location and focuses primarily on air-conditioning systems. Future research could expand to multiple buildings, integrate additional energy loads such as lighting and audio systems, and explore long-term performance under varying environmental and occupancy conditions. Originality/value – This study offers a practical, non-invasive, and replicable IoT-based energy management solution for mosque buildings, contributing to the development of smart energy management systems for smart mosques, particularly in environments with intermittent occupancy patterns.
Advancements in Brain Tumor Classification: Leveraging Mobilnet-V2 and Densenet121 For High-Precision Prediction Yuliawan, Kristia
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.11471

Abstract

Purpose – This study aims to compare the performance of MobileNet-V2 and DenseNet121 in classifying brain tumor types from MRI images under identical preprocessing, partitioning, and training conditions. Design/methods/approach – The study used a Kaggle-based dataset consisting of 3,264 MRI images, divided into 88% training data and 12% testing data. Both models were implemented using transfer learning and fine-tuning. Preprocessing included image resizing, normalization, and data augmentation through rotation, flipping, and zooming. The models were trained using the Adam optimizer, a learning rate of 0.0001, batch size of 32, and early stopping. Performance was evaluated using confusion matrix analysis, precision, recall, and F1-score. Findings – The results show that MobileNet-V2 achieved better overall performance than DenseNet121 in brain tumor classification. MobileNet-V2 produced more stable classification results and higher evaluation scores across most tumor classes, particularly in glioma and pituitary tumor prediction. In contrast, DenseNet121 showed a greater tendency to overfit, although both models performed well in identifying non-tumor images. Research implications/limitations – The study is limited by the relatively small dataset size, the use of a single dataset source, and the absence of external validation, which may affect generalizability. Originality/value – This study provides a direct comparative analysis of MobileNet-V2 and DenseNet121 for four-class brain tumor classification and highlights MobileNet-V2 as a more efficient and reliable model for this task.
A Multi-Branch EfficientNet-U-Net Hybrid Framework for Segmentation of Oyster Mushrooms in Cultivation Media Husain, Nursuci Putri; Kadir, Muh Ichwan
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2607

Abstract

Purpose – This study aims to develop a semantic segmentation model for oyster mushrooms in cultivation media to support automated monitoring, growth analysis, and yield estimation in smart farming systems. Design/methods/approach – A Multi-Branch EfficientNet-U-Net hybrid architecture was proposed, using EfficientNet-B0 as the encoder and a multi-branch fusion strategy to integrate multi-scale features from three encoder levels. The dataset consisted of 150 manually annotated oyster mushroom images collected from two cultivation sites under varying illumination, mushroom cluster density, and background texture. The model was evaluated using Intersection over Union (IoU) and Dice Coefficient metrics on training, validation, and testing subsets. Findings – Experimental results show that the proposed model achieved high segmentation performance, with a median IoU of approximately 0.90 and a Dice coefficient of 0.93. Compared with the baseline U-Net, the proposed architecture produced cleaner segmentation boundaries and more consistent detection of mushroom regions under complex environmental conditions. Research implications/limitations – This study is limited by the relatively small dataset and evaluation on images from only two cultivation sites. Further studies should involve larger and more diverse datasets to assess robustness across broader cultivation environments. Originality/value – This study offers an effective semantic segmentation framework that combines EfficientNet-B0 encoding and multi-branch multi-scale feature fusion to improve oyster mushroom segmentation accuracy in real cultivation settings, with potential application in smart agriculture monitoring systems.
Performance Evaluation of a Cowrie-Based Honeypot Integrated with a Suricata Intrusion Prevention System in a School Wireless Network Putri, Aurellia Maharani; Tahir, Muhlis
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2605

Abstract

Purpose – This study aims to implement and evaluate the integration of the Cowrie honeypot model with a Suricata-based Intrusion Prevention System (IPS) as a proactive security solution for school wireless networks. Design/methods/approach – The research method includes a literature review, needs analysis, security topology design, system implementation, and testing using port scanning and SSH brute force attack scenarios. The Cowrie honeypot is utilized to detect and log attack activities, while Suricata functions as an IPS to perform automatic real-time blocking. Findings – The results show that without a security system, both detection and blocking rates were 0%. After implementing Cowrie, the detection rate increased to 100%, although no blocking capability was present. The integration of Cowrie and Suricata IPS achieved 100% detection and 100% blocking rates for port scanning attacks (10 test packets) with an average response time of 0.8 seconds. In the SSH brute force test, the system successfully blocked attacks after 5 out of 10 login attempts, with an average response time of 0.9 seconds. Research implications/limitations – The evaluation was conducted under controlled experimental conditions using a limited number of attack simulations (10 scanning packets and 10 brute force attempts). Therefore, the results may not fully represent performance in large-scale or real-world network environments. Future studies should involve more extensive testing with diverse attack patterns and higher traffic volumes. Originality/value – This study contributes a practical integration of honeypot and IPS technologies to enhance wireless network security in school environments, providing a proactive and automated approach to both detect and mitigate cyberattacks in real time.
Semar AquaConnect: A Closed-Loop IoT System for Real-Time Monitoring and Autonomous Control in Catfish (Pangasianodon hypophthalmus) Larvae Rearing Rafif Zainun Ridhwan; Basino; ⁠Berbudi Wibowo; Rahmad Surya Hadi Saputra; ⁠I Ketut Daging; Yusuf Syam; Akhmad Syarifudin; Ade Hermawan
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.11782

Abstract

Purpose – This study aims to develop and validate Semar AquaConnect, a closed-loop Internet of Things (IoT) system for real-time monitoring and automated environmental control in catfish (Pangasianodon hypophthalmus) larval rearing tanks. Design/methods/approach – The system integrates an ESP32-based controller with sensors for temperature, pH, dissolved oxygen, total dissolved solids, and water level, as well as relay-based control of pumps, an aerator, and an immersion heater. A web-based dashboard and Telegram Bot were also developed for remote monitoring, data visualization, and emergency notifications. System performance was evaluated through sensor accuracy testing and repeated simulated extreme-condition scenarios (n=5). Findings – The results showed low mean differences of 0.12°C for temperature, 0.33 for pH, 0.08 mg/L for dissolved oxygen, and 5.10 ppm for total dissolved solids. In simulated scenarios, the system achieved a 100% relay activation success rate, including responses to critical pH fluctuations and temperature drops. Mean response latency ranged from 0.85 ± 0.10 s to 1.42 ± 0.18 s. Research implications/limitations – This study is limited to technical validation and has not yet included live biological trials to measure actual larval survival improvement. Originality/value – The study presents an integrated smart aquaculture platform combining multi-parameter sensing, autonomous actuator control, and dual-interface remote monitoring for catfish larval rearing.
Measurement of Gauge Block Surface Structure Using 12-Lamp Photometric Stereo Method Syahwir, Irawati Dewi; Setiawan, Irwan; Khairah, Inayah Dwi
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.11769

Abstract

Purpose – This study aims to develop and evaluate a non-contact method for measuring surface roughness of gauge blocks using an enhanced photometric stereo approach with multiple lighting sources, as an alternative to conventional coordinate measuring machine (CMM) methods that may damage the surface. Design/methods/approach – The research employs a photometric stereo method using 12 different lighting sources arranged at 55° intervals. The captured images are reconstructed using a photometric stereo algorithm to generate a three-dimensional surface model. Surface roughness is determined by measuring peak and valley heights and calculating their average. The objects tested are gauge blocks of class 0 and class 1, compared against standard blocks based on ISO/R 468-1966. Findings – The results show that gauge blocks of class 0 and class 1 have roughness values close to the N7 standard group, with an average roughness of 1.6 μm. The reconstruction results indicate an average error of 0.11933 μm for N7 blocks and -0.0718 μm for N8 blocks. The photometric stereo method demonstrates lower error compared to conventional contact-based measurements. Research implications/limitations – This method provides a promising non-contact alternative for surface roughness measurement and calibration. However, the study is limited to specific lighting configurations and gauge block samples, and further research is needed to validate its application across different materials and surface conditions. Originality/value – This study introduces an improved photometric stereo configuration using 12 lighting sources, enhancing reconstruction accuracy and offering a safer and more precise alternative for surface roughness measurement, particularly for calibration processes regulated by the National Standardisation Agency.
Experimental Assessment of Mining Waste Utilization in Cementitious Construction Materials: Strength, Water Absorption, and Durability Performance Ranggu, Ruth Bunga; Sani, Hendra; Sumbung, Dwi Yolanda
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2610

Abstract

Purpose – This study aims to comparatively evaluate the potential of three Indonesian mining and industrial waste streams gold-mine tailings, ferronickel slag, and coal fly ash for utilization in cementitious materials within a unified experimental framework, supporting sustainable construction and circular economy strategies. Design/methods/approach – A screening-level experimental design was applied by incorporating tailings as a 10% fine-aggregate replacement, and ferronickel slag and fly ash as 10% cement replacements. Performance was assessed using compressive strength, water absorption, and durability-related behavior under 28 days of 5% NaCl immersion, with conventional concrete as a control. Statistical analysis included one-way ANOVA and Tukey HSD, alongside pooled correlation analysis. Findings – Results indicate that waste type significantly influences performance. The slag mixture (S-10) achieved the best balance, with a 28-day compressive strength of 28.93 MPa (90.32% of control), low water absorption (4.50%), and a “Good” durability rating. Tailings-based concrete showed moderate performance, while the fly-ash mixture exhibited the weakest chloride resistance. Statistical tests confirmed significant differences across all groups (p < 0.05), and a strong inverse correlation between compressive strength and water absorption (r = −0.798, p = 0.0019). Research implications/limitations – The study provides initial comparative insights but is limited by its exploratory NaCl immersion method and absence of advanced characterization (XRF, XRD, SEM) and leaching analysis, restricting mechanistic and environmental interpretation. Originality/value – This research contributes a novel comparative framework by evaluating multiple waste streams and utilization pathways under a standardized protocol, offering practical screening evidence to guide material selection in sustainable construction

Page 1 of 2 | Total Record : 13

 1   2 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol 7 No 1 (2026): March 2026 Vol 6, No 4 (2025): Desember 2025 Vol 6, No 3 (2025): September 2025 Vol 6, No 2 (2025): June 2025 Vol 6, No 1 (2025): March 2025 Vol 5, No 3 (2024): November 2024 Vol 5, No 2 (2024): July 2024 Vol 5, No 1 (2024): March 2024 Vol 4, No 2 (2023): November 2023 Vol 4, No 1 (2023): May 2023 Vol 3, No 2 (2022): November 2022 Vol 3, No 1 (2022): May 2022 Vol 2, No 2 (2021): November 2021 Vol 2, No 1 (2021): May 2021 Vol 1, No 2 (2020): November 2020 Vol 1, No 1 (2020): May 2020 More Issue