cover
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
ISSN : 2745925X     EISSN : 2722273X     DOI : -
Core Subject : Science,
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
Articles 125 Documents
Thermoelectric Generator Demonstration On Stove As Alternative Energy Sudarmanto Jayanegara; Muhammad Wiranda; Kamaluddin
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 1 (2025): March 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i1.7703

Abstract

Thermoelectric generators are power plants that utilize the Seebeck effect, a phenomenon that produces electric current when there is a temperature difference in a conductor or semiconductor. In practice, thermoelectric generators are often used to utilize waste heat from various systems. One significant heat source is a stove, which can produce temperatures up to 80ºC. By utilizing a thermoelectric generator, the heat accumulated on the stove wall can be converted into electrical energy. To support this conversion, an effective cooling system is needed so that the temperature difference between the two sides of the thermoelectric module is maintained. This study aims to explore the potential of electrical energy generated by a thermoelectric generator (TEG) module as an alternative energy source through heat from the stove wall with variations in flame settings. The cooling system used consists of an aluminum heat sink and a fan, which works to maintain the temperature difference on the cold side of the thermoelectric at around 12ºC. The test results show that the performance of the thermoelectric generator has quite promising potential as an alternative energy source. This can be seen from the increase in efficiency obtained from each flame variation. In large flames, the maximum measured efficiency value reaches 0.76%, while in small flames it reaches 0.47%. Therefore, the application of the Seebeck effect principle shows very good potential for the development of alternative energy in the future.
High-Precision Object Detection Using 8 Proximity Sensors: Integration of Switching Algorithm and Visual Display Suhaeb, Sutarsi; Ahmad Risal; Andi Rakhmat Baharuddin
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8133

Abstract

This study developed an object detection system based on 8 proximity sensors implemented in a line follower robot using a switching algorithm. The system is controlled by an Arduino Nano microcontroller and displays detection results on a 16x2 LCD. The switching method is employed to read the sensors alternately, thereby reducing channel interference and lowering power consumption without compromising reading speed. Each sensor is calibrated with a predefined threshold to convert analog readings into digital signals, which are then visualized as icons or underscore symbols on the display. This research follows an experimental approach involving hardware design, microcontroller programming, and direct testing on a robotic track. The system was tested in five different track position scenarios. The results show that the system consistently and responsively detects objects. The switching method proved effective in improving reading efficiency and enhancing the robot’s navigation stability for accurate line following..
Carbon Emission Simulation at the Slamet Riyadi Three-Way Intersection in Samarinda City Using Urban Mobility Simulation Kumala Jaya, Arsan; Fara Triadi; Abdullah Hanif
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8212

Abstract

This study uses Simulation Urban Mobility (SUMO) to simulate carbon emissions at the Slamet Riyadi Samarinda intersection. One of the big cities in Indonesia, Samarinda, faces major problems related to increasing traffic volume and its impact on air quality, especially carbon emissions. This simulation uses various traffic parameters, such as vehicle density, red light duration, and vehicle type. The purpose of this simulation is to evaluate the level of carbon emissions produced by vehicles passing through the intersection. The simulation begins by collecting traffic data and then converting it into an XML file that can be read by SUMO. This XML file contains information about traffic parameters, road networks, and vehicles. According to the simulation results, trucks contributed the most emissions per vehicle, with a total emission of almost 18,500 grams of CO₂ per hour. Traffic scenarios under real-world conditions were simulated using the SUMO tool with HBEFA-based emission models.. This study is expected to provide a clearer picture of the impact of traffic on the environment as well as recommendations for more effective traffic management strategies to reduce carbon emissions in Samarinda City.
Zero Trust Architecture as a New Paradigm in Cyber Security Andi M. Yusuf; Dian Megah Sari; Hilda Ashari; Hamdy Nur Saidy; Musawwir
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8272

Abstract

The traditional perimeter-based security model has proven inadequate in addressing modern cybersecurity challenges characterized by cloud adoption, remote work, and sophisticated cyber threats. This mixed-methods study examines Zero Trust Architecture (ZTA) as an emerging paradigm that fundamentally shifts security principles from "trust but verify" to "never trust, always verify." Through systematic literature review of 156 peer-reviewed articles and analysis of 12 cross-sector implementation case studies, this research explores the core principles, implementation strategies, benefits, and challenges of ZTA adoption. Key quantitative findings demonstrate that organizations implementing ZTA achieve 67% reduction in breach costs, 48% improvement in threat detection, and 52% enhancement in incident response capabilities. However, implementation faces significant barriers including technical complexity (78% of organizations), cultural resistance (65%), and skills gaps (72%). This study contributes a novel cross-sector ZTA maturity framework and provides evidence-based insights for cybersecurity professionals and organizational leaders considering ZTA adoption.
COMPASS: Comparative Evaluation of Machine Learning Algorithms for DDoS Detection Using ANOVA F-Value on AISED Dataset Hartinah; Syamsuddin, Irfan; Syarwani, Andi
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8276

Abstract

This study presents COMPASS, a comparative evaluation of ten Machine Learning algorithms for DDoS attack detection using the AISED Dataset on Cloud DDoS Attacks. Feature selection was performed using SelectKBest with ANOVA F-Value, evaluating model performance across varying feature dimensions (K = 10, 15, 20, 25). Experimental results demonstrate that ensemble-based methods, particularly Random Forest, Gradient Boosting, and AdaBoost, achieve near-theoretical maximum AUC scores (>0.998) while maintaining fast training times (<0.1 seconds). K-Nearest Neighbors (KNN) also exhibits robust performance (AUC > 0.98) with minimal computational cost. In contrast, Support Vector Machine (SVM) and Quadratic Discriminant Analysis (QDA) show relatively lower accuracy (AUC > 0.85) and suffer from high computational complexity, with SVM requiring up to 572 seconds to train at K=25. These findings highlight the critical trade-off between classification accuracy and computational efficiency in selecting optimal models for real-time DDoS detection systems. As future work, we propose deploying a lightweight version of COMPASS on edge computing devices and integrating it into federated learning frameworks to enable collaborative, privacy preserving model training.
Expert System Engineering to Diagnose Diseases Transmitted by Mosquito Bites Based on Web Arfan, Muhammad; Pebriadi, Muhammad Syahid
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8296

Abstract

This research is software development aimed at engineering an expert system to diagnose diseases transmitted by mosquito bites based on the web. This system can provide an initial diagnosis of diseases transmitted by mosquito bites to patients based on symptoms they experience, without needing to directly consult an expert. The system development follows the Systems Development Life Cycle (SDLC) approach. SDLC itself in software engineering is a process for creating and developing systems, as well as models and methodologies used to develop systems. The method used in this expert system is forward chaining, where the tracking starts with a set of facts and then moves toward a conclusion. The system was developed using PHP programming language and MySQL as the software to store the data. The results show that the expert system provides consistent results and answers. Expert validation looked at two key aspects, resulting in scores of 91.50% and 90.95%. Both are categorized as "highly valid," which shows that the system is reliable and ready to be used in practice.
Applying Few-Shot Learning with Graph Neural Network (GNNs) For Fraud Detection Ricky Maulana Fajri; Antony, Fery; Rachmansyah
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8319

Abstract

Detecting fraudulent transactions in financial systems presents a major challenge due to the scarcity of fraud instances and the limited availability of labeled data. This study explores the use of few-shot learning techniques combined with Graph Neural Networks (GNNs) to address these constraints. We evaluate four GNN architectures—Graph Convolutional Network (GCN), GraphSAGE, Graph Attention Network (GAT), and Simplified Graph Convolutional Network (SGCN)—on four real-world fraud detection datasets: Bank Fraud, IEEE-CIS, PaySIM, and ECommerce. Graph-based representations are constructed for each dataset, and models are trained using only 0%, 1%, 5%, and 10% of labeled data to simulate few-shot conditions. Experimental results show that GNNs, particularly GAT and GraphSAGE, maintain strong performance even with minimal supervision. Notably, GAT and GCN achieved an F1-score of 0.88 on the PaySIM dataset with just 10% labeled data, and GraphSAGE reached 0.25 on the highly imbalanced IEEE-CIS dataset. ROC curve analysis further demonstrates the discriminative capabilities of each model under different label settings. These findings highlight the potential of GNNs for effective fraud detection in low-resource and imbalanced environments, offering a practical solution for financial institutions aiming to enhance security with minimal labeled data.
Random Forest Implementation for Suricata-Based Real-Time DDoS Attack Detection Juhari; Nuralamsah Zulkarnaim; Muh Rafli Rasyid; Andi M. Yusuf
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8339

Abstract

The Random Forest classifier model trained on the CICDDoS2019 dataset achieved an accuracy of 99.94%, precision of 99.79%, recall of 99.94%, and F1-Score of 99.87%, demonstrating strong performance in detecting Distributed Denial of Service (DDoS) attacks. This study aims to develop a real-time DDoS detection system by integrating Suricata as an intrusion detection system (IDS) and Random Forest as a machine learning model. The Dataset used consisted of 431,371 samples and 31 selected features from the results of feature selection. The system works by monitoring log eve.json from Suricata, extracts relevant features directly, then performs classification using a trained model. Predictions are displayed via a Flask-based web interface for easy monitoring. In the live traffic test, the model gave a confidence score of 0.65 for attacks and 0.81 for normal traffic. These results prove that the built system is able to recognize DDoS attack patterns efficiently and can be applied to real network infrastructure as a real-time Threat Detection Solution.
Implementation of K-Means and TOPSIS Algorithm for Determining High School Student Majors Yunita, Yunita; Rodiah, Desty; Wahyuni, Putri Eka; Kurniati, Junia; Sarpanda, Dama Putra
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8358

Abstract

This study focuses on the implementation of the K-means algorithm to assist high school students in selecting majors that align with their interests and skills. Utilizing a dataset of 231 grade X students from 2022, the K-means algorithm successfully formed two distinct clusters. The results indicated an accuracy of 81.81% for the K-means clustering process, recall of 81.75%, precision of 77.87%, and specificity of 81.75%. Following this, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) was applied to rank the students within each cluster based on various weighted criteria. The TOPSIS method achieved a final ranking accuracy of 80.9%. The findings demonstrate the effectiveness of combining K-means and TOPSIS in facilitating informed decision-making for students regarding their academic paths.
Performance Analysis of SVM In Emotion Classification: A Comparative Study Of TF-IDF and Countvectorizer Fitriana, Frizka; Setiawan, Hendrik
Journal of Embedded Systems, Security and Intelligent Systems Vol 6, No 2 (2025): June 2025
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v6i2.8396

Abstract

In today’s digital era, emotion analysis of social media comments plays a critical role in gaining deeper insights into user sentiment. This study aims to compare two text representation methods TF-IDF and CountVectorizer in enhancing the performance of the Support Vector Machine (SVM) algorithm for emotion classification. The dataset employed in this research is a subset of GoEmotions, consisting of 1,000 YouTube comments labeled with 27 distinct emotion categories. The dataset was split into training and testing sets with an 80:20 ratio. Both text representation methods were tested separately using a linear kernel in the SVM algorithm. The models were evaluated based on accuracy, precision, recall, and F1-score. The classification results show that TF-IDF slightly outperformed CountVectorizer in terms of accuracy (35% vs. 32%). However, CountVectorizer exhibited marginally better performance in precision and F1-score. These findings suggest that the choice of text representation significantly impacts emotion classification outcomes. This research contributes to the development of text-based emotion analysis systems for social media platforms.

Page 9 of 13 | Total Record : 125