cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota banjarmasin,
Kalimantan selatan
INDONESIA
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer
ISSN : 25983245     EISSN : 25983288     DOI : -
We are the Editor of Jurnal ELTIKOM, invites Mr. / Ms Lecturer, researcher and practitioner to be able to publish your paper on topics covering Electrical Engineering, Electronics Engineering, Telecommunications Engineering, Computer Engineering, Information Technology.
Arjuna Subject : -
Articles 243 Documents
Wound Depth Measurement System in Forensic Cases using Image Processing and Machine Learning Wahyuni, Elvira Sukma; Ahnaf, Kern Cesarean; Firdaus, Firdaus; Abdul-Kadir, Nurul Ashikin; Zakaria, Nor Aini; Wiraagni, Idha Arfianti; Kadarmo, Diwangkoro Aji
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 9 No. 2 (2025)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v9i2.1636

Abstract

Accurate evaluation of wound depth is crucial in forensic investigations, as it significantly affects case assessments and outcomes. This study introduces a method for classifying wound depth using a Support Vector Machine (SVM) model and compares its performance with Decision Tree and Logistic Regression models. The classification was based on color features extracted from HSV and LAB color spaces. The da-taset consisted of 76 images categorized into three stages: stage 2 (36 images), stage 3 (12 images), and stage 4 (28 images). Model performance was evaluated using confusion matrices, precision, recall, and F1-score. The SVM model achieved an overall accuracy of 85%, demonstrating higher precision and re-call across all stages compared to the Decision Tree and Logistic Regression models, which achieved 50% and 70%, respectively. The results indicate that the SVM model performed particularly well in distinguish-ing stage 2 wounds, although differentiating between stages 3 and 4 remained challenging. Overall, the proposed system shows potential to enhance the accuracy and efficiency of forensic wound evaluation by providing a rapid and objective classification tool. However, as the system was tested on a limited dataset under controlled conditions, further research should expand the dataset, incorporate additional features, and explore other machine learning algorithms to improve robustness and applicability in real forensic contexts.
The Synergy of Blockchain and Cybersecurity: Building Trust in Digital Environments Zangana, Hewa Majeed; Sallow, Zina Bibo; Mustafa, Firas Mahmood; Husain, Mamo Muhamad
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 9 No. 2 (2025)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v9i2.1701

Abstract

The rapid expansion of digital ecosystems has intensified concerns about data security, privacy, and trust. Blockchain technology, characterized by its decentralized, immutable, and transparent nature, offers a transformative approach to strengthening cybersecurity. This paper examines the synergy between blockchain and cybersecurity, emphasizing how blockchain’s cryptographic foundations, consensus mechanisms, and smart contracts can mitigate cyber threats, enhance authentication, and ensure data integrity. By analyzing emerging trends, challenges, and real-world applications, this study underscores the potential of blockchain to reinforce digital trust and resilience across diverse sectors. The findings contribute to the ongoing discourse on secure digital environments by proposing an integrated framework for blockchain-based cybersecurity solutions
Optimization Model for Fake Account Detection on Twitter (X) Social Media using Feature Engineering and Machine Learning Approaches Perimawati, Ni Nyoman Eny; Huizen, Roy Rudolf; Hostiadi, Dandy Pramana
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 9 No. 2 (2025)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v9i2.1727

Abstract

Twitter (X) has become an important platform for community interaction, but this also creates serious challenges due to the proliferation of fake accounts that can harm users and undermine credibility. Previous studies have proposed detection methods but often lacked forensic analysis based on extracted feature information. This study utilizes labeled datasets and supervised evaluation metrics (precision, recall, and F1-score) to validate model performance. Extracting behavioral information from features is crucial for achieving accurate and reliable detection results. The study introduces a novelty in the form of engineered behavioral features that significantly enhance detection accuracy, achieving up to 99.94% using AdaBoost. The proposed approach detects fake accounts on Twitter (X) by extracting key feature information and developing an optimal detection method through machine learning algorithms, including Random Forest, SVM, and AdaBoost. Furthermore, the model is optimized using feature engineering techniques. The novelty of this work lies in the development of engineered features through distribution analysis based on data characteristics and the improvement of classification performance through feature engineering optimization. The initial experiment without feature engineering shows that Random Forest achieved the highest accuracy of 98.77%, followed by AdaBoost at 98.57% and SVM at 95.90%. After applying feature engineering, performance improved, with AdaBoost reaching 99.94%, Random Forest 99.69%, and SVM 99.32%. The proposed model can assist system analysts in detecting fake accounts and contribute to solving forensic cybercrime challenges, particularly in identifying fake social media profiles.
Comparative Analysis of Graph Neural Networks for Fraud Detection Fajri, Ricky Maulana; Teary, Muhammad Gald; Praditya, Ni Wayan Pricila Yuni
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/93y6ve52

Abstract

Detecting financial fraud is a complex and evolving challenge, particularly because of the relational nature of transaction data, graph sparsity, and severe class imbalance. To the best of our knowledge, this study repre-sents one of the first systematic benchmarks of five prominent Graph Neural Network (GNN) architectures, GCN, GAT, GraphSAGE, GIN, and SGCN, for fraud detection under balanced and imbalanced conditions across multiple public datasets. We explicitly evaluate the impact of the Synthetic Minority Oversampling Technique (SMOTE) on graph-based fraud detection performance, an aspect that has rarely been addressed in prior research. The comparative analysis considers predictive performance (AUC, F1-Score, Precision, Re-call) and computational efficiency to provide actionable guidance for real-world development. The experimental results show that GraphSAGE offers the best trade-off between accuracy and execution time for laten-cy-sensitive environments, while GAT’s attention mechanism supports offline, interpretability-driven analysis. These findings provide empirical evidence to inform GNN selection strategies for scalable and effective fraud detection systems.
Adaptive Power Management for Multi-User Indoor LiFi Communication Systems using Evolutionary Algorithms Abed, Saif Ahmed; Salih, Nahla Abdul Jalil; Hasan, Ihsan Jabbar; Abdulkhaleq, Nadhir Ibrahim
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.1652

Abstract

Visible Light Communication (VLC) systems have emerged as a promising alternative to RF-based solutions, especially in electromagnetic-sensitive environments such as hospitals and aircraft cabins. This study presents a MATLAB-based simulation of an indoor VLC setup using corner and center LED array layouts in an emer-gency room scenario. The model supports variations in room length and user density and applies a genetic al-gorithm (GA) for dynamic LED current optimization to improve coverage fairness. This paper proposes an adaptive beam-shaping and power-optimization framework for multi-user indoor LiFi communication systems. The design is particularly suited for environments sensitive to electromagnetic interference (EMI), such as hospitals and emergency rooms, where RF-based systems may pose risks or interfere with medical equipment. Simulation results show that the corner configuration consistently outperformed the center configuration in terms of minimum and average received power, especially in larger rooms (10 m to 12 m) and with higher user numbers (6 to 8). For instance, in the corner case, the mean received power changed from 1.4075×10⁻⁶ to 1.3808×10⁻⁶ W when the number of users increased from 6 to 8, whereas in the center case it dropped from 1.0154×10⁻⁶ to 7.9926×10⁻⁷ W. Additionally, the optimal minimum power improved in larger rooms and with higher user densities, thus helping maintain communication even for the weakest users. The results confirm that GA-based current shaping improves energy efficiency and signal distribution, making this approach valu-able for robust and future-ready VLC applications in emergency scenarios.
Lightweight Multi-Model CNN Fusion of ResNet50v2 and MobileNetv2 for Accurate Brain Tumor Classification on MRI Scans Abd Salam At Taqwa; Muhammad Fadhlullah; La Ode Fefli Yarlin
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.1894

Abstract

Brain tumor classification remains a critical challenge in medical imaging because manual diagnosis from Magnetic Resonance Imaging is time-consuming and may produce inconsistent interpretations. Automated approaches using deep learning have shown promising results, although single-model methods may still face limitations in generalization and stability. This study introduces a lightweight multi model Convolutional Neural Network that combines MobileNetV2 and ResNet50V2 as dual-backbone feature extractors. Mo-bileNetV2 supports computational efficiency, while ResNet50V2 strengthens residual feature learning. The Bangladesh Brain MRI Dataset, which contains 6,056 images in three categories, Brain Glioma, Brain Menin-gioma, and Brain Tumor, was used in this study. All images were resized to 224 × 224 pixels before feature extraction, fusion, and classification. The proposed multi-model achieved 99.56% training accuracy and 93.37% validation accuracy, outperforming MobileNetV2 with 98.37% and 89.60 percent, and ResNet50V2 with 97.55% and 86.17 percent. On the test set, it reached 94.89% accuracy, 0.1536 loss, and 0.991 ROC AUC. These results show that integrating lightweight and deep architectures can improve robustness and accuracy while maintaining efficiency, making this approach suitable for real-world clinical support in brain tumor diagnosis.
Accuracy Comparison of Multivariate Newton-Raphson and Newton-Kantorovich Methods through Numerical Simulation in Nonlinear Systems Syaharuddin; Hidayah, Hendi; Mahsup, Mahsup; Mehmood, Saba; Raza, Wasim
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.1971

Abstract

Nonlinear systems of equations often appear in various fields of science and generally cannot be solved analytically, so numerical methods are required. However, previous studies have not provided a direct comparison of the accuracy and efficiency of the Multivariate Newton-Raphson method and the Newton-Kantorovich method when applied to the same nonlinear system, creating a gap in understanding their relative performance. This study aims to analyze and compare the performance of two numerical methods, namely the Newton-Raphson method and the Newton-Kantorovich method, in solving nonlinear systems of equations numerically. The evaluation is based on the convergence rate, result accuracy, and iteration efficiency of each method. The nonlinear system used involves trigonometric, exponential, and polynomial functions. Simulations were conducted twice using three equations directly for each method. The error tolerance was set at 0.001, with a maximum of 100 iterations. The simulation results showed that the Multivariate Newton-Raphson method had the best performance, requiring only 7 iterations to achieve convergence with a very small error of 2.711×10^(-7). In contrast, the Newton-Kantorovich method required 21 iterations and produced an error of 6.770×10^(-5), indicating slower convergence and lower efficiency. Based on these results, it can be concluded that the Multivariate Newton-Raphson method is the more accurate and efficient method for solving nonlinear systems of equations through numerical simulation. This finding contributes to the selection of an appropriate numerical method and opens opportunities for further exploration in higher-dimensional systems.
Enhancing The Performance of LSB Steganography with RSA and Huffman Fatah, Muhammad Rifqy Abdul Gofur Al; Akbi, Denar Regata; Muthohirin, Bashor Fauzan
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.2022

Abstract

The growing sophistication of digital threats has exposed major vulnerabilities in traditional data protec-tion methods, particularly those that rely only on cryptography or steganography. These single-layer tech-niques often fail to ensure both data confidentiality and concealment, which makes information more vulnera-ble to detection and attack. This study addresses the limited effectiveness of existing security mechanisms in balancing secrecy, efficiency, and image quality. Therefore, this study aims to develop a multi-layer steganog-raphy system that integrates Huffman-based data compression, enhanced RSA encryption, and optimized Least Significant Bit (LSB) embedding to improve data protection and performance. The proposed model was imple-mented in Python with a graphical user interface to improve usability. The experimental results show high im-perceptibility, with a Peak Signal-to-Noise Ratio (PSNR) of 48.32 dB and a Structural Similarity Index (SSIM) of 0.9987, indicating minimal visual distortion. Security testing confirmed resistance to steganalysis and brute-force attacks, while performance evaluation showed stable processing efficiency. These findings indicate that the proposed system offers a secure, efficient, and practical framework for digital information hiding in modern communication environments.
Hybrid ResNet50 with Convolutional Block Attention Module (CBAM) for Image Classification using Fine-Tuning Aulya Rachma Dewi; Aris Thobirin; Sugiyarto Surono
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.2089

Abstract

Image classification is a crucial area in digital image processing that requires models capable of robust and stable feature representation. The main challenges in this study include variations between visual classes, di-verse image quality, and limited labeled data, which often hinder the model’s ability to generalize optimally. This study proposes a hybrid ResNet50-CBAM approach, which integrates the strengths of the ResNet50 archi-tecture in deep feature extraction with the Convolutional Block Attention Module (CBAM) attention mecha-nism to improve the model’s focus on the most informative areas of the image. The training process was carried out in two phases, namely transfer learning to utilize the initial representation from the ImageNet dataset, fol-lowed by fine-tuning to adjust the network weights to the image characteristics of the research dataset. The datasets were reorganized and split into 70% training, 15% validation, and 15% testing subsets to ensure a balanced distribution of samples. In addition, various augmentation techniques were applied to increase data diversity and improve the model’s generalization capability. The evaluation results showed that this hybrid approach achieved an overall accuracy of 99%, indicating very high and consistent performance across the entire dataset. The integration of CBAM into the ResNet50 architecture was proven to strengthen the feature extraction process by highlighting the most relevant areas, resulting in a more accurate, stable, and effective image classification model for a wide range of artificial intelligence image processing applications.
Detecting Research Evolution and Trends in The Computer Vision Domain using Topic Modeling and Large Language Models Setio Basuki; Zamah Sari; Rizky Indrabayu; Masatoshi Tsuchiya
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 10 No. 1 (2026)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v10i1.2098

Abstract

Research evolution and trends in computer vision (CV) are important for understanding the field’s land-scape. Trends show which topics are gaining attention, while evolution reveals how those topics change over time. Understanding both helps researchers gain insight into CV and anticipate emerging areas of focus. How-ever, the rapid growth of publications makes such detection challenging. This paper aims to detect research evolution and trends in CV using topic modeling (TM) and large language model (LLM) techniques. The study applies TM and LLM approaches to papers from leading CV conferences, Computer Vision and Pattern Recog-nition (CVPR), International Conference on Computer Vision (ICCV), and Winter Conference on Applications of Computer Vision (WACV), published between 2013 and 2023, totaling more than 21,000 papers, using only abstracts and titles. The TM methods used are Latent Dirichlet Allocation (LDA) and Bidirectional Encoder Representations from Transformers for Topic Modeling (BERTopic), which generate keywords that represent topics. LLMs then refine these topics to support better analysis. The results show that research evolution and trends are easier to identify from abstracts than from titles, with BERTopic outperforming LDA in internal va-lidity based on coherence metrics and external validity based on human judgment. In addition, the topics evolved from traditional image processing tasks in earlier years to a stronger focus on deep learning and, more recently, generative approaches. Integrating TM techniques with LLMs enhances the detection of evolving re-search themes and trends in CV. This approach provides a clearer understanding of the field's development and helps anticipate future directions.