cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Antomi Saregar
Contact Email
antomisaregar@radenintan.ac.id
Phone
+6285279618867
Journal Mail Official
antomisaregar@radenintan.ac.id
Editorial Address
Jl. Letnan Kolonel H Endro Suratmin, Sukarame, Kec. Sukarame, Kota Bandar Lampung, Lampung
Location
Kota bandar lampung,
Lampung
INDONESIA
International Journal of Electronics and Communications Systems
Published by Universitas Islam Negeri Raden Intan Lampung
ISSN : -     EISSN : 27982610     DOI : 10.24042
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
International Journal of Electronics and Communications System (IJECS) [e-ISSN: 2798-2610] is a medium communication for researchers, academicians, and practitioners from all over the world that covers issues such as the improvement about design and implementation of electronics devices, circuits, and communication systems including but not limited to: circuit theory, integrated circuits, analog circuits, digital circuits, mixed-signal circuits, electronic components, filters, oscillators, biomedical circuits, neuromorphic circuits, RF circuits, optical communication systems, microwave systems, antenna systems, communications circuits for optical communication, development of physics evaluation instruments, development of physics instructional media, digital signal processing, communication theory and techniques, modulation, source and channel coding, microwave theory and techniques, wave propagation and more.
Arjuna Subject : Ilmu Komputer (semua kategori) - Jaringan Komputer dan Komunikasi
Articles 58 Documents
 2   3   4   5   6 
Seasonal Forecasting of Ferry Passenger Demand for Operational Planning: Evidence from Bakauheni Port, Indonesia Abdullah, Khoirul Mizan; Muthoharoh, Luluk; Satria, Eggie; Neliyana, Rahma; Presilia, Presilia; Khoarizmy, Gymnastiar Al; Muslim, Anwar; Safitri, Ira
International Journal of Electronics and Communications Systems Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i2.26694

Abstract

Forecasting ferry passenger numbers is essential for efficient port operations and resource planning. This study applies the Seasonal Autoregressive Integrated Moving Average (SARIMA) model to forecast monthly passenger volumes at Bakauheni Port, Lampung. The SARIMA (2,1,1)(0,1,1)₁₂ model was selected for its ability to capture trend and seasonal patterns effectively. Diagnostic checks confirmed the model's adequacy, and validation yielded a MAPE of 11.47 percent, indicating 88.53 percent accuracy. These results show that the SARIMA model offers reliable predictive performance and can support data-driven decisions in scheduling, resource allocation, and service optimization. These results demonstrate that the developed SARIMA model possesses reliable predictive performance and can serve as a practical tool for supporting operational decision-making. The model can help this port authorities and managers optimize service provision, allocate resources more efficiently, and respond proactively to anticipated changes in passenger volume, thereby improving overall port performance and customer satisfaction in the future. Although it does not incorporate external factors, the model provides a solid foundation for future improvements and research.
Hybrid Database Architecture for Retail Big Data Analytics: PostgreSQL vs MongoDB Performance Analysis Noor, Tubagus Firman Iskandar; Nugraha, Eki; Maknun, Johar; Kustiawan, Iwan; Shaymanov, Farxod Xushbakovich
International Journal of Electronics and Communications Systems Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i2.28108

Abstract

The rapid growth of retail big data has intensified the challenge of selecting a database architecture that can balance analytical performance and resource efficiency, particularly in data-intensive retail environments. This study aims to conduct a comparative performance analysis between PostgreSQL 16 and MongoDB 8.0 in the context of implementing big data analytics in the retail industry. An experimental quantitative approach is used, utilizing a large-scale, real-world retail sales and inventory dataset to benchmark PostgreSQL 16 and MongoDB 8.0 across a range of representative analytical workloads. Results show MongoDB is 28-31% faster in query processing, but PostgreSQL is 13-17% more efficient in resource usage (CPU, RAM, Storage I/O) and requires 6x less storage. These results indicate that MongoDB consistently achieves faster execution times for read-intensive analytical queries, especially in large-scale aggregation operations. Conversely, PostgreSQL exhibits superior storage efficiency and lower computational resource consumption due to its normalized relational architecture. These findings reveal a fundamental trade-off between analytical speed and infrastructure efficiency in retail big data systems. This research contributes to the development of hybrid data architecture strategies for big data analytics in the retail industry, supporting performance optimization and informed decision-making in data-rich environments
Enhancing Academic Staff Performance Prediction in Higher Education: A Data-Driven Hybrid Machine Learning Approach Triyoga, Khavid Wasi; Laksono , Pringgo Widyo; Damayanti, Retno Wulan
International Journal of Electronics and Communications Systems Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i2.28670

Abstract

Enhancing the performance of academic staff is a key factor in maintaining institutional productivity and service quality in higher education. This study aims to develop a data-driven hybrid model capable of enhancing performance management effectiveness through the integration of predictive intelligence and evidence-based managerial recommendations. This model combines K-Means Clustering, Data Envelopment Analysis (DEA), Exploratory Factor Analysis (EFA), and Random Forest to analyze digital attendance data, service satisfaction surveys, and performance records from 2022 to 2024. This research was conducted at the Faculty of Teacher Training and Education, Sebelas Maret University (FKIP UNS) as a representative case study. The test results show that the predictive model achieved 92 percent accuracy and an F1-score of 0.90 in classifying low performance risk. A strong negative correlation was found between attendance tardiness and service satisfaction levels. DEA analysis identified 32 percent inefficiency in resource utilization, while EFA revealed three dominant latent factors: compliance with SOPs (0.82), academic productivity (0.89), and psychosocial well-being (0.93). Intervention cluster management (SOP training and workload reduction) resulted in a 28 percent increase in SOP compliance. These findings indicate that the integration of hybrid machine learning with efficiency and factor analysis can be an effective framework for data-driven improvement in academic staff performance.
Dynamic Decay Adjustment in Radial Basis Function Networks: Does It Improve Software Defect Prediction? Kamil, Hawariul; Faisal, Mohammad Reza; Farmadi, Andi; Hertono, Rudy; Saputro, Setyo Wahyu
International Journal of Electronics and Communications Systems Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i2.29288

Abstract

Software quality depends heavily on the early detection of potentially defective modules, yet the complexity of software metrics and class imbalance often leads to inconsistent prediction performance. This study aims to compare the effectiveness of Radial Basis Function Neural Network (RBFNN) and RBFNN with Dynamic Decay Adjustment (RBFNN-DDA) in predicting software defects using five NASA PROMISE datasets (CM1, KC1, MC1, MW1, and PC1). The research employed quantitative experimentation through data normalization, a 70 to 30 train–test split, and model evaluation across maximum iterations ranging from 200 to 1,000. Model performance was assessed using Accuracy, Precision, Recall, F1 Score, and AUC. The results indicate that RBFNN provides higher Recall and F1 Score, making it better at identifying defective modules, although its performance is less stable. Meanwhile, RBFNN-DDA yields more consistent performance with higher Precision, Accuracy, and AUC on imbalanced datasets, albeit with lower Recall. Both models reached performance saturation at 200 until 400 iterations, showing minimal improvement at higher iteration counts. The findings imply the need for balancing sensitivity and stability when selecting defect prediction models, particularly in environments with severe class imbalance
Evacuation Route Optimization for Volcanic Hazards Using Ant Colony Metaheuristics and Mobile GIS Aziz, Muhammad; Prabowo, Basit Adhi
International Journal of Electronics and Communications Systems Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i2.29349

Abstract

Effective evacuation planning in volcanic areas requires real-time spatial awareness, community integration, and algorithm validation. This study aims to introduce SVACO-GIS, an innovative system that integrates Ant Colony Optimization (ACO), Geographic Information Systems (GIS), and the Sister Village framework to optimize evacuation routes under volcanic hazard conditions by identifying safe and efficient evacuation routes and strengthening community-based evacuation planning. The research applies the SVACO-GIS approach using a multi-parameter asymmetric heuristic matrix that incorporates slope, river distance, red zone exclusion, shelter readiness, and population density to better represent real-world constraints and safety priorities. Simulation results show that the application of SVACO-GIS produces structurally different evacuation route patterns compared to the shortest path-based approach. Routes optimized with SVACO-GIS consistently avoid major river corridors and areas with high slope gradients previously identified as high-risk zones in the context of Mount Merapi eruptions. The resulting evacuation network is directional and does not allow movement back toward zones with higher hazard levels, aligning with the one-way evacuation principle of the Sister Village system. The integration of local wisdom with intelligent spatial computing improves evacuation efficiency and sets a replicable standard for disaster preparedness in other high-risk geographies. These findings suggest that SVACO-GIS can support more informed decision-making, strengthen the resilience of vulnerable communities, and guide the development of intelligent evacuation systems in volcanic regions in the future
Lightweight Image-Based Mold Detection System for Real-Time Bread Quality Monitoring Using Artificial Neural Networks (ANN) Saputra, Nikola; Ilyas, Muh.; Riswansyah , Muh Fikra Junian; Kaswar, Andi Baso; Lamada, Mustari S.
International Journal of Electronics and Communications Systems Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i2.28706

Abstract

Mold contamination of white bread is an ongoing challenge for quality monitoring, while conventional visual inspection remains unreliable for early and consistent detection. This study aims to propose a lightweight image-based mold detection system for white bread oriented towards real-time quality monitoring using Artificial Neural Networks (ANNs). An experimental workflow combining digital image acquisition, pre-processing, Otsu-based segmentation, morphological refinement, multicolor color space feature extraction, and an Artificial Neural Network (ANN) classifier is implemented. Results indicate that color information is the dominant discriminatory cue for mold identification, while texture descriptors provide complementary structural information that improves class separation. The RGB+HSV+LAB combination achieved the highest performance, with a training accuracy of 97.91 percent and a testing accuracy of 96.66 percent. These findings demonstrate that effective mold classification can be achieved without relying on deep or computationally intensive architectures when the feature representation is well-designed. In conclusion, a lightweight, feature-centric ANN (Artificial Neural Network) is sufficient for reliable classification of mold growth levels on white bread. This study confirms that a compact, feature-based learning strategy is sufficient for reliable classification of mold on white bread, providing a technically efficient basis for a vision-based food quality assessment system.
K-Means-Based Behavioral Segmentation of Social Media Users for Digital Communication Analysis in Indonesia Nurhidayat, Nurhidayat; Nur Fadillah; Dilla, Salsa; Syahrul, Syahrul; Surianto, Dewi Fatmarani
International Journal of Electronics and Communications Systems Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i2.28749

Abstract

Social media has become a central part of daily life in Indonesia, yet the rapid growth of digital platforms presents challenges in analyzing large, unstructured user data. Responding to this issue, this study aims to cluster the behavioral patterns of Indonesian social media users using the K-Means Clustering algorithm, a data mining technique for unsupervised segmentation. Employing a quantitative approach, data were collected through an online questionnaire from 553 respondents aged 15–80 years. After data cleaning, normalization, and feature encoding, the optimal number of clusters was determined using the Elbow method and Silhouette Coefficient, resulting in two clusters with a Silhouette score of 0.177. Cluster 0 (303 respondents) represents highly interactive multi-platform users active on Instagram, TikTok, and YouTube for 3–6 hours daily, showing strong interest in entertainment and motivational content. Cluster 1 (250 respondents) includes more passive users, mainly on Instagram and TikTok, spending 3–4 hours per day with moderate engagement and a preference for motivational and self-development content. The findings demonstrate that K-Means Clustering effectively maps user behavior based on platform use, content preferences, motivations, and interaction patterns. The implications of these findings suggest that digital communication strategies need to be tailored to the characteristics of each user cluster so that the messages and content conveyed are more effective.
Credit Card Fraud Detection Using a Stacked DNN–XGBoost–LightGBM–CatBoost Ensemble (DXCL): A Comparative Performance Study on Real-World Transaction Data Ghosh, Kingkar Prosad; Roy, Ankan; Saha, Shatabdi; Singha, Anupam; Chakraborty, Kanika; Mandal, Sukanya
International Journal of Electronics and Communications Systems Vol. 5 No. 1 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i1.28228

Abstract

E-commerce has increased the productivity of international trade, causing an increase in credit card fraud that has damaged finances and weakened public confidence in digital payment systems. This study aims to improve the sensitivity and reliability of fraud detection on highly imbalanced transaction data through the design and evaluation of the DXCL model compared to conventional individual and ensemble models. This methodology uses resampling approaches such as random undersampling and SMOTE oversampling during training to reduce class imbalance. DXCL's performance is evaluated against six benchmark models Random Forest, standalone DNN, XGBoost, LightGBM, CatBoost, and a dummy classifier utilizing accuracy, precision, recall, F1-score, ROC-AUC, TPR, and FPR metrics on a 2013 European credit card transaction dataset. The results prove that DXCL outperforms individual models and Random Forest in effective rate while eliminating false positive rate with 99.98% accuracy, precision, recall, F1-score, and ROCAUC of 1.00. Deep feature extraction and ensemble enhancement significantly improve fraud examination of class imbalanced transaction datasets. DXCL supports the application of a more dependable approach for detecting credit card fraud with low false positive rates in highly imbalanced digital transaction environments

Page 6 of 6 | Total Record : 58

 2   3   4   5   6 

Filter by Year

2021 2025


Reset
Filter By Issues
All Issue Vol. 5 No. 2 (2025): International Journal of Electronics and Communications System Vol. 5 No. 1 (2025): International Journal of Electronics and Communications System Vol. 4 No. 2 (2024): International Journal of Electronics and Communications System Vol. 4 No. 1 (2024): International Journal of Electronics and Communications System Vol. 3 No. 2 (2023): International Journal of Electronics and Communications System Vol. 3 No. 1 (2023): International Journal of Electronics and Communications System Vol. 2 No. 2 (2022): International Journal of Electronics and Communications System Vol. 2 No. 1 (2022): International Journal of Electronics and Communications System Vol. 1 No. 2 (2021): International Journal of Electronics and Communications System Vol. 1 No. 1 (2021): International Journal of Electronics and Communications System