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 69 Documents
 3   4   5   6   7 
Hybrid CNN–LSTM–Transformer Architectures for Stock Price Prediction: Comparing Sequential and Parallel Integration Strategies Taufik, Mhd; Zahra, Amalia
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.29617

Abstract

Accurate stock price forecasting remains challenging because financial time-series exhibit complex local patterns, long-term temporal dependencies, and rapidly changing market dynamics. Although hybrid deep learning models have demonstrated promising predictive capabilities, limited evidence is available on how different architectural integration strategies influence forecasting performance. This study compares sequential and parallel hybrid CNN–LSTM–Transformer architectures enhanced with attention mechanisms and Bayesian optimization for predicting BBNI stock prices. Historical market data were processed through convolutional, recurrent, and attention-based learning components, while Bayesian optimization was employed to identify optimal hyperparameter configurations. Both hybrid architectures consistently outperformed the baseline CNN–LSTM model, demonstrating substantial improvements in prediction accuracy. The parallel architecture achieved superior performance in minimizing large prediction errors and explaining variance, whereas the sequential architecture produced lower absolute prediction errors with greater computational efficiency. These findings indicate that predictive performance depends not only on model complexity but also on the way deep learning components are structurally integrated. The study provides practical guidance for designing hybrid forecasting architectures that balance predictive accuracy and computational efficiency for financial time-series prediction in emerging markets.
YOLOv5s for Traffic Prohibition Sign Detection in Bandar Lampung: An Empirical Evaluation Under Real-World Urban Conditions Sholehurrohman, Ridho; Junaidi, Akmal; Dewi, Tasya Nursita; Andrian, Rico; Ilman, Igit Sabda; Reza Habibi, Mohammad
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.28786

Abstract

The detection of traffic prohibition signs in tropical urban environments is under-documented, as existing benchmark datasets such as GTSRB and TT100K do not represent the specific conditions of Southeast Asia. This study evaluates YOLOv5s for detecting and classifying six classes of traffic prohibition signs on four urban roads in Bandar Lampung, Indonesia, using a dataset of 9,898 labeled images extracted from real-world video recordings under various environmental conditions. YOLOv5s was directly compared with YOLOv4, YOLOv5m, and Faster R-CNN under identical evaluation conditions. YOLOv5s outperformed all comparison models with an average accuracy of 93.34% and an average F1-Score of 95.97%, with performance ranging from 88.65% in Pagar Alam to 97.28% at Unila, reflecting the documented gradation of environmental complexity. Processing speeds of 7.3–8.8 FPS place the system in the near-real-time category, making it suitable for offline traffic monitoring applications. This study provides a method for detecting prohibition signs in tropical urban environments in Indonesia and offers a practical reference point for the development of intelligent transportation systems in developing cities facing similar environmental challenges.
Optimizing Student Graduation Prediction Using XGBoost with SMOTE-ENN, Hyperparameter Tuning, and Threshold Adjustment Fadillah, Nur; Safira, Wahyuni Edsa; Suherman, Muhammad Ilham; Surianto, Dewi Fatmarani; Zain, Satria Gunawan
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.28867

Abstract

Predicting students at risk of delayed graduation is essential for enabling timely academic intervention, yet educational datasets are often characterized by class imbalance that limits predictive performance. This study proposes and evaluates an optimized XGBoost framework that integrates SMOTE-ENN, hyperparameter tuning, and decision threshold adjustment for student graduation prediction. A quantitative machine learning approach was conducted using academic records from 315 alumni across multiple Indonesian universities. Six classification algorithms were systematically compared to identify the most suitable baseline model before optimization. Model performance was assessed using multiple classification metrics to ensure comprehensive evaluation. The findings demonstrate that XGBoost consistently outperformed the competing algorithms and achieved its strongest predictive performance after integrating all three optimization strategies. Compared with applying each optimization technique individually, the combined framework produced more balanced classification results, improved minority-class recognition, and reduced prediction bias caused by imbalanced data. Feature analysis further revealed that academic variables, particularly cumulative grade point average, accumulated credits, and course repetition history, were the strongest predictors of timely graduation, whereas social and non-academic variables contributed comparatively less. These findings provide an effective and replicable machine learning framework for early identification of students at risk of delayed graduation and offer practical support for data-driven academic intervention and decision-making in higher education
Efficient Smartphone-Based Skin Lesion Classification for Early Skin Cancer Detection Pomalingo, Jodikal; Kusuma, Gede Putra
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.29476

Abstract

Early detection of skin cancer is critical for improving clinical outcomes, yet access to dermatological expertise remains limited in many regions. Smartphone-based artificial intelligence offers a promising alternative for accessible skin lesion screening; however, practical deployment requires an appropriate balance between diagnostic performance and computational efficiency. This study compared three deep learning architectures—MobileNetV2, EfficientNetB0, and Swin Transformer—to identify the most suitable model for smartphone-based skin lesion classification. A comparative experimental design was conducted using transfer learning with ImageNet-pretrained models and the ISIC 2019 dermoscopic image dataset comprising eight skin lesion categories. Model performance was evaluated based on predictive capability and on-device resource utilization following Android implementation. The findings reveal a clear trade-off between classification performance and computational efficiency. EfficientNetB0 achieved the strongest predictive performance, whereas MobileNetV2 consistently demonstrated superior computational efficiency, requiring the least processing resources, memory consumption, energy usage, and inference time during smartphone deployment. Although Swin Transformer delivered competitive predictive capability, its substantially higher computational demands reduced its practicality for resource-constrained devices. These results indicate that lightweight convolutional architectures remain the most appropriate choice for real-time smartphone-based skin cancer screening. This study provides an evidence-based framework for selecting deep learning architectures that balance diagnostic accuracy with deployment efficiency in mobile health applications.
Understanding Telegram User Continuance: Extending the ECM with Trust and Perceived Risk Aryaguna, Arvin; Oktavia, Tanty
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.29979

Abstract

Sustaining user engagement has become a critical challenge for encrypted instant messaging platforms, where continued usage depends not only on functional performance but also on users’ perceptions of trust and security. This study examines the determinants of Telegram continuance intention in Indonesia by extending the Expectancy-Confirmation Model (ECM) with trust and perceived risk. A quantitative survey was conducted among 410 active Telegram users with at least three months of experience, and the proposed model was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings confirm that expectation confirmation enhances both perceived usefulness and user satisfaction, while satisfaction emerges as the strongest determinant of continuance intention. Trust also plays a pivotal role by directly strengthening satisfaction and users’ intention to continue using Telegram. Interestingly, higher trust is associated with greater awareness of potential risks, revealing a trust–risk paradox in highly encrypted communication platforms. However, perceived risk does not directly discourage continued use, suggesting that strong trust can offset the negative influence of perceived security concerns. In addition, perceived usefulness no longer directly predicts continuance intention, indicating that functional benefits have become baseline expectations on mature messaging platforms. This study extends the ECM by demonstrating that long-term user retention is primarily driven by the interplay between trust and satisfaction rather than functional usefulness alone, offering practical implications for designing trust-centered communication platforms.
Privacy-Safe Marketing Mix Modeling and Budget Optimization Under Identifier Loss: A Controlled Simulation Study Bai, Jingwen; Wu, Qiyou
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.30533

Abstract

This study aims to examine whether aggregate marketing mix (MMM) modeling can support the measurement and budget planning of this system when user-level data are unavailable. A controlled simulation study applied specific implementations of ridge regression, adstock, and the Hill transformation to the weekly Robyn simulation dataset, comparing a regulated linear baseline with geometric-adstock–Hill and Weibull-adstock–Hill specifications on a shared chronological holdout set. The linear model provided the strongest holdout forecast, whereas the nonlinear specifications represented carryover and diminishing marginal returns needed for decision analysis. The geometric model shifted spending toward channels with higher fitted marginal returns, although the predicted gain depended materially on the allocation bounds. Across repeated stress-test runs, attribution–MMM disagreement increased as channel measurability was reduced. These findings explain why forecasting accuracy, channel attribution, and allocation utility are interrelated yet distinct components in measuring communication systems, and provide an integrated framework for evaluating all three simultaneously under conditions of partial observability, while limiting conclusions to simulation and observational evidence.
Design and Simulation of an Aperture-Coupled Microstrip Patch Antenna for 6 GHz FR1 Band Applications Santoso, Subekti Ari; Adiwidya, Andre Suwardana; Martini , Ni Putu Devira Ayu; Jantarachote, Vasan
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.30762

Abstract

Microstrip patch antennas are widely used for 6 GHz FR1 applications, but practical design references in this frequency band are still limited. This study aims to investigate the design and electromagnetic performance of a compact aperture coupled microstrip patch antenna (ACMPA) operating near the 6 GHz FR1 spectrum using full-wave simulations in CST Studio Suite. Two antenna configurations were designed and evaluated using CST Studio Suite on a Rogers RT/duroid® 6002 substrate. The antenna performance was evaluated in terms of reflection coefficient, VSWR, impedance bandwidth, realized gain, and radiation efficiency. The optimized design (D2) achieves an impedance bandwidth of approximately 73 MHz (6.03–6.11 GHz) with VSWR below 2, a realized gain of approximately 7.7 dBi, and radiation efficiency close to 75%. The simulation results indicate that optimizing the coupling-antenna geometry optimization enhances the electromagnetic coupling mechanism, resulting in improved impedance matching, realized gain, and radiation efficiency while preserving a compact single-element antenna structure. These findings confirm that optimizing the aperture geometry in a single-element configuration is an effective design strategy that reduces fabrication complexity to improve the performance of compact ACMPA antennas.
Tesla Coil-Based Wireless Power Transfer: Design, Performance, and Future Directions Kulkarni, Swati; Batod, Swastik; Singh, Suraj Kumar; Saini, Tejas; Vanshaj, Vanshaj
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.29522

Abstract

Tesla coil-based wireless power transfer (WPT) has attracted increasing attention because of its ability to transmit electrical energy without physical connections through high-frequency resonant coupling. However, existing studies remain fragmented across power electronics, high-voltage engineering, education, and electric vehicle applications, with limited integrated evaluation of design, performance, safety, and implementation challenges. This review synthesizes the literature on Tesla coil-based WPT published between 2016 and 2024, together with selected foundational studies, to examine design principles, performance characteristics, application domains, safety considerations, and remaining research gaps. The synthesis indicates that system performance is governed by the interaction of four key parameters: coupling coefficient, quality factor, resonant frequency, and mutual inductance. Existing studies demonstrate reliable short-range power transmission and substantial voltage amplification, but also highlight strong electromagnetic fields that require standardized safety assessment before practical deployment. Tesla coil-based WPT is particularly suitable for educational demonstrations, laboratory prototypes, and other low-power applications because of its simplicity and low cost. In contrast, its loose-coupling architecture limits efficiency and scalability for high-power applications, including electric vehicle charging, when compared with conventional inductive WPT systems. Future research should establish standardized safety protocols, perform quantitative comparisons between spark-gap and solid-state Tesla coil configurations, and validate renewable-energy-integrated WPT systems under realistic operating conditions.
Technology Utilization and Digital Literacy as Predictors of Learning Interest: Examining the Role of Self-Regulated Learning Gunawan, Guntur; Yumiarty , Yuyun
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): 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.v6i1.31008

Abstract

This study examined the relationships among technology utilization, digital literacy, self-regulated learning (SRL), and students' learning interest, with SRL serving as a mediating variable. An explanatory cross-sectional survey design was employed, involving 150 students from the PGMI Study Program at IAIN Curup selected through simple random sampling. Data were collected using a five-point Likert-scale questionnaire measuring technology utilization, digital literacy, self-regulated learning, and learning interest. The data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) in SmartPLS 4 with a bootstrapping procedure (add: 5,000 resamples, if applicable). The results showed that technology utilization was positively associated with self-regulated learning (β = 0.279, p = 0.001), while digital literacy was positively associated with self-regulated learning (β = 0.532, p = 0.000). Furthermore, self-regulated learning was positively associated with learning interest (β = 0.551, p = 0.000). Digital literacy demonstrated a positive direct association with learning interest (β = 0.179, p = 0.050), whereas technology utilization was not directly associated with learning interest (β = 0.081, p = 0.252). Indirect association analysis indicated that self-regulated learning fully mediated the relationship between technology utilization and learning interest and partially mediated the relationship between digital literacy and learning interest. The structural model explained 59.1% of the variance in self-regulated learning and 57.5% of the variance in learning interest. These findings highlight the important role of self-regulated learning in linking students' digital competencies and technology utilization with learning interest in higher education.

Page 7 of 7 | Total Record : 69

 3   4   5   6   7 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 1 (2026): International Journal of Electronics and Communications System 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 More Issue