cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Bulletin of Electrical Engineering and Informatics
ISSN : -     EISSN : -     DOI : -
Core Subject : Engineering,
Bulletin of Electrical Engineering and Informatics (Buletin Teknik Elektro dan Informatika) ISSN: 2089-3191, e-ISSN: 2302-9285 is open to submission from scholars and experts in the wide areas of electrical, electronics, instrumentation, control, telecommunication and computer engineering from the global world. The journal publishes original papers in the field of electrical, computer and informatics engineering.
Arjuna Subject : -
Articles 3,276 Documents
Optimizing and evaluating proximal policy optimization and soft actor-critic agents in Unity ML-Agents-based games Muhammad Fakhri Loebis; Andry Chowanda
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.11864

Abstract

This study presents a comparative analysis of proximal policy optimization (PPO) and soft actor-critic (SAC) for training autonomous delivery agents in high-fidelity 3D environments using Unity ML-Agents. Both algorithms were evaluated with identical hyperparameters and reward functions across five independent runs to ensure statistical robustness. Results show that PPO achieves 31.4% higher final reward (6658.82 versus 5067.27) and superior policy improvement consistency (ratio 2.00 versus 0.31). However, PPO exhibits greater reward variability (coefficient of variation (CV) 0.533 versus 0.107) and slower convergence (33 versus 6 steps). SAC demonstrates faster initial convergence and superior stability with lower performance variance. These findings indicate that PPO is preferable for applications prioritizing maximum final performance in stable environments, while SAC is more suitable for tasks requiring adaptability and consistent performance under dynamic conditions. This study provides practical guidance for researchers implementing reinforcement learning (RL) in Unity-based simulations for autonomous systems.
Leveraging vision language models for digit recognition on digital measuring devices: a comparative analysis Adindra Vickar Ega; Dadang Gunawan; Abdul Halim; Rudi Anggoro Samodro
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.11769

Abstract

Large language models (LLMs) with multimodal input capability have been demonstrated in various applications. Vision language models (VLMs), which were developed from LLMs, can process and learn both visual and textual data simultaneously, enabling them to generate descriptive text from images. This study explores the use of several VLM models for the seven-segment digit recognition of a digital measuring device compared with other baseline optical character recognition (OCR) methods, such as Tesseract OCR, EasyOCR, PaddleOCR, KerasOCR, and YOLO11, with or without the integration of you only look once 11 (YOLO11) for LCD screen cropping. The results showed that the Gemini model outperformed conventional OCR methods and other VLM models with an average per-digit-recognition (PDR) accuracy of 98.10% (?=0.36%) and full sequence reading (FSR) accuracy of 93.85% (?=1.29%). The performance evaluation across the distance variation also demonstrates high accuracy for the VLM result with stable results. Simultaneously, YOLO11 exhibits degradation at longer distances due to difficulty in detecting small decimal digits, whereas the traditional OCR method yields inconsistent results. This study showed promising results for the further development, improvement, and deployment of VLM models in the automatic seven-segment digit recognition task on the edge device.
DroidRan: hardware behavior dataset for multi-stage android ransomware detection Kalaivani Selvaraj; Manmeet Mahinderjit Singh
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.11999

Abstract

Android ransomware increasingly exploits unpatched kernel vulnerabilities, still conventional detection methods rely on static application features, system logs, or network flows that polymorphic variants readily obfuscate. Hardware-level behavioral telemetry offers a tamper-resistant alternative, but no public dataset links such telemetry to the ransomware lifecycle. This paper presents DroidRan, a benchmark dataset of 22 dynamic hardware-behavior features spanning six resource categories, collected from an Android device carrying the unpatched CVE-2024-36971 vulnerability while 12 ransomware families were executed through three squatting attack vectors. Feature variations are mapped to four MITRE ATT&CK mobile stages: initial access (IA), privilege escalation (PE), command and control (CC), and impact (Im). A gated recurrent unit–long short-term memory (GRU-LSTM) framework combining parallel stage-specific branches, a cluster-based graph Bayesian network with correlation attention, and a dynamic threat intelligence module is proposed to exploit these traces. The Friedman test confirms that all 22 features discriminate benign from ransomware behavior, and cross-dataset benchmarking against CICMaldroid2017, CICAndMal2020, and HelDroid with Wilcoxon post-hoc analysis ranks DroidRan first for both accuracy and F1-score. The proposed framework outperforms four recent deep learning baselines on DroidRan, supporting stage-aware and obfuscation-resilient ransomware detection.
An efficient ANN-based global maximum power point searching approach for solar PV system under partial shading conditions Lakshminarayana Munirathnam; Yogeesh Amabalagere Chandrashekaraiah; Somu Pundalik Parande; Vani Bengaluru Purushothama; Ramya Mullur Varadhanayaka; Bellary Kursheed
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.11597

Abstract

For solar photovoltaic (PV) systems operating in partial shading conditions (PSCs), this research suggests a simplified maximum power point tracking (MPPT) controller based on artificial neural networks (ANNs). By adding multiple local peaks (LPs) to the power-voltage (P-V) curve, PSCs make it impossible for traditional techniques to follow the global maximum power point (GMPP), which results in substantial energy loss and decreased system reliability. In order to overcome this, a DC–DC boost converter's (BC's) duty cycle is adaptively controlled by the suggested ANN-based controller for precise GMPP tracking. Three shading scenarios are used to validate the approach on a 3×2 PV array. According to simulation results, tracking efficiency is higher than 99.4% and overall system efficiency is higher than 99.3%. The ANN greatly reduces oscillations around the GMPP by achieving quick convergence (
TF-IDF, chi-square, and ANN machine learning techniques for fake news anomaly detection in online social networks Venkata Ashok Kumar Boyina; N. Sabiyath Fatima; Omar Isam Al Mrayat; Pallavi S. Bangare; Kasula Venkata Durga Kiran; D. Vetrithangam; Sunil L. Bangare; Mohan Awasthy; Bhaskar Roy; Batyrkhan Omarov; Guna Sekhar Sajja
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.10532

Abstract

Platforms such as Facebook, WhatsApp, Twitter, and Telegram have a substantial influence on the dissemination of information in modern society. Numerous individuals rely on them without verifying the veracity of their information or the sources of their knowledge. False information is referred to as "Fake News" and is disseminated through both traditional and non-traditional media channels including social media. Contemporary media consumers uncritically embrace the news they read online, rather than taking the time to critically assess it. This method has led to a heightened trust in internet content, which has facilitated the spread of misinformation. This article describes a machine learning (ML)-based approach to classifying and detecting fake news anomalies in online social media data. This framework accepts social media data as input. Features are chosen using the term frequency identification term frequency–inverse document frequency (TF-IDF) and chi-square tests. The categorization model is then built utilizing approaches such as artificial neural network (ANN), support vector machine (SVM), and random forest (RF). The classification model is trained and tested on a preprocessed data set. Finally, fake news is discovered, and the suggested framework is evaluated using measures such as accuracy, precision, recall, and F1-score. ANN is performing better for fake news classification and detection.
Finite-set MPC for a 7-level cascaded H-bridge simulation-based evaluation with reference extrapolation and non-idealities Asep Andang; Muhammad Aris Risnandar; Imam Taufiqurrahman; Rizal Anshor; Miftahul Huda Pratama; Muhammad Lutfi Azhari
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.11500

Abstract

Multilevel cascaded H-bridge (CHB) inverters are widely used in power conversion systems because they can create high-quality voltage waveforms with low harmonic distortion. However, the predictive control of multilevel converters faces challenges such as computational delays, switching dynamics, and maintaining performance under nonideal conditions. This study explores finite-control-set model predictive control for a three-phase seven-level CHB inverter with an inductor capacitor inductor (LCL) filter, taking into account hardware-related imperfections. A discrete state-space model and a voltage-tracking cost function are used to assess 343 possible switching vectors at each sampling interval. Second-order reference extrapolation is applied to manage the typical one-sample actuation delay in real-time digital systems. Simulation results show that, in ideal conditions, the inverter achieves a voltage total harmonic distortion (THD) of less than 0.1% and a power factor close to one. Under realistic disturbances, such as dc-link voltage drops and load imbalances, the system remained stable, with the THD increasing slightly to approximately 5%. Thus, the controller maintains good waveform quality and dynamic stability despite common disturbances in converter operations and digital control limits. The main contribution is integrating second-order reference extrapolation within a hardware-aware finite-control-set model predictive control (FCS-MPC) framework, providing a practical basis for future real-time implementation and validation through processor-in-the-loop (PIL) or hardware-in-the-loop testing.
Geographic information systems, practical experiences in higher education María Rodríguez-Gámez; Antonio Vázquez-Pérez; Carlos Gustavo Villacreses-Viteri; Jorge L. Macias-Ramos; Víctor Alfonso Martínez-Falcones; Xavier Horacio Valencia-Zambrano; José Ricardo Núñez-Álvarez
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.11745

Abstract

Geographic information systems (GIS) are technological tools for capturing, storing, analyzing, and visualizing geospatial data. This study presents the development and educational implementation of the Sistema de Información Geográfica para el desarrollo Sostenible (SIGDS) or geographic information system for sustainable development, an open-source geoportal integrating renewable energy assessment, smart-grid monitoring, and disaster-risk management at the Technical University of Manabí, Ecuador. A mixed-methods approach was adopted, combining GIS implementation, spatial database development, root mean square error (RMSE)-based validation, and educational evaluation through a structured survey administered to 77 engineering students. Survey reliability was confirmed using Cronbach's alpha (alpha=0.84). GIS validation revealed positional and thematic discrepancies of less than 5%. Results indicate that 85% of users reported improved interdisciplinary understanding, while spatial problem-solving performance increased by approximately 20% compared with conventional instruction. Survey scores revealed strong perceptions of employability enhancement (4.62/5), interdisciplinarity (4.35/5), and acceptable accessibility (3.88/5). The proposed geoportal contributes to higher education by providing a replicable framework for integrating renewable energy planning, disaster resilience, and geospatial analysis into engineering curricula. The platform also supports real-time monitoring and decision-making processes for sustainable territorial development.
Internet of things-enabled biomedical engineering: current applications, challenges, and emerging directions Hamza Abu Owida; Areen Arabiat
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.12640

Abstract

The internet of medical things (IoMT) is a structured integrative review of the internet of things (IoT) that focuses on the medical field, specifically on the integration of physiological sensors, medical devices, communication networks, and the clinical information systems to monitor and track patients' health and conditions continuously, and use data to support medical treatment. Through July 2026, a reproducible search and evidence audit of PubMed/MEDLINE, IEEE Xplore, Google Scholar, publisher/digital object identifier (DOI) records, and authoritative regulatory and standards repositories was conducted. The final evidence base consisted of 65 distinct sources that were assessed using a set of explicit eligibility criteria and evidence weighting. Wearable atrial-fibrillation screening, remote monitoring, digital inhalers and continuous glucose monitoring (CGM), and connected hospital infrastructure were shown to be clinically significant in large-scale studies, but such benefits were only seen if there was confirmatory pathway, workflow integration, data quality and persistent engagement. Cybersecurity, privacy, interoperability, validation, workforce capacity, equity, and lifecycle sustainability were all key challenges. The review also brought a synthesis and readiness framework that connects edge artificial intelligence (AI), federated learning, digital twins, advanced connectivity, and circular lifecycle management with measurable validation and governance requirements across the domains.
Assessing capacity and coverage planning: 5G NR performance using 2300 MHz in urban area Putri Rahmawati; Muhammad Adam Nugraha; Lina Marlina
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.10578

Abstract

The rapid evolution of mobile communications technology and increasing data traffic demands have necessitated fifth generation (5G) network development, especially in urban environments. While previous studies examined 3.5 GHz and 700 MHz bands, the 2300 MHz mid-band frequency remains unexplored despite offering optimal balance between coverage and capacity. This research analyzes capacity and coverage planning for 5G implementation at 2300 MHz in Bandung City’s urban area (167.31 km²), employing the urban macro (UMa) propagation model for line of sight (LoS) and non-line of sight (NLoS) conditions, validated through network planning simulations. Capacity planning projects user growth from 421,758 (2024) to 479,453 (2028), with traffic demand increasing from 1.92 to 2.37 Gbps/km². Coverage analysis identifies 86 sites required for optimal deployment, driven by downlink requirements. Performance simulations demonstrate “Excellent” signal strength synchronization signal–reference signal received power (SS-RSRP: -75 to -70 dBm), “Good” signal quality synchronization signal–signal-to-interference-plus-noise ratio (SS-SINR: 10-15 dB), and average throughput of 137.42 Mbps, exceeding IMT-2020 requirements by 37%. The deployment achieves 72.5% user connectivity (132,071 users). While simulation results confirm successful urban 5G deployment balancing coverage and capacity, real-world pilot validation would strengthen practical applicability for network planners implementing similar urban networks.
Dynamic adaptive session-based advanced encryption standard Jerico S. Baladhay; Marlon V. Gamido
Bulletin of Electrical Engineering and Informatics Vol 15, No 5: October 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i5.12384

Abstract

Dynamic adaptive session-based advanced encryption standard (DASE) is an adaptive modification of the advanced encryption standard (AES) that allows the number of rounds to be adjusted to the security needs and timing constraints of each session. Conventional AES deployments run a fixed number of rounds regardless of data sensitivity, imposing needless processing on low-risk information and reducing flexibility in how security is applied. DASE defines three configurations: DASE-6, DASE-8, and DASE-10, and replaces the computationally heavy MixColumns transformation with a lightweight bit-permutation layer that preserves strong diffusion. Cryptographic robustness was evaluated using the avalanche effect and the strict avalanche criterion (SAC) across diverse plaintext patterns, while performance was measured on heterogeneous file types and sizes. DASE reached an average SAC of up to 53%, matching or exceeding standard AES-10, while DASE-6 delivered average encryption and decryption speed-ups of 50.55% and 38.94% over AES-10. DASE-8 and DASE-10 remained 40.46% and 32.54% faster in encryption, respectively, with DASE-10 retaining a clear advantage despite using the same round count as AES. The results demonstrate a tunable spectrum of security-performance trade-offs suitable for resource-constrained, high-throughput, and real-time data-protection scenarios.

Filter by Year

2012 2026


Filter By Issues
All Issue Vol 15, No 5: October 2026 Vol 15, No 4: August 2026 Vol 15, No 3: June 2026 Vol 15, No 2: April 2026 Vol 15, No 1: February 2026 Vol 14, No 6: December 2025 Vol 14, No 5: October 2025 Vol 14, No 4: August 2025 Vol 14, No 3: June 2025 Vol 14, No 2: April 2025 Vol 14, No 1: February 2025 Vol 13, No 6: December 2024 Vol 13, No 5: October 2024 Vol 13, No 4: August 2024 Vol 13, No 3: June 2024 Vol 13, No 2: April 2024 Vol 13, No 1: February 2024 Vol 12, No 6: December 2023 Vol 12, No 5: October 2023 Vol 12, No 4: August 2023 Vol 12, No 3: June 2023 Vol 12, No 2: April 2023 Vol 12, No 1: February 2023 Vol 11, No 6: December 2022 Vol 11, No 5: October 2022 Vol 11, No 4: August 2022 Vol 11, No 3: June 2022 Vol 11, No 2: April 2022 Vol 11, No 1: February 2022 Vol 10, No 6: December 2021 Vol 10, No 5: October 2021 Vol 10, No 4: August 2021 Vol 10, No 3: June 2021 Vol 10, No 2: April 2021 Vol 10, No 1: February 2021 Vol 9, No 6: December 2020 Vol 9, No 5: October 2020 Vol 9, No 4: August 2020 Vol 9, No 3: June 2020 Vol 9, No 2: April 2020 Vol 9, No 1: February 2020 Vol 8, No 4: December 2019 Vol 8, No 3: September 2019 Vol 8, No 2: June 2019 Vol 8, No 1: March 2019 Vol 7, No 4: December 2018 Vol 7, No 3: September 2018 Vol 7, No 2: June 2018 Vol 7, No 1: March 2018 Vol 6, No 4: December 2017 Vol 6, No 3: September 2017 Vol 6, No 2: June 2017 Vol 6, No 1: March 2017 Vol 5, No 4: December 2016 Vol 5, No 3: September 2016 Vol 5, No 2: June 2016 Vol 5, No 1: March 2016 Vol 4, No 4: December 2015 Vol 4, No 3: September 2015 Vol 4, No 2: June 2015 Vol 4, No 1: March 2015 Vol 3, No 4: December 2014 Vol 3, No 3: September 2014 Vol 3, No 2: June 2014 Vol 3, No 1: March 2014 Vol 2, No 4: December 2013 Vol 2, No 3: September 2013 Vol 2, No 2: June 2013 Vol 2, No 1: March 2013 Vol 1, No 4: December 2012 Vol 1, No 3: September 2012 Vol 1, No 2: June 2012 Vol 1, No 1: March 2012 List of Accepted Papers (with minor revisions) More Issue