cover
Contact Name
I Gde Dharma Nugraha
Contact Email
i.gde@ui.ac.id
Phone
+6281558805505
Journal Mail Official
ijecbe@ui.ac.id
Editorial Address
IJECBE Secretariat Electrical Engineering Department, Faculty of Engineering, Universitas Indonesia Kampus UI Depok, West Java, Indonesia 16424
Location
Kota depok,
Jawa barat
INDONESIA
International Journal of Electrical, Computer, and Biomedical Engineering (IJECBE)
Published by Universitas Indonesia
ISSN : -     EISSN : 30265258     DOI : https://doi.org/10.62146/ijecbe.v2i1
The International Journal of Electrical, Computer, and Biomedical Engineering (IJECBE) is an international journal that is the bridge for publishing research results in electrical, computer, and biomedical engineering. The journal is published bi-annually by the Electrical Engineering Department, Faculty of Engineering, Universitas Indonesia. All papers will be blind-reviewed. Accepted papers will be available online (free access) The journal publishes original papers which cover but is not limited to Electronics and Nanoelectronicsc Nanoelectronics and nanophotonic devices; Nano and microelectromechanical systems (NEMS/MEMS); Nanomaterials; Quantum information and computation; Electronics circuits, systems on chips, RF electronics, and RFID; Imaging and sensing technologies; Innovative teaching and learning mechanism in nanotechnology education; Nanotechnologies for medical applications. Electrical Engineering Antennas, microwave, terahertz wave, photonics systems, and free-space optical communications; Broadband communications: RF wireless and fiber optics; Telecommunication Engineering; Power and energy, power electronics, renewable energy source, and system; Intelligent Robotics, autonomous vehicles systems, and advanced control systems; Computational Engineering. Computer Engineering Architecture, Compiler Optimization, and Embedded Systems; Networks, Distributed Systems, and Security; High-performance Computing; Human-Computer Interaction (HCI); Robotics and Artificial Intelligence; Software Engineering and Programming Language; Signal and Image Processing. Biomedical Engineering Cell and Tissue Engineering; Biomaterial; Biomedical Instrumentation; Medical Imaging.
Articles 83 Documents
Optimization of Preventive Maintenance Planning for the Motor Cooling System at PLTGU Using Differential Evolution Putranugraha, Derry; Garniwa, Iwa
International Journal of Electrical, Computer, and Biomedical Engineering Vol. 3 No. 3 (2025)
Publisher : Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62146/ijecbe.v3i3.132

Abstract

Determination of the optimal preventive maintenance time of the three-phase induction motor (88WC) during operation at 380V in the cooling system of the Semarang Gas and Steam Power Plant (PLTGU) is done by combining the Power-Law Non-Homogeneous Poisson Process (NHPP) model and the Differential Evolution (DE) Algorithm to achieve minimum total maintenance cost. The parameters of NHPP, β = 1.75 and η = 7,198.99 hours, are estimated using the least squares method from the historical failure data for the 2020–2024 period, recording failures beyond 20,000 operating hours. The DE optimization results provide the optimum PM time of 371.60 hours to reduce the total cost from IDR 28,198,935 (for the 500-hour interval) to IDR 20,299,822, achieving a cost savings of 38%. Validation is performed using Monte Carlo simulations with 1,000,000 iterations that yield a pre-optimization failure probability of 0.56%. Sensitivity analysis using a ±20% parameter variation also proves the model's robustness. This data-driven framework is thus anticipated to increase the reliability and cost-effectiveness of the PLTGU cooling system and is scalable to other power-generating facilities
Defying Data Scarcity: High-Performance Indonesian Short Answer Grading via Reasoning-Guided Language Model Fine-Tuning Faza, Muhammad Naufal; Purnamasari, Prima Dewi; Ratna, Anak Agung Putri
International Journal of Electrical, Computer, and Biomedical Engineering Vol. 3 No. 3 (2025)
Publisher : Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62146/ijecbe.v3i3.148

Abstract

Automated Short Answer Grading (ASAG) is crucial for scalable feedback, but applying it to low-resource languages like Indonesian is challenging. Modern Large Language Models (LLMs) severely overfit small, specialized educational datasets, limiting utility. This study compares nine traditional machine learning models against two fine-tuning strategies for Gemma-3-1b-it on an expanded Indonesian ASAG dataset (n=220): (a) standard fine-tuning predicting only scores, and (b) a proposed reasoning-guided approach where the model first generates a score rationale using knowledge distillation before predicting the score. The reasoning-guided model (Gemma-3-1b-ASAG-ID-Reasoning) achieved state-of-the-art performance (QWK 0.7791; Spearman’s 0.8276), significantly surpassing the best traditional model in this study (SVR, QWK 0.6952). This work advances foundational LSA-based approaches for this task by introducing a more robust methodology and evaluation framework. Crucially, standard fine-tuning (Gemma-3-1b-ASAG-ID) suffered catastrophic overfitting (QWK 0.7279), indicated by near-perfect training but poor test scores. While the reasoning-guided LLM showed superior accuracy, it required over 35 times more inference time. Results demonstrate that distilled reasoning acts as a powerful regularizer, compelling the LLM to learn underlying grading logic rather than memorizing pairs, establishing a viable method for high-performance ASAG in data-scarce environments despite computational trade-offs.
Reliability Improvement of Defense Scheme Implementation Using Adaptive Load Shedding Based On System Strength Index Widyantara, Dwitiya Bagus; Garniwa, Iwa; Jufri, Fauzan Hanif
International Journal of Electrical, Computer, and Biomedical Engineering Vol. 3 No. 3 (2025)
Publisher : Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62146/ijecbe.v3i3.150

Abstract

One of the defense schemes in power systems is Under Frequency Load Shedding (UFLS), designed to mitigate cascading blackouts caused by frequency disturbances. UFLS operates based on predetermined frequency thresholds and time delays, which inherently characterizes it as a static protection mechanism and may cause unnecessary excessive or insufficient load shedding. Therefore, an Adaptive Load Shedding (ALS) approach started to gain popularity, which enables load shedding based on real-time conditions, particularly during generator outages. In this research, a comparative analysis is conducted between the conventional UFLS method and a newly developed ALS scheme that integrates the System Strength Index (SSI) to improve the system's reliability, as evaluated by Energy Not Served (ENS). The proposed ALS algorithm processes real-time feeder load data, ranks the feeders by load magnitude in descending order, and optimizes the load shedding setpoints by incorporating the SSI. The proposed method is simulated in the Flores power system model using actual historical data for two load conditions: the highest and the lowest. The results show that the proposed method outperforms the conventional UFLS by 7.31% in terms of improved ENS.