cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Solly Aryza
Contact Email
sollyaryzalubis@gmail.com
Phone
+6281260252061
Journal Mail Official
jet@ft.uisu.ac.id
Editorial Address
Jl. Sisingamangaraja, Teladan, Medan 20217
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Electrical Technology
Published by Universitas Islam Sumatera Utara
ISSN : 25023624     EISSN : 25981099     DOI : https://doi.org/10.30743/jet
Core Subject : Science, Engineering,
Automotive Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology
Focus and Scope Journal of Electrical Technology is a peer-reviewed scientific journal that publishes high-quality original research papers, review articles, and technological developments in the fields of Electrical Engineering, Computer Engineering, and Informatics Engineering. The journal aims to provide a platform for researchers, academics, and practitioners to disseminate innovative ideas, theories, methodologies, and applications that contribute to the advancement of science and technology in electrical, computer, and information systems engineering. Focus The primary focus of the journal is on theoretical development, design, implementation, analysis, and evaluation of technologies related to electrical systems, computer engineering, and informatics that support industrial development, digital transformation, and sustainable technological innovation. Scope 1. Electrical Engineering Power systems and renewable energy Power quality analysis Power electronics Control systems and instrumentation Electrical machines and drives Electrical protection systems Smart grid technology Energy efficiency and energy management Industrial electrical systems High voltage engineering 2. Computer Engineering Computer architecture and embedded systems Internet of Things (IoT) Digital systems and microprocessors Computer networks and data communication Robotics and intelligent systems Sensors and actuators Computer-based monitoring and control systems Edge computing and cyber-physical systems Hardware design and system integration 3. Informatics Engineering Software engineering Information systems Artificial Intelligence Machine learning and data mining Cyber security and information security Big data and data analytics Web and mobile application development Human-computer interaction Cloud computing Multimedia and image processing Types of Articles Accepted Original research articles Review articles Case studies System or prototype development Technology implementation studies Modeling and simulation studies Soft Computing.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 484 Documents
 45   46   47   48   49 
Identification of Partial Discharge Phenomena in Glass Insulator Testing Using HFCT Syofyan Anwar Syahputra; Muhammad Fadlan Siregar; Muhammad Ikhwan Fahmi; Mhd Fahmi Syawali Rizki; Ahmad Faisal
JET (Journal of Electrical Technology) Vol 11, No 2 (2026): : Edisi June
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/jet.v11i2.13301

Abstract

Insulators are vital components in electrical power transmission systems, yet they are susceptible to degradation caused by electrical and environmental stresses. This study aims to analyze Partial Discharge (PD) characteristics in glass and porcelain insulators as an early indicator of insulation failure. Experimental testing involved a step-wise increase in AC voltage from 5 kV to 20 kV, alongside simulations of extreme conditions using exposure to a flame to trigger flashover phenomena. Discharge activity was detected using a PMDT PDetector instrument in accordance with the IEC 60270 standard. The results indicate that within the 5–15 kV range, the insulators exhibited stable performance with PD magnitudes below 20 dB. However, at 20 kV, a significant anomaly was observed in the glass insulator, characterized by a magnitude spike reaching 174 dB across the 360° phase, signaling a transition toward total failure. Phase-Resolved Partial Discharge (PRPD) pattern analysis demonstrated that thermal stress drastically lowers the air breakdown voltage threshold near the insulator surface. The study concludes that high-frequency detection methods are highly effective for the non-intrusive monitoring of insulation conditions, thereby helping to prevent catastrophic failures in electric power systems.
Temporal Gradient Oscillation with Accuracy Recovery Mechanism for Efficient BERT-Based Text Classification Indra Listiawan; Ema Utami; Kusrini Kusrini; Arief Setyanto
JET (Journal of Electrical Technology) Vol 11, No 2 (2026): : Edisi June
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/jet.v11i2.13472

Abstract

Large Language Models (LLMs) such as BERT have demonstrated impressive performance across various NLP tasks, yet their high computational cost poses challenges for deployment in resource-constrained environments. This paper proposes a dynamic temporal token pruning approach based on gradient oscillation monitoring, where token importance is estimated from the temporal variability of gradient signals during training. Tokens exhibiting low gradient oscillation are selectively pruned to reduce effective input length. To mitigate potential performance degradation caused by aggressive pruning, an accuracy recovery mechanism based on lightweight re-finetuning is introduced. Experimental results on benchmark sentiment classification datasets, including IMDB and SST-2, demonstrate that the proposed method substantially reduces the number of input tokens while maintaining or recovering predictive performance. These results indicate that gradient oscillation provides a viable signal for token-level efficiency, achieving a favorable trade-off between input sparsity and model accuracy without modifying the underlying Transformer architecture.
Representasi Distribusi Energi EEG Multi-Channel untuk Deteksi Aktivitas Epilepsi Menggunakan SVM Siswandari Noertjahjani; Ratih Sari Wardani; Aris Kiswanto
JET (Journal of Electrical Technology) Vol 11, No 2 (2026): : Edisi June
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/jet.v11i2.13713

Abstract

Deteksi epilepsi berbasis electroencephalogram (EEG) menghadapi tantangan berupa ketidakseimbangan kelas, data leakage, dan variasi sinyal antarpasien. Penelitian ini mengusulkan representasi distribusi energi EEG multikanal menggunakan Support Vector Machine (SVM) dengan kernel Radial Basis Function (RBF). Dataset CHB-MIT dipreproses dan disegmentasi menjadi window berdurasi 2 detik dengan overlap 25%. Setiap window direpresentasikan oleh 23 fitur energi domain waktu dan 23 fitur Power Spectral Density (PSD) metode Welch, sedangkan energy map berukuran 23 × 16 digunakan sebagai visualisasi distribusi energi kanal–waktu dan bukan sebagai masukan model. Evaluasi dilakukan menggunakan independent file-wise testing, grouped file-wise 5-fold cross-validation, dan patient-wise Leave-One-Subject-Out (LOSO). Untuk mencegah data leakage, pembagian data dilakukan pada tingkat file atau pasien sebelum segmentasi, sedangkan undersampling dan standardisasi hanya diterapkan pada data pelatihan. Hasil file-wise testing menunjukkan akurasi 93,247%, sensitivitas 98,387%, F1-score 42,958%, dan ROC-AUC 0,9880. Pada evaluasi LOSO, akurasi, sensitivitas, dan F1-score menurun menjadi 78,071%, 51,909%, dan 20,550%, yang menunjukkan adanya inter-subject variability. Uji Mann–Whitney menunjukkan perbedaan distribusi energi yang signifikan antara kelas seizure dan non-seizure (p = 2,1804 × 10⁻¹⁴⁰). Metode ini efektif untuk deteksi antarfile pada pasien yang sama, namun masih memerlukan validasi lintas pasien dan dataset eksternal untuk meningkatkan kemampuan generalisasi. Kata kunci: CHB-MIT, deteksi epilepsi, distribusi energi EEG, patient-wise LOSO, SVM.
Experimental Study of Contour Sources of Noise from Airland without Crew with DLE Gas Engine-30 and the Most Noise Counter Optimized by Using Method of Active Noise Control with a Variety of 45°, 90°,135° Alfisyahrin - -; Ikhwansyah Isranuri; Muhammad Rafiq Yanhar; Syukriyadin -; Deni Sigar
JET (Journal of Electrical Technology) Vol 11, No 2 (2026): : Edisi June
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/jet.v11i2.13645

Abstract

Unmanned Aerial Vehicle is a flying machine aircraft that can be controlled remotely to perform its function. As with other machines, noise problems are unavoidable. One of the components contributing to noise in aircraft is the engine. To reduce the noise level produced, it is necessary to study and research further the noise factor through acoustic science by conducting experimental and simulation tests using ANSYS software which was developed in Noise Control science. In this case, simulation has the advantage because it can be used to analyze more complex systems and conditions that can be adjusted and also have more accurate results. This study aims to make comparisons and determine the optimal sound reduction angle in the experimental method and noise simulation on the DLE GAS ENGINE-30 drone engine. Based on the results of experimental tests conducted on the DLE Gas Engine-30 engine, the optimal reduction value is obtained with an engine speed of 2000 RPM on the z- axis, a distance of 0.75 m and an angle of 45° with a reduction value of 4.1 dB and at 3000 RPM engine speed is on the x- axis, a distance of 1.25 m and an angle of 135° with a reduction value of 3.5 dB. While testing based on the results of simulation testing conducted on the DLE Gas Engine-30 engine, the optimal reduction value is obtained with an engine speed of 2000 RPM on the z+ axis, 1 m distance and 45° angle with a reduction value of 9.1 dB and at 3000 RPM engine speed found on the z+ axis, a distance of 0.75m and an angle of 135° with a reduction value of 12.8 dB.

Page 49 of 49 | Total Record : 484

 45   46   47   48   49 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol 11, No 2 (2026): : Edisi June Vol 11, No 1 (2026): EDISI FEBRUARI Vol 10, No 3 (2025): Edisi Oktober Vol 10, No 2 (2025): Edisi Juni Vol 10, No 1 (2025): Edisi Februari Vol 9, No 3 (2024): Edisi Oktober Vol 9, No 2 (2024): Edisi Juni Vol 9, No 1 (2024): Edisi Februari Vol 8, No 3 (2023): Edisi Oktober Vol 8, No 2 (2023): Edisi Juni Vol 8, No 1 (2023): Edisi Februari Vol 7, No 3 (2022): JET Edisi Oktober Vol 7, No 2 (2022): JET Edisi Juni Vol 7, No 1 (2022): JET Edisi Februari Vol 6, No 3 (2021): JET Edisi Oktober Vol 6, No 2 (2021): JET Edisi Juni Vol 6, No 1 (2021): JET Edisi Februari Vol 5, No 3 (2020): JET Edisi Oktober Vol 5, No 2 (2020): JET Edisi Juni Vol 5, No 1 (2020): JET Edisi Februari Vol 4, No 3 (2019): Edisi Oktober Vol 4, No 2 (2019): JET Edisi Juni Vol 4, No 1 (2019): Edisi Februari Vol 3, No 3 (2018): JET Edisi Oktober Vol 3, No 2 (2018): JET Edisi Juni Vol 3, No 1 (2018): JET Edisi Februari Vol 2, No 3 (2017): JET Edisi Oktober Vol 1, No 2 (2016): JET Edisi Juni Vol 1, No 1 (2016): JET Edisi Februari More Issue