cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
ekrek@gunadarma.ac.id
Editorial Address
Jalan Margonda Raya 100
Location
Kota depok,
Jawa barat
INDONESIA
Jurnal Ilmiah Teknologi dan Rekayasa
Published by Universitas Gunadarma
ISSN : 14109093     EISSN : 20898088     DOI : http://dx.doi.org/10.35760/tr.
Core Subject : Science, Engineering,
Automotive Engineering Computer Science & IT Electrical & Electronics Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology
Jurnal ini diterbitkan secara berkala tiga kali dalam setahun, April, Agustus, dan Desember. Artikel yang dimuat dalam jurnal ini merupakan artikel ilmiah hasil penelitian tentang teknologi dan rekayasa yang meliputi teknik informatika, teknik elektro, teknik mesin, dan teknik industri. Artikel dapat ditulis dalam bahasa indonesia maupun bahasa inggris.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 5 Documents
 1 
Search results for , issue "vol. 31 no. 2 (2026)" : 5 Documents clear
Image captioning bilingual berbasis BLIP-2 dan MarianMT dengan integrasi text-to-speech untuk literasi visual siswa Rizka Oktaviani; Fauziah Fauziah
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 31 No. 2 (2026)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2026.v31i2.152

Abstract

Visual literacy is the ability to understand and interpret information from visual representations, which involves linguistic processing. In the context of elementary education, this ability is crucial for helping students associate visual objects with bilingual vocabulary. However, most image captioning research remains monolingual, few studies accommodate Indonesian, and none have integrated audio representations into a single multimodal learning system. This study develops a bilingual image captioning system based on BLIP-2 and MarianMT, integrated with Text-to-Speech (TTS) within a FastAPI-based web application. English captions are generated using a pretrained BLIP-2 model, then translated into Indonesian using MarianMT, and converted to audio using gTTS. Additionally, a QLoRA fine-tuning experiment was conducted to compare model performance. The dataset consists of 6400 animal images relevant to the elementary school learning context, with caption quality evaluated using the METEOR metric. The results show that the pretrained BLIP-2 model delivers relatively stable performance with a METEOR score of 0.3765 for English and 0.3295 for Indonesian. These scores indicate that the generated captions are semantically relevant, although the overall performance is still relatively moderate compared to advanced image captioning systems. Functional testing of the prototype involving five elementary school students showed that the system is capable of generating bilingual captions and audio in real time and is easy to use. This multimodal integration supports the visual–verbal association process and has the potential to enrich students’ bilingual vocabulary, although no controlled experimental testing has yet been conducted to quantitatively measure improvements in literacy.
Pengaruh variasi elektroda dan arus pengelasan terhadap kekuatan tarik sambungan las SMAW pada stainless steel 304 Ario Ardiansyah; Basuki; Retno Eka Pramitasari; Dian Anisa Rokhmah Wati
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 31 No. 2 (2026)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2026.v31i2.367

Abstract

Penelitian ini bertujuan menganalisis pengaruh penggunaan elektroda E6013 dan E7016 serta variasi arus pengelasan terhadap kekuatan tarik sambungan las pada material Stainless Steel 304 yang dilas menggunakan metode Shielded Metal Arc Welding (SMAW). Metode yang diterapkan dalam penelitian ini adalah eksperimen kuantitatif dengan memvariasikan jenis elektroda dan besar arus pengelasan sebagai variabel bebas. Elektroda yang digunakan terdiri atas E6013 dan E7016 dengan variasi arus sebesar 75 A dan 80 A. Adapun variabel terikat yang diamati meliputi tegangan tarik, regangan, dan modulus elastisitas hasil pengelasan. Material uji berupa plat Stainless Steel 304 dengan ketebalan 1,8 mm yang dibuat menjadi 12 spesimen pengujian. Seluruh spesimen kemudian diuji menggunakan mesin uji tarik untuk mengetahui karakteristik mekanik sambungan las yang dihasilkan. Hasil pengujian menunjukkan bahwa kombinasi elektroda E6013 pada arus 75 A menghasilkan performa terbaik dengan nilai tegangan tarik rata-rata sebesar 527,94 MPa dan modulus elastisitas sebesar 15.994,9 MPa. Sementara itu, pada penggunaan elektroda E7016, nilai tegangan tarik rata-rata tertinggi diperoleh pada arus 80 A sebesar 409,3 MPa. Temuan penelitian menunjukkan bahwa jenis elektroda dan besar arus pengelasan memberikan pengaruh terhadap kekuatan tarik sambungan las. Peningkatan arus yang melebihi kondisi optimum cenderung menurunkan kekuatan tarik akibat bertambahnya masukan panas yang memengaruhi karakteristik daerah las dan daerah terpengaruh panas.
Design and performance evaluation of a solar-powered electrical system for shrimp pond aerators Walker Joseph; Rudi Nur Jaya; Irdandi; Haris Rudianto
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 31 No. 2 (2026)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2026.v31i2.186

Abstract

This study presents the design and performance evaluation of a solar-powered electrical system for shrimp pond aerators. The system was developed to provide a reliable off-grid energy solution by considering electrical load requirements, photovoltaic performance, and energy storage configuration. A 300 Wp photovoltaic panel, battery-based energy storage, and a DC motor aerator with a rated power of 250 W were utilized in the proposed system. Experimental testing was conducted under Standard Test Conditions (STC) and normal operating conditions through field measurements at Setu Hambaro, Cileungsi, Bogor. The results show that the photovoltaic system delivered an effective output power of approximately 281 W under normal operating conditions, providing a safety margin of around 12% above the aerator power requirement. The measured system efficiency ranged from 9.84% under STC to 11.58% under normal field conditions, reflecting typical efficiency variations caused by environmental factors and system- level losses. The findings indicate that the proposed electrical system design is capable of maintaining stable aerator operation without abrupt power fluctuations. Despite reduced efficiency compared to nominal photovoltaic module ratings, the system performance remains within acceptable limits for standalone photovoltaic applications. Overall, the results confirm that the proposed solar-powered electrical system is technically feasible and suitable for shrimp pond aerator applications in areas with limited access to grid electricity.
Perancangan sistem keamanan audio streaming menggunakan adaptive bitrate dengan enkripsi AES-128 Firman Al Islami; Ega Hegarini Ega
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 31 No. 2 (2026)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2026.v31i2.369

Abstract

Peningkatan kebutuhan layanan audio streaming yang cepat, stabil, dan aman mendorong pengembangan sistem yang mampu menyesuaikan kualitas audio sekaligus menjaga kerahasiaan konten. Penelitian ini merancang sistem berbasis HTTP Live Streaming (HLS) yang mengintegrasikan adaptive bitrate streaming dan enkripsi Advanced Encryption Standard 128-bit (AES-128). Sistem menyediakan empat variasi bitrate, yaitu 32, 64, 128, dan 256 kbps. Setiap segmen audio dienkripsi sebelum didistribusikan dan didekripsi oleh pemutar menggunakan kunci yang valid. Pengujian dilakukan terhadap dua file MP3, sedangkan kualitas audio dievaluasi menggunakan metode Mean Opinion Score (MOS) yang melibatkan 30 responden. Hasil pengujian menunjukkan bahwa sistem berhasil menyesuaikan bitrate berdasarkan kondisi jaringan dan segmen terenkripsi tidak dapat diputar tanpa kunci dekripsi yang valid. Nilai rata-rata MOS yang diperoleh adalah 1,60 pada 32 kbps, 3,00 pada 64 kbps, 4,70 pada 128 kbps, dan 4,93 pada 256 kbps. Dengan demikian, integrasi adaptive bitrate streaming dan AES-128 mampu menghasilkan layanan audio streaming yang adaptif sekaligus menjaga kerahasiaan data selama distribusi.
Ekstraksi aturan Decision Tree berbasis information gain untuk mendekati klasifikasi risiko cuaca penerbangan berbasis skor SMB II Palembang Hesti Annisa Jannah; Afina Meutya Putri; Rendra Gustriansyah
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 31 No. 2 (2026)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2026.v31i2.413

Abstract

Aviation safety is a concern in global air transportation, where adverse weather conditions, including heavy rainfall, high humidity, and strong winds, can disrupt flight operations and threaten passenger and crew safety. Sultan Mahmud Badaruddin II (SMB II) Airport in Palembang, South Sumatra, operates within a tropical climate marked by extreme humidity and frequent heavy rainfall. This study applies the interpretable Decision Tree algorithm using an information gain criterion to reproduce a multivariable weighted-scoring classification of same-day aviation weather risk and generate transparent, auditable decision rules. The study uses meteorological data from the Indonesian Meteorological, Climatological, and Geophysical Agency (BMKG), covering May 2025 to May 2026, comprising 371 daily records with five attributes: average temperature (Tāvg), relative humidity (RH_avg), rainfall (RR), wind direction (DDD_X), and wind speed (FF_avg). Risk labels were derived from a weighted-scoring system grounded in BMKG thresholds and references from the Civil Aviation Safety Regulation (CASR) and International Civil Aviation Organization (ICAO), yielding three classes: Safe (40.7%), Caution (39.1%), and Dangerous (20.2%). Data were split 80:20 with stratified sampling. The Synthetic Minority Over-sampling Technique (SMOTE) was applied to balance the training data. The model achieved 91.89% accuracy on the test set, with perfect recall on the Dangerous class (recall = 1.00, F1-score = 0.94). Because four of the five attributes are also used to construct the scoring labels, this accuracy primarily reflects the Decision Tree model's ability to reproduce the scoring structure rather than independently validating against actual operational risk.

Page 1 of 1 | Total Record : 5

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 31 No. 2 (2026) Vol. 31 No. 1 (2026) Vol. 30 No. 3 (2025) Vol 30, No 2 (2025) Vol 30, No 1 (2025) Vol 29, No 3 (2024) Vol 29, No 1 (2024) Vol 28, No 3 (2023) Vol 28, No 2 (2023) Vol 28, No 1 (2023) Vol 27, No 3 (2022) Vol 27, No 2 (2022) Vol 27, No 1 (2022) Vol 26, No 3 (2021) Vol 26, No 2 (2021) Vol 26, No 1 (2021) Vol 25, No 3 (2020) Vol 25, No 2 (2020) Vol 25, No 1 (2020) Vol 24, No 3 (2019) Vol 24, No 2 (2019) Vol 24, No 1 (2019) Vol 23, No 3 (2018) Vol 23, No 2 (2018) Vol 23, No 1 (2018) Vol 22, No 3 (2017) Vol 22, No 2 (2017) Vol 22, No 1 (2017) Vol 21, No 3 (2016) Vol 21, No 2 (2016) Vol 21, No 1 (2016) Vol 20, No 1 (2015) Vol 19, No 3 (2014) More Issue