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 6 Documents
 1 
Search results for , issue "Vol. 30 No. 3 (2025)" : 6 Documents clear
Optimasi Hyperparameter Berbasis Bayesian dengan Optuna untuk Spectral Clustering - K-Means: Studi Kasus pada Dataset Leukemia CuMiDa Cahyaningrum, Rosalia Deviana; Hura, Hendy Fergus Atheri
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i3.16

Abstract

Leukemia is one of the cancers with the highest mortality rate worldwide; therefore, identifying its subtypes is crucial to support accurate diagnosis and effective treatment. The analysis of high-dimensional gene expression data, such as the CuMiDa dataset, still faces major challenges due to overlapping patterns and limited sample sizes. This study proposes the application of Bayesian Optimization using Optuna to perform hyperparameter tuning on the Spectral Clustering – K-Means method to improve the clustering performance of leukemia subtypes. Four key parameters (n_components, affinity method, n_neighbors, and gamma) were optimized through 1,000 iterations. The best configuration was obtained at n_components = 5 using the Nearest Neighbors method with n_neighbors = 6. The resulting Spectral Embedding matrix was then grouped using K-Means. The results showed that this approach achieved a clustering accuracy of 92,19%, outperforming both K-Means and Hierarchical Clustering when applied separately. Heatmap visualization demonstrated that the optimized method effectively grouped samples with similar gene expression patterns. This study demonstrates that the combination of Spectral Clustering–K-Means and Bayesian optimization using Optuna can improve the clustering quality of complex gene expression data and open up broader opportunities for application in other bioinformatics studies.
Strategi Pemeliharaan Berbasis CBM+ pada Mesin TPE331 untuk Meningkatkan Keandalan Operasional: Studi Kasus Pesawat CASA 212-200 di PT NTP Ramadhani, Agita; Amperiawan, Gita; Manawan, Maykel; Gani, Erzi Agson; Furqon, M Zainal
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i3.17

Abstract

Aircraft engine maintenance strategies have evolved from schedule-based approaches toward condition-driven systems that emphasize actual component health conditions. The TPE331 turboprop engine used on the CASA 212-200 aircraft is critical in supporting both military and civil aviation operations. However, its maintenance process faces challenges related to high operational intensity, diverse operating environments, spare part availability, and turnaround time. This research was conducted at PT Nusantara Turbin dan Propulsi (NTP) to analyze the existing maintenance system and to propose the implementation of Condition-Based Maintenance Plus (CBM+) as an optimization strategy. The research employed a qualitative descriptive approach using maintenance records, engine performance parameters, and operational cost data. The results show that CBM+ implementation has the potential to reduce unexpected downtime, improve cost efficiency by approximately 8–12%, and enhance fleet readiness through early detection of component degradation. This research demonstrates that CBM+ provides not only technical benefits but also strategic value in supporting the transformation of the national MRO industry toward data-driven maintenance practices.
Analisis Korelasi Antar Parameter QoS: Studi Kasus Kecepatan Data dan Consistency, Serta Hubungan Antara Latency dan Stabilitas Jaringan Utami, Priska Restu; Kristianti, Veronica Ernita; Afriyenny, Lince
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i3.65

Abstract

The growing demand for modern network services, including multimedia applications, real-time communications, and the Internet of Things (IoT), necessitates Quality of Service (QoS) evaluations that extend beyond high data transmission rates to encompass network stability and performance consistency. This study investigates the relationships among QoS parameters, with a particular focus on the correlation between throughput and network consistency, as well as the association between latency and service stability. A quantitative, non-experimental correlational approach was adopted using secondary QoS data derived from the open NordicDat dataset, which reflects real-world network measurements. The analyzed parameters comprise throughput, latency, jitter, and a derived consistency metric computed as an inverse function of jitter. Statistical analyses were performed using descriptive statistics and Pearson and Spearman correlation methods, supported by data visualizations in the form of scatter plots and boxplots. The results reveal that throughput exhibits a strong negative correlation with latency, while demonstrating only a weak positive relationship with network consistency. In contrast, latency and jitter show a more pronounced impact on service stability. The very strong negative association between jitter and consistency confirms that delay variation is a dominant factor in determining network performance stability. These findings indicate that high throughput alone does not ensure network consistency, underscoring the importance of a multidimensional QoS evaluation framework that simultaneously accounts for both transmission speed and stability-related parameters. The outcomes of this study provide valuable insights for the evaluation and design of modern networks that prioritize service quality and sustained performance
Optimalisasi Deteksi Tingkat Kematangan Tanda Buah Segar Kelapa Sawit Menggunakan YOLOV8 Dengan Platform Web Mardhiyah, Iffatul; Sari, Dyan Prawita; Genoveva, Zahwa; Kosasih, Rifki; Irawati, Dyah Cita
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i3.67

Abstract

Oil palm represents one of Indonesia’s principal commodities. Traditionally, farmers manually monitor the ripeness level of palm oil, but this method is neither effective nor efficient for large-scale harvests. Therefore, a system that can automatically detect the ripeness level of fresh fruit bunches (FFB) is needed. In this study, the YOLOv8 algorithm was used which was integrated into a web-based application. The system is designed to improve accuracy and efficiency in the grading process of oil palm fruits, which directly impacts the quality of processed products and palm oil production. The dataset used consists of 6.592 images obtained through the Roboflow platform, covering various ripeness categories. The system development follows the CRISP-DM approach, consisting of business understanding, data understanding, data preparation, modeling, evaluation and deployment. The model training process approximately 3,1 hours, with evaluation results showing a precision of 94,5%, recall of 94,7%, and a mean Average Precision (mAP) of 98%. The model’s performance is further supported by an F1-confidence curve of 95% and a precision-recall curve of 98%, indicating stable and accurate classification capabilities. The model is deployed through a Streamlit-based web interface, allowing users to perform real-time detection from images or videos without requiring additional installations.
Aplikasi Deteksi Website Phishing Berbasis Web Menggunakan Random Forest dan Ekstraksi Fitur URL Wulandari, Adytia Dwi; Irawati, Dyah Cita
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i3.71

Abstract

Advancements in information technology have raised growing concerns among various stakeholders. Phishing attacks have become one of the most common cyber threats, targeting users by imitating legitimate websites to obtain sensitive information. This study aims to develop a web-based application by implementing a supervised learning approach using the Random Forest algorithm to automatically classify URLs as phishing or legitimate. The dataset used consists of 11,054 URL instances with 30 URL-based features. The research process includes data preprocessing, feature extraction, data splitting, and classification model development and evaluation using four data partition scenarios. Model performance was assessed using accuracy, precision, recall, and F1-score as evaluation metrics. The results of the experiments show that the model achieved optimal performance with an 80:20 data split, obtaining an accuracy of 97%, precision of 97%, recall of 98%, and an F1-score of 97%. Furthermore, the trained model was implemented in a web-based application, allowing users to automatically detect URLs.
Deteksi Kerusakan Modul Surya Menggunakan Faster R-CNN ResNet-50 Ikhsan, Fathirul; Cahyaningtyas, Rizqia; Kuswardani, Dwina
Jurnal Ilmiah Teknologi dan Rekayasa Vol. 30 No. 3 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i3.116

Abstract

Solar modules play a crucial role in photovoltaic power generation systems, yet their performance can degrade due to physical and electrical damage. Therefore, automatic inspection is required to improve maintenance efficiency and prevent long-term performance loss. This study aims to implement an object detection approach for identifying solar module defects from visible RGB images using Faster R-CNN with a ResNet-50 backbone. The dataset was obtained from the Kaggle platform and manually annotated into PASCAL VOC format with two defect classes, namely physical damage and electrical damage, and expanded through data augmentation. The model was trained under several training configurations and evaluated using mean Average Precision (mAP), precision, recall, F1-score, and accuracy. The best performance was achieved using a batch size of 8, learning rate of 0.0001, and 30 epochs, resulting in 89% accuracy and 93% mAP. The results indicate that the model consistently detects both defect types and demonstrates potential for automated solar module inspection.

Page 1 of 1 | Total Record : 6

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue 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