Jurnal Media Elektro

DESAIN APLIKASI DAN PENGUKURAN USER EXPERIENCE PADA BANKING SMART SYSTEM MENGGUNAKAN METODE SUPERGOLDEN RATIO

Nyoman Gunantara — Wed, 14 Oct 2026 05:43:12 +0000

PT Bank Perkreditan Rakyat Tapa cukup banyak mengalami kendala akan proses pembayaran kredit yang banyak dan bermasalah. Salah satu keluhan yang paling sering terjadi adalah terhambatnya proses penginputan data pembayaran kredit, hal ini tentu menjadi penghambat PT Bank Perkreditan Rakyat Tapa dalam melaksanakan tugasnya. Selain memiliki fungsi sesuai kebutuhan, aplikasi Banking Smart System harus juga memperhatikan User Interface (UI) dan User Experience (UX). Metode yang sudah banyak digunakan untuk membuat desain UI adalah Golden Ratio. Selain Golden Ratio, ada Ratio yang belum dikembangkan di bidang desain UI, Ratio tersebut adalah Supergolden Ratio. Supergolden Ratio adalah ratio diperoleh dari Ratio Limit Narayana Sequence yang bernilai 1,4656. Pada penelitian ini akan membuat desain aplikasi Banking Smart System yang didesain menggunakan metode Supergolden Ratio. Desain aplikasi Banking Smart System dan User Experience Questionnaire (UEQ) diberikan kepada pengguna untuk mengetahui pengalaman pengguna (UX) ketika menggunakan desain aplikasi Banking Smart System. Kuisioner UEQ akan diberikan kepada 50 pegawai di lingkungan PT Bank Perkreditan Rakyat Tapa. Hasil pengujian UEQ menunjukkan bahwa user experience dari desain aplikasi menggunakan metode Supergolden Ratio menunjukkan positif yaitu aspek daya tarik, kejelasan, efisiensi, ketepatan dan stimulasi memberikan hasil excellent, sedangkan aspek kebaruan memberikan hasil good.

ANALISIS DISSOLVED GAS ANALYSIS PADA TRANSFORMATOR BERBASIS FR3 OIL MENGGUNAKAN METODE DUVAL TRIANGLE

Gilang Al Ghaniyy, Tri Wrahatnolo — Wed, 14 Oct 2026 00:00:00 +0000

Power transformers are essential components of electrical power systems that require continuous condition monitoring to ensure reliable operation. One of the most widely used diagnostic techniques is Dissolved Gas Analysis (DGA), which detects internal faults by analyzing gases dissolved in insulating oil. This study aims to evaluate the condition of a transformer insulated with natural ester (FR3 oil) using Duval Triangle 3, Duval Triangle 6, and Duval Triangle 7. Historical DGA data from the Unit Auxiliary Transformer (UAT) #2A at Paiton Power Plant were analyzed using Project STARS, a web-based application developed with HTML and JavaScript. The results show that Duval Triangle 3 classified two datasets as Normal, three as T1 (Low Thermal Fault), and one as T3 (High Thermal Fault). Further analysis using Duval Triangle 6 resulted in Not Determined (N/D), while Duval Triangle 7 confirmed the T3 diagnosis. These findings demonstrate that the proposed approach supports systematic condition assessment of FR3 oil-insulated transformers for preventive maintenance.

IMAGE-BASED DETECTION OF SURFACE DAMAGE ON SHIP HULLS USING YOLOV8, FASTER R-CNN, AND SSD

Wed, 14 Oct 2026 00:00:00 +0000

Corrosion on ship hull surfaces poses a critical challenge in the maritime industry, directly affecting structural safety, fuel efficiency, and maintenance costs. Conventional manual visual inspection at drydocks is time-consuming, expensive, and poses potential safety hazards to inspectors. This study aims to develop an image-based ship hull corrosion detection system and objectively compare the performance of three deep learning architectures—YOLOv8, Faster R-CNN, and SSD300—under identical experimental conditions. The dataset combines the Marine Vessel Corrosion Dry-Dock Dataset (MaVeCoDD) with self-collected hull images, yielding a total of 76 images. Data were split consistently into training, validation, and testing subsets. Each model was trained via transfer learning from COCO pretrained weights and evaluated using mAP50, Precision, Recall, and F1-Score on the identical test set. Experimental results demonstrate that YOLOv8n outperforms the other architectures, achieving an mAP50 of 0.131, Precision of 0.313, Recall of 0.226, and F1-Score of 0.263. Faster R-CNN attained the highest Precision (0.651) but suffered from a low Recall (0.088), whereas SSD300 yielded the lowest performance with an mAP50 of 0.003. In conclusion, YOLOv8 proves to be the most suitable architecture for ship hull corrosion detection due to its superior balance between Precision and Recall compared to Faster R-CNN and SSD300.

YOLOv8-BASED SMART ALERT SYSTEM FOR DETECTING MAHRAM RESTRICTIONS IN CONFINED SPACES

Wed, 14 Oct 2026 00:00:00 +0000

This study aims to develop a YOLOv8-based intelligent security system (Smart Alert) to detect mahram boundary violations in restricted spaces, such as female dormitories. Utilizing the Research and Development (R&D) method with a Prototyping approach, the model was trained for 100 epochs using a custom dataset consisting of Male and Female classes. The results show that the model achieved optimal performance at epoch 20 with a mAP@50 of 0.840, Precision of 0.828, and accuracy rates of 0.78 for the Female class and 0.87 for the Male class. Upon detecting a male in the restricted area, the system automatically triggers a danger status and sends real-time notifications via a Telegram Bot. This system is proven effective in maintaining the privacy and security of dormitory residents in accordance with Islamic principles.

PERBAIKAN LOKAL KANDIDAT CACAT TANPA PEMBELAJARAN UNTUK INSPEKSI PCB BERBASIS TEMPLATE DENGAN KLASIFIKASI ROI SELEKTIF

Bernadectus Yudi Dwiandiyanta — Wed, 14 Oct 2026 05:48:42 +0000

Printed circuit board (PCB) defect inspection is difficult because many defects are small and visually subtle. This study proposes a template-based inspection method combining image differencing, learning-free local candidate refinement, and selective ROI classification. Initial candidates are obtained from aligned test and template images, then locally refined using grayscale residual information without adding new candidates. Refined ROIs are represented by test, template, and residual patches and classified using MobileNetV3-Small. On DeepPCB, candidate recall at IoU 0.20 increases from 0.3389 to 0.9586 and at IoU 0.30 from 0.1153 to 0.6344. ROI classification achieves 0.9874 accuracy and 0.9855 macro F1. With a rejection threshold of 0.90, coverage remains 0.9762 with macro F1 of 0.9927. The method improves coarse defect localization, although strict bounding-box localization remains limited.