I Gede Angga Saputra
Politeknik Negeri Bali

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Hyperparameter Tuning of YOLOv8n for Real-Time Material Truck Detection I Gede Angga Saputra; I Nyoman Eddy Indrayana; Ida Bagus Adisimakrisna Peling
Jurnal Teknologi Informasi dan Pendidikan Vol. 19 No. 2 (2026): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v19i2.1138

Abstract

The increasing number of material trucks on arterial roads has posed challenges for traffic surveillance and regulatory compliance. Traditional monitoring techniques that rely on manual observation are often ineffective and susceptible to irregularities, highlighting the need for automated real-time monitoring systems. This study proposes a lightweight object detection approach using YOLOv8n to improve real-time truck detection performance in traffic monitoring applications. A quantitative experimental methodology was employed by performing hyperparameter tuning through adjustments to the number of epochs, batch size, optimizer, and learning rate. The dataset was collected from real traffic environments using smartphone cameras and CCTV (TP-Link Tapo C320WS). A total of 36 experimental configurations were evaluated using Precision, Recall, F1-score, mAP@50, and mAP@50–95 metrics. Experimental results showed that the optimal configuration, consisting of 100 epochs, a batch size of 16, the Adam optimizer, and a learning rate of 0.001, achieved a mean Average Precision (mAP)@50 of 0.9302 and mAP@50–95 of 0.7226. Although the performance improvement over the baseline YOLOv8n model was relatively modest, repeated experiments demonstrated improved model stability and consistency after hyperparameter optimization. Real-time deployment on a local GPU achieved a stable processing speed of 14–23 Frames Per Second, with an average of 19 FPS, enabling real-time monitoring performance aligned with the camera input rate. The integrated system successfully combines object detection, tracking, and license plate recognition for practical traffic monitoring applications. However, smaller objects such as license plates remained more challenging to detect due to localization limitations under occlusion and low-light conditions.
Banana Ripeness Identification Using CLAHE-Enhanced HSV Images and K-Means Clustering Ida Bagus Adisimakrisna Peling; Made Pasek Agus Ariawan; I Gede Angga Saputra
Bulletin of Network Engineer and Informatics Vol. 4 No. 2 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) October 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/83w00p83

Abstract

The sorting stage of banana ripeness in the post-harvest industry is generally still performed manually, which is highly susceptible to human subjectivity and the risk of physical damage to the fruit. This study aims to design a banana ripeness classification system (raw, half-ripe, and ripe) based on digital image processing by combining the Contrast Limited Adaptive Histogram Equalization (CLAHE) and K-Means Clustering methods. The CLAHE method is applied to the Value (V) channel of the HSV color space to improve local contrast and stabilize lighting variations. Object segmentation from the background is executed using K-Means Clustering (k=2) based on the highest saturation value, refined through morphological operations and Canny edge detection. The average HSV parameters and dominant color ratios (green, yellow, brown) are extracted to be classified using rule-based logic. Testing was conducted on 280 test images consisting of 99 raw images, 122 half-ripe images, and 59 ripe images. The experimental results demonstrate that the system achieves an overall accuracy of 94.64%, with F1-Score values of 94.53% (raw), 93.67% (half-ripe), and 96.72% (ripe). These results indicate that the integration of CLAHE-enhanced HSV features, K-Means-based segmentation, and rule-based classification provides a reliable approach for automated banana ripeness identification under varying imaging conditions.