Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization
Dwi Putra, Sulistyo Emantoko
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Automated Detection of Molting Crabs Using YOLO: Enhancing Efficiency in Soft-Shell Crab Aquaculture Saputra, Dany Eka; Rangkuti, Abdul Haris; Dwi Putra, Sulistyo Emantoko; Daru Kusuma, Purba; Kurniawan, Albert; Gabriela, Melanie
JOIV : International Journal on Informatics Visualization Vol 9, No 5 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.5.3468

Abstract

Crab molting detection is a crucial process in aquaculture, particularly to produce soft-shell crabs, which are considered a delicacy in many markets. Traditional methods of manually monitoring crabs for molting are labor-intensive and susceptible to human error. To address this challenge, this study examines the application of the YOLO (You Only Look Once) object detection model for automating the detection of molting crabs. YOLO is renowned for its capability to perform real-time object detection, making it an ideal choice for this application. Our research focuses on developing a YOLO-based system that accurately identifies molting crabs from videos or images captured in farming environments. The model was trained on a comprehensive dataset comprising images of crabs at various stages of molting, ensuring robustness against environmental variations and different lighting conditions commonly encountered in aquaculture settings. The results indicate that the YOLO model achieves high accuracy in detecting molting crabs, significantly enhancing the efficiency and reliability of the detection process compared to manual observation and other machine learning approaches. These advancements facilitate timely intervention and harvesting, which are critical for optimizing the quality and yield of soft-shell crabs. In our experiments, the recognition of the crab molting process was categorized into three classes: the molting crab, the crab skin, and the newly molted crab. Overall, the YOLOv8 and YOLOv11 models demonstrated impressive performance, achieving an average accuracy of 96% to 98%. This research on molting crab detection has proven successful and can be further extended to include other types of crabs.
Co-Authors Albert Kurniawan, Albert Gabriela, Melanie Purba Daru Kusuma Rangkuti, Abdul Haris Saputra, Dany Eka