Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Ambidextrous : Journal of Innovation, Efficiency and Technology in Organization
Ovan Pramana Putra
Prodi Informatika, Universitas Islam Majapahit
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Implementation of the Yolov8 Model for Component Detection and Image-Based Free Nutritional Food Nutrition Ovan Pramana Putra; Ronny Makhfuddin Akbar; Ahmad Syaifuddin
Ambidextrous Journal of Innovation Efficiency and Technology in Organization Vol. 5 No. 03 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization
Publisher : Takaza Innovatix Labs Ltd.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61536/ambidextrous.v5i03.698

Abstract

The Free Nutritional Food Program (MBG) is a government effort to improve the nutritional status of students by providing balanced nutritious meals. However, the process of verifying food components and evaluating nutritional content is still done manually, which is time-consuming, subjective, and inefficient. Previous studies have applied the YOLO algorithm for food detection and calorie estimation, but generally focused on individual consumption or only produced energy estimates. This study proposes the implementation of the YOLOv8 model integrated with a nutrition database to detect food components and estimate energy, protein, fat, and carbohydrates in the image-based Free Nutritional Food package. The dataset was obtained by extracting videos from the MBG package into 400 images consisting of 19 food classes. The dataset was annotated using bounding boxes, preprocessed, augmented, and divided into training, validation, and testing data. The model was trained using Roboflow with GPU support, then the detection results were integrated with the nutrition API and implemented in a web application to automatically present nutritional information. System performance was evaluated using precision, recall, and mean Average Precision (mAP) metrics. The contribution of this research is the development of an integrated system based on YOLOv8 to support monitoring of MBG nutritional quality objectively, efficiently, accurately, adaptively, sustainably, and support artificial intelligence-based decision making.
Co-Authors Ahmad Syaifuddin Ronny Makhfuddin Akbar