Development of a peanut allergen detection system using yolov8 for biolabs elisa kits/
Fatima Ysabel V. Alfonso, Jerico Simone F. Almarines, Hannah Mea F. Palcutan, Galilee T. Reyes, and Vincent M. Thompson.--
- Manila: Technological University of the Philippines, 2025.
- xiii, 135pages: 29cm.
Bachelor's thesis
College of Industrial Technology.--
Includes bibliographic references and index.
The continuing rise in deaths due to anaphylaxis highlighted the importance of improved allergen detection. This research aimed to develop a system using the YOLOv8 image processing algorithm to assist in interpreting ELISA test results for peanut allergens. The researchers proposed a system that utilized a device capable of analyzing Biolabs ELISA test kits and categorizing results into Low, Moderate, and High levels using Agile methodology to satisfy the objective of functional correctness, time behavior and efficiency. The accuracy of the system was found to correctly classify 31 out of 33 test samples, showing a 44.1% confidence level for Low classification, 36.0% for Moderate, and 55.2% for High classification, resulting in a 93.94% overall confidence match based on 710 trained images, with the lower accuracy attributed to background interference. The system was evaluated based on ISO 25010:2023 software quality and ISO 30141:2024 IoT quality standards, focusing on functional correctness, time behavior, usability, testability, and efficiency. The system correctly classified 31 out of 33 test samples, achieving a 93.94% overall confidence match. Evaluation scores were high in functional correctness (4.27), time behavior (4.25), usability (4.32), testability (3.53), and efficiency (4.37), resulting in an overall mean score of 4.15. In conclusion, the system demonstrated high efficiency and reliability in identifying peanut allergen levels through ELISA test colorimetry using the trained YOLOv8 model. This aligns with the United Nations Sustainable Development Goal (UN SDG) Goal 3, Good Health and Well-Being, UN SDG Goal 12, Responsible Consumption and Production, and UN SDG Goal 17, Partnerships for the Goals.