Quality Level Identification of Stored Chicken Using Machine Learning Algorithms

This research addresses the need for accurate and efficient identification of chicken meat quality. By applying machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), a comprehensive strategy for determining the quality levels of stored chicken has been developed. Experimental results demonstrate the effectiveness of these techniques in accurately identifying quality levels. While SVM achieved 97% accuracy, the classifiers K-Nearest Neighbors, Random Forest, and Decision Tree achieved 89%, 81%, and 72% accuracy, respectively. This work highlights the potential of machine learning algorithms to enhance quality control and address food safety issues in the poultry industry. By automating the quality identification process, our approach provides a more efficient and objective method compared to traditional subjective evaluations. This research bridges the gap between traditional evaluation methods and modern technological advancements, contributing to the broader fields of AI and the food industry, ultimately enhancing food safety and customer satisfaction.