Machine Learning-Based Recognition of White Blood Cells in Juvenile Visayan Warty Pigs

Accurately monitoring the health of visayan warty pigs, especially through blood sample analysis, provides conser-vationists and researchers with deeper insights into their immune responses and overall well-being. However, manually recognizing white blood cells (WBCs) in blood smears is labor-intensive, and automation can be costly. To address these challenges, this research employs machine learning techniques for WBC recognition. Machine learning algorithms aim to establish a comprehensive mathematical framework for categorizing images into predefined classes. This involves iterative weight optimizations using gradient descent to minimize the loss or cost function. Diverse machine learning algorithms were applied and compared, with the best-performing one fine-tuned for increased robust-ness and accuracy enhancement. The leading machine learning model showcased remarkable accuracy in classifying WBCs from juvenile visayan warty pigs, achieving an impressive 96.99% accuracy rate. While this success underscores the potential of machine learning, the study also highlights its limitations. As refinement of these methods persists, advanced technologies will unquestionably play a pivotal role in safeguarding endangered species and preserving biodiversity for future generations.