Penguins Disease Detector On Pododermatitis By Using Machine Learning (CNN)
Main Article Content
Abstract
In this research to the pressing challenge of pododermatitis affecting penguin populations, this study investigates the integration of Machine Learning (ML) as a solution for precise and timely detection. Utilizing an extensive dataset comprising images capturing foot conditions, we applied a Convolutional Neural Network (CNN) as our ML model. The outcomes were notably promising, with the model achieving a commendable accuracy of 95%, precision of 92%, and recall of 94% in identifying cases of pododermatitis. These results highlight the potential of ML as a powerful tool for early disease detection among penguins. Beyond its diagnostic prowess, the integration of ML significantly expedites the identification process, thereby contributing to more effective conservation strategies [1]. This study not only underscores the relevance of ML in wildlife health monitoring but also lays the groundwork for future research exploring ML applications in diverse wildlife health assessments. Pododermatitis commonly known as bumblefoot is a prevalent condition among captive penguins, leading to discomfort, impaired mobility, and even mortality if left untreated. Early detection is crucial for effective intervention and management. This study presents the development of a novel pododermatitis detection system tailored specifically for penguins utilizing advanced imaging techniques. The proposed system integrates high-resolution feet. These images are then processed using machine learning algorithms trained on a comprehensive dataset of both healthy and affected feet. The machine learning model employs feature extraction and classification techniques to differentiate between healthy and affected feet, enabling automated detection with high accuracy and efficiency. Moreover, the system provides real-time feedback, allowing for timely intervention by care takers and veterinaries. Preliminary testing of the developed system on a cohort of captive penguins has demonstrated promising results, with high sensitivity and specificity in identifying early signs of pododermatitis. Future work involves further validation on diverse penguins’ species and refinement of the detection algorithm to enhance performance in varied environmental conditions.