Analysis of deep learning algorithm for predicting poultry diseases

Abstract

In recent years, the agricultural sector has increasingly embraced advanced technologies to tackle food security and animal health issues. Poultry farming, a crucial part of agriculture, faces significant challenges from diseases affecting poultry health and economic sustainability. This project employs Convolutional Neural Networks (CNNs), a form of deep learning, to enhance poultry disease prediction accuracy, using chicken diseases as a case study. CNNs have revolutionised various fields, including disease prediction, by extracting meaningful patterns from data like images. This project leverages CNNs to analyse a diverse dataset of chicken disease images, creating a robust prediction model. The process involves compiling an extensive dataset of high-resolution chicken disease images, designing a CNN architecture with convolutional and pooling layers, and exploring transfer learning from pre-trained models. Rigorous training, validation, hyperparameter tuning, and data augmentation ensure model reliability. The project’s goals are twofold: demonstrating the feasibility of using CNNs for poultry disease prediction and offering a comprehensive poultry disease prediction framework. The latter could enable early disease detection and target interventions, reducing economic losses and enhancing food security. The proposed model achieved an overall accuracy of 96.5% and an F1 score of 96.8% respectively, on the tested dataset of poultry disease, indicating its high performance in poultry disease prediction.