Deep Learning Based Classification of Poultry Disease

Abstract

Poultry diseases including Coccidiosis, Salmonella, and Newcastle can lower chicken productivity if they are not detected early on. Deep learning algorithms can assist with the early identification of diseases. In this study, a Convolutional Neural Network based framework has been proposed to classify poultry diseases by distinguishing healthy and unhealthy fecal images. Unhealthy images can be a sign of the poultry diseases. The Image Classification dataset was used to train the framework, and it was discovered that it performed with an accuracy of 99.99%, 96.05%, 93.23% on the training set, validation set, testing set respectively. When the proposed network's performance was evaluated against pre-trained models, it was discovered that the proposed model was unquestionably the best one for classifying chicken disease. This framework can beat resource-intensive machine learning methods due to the trained model's reduced weight and can be implemented with a small amount of memory and computational power.