Exploration and Implementation of Computational Convolutional Neural Network Model for Poultry Disease Detection

Background: Despite a remarkable growth track of the poultry industry over the last two decades, the challenges remain significantly dominant. The production decreased due to disease outbreaks. The stacking and confinements of fowl lead to widespread infections and a sharp decline in the productivity of farms. Rapid detection of diseases to prevent such outbreaks requires constant monitoring with minimum dependence on human intervention. Computer vision and the use of AI-enabled algorithms facilitate timely screening and surveillance of the flock to prevent disease spread. Methods: In this work, the sequential CNN model is used to explore the classification of diseases in poultry. The dataset is sourced from the Zenodo database and contains nearly 7,721 images. The preprocessing of the images is done via the Keras image dataset generator. The model focuses on the identification of three distinct classes of diseases from the faecal images of the chicken droppings. The use of a smaller convolutional filter minimises the network’s tendency to overfit during training. Result: The study evaluated the efficacy of a classification model by considering many criteria such as dataset features, hyperparameters and model architecture. The model has a remarkable overall accuracy of 94.32%, indicating its strong categorisation capabilities across several categories. Although the model has a high overall accuracy, it exhibits differing degrees of performance across several classes, suggesting that there is potential for development in some areas.