Breed Lineage Prediction of Small Ruminants Using Deep Learning

Abstract

Sheep are a significant food source for humans, besides cattle and poultry. Despite its significance to Malaysian Muslims, who make up approximately 60% of the local population, the sheep supply is limited by the high mortality rate caused by fatal diseases such as foot and mouth disease (FMD) and tetanus. Infected sheep can spread food-borne bacteria, such as Escherichia coli, at various preparation phases, contaminating the meat. The objectives of this study are to identify internal and external factors that influence sheep breed lineage continuity, investigate current practices for collecting and managing data knowledge on sheep breed and hereditary diseases, and propose a sheep breed and disease data knowledge model based on the feedforward artificial neural network (FANN) deep learning method. This study utilized qualitative and quantitative data to obtain in-depth answers to the research questions, which involves collecting all the information required for the system development using the FANN deep learning method. This study found that breeding is the leading data group for tracking each sheep's ADG and BCS. Feed type, sanitization, and medication influence sheep’s daily increase and health. Collaboration, worker knowledge, and climate are recognized as external factors that potentially influence sheep's daily increase. The interview analysis also suggested attributes that could contribute to detecting breed lineage, including breed, category, ADG, and BCS. Therefore, it is recommended that future research adopt this method for other farmed animals.