The increasing prevalence of animal diseases, along with the increasing need for animal products, highlights the urgent need for efficient diagnostic tools in veterinary medicine. The aim of this research is to create an expert system that uses a forward chaining algorithm to diagnose animal diseases. The forward chaining algorithm is a deductive reasoning approach that starts with existing facts and uses expert tree rules for hypotheses. This process continues until the desired goal is achieved or no additional conclusions can be drawn. Even though there are developments in expert systems, there are still shortcomings in implementing the forward chain for rapid and precise diagnosis of livestock diseases. This work aims to fill this gap by developing an expert system that improves the accuracy and efficiency of disease diagnosis in the livestock industry. A database of animal diseases and symptoms was created by observing and interacting directly with farmers. The system architecture is specifically intended to optimize data processing and user engagement, enabling rapid diagnosis and treatment recommendations. This test shows a level of accuracy and precision, thereby reducing the possibility of misdiagnosis. The capacity of expert systems to provide fast and reliable diagnoses has the potential to improve livestock health management, thereby helping farmers maintain animal welfare and productivity. The results of this work advance the field of veterinary diagnostics and propose other uses of expert systems in animal health management.
Read full abstract