Sheep and goat expert system using artificial bee colony (ABC) algorithm and particle swarm optimization (PSO) algorithm

Machine learning is a subfield of Artificial Intelligence, concerned with the development of algorithms that allow computers to learn based on data, such as sensor data or databases. A major focus of machine learning research is to automatically learn to recognize complex patterns and make intelligent decisions based on such data. In this paper both sheep and goat disease database is created using rule-based techniques and machine-learning algorithms (ABC and PSO). These techniques are also applied on this database to develop expert systems to diagnose the diseases affected to sheep and goat animals. The system diagnoses the diseases for the different symptoms entered by the user dynamically. If the symptoms entered by the user matches to the rules already available in the Knowledge base designed by the expert, it displays the actual disease with which sheep is suffering with. Else it displays a message saying that the knowledge is insufficient. In this case the system calls the technique called, Particle Swarm Optimization. Using this system determines the narrowest probabilistic disease with which the animal is suffering. Here the PSO technique is grouping by the intelligence in order to get the optimistic solution for the entered symptoms by the user. The proposed system is also supported by another feature called as Artificial Bee Colony Optimization i.e., a probabilistic application to enhance the capabilities.