An equine disease diagnosis expert system based on improved reasoning of evidence credibility

Abstract

In China, there is a troubling shortage of well-trained equine veterinarians, leaving the needs of many equine farmers unmet. This is especially true with respect to the diagnosis of equine diseases. To solve this shortcoming, an equine disease diagnosis expert system was developed. For the aspect of knowledge representation, the structure of equine disease diagnosis knowledge was analyzed using an ontology system. Next, the clinical signs were described using an object-attribute-value (O-A-V) format, and the knowledge representation was then expressed using production rules. With respect to the reasoning mechanism, the weights of the clinical signs and promoted confidence factors (PCF) were combined to express information and rules pertaining to clinical signs with an associated level of uncertainty. The model was established based on improved reasoning of evidence credibility. Finally, using the ASP.Net platform and the SQL Server 2008 database, the equine disease diagnosis expert system based on the B/S structure has been developed, and is capable of reliably diagnosing 40 of the most common equine diseases. A functional evaluation of the system was conducted, and the diagnostic accuracy was observed to be 88%. This study demonstrates a bright prospect for the popularization and application of the system through continuous system maintenance and knowledge-based updates.