Expert Systems for Farmed Fish Disease Diagnosis: An Overview and a Proposal

Abstract

The expert system approach, although quite old, is still quite effective in scientific areas where experts are required to make diagnoses and predictions. One of those areas is fish disease diagnosis. It is an application domain that currently employs complicated processes, which require high level skills for making accurate diagnoses. On the other hand, complete datasets for full diagnosis to be able to use machine learning techniques are not available. Therefore, in aquaculture, now more than ever, fish farmers do not have the required expertise or equipment to accurately diagnose a fish disease. For that reason, expert systems that can help in the diagnosis, prevention, and treatment of diseases have been developed. In this paper, we attempt to give an overview of the expert system approaches for fish disease diagnosis developed in the last two decades. Based on the analysis of their technical and non-technical characteristics, we propose an expert system architecture and a fish disease diagnosis process aiming at improving the deficiencies of the existing systems. The proposed system can handle all types of fish diseases based on image and non-image data as well as on molecular test results and can provide explanations. The diagnosis process goes through four consecutive levels, where each next level considers an additional category of parameters and provides diagnoses with a higher certainty.

Using Level-Based Multiple Reasoning in a Web-Based Intelligent System for the Diagnosis of Farmed Fish Diseases

“…On the other hand, ML and DL methods cannot give any explanation about their outputs (decisions), while explanations are very desirable in such systems [11]. So, although the expert system approach is an old one, it is still necessary as a primary framework for full fish disease diagnosis [12].…”

“…Therefore, in this paper, we propose and present a web-based intelligent system for farmed European sea bass disease diagnosis that uses a combination of the ES approach with other KR approaches and a level-based diagnostic process. It can be regarded as an implementation of the general architecture proposed in [12]. Our main focus is on the hybrid reasoning scheme introduced here.…”