Fish Disease Detection Model using Multidomain Feature Analysis

In aquaculture, the early and accurate detection of fish diseases is crucial to prevent widespread epidemics and ensure sustainable fish farming operations. However, current fish disease detection methods often rely on manual inspection, which is labor-intensive, timeconsuming, and prone to human error. Additionally, existing automated methods are limited in their ability to handle complex and diverse fish images, thus impacting their effectiveness and reliability. Addressing these challenges, this study presents the design and evaluation of an efficient fish disease detection model that incorporates multidomain feature analysis with incremental Deep Q Learning operations. In comparison to existing methods, the proposed model exhibits significant improvements, achieving 10.5% higher precision, 8.3% higher accuracy, 9.4% higher recall, 4.5% higher AUC, and 3.9% higher specificity levels. The proposed model is broadly applicable to various fish species and farm environments, enhancing its potential for widespread adoption and positive impact on the aquaculture industry for different scenarios.