Publication

Abstract : In aquaculture, detecting fish diseases early is crucial for farmers to prevent outbreaks and financial losses. These diseases, often caused by viruses and bacteria, disrupt water quality parameters, leading to fish mortality. Inspired by recent successes in machine learning, this study utilizes cutting-edge algorithms to swiftly and accurately detect and predict water quality degradation. This research proposes the use of machine learning techniques to enable early identification of diseases in fish populations by predicting deteriorating water quality conditions. The aim is to provide stakeholders with a system that allows them to take preventive actions before disease outbreaks occur. The study evaluated the performance of several machine learning models, including Logistic Regression, Support Vector Machines (SVM), Multilayer Perceptrons (MLP), and Random Forest classifiers, in predicting disease occurrences. Among these techniques, the Random Forest algorithm demonstrated the highest predictive accuracy, achieving 98.97% correct classification of diseased and non-diseased cases. This integration of machine learning enhances aquaculture management, safeguarding against economic losses and fostering sector resilience. A web application utilizing machine learning predicts fish disease outbreaks based on real-time water quality data, providing early warnings to aquaculture farmers. It offers proactive measures to mitigate risks and promotes sustainable aquaculture practices.