Performance Analysis of ML Algorithms for Disease Prediction Using Water Quality Parameters

This article delves into the utilization of machine learning algorithms to advance water quality prediction and disease prediction within aquaculture. Through the integration of technology-driven solutions, such as cutting-edge monitoring systems and predictive analytics, our objective is to optimize efficiency, productivity, and environmental stewardship in fish farming practices. In our comparative analysis of various machine learning models based on accuracy scores, Random Forest emerges as the standout performer, boasting an impressive accuracy of $\mathbf{9 8. 3 5 \%}$. This exceptional performance is attributed to Random Forest’s ensemble nature, resilience to over fitting, and adept handling of complex data structures. While alternative classifiers like Logistic Regression and Support Vector Machines demonstrate satisfactory performance, the superior accuracy of Random Forest underscores its potential to revolutionize aquaculture practices. By harnessing advanced technologies like machine learning algorithms, we aim to propel sustainable aquaculture production while ensuring economic viability and environmental conservation.