<![CDATA[This research aims to design and build an integrated system utilizing the Internet of Things (IoT) and Machine Learning (ML) for the optimization of sustainable aquaculture. The primary objective is to address key aquaculture challenges, including unstable water quality, feed inefficiency, and slow disease detection. The research design involves a real-time monitoring system using IoT sensors (pH, temperature, and dissolved oxygen) connected to an ESP32 microcontroller. The methodology consists of data collection from these sensors, which is then analyzed using machine learning algorithms: Linear Regression to predict water quality and a Decision Tree to classify fish health. The main outcomes show the system successfully monitors water quality in real-time. The Linear Regression model achieved a low Mean Squared Error (MSE) of 0.042 for predictions, and the Decision Tree model achieved a 93.7% accuracy in classifying fish health conditions. The conclusion is that this system is proven to be an effective decision support tool for enhancing the productivity and sustainability of aquaculture.]]>
Copyrights © 2025
