<![CDATA[Water quality is a critical factor in ornamental fish maintenance because it directly affects fish health and aquarium ecosystem stability. Parameters such as pH, temperature, and turbidity must be monitored regularly to maintain suitable water conditions. However, water quality monitoring and water replacement scheduling are often performed manually, which may lead to delayed responses when water quality deteriorates. This study aims to develop an Internet of Things (IoT) and Machine Learning-based Smart Aquarium system for real-time water quality monitoring and water replacement prediction. The system utilizes pH, DS18B20 temperature, and turbidity sensors connected to an ESP32 microcontroller to continuously collect water quality data. Sensor data are transmitted to a Flask-based server and stored in a MySQL database for further analysis. A Decision Tree algorithm is employed to classify water conditions into ideal and non-ideal categories, while a Gradient Boosting Regressor is used to predict the remaining days before water replacement is required. Experimental results show that the Decision Tree model achieved an accuracy of 100%, while the Gradient Boosting Regressor obtained a Root Mean Squared Error (RMSE) of 0.44. The developed system is capable of monitoring water quality and providing water replacement predictions, providing information about water conditions, and assisting users in determining the optimal time for water replacement more effectively and efficiently.]]>
