Aquatic Environment Monitoring Using Linear Regression and Fuzzy Logic on Internet of Things (IoT) System to Stabilize Measurement Values

Water quality linearly significantly affects the health of aquatic organisms. This study introduces an Internet of Things (IoT) enabled system for automating pH regulation and turbidity measurement in aquaculture environments. With integrated pH and turbidity sensors, the system collects real-time data processed via a microcontroller and adjusts water pH using an acid/base dispenser. System tests validate precise pH adjustment and prompt turbidity detection using fuzzy logic algorithms and linear regression models. The experiment used samples including two buffer powders (pH 6.86 and 4.00) for pH sensor calibration and turbidity sensor evaluation. The pH sensor stabilized from initial deviations to consistent measurements near target values, while the turbidity sensor effectively distinguished between clear and turbid conditions. The results demonstrate that implementing fuzzy logic and linear regression models provides accurate and reliable measurements, enhancing aquaculture maintenance efficiency and holding potential for broader applications in industrial fish farming. To validate the effectiveness of the proposed approach, performance indices were computed, showing a pH stability rate of 98% and a turbidity classification accuracy of 95%, which are improvements over conventional methods by 10% and 15%, respectively.