<![CDATA[Introduction: Heavy metal pollution is a serious environmental issue that can damage human health and ecosystems. The main sources of heavy metal pollution come from industrial activities and natural processes. Heavy metals such as lead (Pb), arsenic (As), and cadmium (Cd) have the potential to cause serious health problems in humans and flora and fauna. Purposed: To develop a water quality monitoring system based on electrochemical sensors and machine learning models to detect heavy metal concentrations in water in real-time. Research Methods: This includes sensor design, calibration, data collection, and training machine learning models such as logistic regression, decision tree, and artificial neural network (ANN). Results: Electrochemical sensors integrated with IoT technology were able to detect heavy metals with good accuracy. Testing was conducted at four different locations, and the highest lead (Pb) concentration was found in the C River (150.8 µg/L). The evaluation of machine learning models showed that ANN performed the best with the lowest MAE (2.5), followed by Decision Tree (2.8) and Logistic Regression (3.2). This system provides an efficient solution for real-time water quality monitoring and can be implemented in more sustainable water resource management. This study suggests further development of cloud-based monitoring systems and the use of more complex models like deep learning to improve system accuracy and flexibility.]]>
Copyrights © 2025
