Classification of Batik Industry Wastewater Quality Using Machine Learning and IoT

Batik industrial wastewater contains various chemical substances that can pollute the environment and threaten human health. Therefore, it is important to monitor and analyze wastewater quality efficiently and accurately. In this study, we collect data on the quality of batik industrial wastewater using IoT technology. The data includes parameters such as pH, BOD (Biochemical Oxygen Demand), COD (Chemical Oxygen Demand), temperature, and other heavy metal concentrations. The data is then processed and prepared for the classification process. Machine Learning methods, especially classification algorithms, are implemented to classify wastewater quality into several categories based on predetermined quality standards. The three Machine Learning algorithms used in this research are SVM (Support Vector Machine), KNN (K-Nearest Neighbors), and DT (Decision Tree). The results of this study indicate that the use of the SVM, KNN, and DT algorithms in classifying the quality of batik industry wastewater produces a high degree of accuracy. This system can help identify potential problems in waste management more effectively. As such, this research makes an important contribution in the development of technological solutions to address environmental problems associated with the batik industry and has the potential to become a foundation for the development of better wastewater quality monitoring and analysis systems.