An IoT-Based Sanitation Monitoring System Using Machine Learning for Stagnant Water to Prevent Water-Borne Diseases
In low and middle-income countries, people die as a result of unhygienic water quality each year. The proposed method monitors stagnant water quality. Improving sanitation facilities by prior detection of contamination depends on both knowledge and resources (both microbiological and personnel). The proposed method uses Node MCU as core controller and various sensors to monitor the water quality. The micro controller will access the data from different sensors and then processes the data. Once the data is collected, the data is fed into machine learning models, and it is trained using machine learning algorithms (classification - SVM) or neural networks (ANN). Productive decision can be made out of the results from the model. Model will be trained using the parameters such as temperature, dissolved oxygen (D.O.), pH, biochemical oxygen demand (B.O.D), Nitrate-N and Nitrite-N, and fecal coliform. The outcome of the proposed work gives a complete report about contamination in the stagnant water and gives early alert to municipalities for preventing water-borne diseases.