Data-driven IoT-based Water Quality Monitoring and Potability Classification System in Rural Areas
Melchizedek Alipio
Abstract
Access to a safe and sustainable water source is a major problem especially in rural areas of developing countries. Water monitoring in different water resources has been practiced to ensure safe drinking water. However, manual monitoring of safe drinking water is known to be inconvenient since it requires high operational and transportation costs, and time-consuming. This work develops a water quality monitoring and potability classification system utilizing an Internet of Things framework. Portable sensor nodes capable of collecting physicochemical properties of water are deployed in different water sources from rural household areas. Data collected by nodes are being sent out wirelessly to a base station in real-time. The base station performs potability classification using ensemble learning. In addition, the base station sends the result of classification to households using 2G/3G communication. Also, the predicted output and the actual sensor data are being sent to a cloud server for remote monitoring via a web interface. Results show that the system achieves a 93.33% match with conventional industrial water laboratory tests. Moreover, the system is able to communicate the water potability status to households with minimal delay.