2021 | Mae Chew
Deep Convolutional Neural Networks as a Novel Approach to Real-Time Freshwater Quality Monitoring and the Prevention of Waterborne Disease Outbreaks
The discharge of sewage and industrial waste into the world’s freshwater bodies has become an increasingly alarming issue with highly pervasive implications: waterborne diseases contracted by exposure to contaminated water result in 3.4 million deaths each year. This project thus aims to establish a cost-effective and accurate method of real-time water impurity detection, and to design an early-warning system for water-borne disease outbreaks in rural and low-resource settings. A novel software application that applies deep convolutional neural networks and sensing technology to the bacteriological and chemical evaluation of freshwater sources was developed. When synergized with IoT, the application can facilitate communication with individual households, local governments, and health authorities, streamlining environmental support and increasing the efficacy of purification efforts.
