Development of a Secured IoT-Based Flood Monitoring and Forecasting System Using Genetic-Algorithm-Based Neuro-Fuzzy Network

The paper aims to provide a flood prediction system in the Philippines to increase flood awareness, which may help reduce property damage and save lives. Real-time flood status can significantly increase community awareness and preparedness. A flood model will simulate the flood level with secured data flow from the sensor to the cloud. The algorithms embedded in the flood predicting model include fuzzy logic, LSTM neural network, and genetic algorithm. The project used the Infineon security module (Infineon Technologies Philippines Inc., Metro Manila, Philippines) to create a secure connection from the setup to the AWS. All data transmitted were encrypted when being sent to AWS IoT Core, Timestream, and Grafana. After training and testing, the neuro-fuzzy LSTM network with genetic algorithm solution showed improved flood prediction accuracy of 92.91% compared to the ADAM solver that predicts every 2 h using an 0.02 initial learning rate, 1000 LSTM hidden layers, and 1000 epochs. The best solution predicts a flood every 3 h using an ADAM solver, a 0.01 initial learning rate, and 244 LSTM hidden layers for 158 epochs.