Back to Search
Start Over
Embedded and machine learning based flood monitoring system using IoT.
- Source :
-
AIP Conference Proceedings . 2023, Vol. 2523 Issue 1, p1-7. 7p. - Publication Year :
- 2023
-
Abstract
- Flood catastrophes afflict millions of people throughout the world, inflicting significant loss of life and massive property damage. The Internet of Things (IoT) has been used in fields such as flood prediction, monitoring, and detection. Although IoT technologies cannot prevent flood catastrophes from occurring, they are an extremely important tool for transmitting disaster preparation and counteractive response data. Artificial neural networks have been used to make advances in flood prediction (ANN). Despite many advances in flood prediction systems through the use of ANN, there has been less emphasis on the use of edge computing to increase the efficiency and reliability of such systems.This paper proposes that all the automotive owners who use their cell phones should construct an Android application while traveling and receiving flood reports on their journeys. Working with an Arduino flood detection prototype, the application warns the user if the car is safe to travel through the flood, precautionary, or never traverse the road due to the flood. To detect the position of the user, the program will utilize the Smartphone GPS. Whenever the car owner enters the range of the prototype depending on the driver's position, the owner of the car informs the user by voice if it is acceptable. It also enables them to not stay in a flooded region, or worse, their motors might get damaged due to the floods in their motors since they did not realize how high a flood was and tried to cross it. The project's main objective is a Smartphone application that helps drivers monitor the street flood and assess if they can go on a flooded road. [ABSTRACT FROM AUTHOR]
- Subjects :
- *MACHINE learning
*INTERNET of things
*MOBILE apps
*CELL phones
Subjects
Details
- Language :
- English
- ISSN :
- 0094243X
- Volume :
- 2523
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- AIP Conference Proceedings
- Publication Type :
- Conference
- Accession number :
- 161617775
- Full Text :
- https://doi.org/10.1063/5.0111042