International Journal of Advanced Computer Science and Applications · 2020 · 82 citations · 14 references
ComputingAutonomous SystemsComputer ScienceComputer VisionInternet Of ThingsMachine LearningDeep LearningEnvironmental Sensor NetworksFire DetectionIot SensorsSensor NetworksWireless Sensor NetworksDeep Learning DetectionDeep Learning-based DetectionForest Fire DetectionForest Fire MonitoringInternet Of Things SensingLow-power Wide-area NetworksReal-time MonitoringWireless Fire Detection Systems
Due to the global warming, which mechanically increases the risk of starting fires. The number of forest fires is increasing and will increase more and more. To better support the fire soldiers on the ground, we present in this work a system for early detection of forest fires. This system is more precise compared to traditional surveillance approaches such as lookout towers and satellite surveillance. The proposed system is based on collecting environmental wireless sensor network data from the forest and predicting the occurrence of a forest fire using artificial intelligence, more particularly Deep Learning (DL) models. The combination of such a system based on the concept of the Internet of Things (IoT) is made up of a Low Power Wide Area Network (LPWAN), fixed or mobile sensors and a good suitable model of deep learning. That several models derived from deep learning were evaluated and compared enabled us to show the feasibility of an autonomous and real-time environmental monitoring platform for dynamic risk factors of forest fires.
14
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Recent Advances in Recurrent Neural Networks
Hojjat Salehinejad, Joseph Barfett, Errol Colak et al. · arXiv (Cornell University) · 2017 · 584 citations · Full text
Gate-variants of Gated Recurrent Unit (GRU) neural networks
Rahul Dey, Fathi M. Salem · 2017 · 202 citations · Full text