Deployment and integration of smart sensors with IoT devices detecting fire disasters in huge forest environment

Abstract

Surveillance system applications are drastically growing from small buildings to a wide area of forest monitoring. Forests provide various important things to our daily lives like oxygen, honey. Living things like animals and birds are living in forests. Thus, it is essential to monitor and protect the forests and their assets. To do that, smart sensors have been deployed in the forest to monitor and record the environmental impacts. The abnormal events are identified and detected using the appropriate IoT devices to reduce the risk. Also, to improve the accuracy, the sensed data is analyzed, processed using a software module. Various existing approaches used for learning the data and object detection was good, but slow in the process, which fails in reducing risks. To overcome these issues, this paper utilizes one of the Deep Learning Algorithms such as the Convolution Neural Network (CNN) for Forest Monitoring and identifying the abnormality. The deep CNN has experimented with MATLAB software and the results are verified. The performance of deep CNN is evaluated by comparing the obtained results with the existing approaches and found that deep CNN outperforms the others.