Intelligent Wireless Sensor Networks for Early Fire Warning System

Year 2019, , 0 - 0, 27.08.2019

Atıf Fazıl Önal Bural Ulver Alper Durusoy Burcu Erkmen

Abstract

DOI: 10.26650/electrica.2019.19019

Forest and wide area fires are one of the
biggest obstacles to the protection of green areas, which are the life
guarantee for future generations. These fires, which constitute a major threat
to the ecosystem, can lead to human and animal deaths. In this work, an early
warning system was proposed to detect forest fires with wireless sensor networks.
The wireless sensor network consists of spatially distributed sensors to
analyze the situations of the environment for various scenarios. Near real-time
data from various sensors are transmitted to the server within mesh network
structure via redundant paths using low cost and low power Zigbee. The
communication in the system is continued thanks to this mesh design without any
loss of data when there is a connection break between the sensor nodes and the
beacons. Multi-layer feed forward neural networks are utilized for
decision-making stage by adopting to the conditions of the environment rhythms.
By designing a graphical user interface that works on a local machine, the
approximate location of the modules, status color codes and status visualization
with Google Maps on web server and notification of the relevant authorities are
provided. 

Cite this article as: Önal AF, Ülver B,
Durusoy A, Erkmen B. Intelligent Wireless Sensor Networks for Early Fire
Warning System. Electrica, vol. 19, DOI: 10.26650/electrica.2019.19019.

Keywords

Wireless sensor networks, forest fires, feed forward neural networks, warning system, web server

References

• 1. P. Cheong, K. Chang, Y. Lai, S. KamHo, I. Sou, K. Tam, "A ZigBee-Based Wireless Sensor Network Node for Ultraviolet Detection of Flame", IEEE Transactions on industrial electronics, vol. 58, no. 11, pp. 5271-5277, November 2011. 2. M. Hefeeda, M. Bagheri, Wireless Sensor Networks for Early Detection of Forest Fires. In Proceedings of the 2007 IEEE International Conf. on Mobile Adhoc and Sensor Systems, pp. 1-6, Pisa, Italy, October 2007. 3. M. Bahrepour, N. Meratnia, M. Poel, Z. Taghikhaki, P. J. M. Havinga, "Distributed Event Detection in Wireless Sensor Networks for Disaster Management," in Intelligent Networking and Collaborative Systems, 2nd International Conference on, pp. 507-512, Thessaloniki, Greece, November 2010, 4. P. U. S. Bolourchi, "Forest Fire Detection in Wireless Sensor Network Using Fuzzy Logic," Fifth International Conference on Computational Intelligence, Communication Systems and Networks, pp. 83-87, Spain, June 2013. 5. J. Zhang, W. Li, Z. Yin, S. Liu, X. Guo, ''Forest fire detection system based on wireless sensor network,'' in Proc 4th IEEE Conf Ind Electron Appl (ICIEA), pp. 520-523, Xi'an, China, May 2009. 6. S. Mohapatra, P. M. Khilar, "Forest fire monitoring and detection of faulty nodes using wireless sensor network". In IEEE Region 10 Conference (TENCON) pp. 3232-3236, Singapore, 2016. 7. S. Anand, R. K. Keetha Manjari,''FPGA implementation of artificial Neural Network for forest fire detection in wireless Sensor Network'' in Computing and Communications Technologies (ICCCT), 2017 2nd International Conference on, Singapore, February 2017. 8. H. Soliman, K. Sudan, A. Mishra, "A Smart Forest-Fire Early Detection Sensory System: Another Approach of Utilizing Wireless Sensor and Neural Networks" in IEEE Sensors Conference, Pittsburgh, PA, USA, November 1-4, 2010. 9. A. Chehri, W. Farjow, H. T. Mouftah, X. Fernando, "Design of Wireless Sensor Network for Mine Safety Monitoring" in 24th Canadian Conference on Electrical and Computer Engineering, Ontario, Canada, May 8-11, 2011. 10. A. K. Jain, A. Khare, K. K. Pandey, "Developing an Efficient Framework for Real Time Monitoring of Forest Fire Using Wireless Sensor Network" in Second IEEE International Conference on Parallel, Distributed and Grid Computing Conference, Solan, Himachal Pradesh, India, 6th to 8th December 2012. 11. A. Bayo, D. Antolin, N. Medrano, B. Calvo, S. Celma, "Development of a Wireless Sensor Network System for Early Forest Fire Detection" in European Workshop on Smart Objects: Systems, Technologies and Applications, Ciudad, Spain, 15-16 June 2010. 12. Z. Chaczko, F. Ahmad, "Wirelee Sensor Network Based System for Fire Endangered Areas" in Third International Conference on Information Technology and Applications (ICITA'05), Sydney, NSW, Australia, 4-7 July 2005. 13. X. Yunjie, ''Wireless sensor monitoring system of Canadian Poplar Forests based on Internet of Things'', Artifcial Life and Robotics, pp: 1-9, 2019. 14. Y.E. Aslan, I. Korpeoglu, O. Ulusoy, ''A framework for use of wireless sensor networks in forest fire detectionand monitoring'', pp: 614-625, Computers, Environment and Urban Systems, No: 36, 2012 15. J. Yao, X. Zhang, A.T. Murray, "Location optimization of urbanfire stations: Access and service coverage" Computers, Environment and Urban Systems, pp: 184-190, No: 73, 2019 16. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, ''TensorFlow: Large-scale machine learning on heterogeneous systems", Available from URL: http://download.tensorflow.org/paper/whitepaper2015.pdf. 17. F. Chollet, (2015) Keras, GitHub. Retrieved from https://github.com/fchollet/keras. 18. D. Kingma, J. Ba, "Adam: A Method For Stochastic Optimization", The International Conference on Learning Representations, May 2015.
• Atif Fazıl Onal: Kocasinan, Kayseri, in 1995. He recieved the B.S. degree in department of electronics and communications engineering from Yildiz Technical University in 2019. His research interests focus on computer security, techniques for network penetration tests and intrusion detection systems.
• Burak Ulver: Merkez, Kırklareli, in 1995. He recieved the B.S. degree in department of electronics and communications engineering from Yildiz Technical University in 2019. His research interests focus on machine intelligence, machine perception, algorithms and theory.
• Alper Durusoy: Karaman, Denizli, in 1995. He recieved the B.S. degree in department of electronics and communications engineering from Yildiz Technical University in 2019. His research interests focus on digital signal processing, pattern recognition and algorithms.
• Burcu Erkmen: Eskişehir, in 1978. She received the B.S., M.S., and Ph.D. degrees in electronics and communication engineering from Yildiz Technical University, Istanbul, Turkey, in 1999, 2001, and 2007, respectively. From 1999 to 2009, she was a Research Assistant in the Department of Electronics and Communications Engineering, Yildiz Technical University, where she has been an associate professor since 2014. Her current research interests include switching power supplies, Optimization Techniques in Electronic Circuits, Artificial Intelligence and Embedded Systems.