Deep Learning Based Temperature Sensor Data and Wildfire Propagation Prediction in Duty Cycled Wireless Sensor Network 


Vol. 44,  No. 6, pp. 1092-1104, Jun.  2019
10.7840/kics.2019.44.6.1092


PDF Full-Text
  Abstract

Wireless Sensor Networks can detect wildfire using real-time temperature data collected by temperature sensors. In wireless sensor networks for monitoring disaster areas, sensors can enter into sleep mode at regular interval in order to minimize energy consumption, resulting in limited sensing information in the entire networks. In this paper, to solve this problem, we propose a deep learning based method that can estimate inactive sensor’s data, and predict sensor data in any desired time. To obtain data from wildfire, we implemented a GUI-based simulator that can generate any 3-D geograpical map, deploy sensors and make any desired wildfire conditions by defining wildfire modeling including spreading speed of wildfire and surrounding environment parameters. By using obtained data from simulator, we can train a deep neural network model and obtain the wildfire situation at the entire sensor field with inactive sensor data estimation. In addition, by using estimated and obtained data, we also train a recurrent neural network model to predict future wildfire propagation so that we are able to prepare for wildfire suppression and evacuation plan. Finally, through the performance evaluation the suggested methods can calculate inactive sensor’s data and predict wildfire propagation with high accuracy.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

W. Yun, Y. Song, J. Moon, S. Jang, S. Yoo, "Deep Learning Based Temperature Sensor Data and Wildfire Propagation Prediction in Duty Cycled Wireless Sensor Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 6, pp. 1092-1104, 2019. DOI: 10.7840/kics.2019.44.6.1092.

[ACM Style]

Wan-Kyu Yun, Yoo-Jin Song, Ji-Sun Moon, Sung-Jeen Jang, and Sang-Jo Yoo. 2019. Deep Learning Based Temperature Sensor Data and Wildfire Propagation Prediction in Duty Cycled Wireless Sensor Network. The Journal of Korean Institute of Communications and Information Sciences, 44, 6, (2019), 1092-1104. DOI: 10.7840/kics.2019.44.6.1092.

[KICS Style]

Wan-Kyu Yun, Yoo-Jin Song, Ji-Sun Moon, Sung-Jeen Jang, Sang-Jo Yoo, "Deep Learning Based Temperature Sensor Data and Wildfire Propagation Prediction in Duty Cycled Wireless Sensor Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 6, pp. 1092-1104, 6. 2019. (https://doi.org/10.7840/kics.2019.44.6.1092)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880