IoT Based Fire Accident Detection System with Deep Learning Intelligence
Hitanshi Jain1, Sai Teja Miyapuram2, Sree Ranga Reddy Bobbala3
1Hitanshi Jain, B.Tech., Department of Mechanical Engineering, Indian Institute of Technology (BHU) Varanasi, India.
2Sai Teja Miyapuram*, B.Tech. Department of Electronics and Communication Engineering, SR Engineering College, Warangal, India.
3Sree Ranga Reddy, Department of Computer Science, Cleveland State University, OH, USA.
Manuscript received on October 03, 2021. | Revised Manuscript received on October 10, 2021. | Manuscript published on October 30, 2021. | PP: 138-142 | Volume-11 Issue-1, October 2021. | Retrieval Number: 100.1/ijeat.A31811011121 | DOI: 10.35940/ijeat.A3181.1011121
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A fire accident can be caused by many hazards, such as a propane tank, a defective product, a vehicle crash, or poor workplace safety. Because accidents involving fire are often unexpected and sudden, there isn’t a standard legal process for dealing with them, other than filing a negligence or workers compensation claim. This project aims to detect and monitor Fire Accident incidents well in advance and alert the surroundings to minimize the losses. This is an integration of IoT and Deep Learning Technologies, where sensors are used to collect the relevant data under the supervision of a controller unit. The controller unit collects and sends this data to a cloud database, from where the data for the Deep Learning model is fetched. This data is then used for making some insights and further predictive analytics. From the insights, many variables were found to be one of the reasons for a fire accident to take place. We considered the information about variables like Flame sensor, Temperature, Heat Index, GPS coordinates, Smoke, Type of Gases, Date, and Time for feature set generation and fed the model to a deep neural network for making future predictions. Comparing to existing conventional methods, this proposed method is different in terms of integrating deep learning with IoT. This method of approach will predict the chance of accidents priorly by classification of data.
Keywords: Deep Learning, IoT, Data Analytics, Cloud Database, Sensors
Scope of the Article: Deep Learning