A smart approach for fire prediction under uncertain conditions using machine learning
- PDF / 839,829 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 33 Downloads / 173 Views
A smart approach for fire prediction under uncertain conditions using machine learning Richa Sharma 1 & Shalli Rani 1
& Imran Memon
2
Received: 2 August 2019 / Revised: 17 April 2020 / Accepted: 13 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
One of the most ubiquitous cause of worldwide deforestation and devastation of wildlife is fire. To control fire and reach the forest area in time is not always possible. Consequently, the level of destruction is often high. Therefore, predicting fires well in time and taking immediate action is of utmost importance. However, traditional fire prediction approaches often fail to detect fire in time. Therefore, a more reliable approach like the Internet of Things (IoT) needs to be adopted. IoT sensors can not only observe the realtime conditions of an area, but it can also predict fire when combined with Machine learning. This paper provides an insight into the use of Machine Learning models towards the occurrence of forest fires. In this context, eight Machine Learning algorithms: Boosted Decision Trees, Decision Forest Classifier, Decision Jungle Classifier, Averaged Perceptron, 2-Class Bayes Point Machine, Local Deep Support Vector Machine (SVM), Logistic Regression and Binary Neural Network model have been implemented. Results suggest that the Boosted decision tree model with the Area Under Curve (AUC) value of 0.78 is the most suitable candidate for a fire prediction model. Based on the results, we propose a novel IoT-based smart Fire prediction system that would consider both meteorological data and images for early fire prediction. Keywords Forest fires . IoT . Boosted decision trees . Machine learning . Predictive systems . Smart environment
* Shalli Rani [email protected]; [email protected] Richa Sharma [email protected] Imran Memon [email protected]
1
Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India
2
Department of Computer Science, Bahria University, Karachi Campus, Sindh, Pakistan
Multimedia Tools and Applications
1 Introduction Forest or wildlife fires which might be the after effect of either ecological conditions or human exercises have been a significant natural issue for over a hundred million years now. Natural fires are the result of lightning, extreme droughts, extreme hot and parched weather; sometimes spontaneous combustion of sawdust and dry leaves can likewise be a reason. Global warming, being nature’s way of rebuffing humankind, further acts as a catalyst in the rapid increase number of such cases. Human activities prompting forest fires vary from smoking to recreational activities like borne fire. Albeit both natural and human factors lead to the annihilation of wildlife, the effect fluctuates in the two situations. Since human-caused fires are distinguished early, they are controlled well in time for the majority of the cases while natural fires, for the most part, take more time to be seen by the fire authorities a
Data Loading...
