Support Vector Machine-Based Fire Outbreak Detection System

TL;DR

This paper presents a fire outbreak detection system using SVM trained on sensor data, achieving 80% accuracy, demonstrating the effectiveness of combining real-world environmental sensors with machine learning for fire prediction.

Contribution

The study develops a novel fire detection system integrating environmental sensors with SVM, providing a practical approach with high accuracy for fire outbreak prediction.

Findings

SVM achieved 80% accuracy in fire prediction.

Sensor data improved detection reliability.

Minimal error rate of 0.2% was observed.

Abstract

This study employed Support Vector Machine (SVM) in the classification and prediction of fire outbreak based on a fire outbreak dataset captured from the Fire Outbreak Data Capture Device (FODCD). The fire outbreak data capture device (FODCD) used was developed to capture the environmental parameters values used in this work. The FODCD device comprised a DHT11 temperature sensor, MQ-2 smoke sensor, LM393 Flame sensor, and ESP8266 Wi-Fi module, connected to Arduino nano v3.0.board. 700 data point was captured using the FODCD device, with 60% of the dataset used for training while 20% was used for testing and validation respectively. The SVM model was evaluated using the True Positive Rate (TPR), False Positive Rate (FPR), Accuracy, Error Rate (ER), Precision, and Recall performance metrics. The performance results show that the SVM algorithm can predict cases of fire outbreak with an accuracy of 80% and a minimal error rate of 0.2%. This system was able to predict cases of fire outbreak with a higher degree of accuracy. It is indicated that the use of sensors to capture real-world dataset and machine learning algorithm such as the support vector machine gives a better result to the problem of fire management.