Using Machine Learning and Regression Analysis to Classify and Predict Danger Levels in Burning Sites

Firefighters go into burning structures to rescue trapped victims and put out the fire as soon as possible. Factors such as extreme temperatures, smoke, toxic gases, explosions, and falling objects inhibit their efficiency and risk their safety. These factors could change within a twinkle of an eye. Firefighters must be provided with accurate information and data about the burning site. They can make informed decisions about their duties and know when it is safe to enter and evacuate to reduce casualties. This research work presents Machine Learning (ML) and regression models for predicting the danger levels in burning sites and utilizes autonomous embedded system vehicles (AESV) to validate the models' performance to increase firefighters' safety. We investigated the classification performance of three ML methods: Support Vector Machines (SVM), Logistic Regression (LR), and k- Nearest Neighbors (k-NN) on the Cross Laminated Timber (CLT) data collected by the National Institute of Standards and Technology (NIST) and the National Research Council Canada while testing the impacts of laminated timber in a controlled fire temperature. We have reported promising results for danger levels classification with the three models, but the k-NN performed slightly better than the other two classifiers.