Generating Synthetic Sensor Data to Facilitate Machine Learning Paradigm for Prediction of Building Fire Hazard
Wai Cheong Tam, Eugene Yujun Fu, Richard D. Peacock, Paul A. Reneke, Jun Wang, Jiajia Li, Thomas G. Cleary
This paper presents a learning-by-synthesis approach to facilitate the utilization of a machine learning paradigm to enhance situational awareness for fire fighting in buildings. An automated Fire Data Generator (FD-Gen) is developed. The overview of FD-Gen and its capabilities are provided. Using CFAST as the simulation engine, time series data for building sensors, such as heat detectors, smoke detectors, and other targets at any arbitrary locations in multi-room compartments with different geometric configurations, are obtained. An example case is presented to demonstrate the use of FD-Gen. Synthetic data is generated for a wide range of fire scenarios. Three machine learning algorithms: support vector machine (SVM), decision tree (DT), and random forest (RF), are used to develop classification models that can predict the location of a fire based on temperature data within a compartment. Results show that DT and RF have excellent performance on the prediction of fire location and maintain model accuracy in between 93 % and 96 %. For SVM, it is observed that the model performance is sensitive to the reduction of training data size. Additional study shows that results obtained from DT and RT can be used to examine the importance of each input feature.