Smoke Detection with Ensemble Modeling

Abstract

This research aims at investigating performance of the ensemble learning method. The ensemble learning brings together various weak learners to create strong learners. Based on this ensemble learning idea, we develop a model for an efficient smoke detection tool. The three schemes of ensemble learning are investigated including bagging, boosting, and stacking. The bagging ensemble algorithm studied in this research is Random Forest and the boosting algorithm is AdaBoost. The stacking ensemble adopts three algorithms, that are Random Forest, AdaBoost, and Logistic Regression. The other learning algorithms adopted for performance comparison include Support Vector Machine, Naïve Bayes, and Decision Tree. The smoke detection data contain 62,630 records and 15 features. The dataset has been separated into training set and test set with a ratio of 75:25. The experimental results reveal that AdaBoost outperforms other learning algorithms when applied to the specific smoke detection application domain.