Development and Comparison of Data Mining-based Prediction Models of Building Fire Probability

Abstract

A lot of manpower and budgets are being used to prevent fires, and only a small portion of the data generated during this process is used for disaster prevention activities. This study develops a prediction model of fire occurrence probability based on data mining in order to more actively use these data for disaster prevention activities. For this purpose, variables for predicting fire occurrence probability of various buildings were selected and data of construction administrative system, national fire information system, and Korea Fire Insurance Association were collected and integrated data set was constructed. After appropriate data cleansing and preprocessing, various data mining methodologies such as artificial neural network, decision trees, SVM, and Naive Bayesian were used to develop a prediction model of the fire occurrence probability of buildings. The most accurate model among the derived models is Linear SVM model which shows 68.42% as experimental data and 63.54% as verification data and it is the best model to predict fire occurrence probability of buildings. As this study develops the prediction model which uses only the set values of the specific ranges, future studies may explore more opportunites to use various setting values not shown in this study.

(Figure 1) ANN Architecture

(Figure 2) Development process of fire probability prediction model

(Table 1) Candidate variables derived using previous studies

(Table 2) EAIS Data

(Table 3) NFDS Collection Data

(Table 4) KFPA Collection Data

(Table 5) List of variables in Data

(Table 6) List of final variables for predicting fire occurrence probability

(Table 7) Neural Networks Model Result

(Table 8) Decision Model Result

(Table 9) Linear SVM Model Result

(Table 10) RBF SVM Tune Result

(Table 11) RBF SVM Model Result

(Table 12) Nive Bayes Model Result

(Table 13) Fire Risk Prediction Result