Application of Spatiotemporal Analysis and Knowledge Discovery for Databases in the Bureau of Fire Protection as Incident Report System: Tool for Improving Fire Services

Abstract

Purpose–This study aims to contribute to the fire research by developing a fire report management system for the BFP that can analyze spatiotemporal attributes of fire and 520apply Knowledge Discovery in Databases (KDD) methods to identify patterns of fire incidents in the city of Manila.Method–The proponents applied the Knowledge Discovery in Databases (KDD) methods for the processing of identifying fire patterns as well as the application of SMOTE, One-Hot Encoding, and Agile Method as Software developmental model. Result–The records obtained from the BFP headquarters in Manila had a total of 3,506 cases during the six years from 2011 to 2016. The accuracy of the Decision Tree classifier model was 95.92%.Using KDD approach, it generated decision rules fire pattern in Manila. Most fire causes fall under the 'Under Investigation' category while Residential-Commercial types of establishments in Intramuros were affected. Lastly, the fire occurred in the mornings, during Sundays when most people are in their homes and the majority of which took place in the Pandacan district.Conclusion–The application of KDD in building a predictive model to be integrated into the system was the major part of this project. The outputs generated by the system can provide material for use in more accurate fire risk assessments, more efficient allocation of fire resources and personnel, and more targeted fire awareness and prevention programs.Recommendation–Future research in this area may include other factors contributing to a higher likelihood of fire incidences such as weather conditions and other geographical attributes of fire-prone locations. Analysis of these and other relevant factors may allow the BFP to gainfurther insights into the causes of fire incidents, which will enable the agency to make the necessary adjustments and changes in their current fire prevention and risk reduction programsPractical Implication–This study provides direct implication for the Bureau of Fire Protection and community through the given insights of the fire activities and the created model of the system that determine Manila's fire patterns that help identify appropriate information about fire activities and preventive measures of fire incidents.

Datasets of Fire and Crime Incidents in Pampanga, Philippines

“…This is where the datasets may be useful, particularly for conducting computational tasks and achieving certain tasks that might be beneficial to the community as a whole (i.e., determining the leading causes of fire and predicting the occurrences of crimes). For example, the fire dataset can be used to map and find certain patterns of fire cases (Balahadia et al, 2020). Crime datasets could be used to determine the susceptibility of one location to becoming a crime hotspot as well as predict the probability of a specific crime occurring (Villarica et al, 2022).…”

“…The merged dataset might be useful to support or reject some of the existing studies as well as the results of this study. Finally, the development of relevant systems (e.g., Asor & Sapin, 2020;Balahadia et al, 2020;Villarica et al, 2022) based on the dataset and findings of this study is needed to improve the data collection, analysis, visualization, and policy-making processes for the two agencies (Balahadia & Trillanes, 2017). These recommendations are widely seen as important and should be pursued.…”