Document Type : Original Research Paper

Authors

• M. Minaei ¹
• M.H. Vahidnia ²
• Z. Rezaei ³

¹ Department of Remote Sensing and GIS, Faculty of Natural Resources and Environment, Science and Research Branch- Islamic Azad University, Tehran, Iran

² Center for Remote Sensing and GIS Research, Faculty of Earth Sciences, Shahid Beheshti University, Tehran, Iran

³ Department of Remote Sensing and GIS, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, Iran

Abstract

Background and Objectives: Spatial data mining techniques offer optimal efficiency in scenarios demanding thorough examination and extraction of results from extensive data sources. Emergency calls, due to their gravity and the involvement of rescue and emergency forces, present a scenario well-suited for geographical data mining. Typically, environmental science and geography researchers employ models such as ordinary least squares (OLS) regression to understand spatial relationships between variables. However, OLS has limitations, particularly at the local scale, prompting the utilization of Geographically Weighted Regression (GWR) in this study to address these shortcomings.
Methods: This study employs OLS and GWR methods to analyze the relationship between the high volume of emergency calls in Dallas, USA, and the influencing factors. Various statistical tests were employed for evaluation. Dependent variables include the number and dispersion of emergency calls, while independent variables encompass population, education levels, peak call hours, and distance from the city center. Spatial-statistical analysis and mapping were conducted using ArcGIS Pro software.
Findings: Results indicate that population, education levels, distance from the city center, and peak call time respectively exert the greatest influence on the occurrence of emergency calls. In the OLS method, Koenker and Jarque-Bera indices, assessing model stationarity and residual normality respectively, did not yield satisfactory results. Evaluation of both OLS and GWR models revealed an R^2 value of approximately 0.61 for GWR and 0.41 for OLS, suggesting greater proximity to reality in the GWR model. Spatially, the weight of population parameter is higher in central city areas, while the weight of peak call time parameter is more pronounced in northern, southern, and western regions. Additionally, the weight of education level parameter is higher in southern parts of the city.
Conclusion: Collectively, the identified factors exhibit a cumulative effect on the occurrence of emergency calls, enabling prediction of future occurrences. Leveraging these insights, appropriate tools can be devised for optimal management and control of regional issues.

Keywords

• Emergency and Rescue Centers
• Geographically Weighted Regression
• Geospatial Information
• Ordinary Least Square

Main Subjects

• Geo-spatial Information System

COPYRIGHTS 
© 2024 The Author(s).  This is an open-access article distributed under the terms and conditions of the Creative Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/)