I.J. Information Technology and Computer Science, 2019, 1, 24-30 Published Online January 2019 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijitcs.2019.01.03 Copyright © 2018 MECS I.J. Information Technology and Computer Science, 2019, 1, 24-30 Classification of the Fire Station Requirement with Using Machine Learning Algorithms Can Aydın Dokuz Eylül University/Management Information System, İzmir, 35160, Turkey E-mail: can.aydin@deu.edu.tr Received: 06 November 2018; Accepted: 22 November 2018; Published: 08 January 2019 Abstract—In crowded cities, selection of the suitable location for fire stations within the town is a vital issue in terms of rapid response to fires and minimizing loss of life and property. For the selection of the suitable fire station location, at first it is necessary to divide the whole city into certain zones and the need for a fire station service should be questioned for each zone. In this study, based on existing fire stations service area, classification of fire station requirement by zones was carried out using machine learning classification algorithms. In order to estimate fire station requirement according to the zones, a classification study was conducted by using some data such as the travel time of the fire engines to zone from closed fire stations, population density of the zone, the mean number of main and assistant vehicles travelling to the zone from closed fire stations, and the fire station existence data in the zone. The purpose of this study was to determine the most successful classification algorithm for the classification of the fire station requirement of 808 zones determined by Izmir Metropolitan Municipality. As a result of the analysis of fire records between 2015 and 2017, it was found that for the classification of the zones, the most successful algorithm was Random Forest algorithm with 93.84% accuracy rate. Experimental evaluation of the study; according to the 5-minute access distance of the existing fire stations, the fire station requirements of the regions and the fire station needs of the regions covered by the machine learning algorithm classification results were found to be 85.43% similar. Index Terms—Machine Learning, Selection of Location, Geographical Information Systems, Management Information System. I. INTRODUCTION In recent years, urban population has been increasing rapidly due to the high birth rates and increased external migration. Since there is not enough infrastructure in the cities, the increasing population causes the municipality services as fire service to not be provided at the desired level. In cities where population density is high and which are not planned, due to the result of the lack of resource management, malfunctions experienced in fire services result in the failure of fire engines to catch fire event in time. Resource management includes the proper distribution of the stations so that fire engines can arrive at the scene as quickly as possible. During this distribution of the stations, the boundary of the fire service has been accepted as the service boundary of the metropolitan municipality defined as the provincial border. Service boundaries have been divided into 808 zones in total in this study. In order to examine whether these zones receive fire service from the fire stations, the current situation has been first determined. When the current situation is examined, it is seen that there are 50 fire stations connected to the Fire Department of the Izmir Metropolitan Municipality. According to the world standards, fire stations need to respond (intervene) to the events occurring in close vicinity within 5 minutes. Within the scope of this bindingness, in line with the buffer zone analysis conducted through considering the current traffic density of fire stations in Izmir province, it is observed that the stations could not provide enough service to 482 of the 808 zones (Fig. 1). Fig.1. Service coverage of the fire stations In this context, the new fire stations should be proposed in order to provide services to the zones that do not receive adequate fire service in line with the above- mentioned standards. In order to determine which zones the new fire stations should be established, first a classification study was carried out according to the fire station needs of the zones by using machine learning methods ([1], [2], [3], [4]). The classification process