Temporal analysis and geo-mapping of fire incidents in the City of Manila

Balahadia, Francis F.; Trillanes, Arlene O.; Armildez, Maria Rizza L.

doi:10.1109/hnicem.2015.7393211

Cited by 7 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With a total area of approximately 161 square kilometers, the city is the most urbanized and most populous city in the National Capital Region [22]. Over the last decade, Quezon City's population has increased by 7.18% which also resulted in an increase in infrastructure construction projects as part of the expansion of the city; in these years, there has also been a continuous rise in fire emergencies and occurrences [23,24]. The DHM criterion on the other hand indicated a lower priority at 26.51% compared to a previous study for optimal site selection of fire stations done in Istanbul, Turkey with a weight of 40.0%.…”

Section: Criteria Shapefilesmentioning

confidence: 99%

Service area determination of fire stations in an urban setting through a GIS-based multi-criteria analysis: the case of Quezon City, Philippines

Cruz¹,

Ong²,

Peralta³

2022

Proceedings of International Exchange and Innovation Conference on Engineering &Amp; Sciences (IEICES)

View full text Add to dashboard Cite

The continuous rise of population and expansion in urban cities results in a higher demand for fire services making the determination of their service areas critical in emergency planning. This study aims to determine the service areas of the existing fire stations in Quezon City, Philippines through the use of a Multi-Criteria Decision-Making (MCDM) method of Analytical Hierarchy Process (AHP) integrated with Geographic Information Systems (GIS). The factors considered for the study are high population density (HPD), density of hazardous material facilities (DHM), distance to existing fire stations (DEF), and proximity to main roads (PMR) with associated AHP weights of 27.9%, 26.51%, 23.62% and 21.97% respectively based on the fire professionals involved in the emergency planning services. Results show that currently, 63.24% is covered by the existing fire stations. Based on the existing service areas and the gaps identified in the analysis, new stations were suggested to improve the coverage to 88.31%.

show abstract

Section: Criteria Shapefilesmentioning

confidence: 99%

Service area determination of fire stations in an urban setting through a GIS-based multi-criteria analysis: the case of Quezon City, Philippines

Cruz¹,

Ong²,

Peralta³

2022

Proceedings of International Exchange and Innovation Conference on Engineering &Amp; Sciences (IEICES)

View full text Add to dashboard Cite

show abstract

“…analyzing a total of 2316 fire incidents in Manila, it was shown that fire incidents follow temporal patterns. 15 A clustering model using K-mean method and based on fire incidents dataset was established for classifying problems towards fire risk. 16 Through data mining of historical fire incidents in the natural environment in Slovenia, predictive models were built to estimate the risk of fire outbreaks.…”

Section: Throughmentioning

confidence: 99%

“…Statistical models of fire occurrence fitted by generalized linear models and boosted regression trees were developed for predicting the number and geographic distribution of fires caused by tsunami inundation and earthquake ground motion in Japan . Through analyzing a total of 2316 fire incidents in Manila, it was shown that fire incidents follow temporal patterns . A clustering model using K‐mean method and based on fire incidents dataset was established for classifying problems towards fire risk .…”

Section: Introductionmentioning

confidence: 99%

Generalized analysis of regional fire risk using data visualization of incidents

Liu

Fan

2019

Fire and Materials

View full text Add to dashboard Cite

Summary Fire has been a worldwide disaster, and it is important to analyze regional fire risk for better fire prevention. Regional fire risk can be generally analyzed by using data visualization of fire incidents. A dataset of 20 622 fire incidents in Changsha City of China from 2011 to 2017 was processed and filtered as the origin risk points. Then, a generalized risk model (GRM) was established for calculating fire risk values of anywhere in Changsha. By using JavaScript and HTML5, the generalized fire risk graphics were drawn based on mapping different fire risk values with different colors. For visualizing fire incidents, the inner and outer generalization radiuses of the origin risk point were set to be 1 (110 m) and 10 (1100 m), respectively. It was found that the high and medium fire risk areas were mainly distributed in urban areas and market towns, especially in central city. The spatial distribution characteristics of fire risk of different time ranges and different causes were significantly varied. The results can provide guidance of fire prevention for the fire department in Changsha. Other cities' regional fire risk and even other types of disaster risk can also be generally analyzed using GRM.

show abstract

“…The cost of fires in human is a global public health concern. Direct physical harm that causes deaths and injuries such as burns, and psychological and emotional trauma are the two-fold effects of fire to human [1]. It was estimated cost was due to losses from fire accidents is approximately one percent of global Gross Domestic Product per annum, according to World Fire Statistics.…”

Section: Introductionmentioning

confidence: 99%

“…Based on records, a total of 2,316 fire incidents was reported from 2011 to 2014. The Bureau of Fire Protection (BFP) has listed several causes of fire such as defective electrical wiring/association, unattended open fire, ignore cooking/stove, LPG, cigarette butt, light, electrical gadgets, and apparatuses, among others [1]. BFP reported that an average of 9 fire incidents take place per day nationwide and NCR has the most astounding fire occurrence record over the years.…”

Section: Introductionmentioning

confidence: 99%

NotiPoy: Early Notification of Detected Fire Using Image Processing Applying Convolutional Neural Network

Nicolas-Mindoro¹

2019

IJATCSE

View full text Add to dashboard Cite

Fire incident is one of the most common undesirable events that cause damages toward houses and human. It can start anytime and anywhere without any prior hint when it would happen. With the cause it brings, the implementation of a device capable of detecting and providing notification is necessary. This study presents the method of early-stage fire-flame detection utilizing image processing integrated with the Android application for emergency notification. The proposed system utilized the image processing applying Convolutional Neural Network (CNN) integrated with mobile app as early notification to the end user. After executing 3999 iterations of 210 images are used for testing to get the Train Accuracy (how accurate the training is) and Cross entropy (how far is the prediction of the actual result), it resulted to 100% trained accuracy and 96% validation. The test evaluation accuracy result was 99% using a cached file of 210, it means that expect the model to perform ~99% accuracy on the new data. From the test that has been done, the proposed system was able to capture the fire flame images and send necessary notification real time. The test results show the captured actual images and the information sent to the end user. The summary test results verified that all gathered data was higher than 90% to be able to send notification. The android app used to show both the pre-investigation information useful for the house owner and BFP personnel.

show abstract

Temporal analysis and geo-mapping of fire incidents in the City of Manila

Cited by 7 publications

References 1 publication

Service area determination of fire stations in an urban setting through a GIS-based multi-criteria analysis: the case of Quezon City, Philippines

Service area determination of fire stations in an urban setting through a GIS-based multi-criteria analysis: the case of Quezon City, Philippines

Generalized analysis of regional fire risk using data visualization of incidents

NotiPoy: Early Notification of Detected Fire Using Image Processing Applying Convolutional Neural Network

Contact Info

Product

Resources

About