Neural network and GA approaches for dwelling fire occurrence prediction

Yang, Lili; Dawson, Christian W.; Brown, M.; Gell, M. A.

doi:10.1016/j.knosys.2005.11.021

Cited by 39 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The probabilities of predicted occurrence of human-caused wildfire are not very accurate mainly due to the complexity of the problem (Yang et al, 2006). Relationships between fire occurrence and environmental factors are often non-parametric and involve complex interactions, especially when humans play an important role in its dynamics.…”

Section: Introductionmentioning

confidence: 99%

Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires

Zhang

Zhou

2010

Journal of Arid Environments

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires

Zhang

Zhou

2010

Journal of Arid Environments

View full text Add to dashboard Cite

“…Although earlier research has examined risk modelling for forest fi res ( Bonazountas et al , 2005 ;Fiorucci et al , 2005 ;Kaloudis et al , 2005 ), there appears to have been little research that has examined risk modelling approaches for unintentional dwelling fi res ( Yang et al , 2006 ) and fatalities arising from such fi res, other than examination of the locations of past fi res ( Corcoran et al , 2007a, b ). Hanea and Ale (2009) examined housing characteristics relating to unintentional dwelling fi re risk, but did not consider population characteristics with regard to unintentional dwelling fi re risk.…”

Section: Dwelling Fi Re Incident and Dwelling Fi Re Fatality Risk Modmentioning

confidence: 99%

An exploration of causal factors in unintentional dwelling fires

et al. 2012

View full text Add to dashboard Cite

We examine the causal factors involved in unintentional dwelling fire incidents within the Merseyside area of the North West region of the United Kingdom. The approach of all-subsets multiple linear regression was used to develop an unintentional dwelling fire risk model for the region. The risk model was based on data obtained from UK government agencies relating to causal factors iden tified by earlier published studies. In the region studied, mental health problems, disability and residents living alone were the most significant factors associated with unintentional dwelling fire fatalities. However, in a separate model of the incidence of unintentional dwelling fires within the region, binge drinking and smoking were additional statistically significant factors.

show abstract

“…Unintentional dwelling fire risk modelling Previous research has examined risk modelling for forest fires (Bonazountas et al 2005;Fiorucci et al 2005;Kaloudis et al 2005); however, there appears to have been little research that has examined risk modelling approaches for unintentional dwelling fires (Yang et al 2006). Corcoran et al (2009) stated that fires in urban areas can cause significant economic, physical and psychological damage.…”

Section: Literature Reviewmentioning

confidence: 99%

Managing unintentional dwelling fire risk

Taylor

Higgins

Francis

et al. 2011

Journal of Risk Research

View full text Add to dashboard Cite

In this paper, we examine the management of unintentional dwelling fire risk through the development of a geographical information system (GIS) for dwelling fire prevention support based upon an 18-month case study in a UK fire and rescue service. Previous research into causal factors in unintentional dwelling fire incidents was used to guide the development of a multiple linear regression risk model for dwelling fire incidents that was the basis of the GIS developed. The GIS provided a more detailed analysis of unintentional dwelling fire risk factors, and enabled more targeted fire prevention activities for the identified atrisk social groups. IntroductionIn this paper, we examine the management of unintentional dwelling fire risk through the development of a geographical information system (GIS) for modelling the risk of dwelling fires within the area covered by a UK fire and rescue service. The purpose of the GIS was to assist in the reduction of unintentional dwelling fires and fatalities within a given geographical area in the UK via more targeted fire prevention initiatives. Fire prevention initiatives (Brussoni, Towner, and Hayes 2006;Rosenberg 1999;Shai 2006;Smith et al. 2007) are increasingly being viewed as an effective means of reducing incidents of unintentional dwelling fires, fire injuries and fire fatalities. In addition, from a resources viewpoint, fire prevention initiatives are increasingly considered to be an effective and efficient utilisation of fire and rescue service personnel.The fire and rescue service studied had previously utilised internal data relating to accidental dwelling fires along with indices of multiple deprivation in the area covered to determine patterns of unintentional dwelling fire incidence. This was used to inform and direct fire prevention activities. However, in order to attempt the management of unintentional dwelling fire risk through improved effectiveness of fire prevention activities, the fire and rescue service studied wished to be able to more specifically target at-risk groups for fire prevention initiatives. Initially, statistical analyses of the fire and rescue service internal accidental dwelling fire data were conducted to determine if such could provide information concerning at-risk groups. However, no significant patterns emerged from the data. The decision was then taken that data from outside organisations would need to be utilised in order to

show abstract

Neural network and GA approaches for dwelling fire occurrence prediction

Cited by 39 publications

References 9 publications

Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires

Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires

An exploration of causal factors in unintentional dwelling fires

Managing unintentional dwelling fire risk

Contact Info

Product

Resources

About