Architecture of ensemble neural networks for risk analysis

dc.contributor.author	De Silva, N
dc.contributor.author	Thurairajah, N
dc.contributor.author	Ransinghe, M
dc.date.accessioned	2013-10-19T10:49:48Z
dc.date.available	2013-10-19T10:49:48Z
dc.identifier.uri	http://dl.lib.mrt.ac.lk/handle/123/8038
dc.description.abstract	Assembling of nemal networks refened to as "Ensemble nemal networks·· consist with many small "expei1 networks" that leam small parts of the complex problem. which are established by decomposing it into its sub leYels. Ensemble nemal network architecnue has been proposed to so lYe complex problems with large munbers of variables. In this paper. this architecture is used to analyze maintainability risks ofhigh-rise buildings. An ensemble neural network that consists with four expert networks to represent four building elements namely roof. fa<;:ade. basement and intemal areas is deYeloped to forecast the maintenance efficiency (ME) of buildings. The model is tested and the results showed good performance. The model is fmther validated using a real case study.
dc.language	en
dc.subject	Ensemble neural networks
dc.subject	Maimenance
dc.subject	Risk analysis
dc.subject	Artificial neural networks
dc.title	Architecture of ensemble neural networks for risk analysis
dc.type	Conference-Abstract
dc.identifier.year	2012
dc.identifier.conference	48th ASC Ammal International Conference
dc.identifier.place	Birmingham City University, England