Pregled bibliografske jedinice broj: 968764
Support Vector Machine Based Hybrid Model for Prediction of Road Structures Construction Costs
Support Vector Machine Based Hybrid Model for Prediction of Road Structures Construction Costs // Book of Abstracts - People, Buildings and Environment 2018, an international scientific conference/ / Korytarova, Jana ; Serrat, Carles ; Hanak, Tomaš (ur.).
Brno: Faculty of Civil Engineering, Brno University of Technology, 2018. str. 29-29 (predavanje, međunarodna recenzija, sažetak, ostalo)
CROSBI ID: 968764 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Support Vector Machine Based Hybrid Model for Prediction of Road Structures Construction Costs
Autori
Petrusheva, S ; Car-Pušić, D ; Zileska-Pancovska, V.
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, ostalo
Izvornik
Book of Abstracts - People, Buildings and Environment 2018, an international scientific conference/
/ Korytarova, Jana ; Serrat, Carles ; Hanak, Tomaš - Brno : Faculty of Civil Engineering, Brno University of Technology, 2018, 29-29
Skup
People, Buildings and Environment 2018, an international scientific conference
Mjesto i datum
Brno, Češka Republika, 17.10.2018. - 19.10.2018
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
support vectore machine, SVM, hybrid model, linear regression, road structure, cost
Sažetak
Cost prediction in early stages of construction projects is one of the crucial problems of project planning. Previous research has been directed to process based and data driven model development by using various techniques, e.g. regression analysis, support vector machine (SVM), neural networks etc. According to the research results, neither one of the techniques could be considered the best for all circumstances. Therefore, the research has been redirected towards the hybrid modelling, i.e. combination of different techniques. In this research, for prediction of the target variable – real construction cost of road structures, using available variables: contracted construction cost, contracted construction time and real construction time and cost, hybrid model – combination of SVM technique (data- driven model) and Bromilow time-cost model (TCM) (process-based model) has been used. Five hybrid models have been built for comparison purposes: SVM-Bromilow TCM, LR-Bromilow TCM, RBFNN-Bromilow TCM, MLP-Bromilow TCM and GRNN- Bromilow TCM, combining Bromilow TCM with SVM, LR (linear regression), RBFNN (radial basis neural network), MLP (Multilayer perceptron) and GRNN (general regression neural network), respectively. The best accuracy has been obtained with SVM-Bromilow TCM with mean absolute percentage error (MAPE) 1.01% and coefficient of determination (R2) 97.61%.
Izvorni jezik
Engleski
Znanstvena područja
Građevinarstvo
