Data-Driven Model for Stability Condition Prediction of Soil Embankments Based on Visual Data Features
| Autor: | Paulo Cortez, David G. Toll, Joaquim Agostinho Barbosa Tinoco, A. Gomes Correia |
|---|---|
| Přispěvatelé: | Universidade do Minho |
| Rok vydání: | 2018 |
| Předmět: |
Science & Technology
Operations research Computer science 0211 other engineering and technologies Stability (learning theory) 02 engineering and technology Computer Science Applications Data-driven Engenharia e Tecnologia::Engenharia Civil 11. Sustainability Engenharia Civil [Engenharia e Tecnologia] 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Transportation infrastructure Budget constraint 021101 geological & geomatics engineering Civil and Structural Engineering |
| Zdroj: | Journal of computing in civil engineering, 2018, Vol.32(4), pp.04018027 [Peer Reviewed Journal] Repositório Científico de Acesso Aberto de Portugal Repositório Científico de Acesso Aberto de Portugal (RCAAP) instacron:RCAAP |
| ISSN: | 1943-5487 0887-3801 |
| DOI: | 10.1061/(asce)cp.1943-5487.0000770 |
| Popis: | Keeping large-scale transportation infrastructure networks, such as railway networks, operational under all conditions is one of the major challenges today. The budgetary constraints for maintenance purposes and the network dimension are two of the main factors that make the management of a transportation network such a challenging task. Accordingly, aiming to assist the management of a transportation network, a data-driven model is proposed for stability condition prediction of embankment slopes. For such a purpose, the highly flexible learning capabilities of artificial neural networks (ANN) and support vector machines (SVM) were used to fit data-driven models for earthwork hazard category (EHC) prediction. Moreover, the data-driven models were created using visual information that is easy to collect during routine inspections. The proposed models were addressed following two different data modeling strategies: nominal classification and regression. Moreover, to overcome the problem of imbalanced data (since typically good conditions are much common than bad ones), three training sampling approaches were explored: no resampling, synthetic minority oversampling technique (SMOTE), and oversampling. The achieved modeling results are presented and discussed, comparing the predictive performance of ANN and SVM algorithms, as well as the effect of the sampling approaches. A comparison between nominal classification and regression strategies was also carried out. Moreover, aiming at a better understanding of the proposed data-driven models, a detailed sensitivity analysis was applied, allowing the quantification of the relative importance of each model input, as well as measuring their global effect on the prediction of embankment stability conditions. This work was supported by FCT - “Fundação para a Ciência e a Tecnologia”, within Institute for Sustainability and Innovation in Structural Engineering (ISISE), project UID/ECI/04029/2013 as well Project Scope: UID/CEC/00319/2013 and through the post-doctoral Grant fellowship with reference SFRH/BPD/94792/2013. This work was also partly financed by FEDER (Fundo Europeu de Desenvolvimento Regional) funds through the Competitivity Factors Operational Programme - COMPETE and by national funds through FCT within the scope of the project POCI-01-0145-FEDER-007633. This work has been also supported by COMPETE: POCI-01-0145-FEDER-007043. A special thanks goes to Network Rail that kindly make available the data (basic earthworks examination data and the Earthworks Hazard Condition scores) used in this work. info:eu-repo/semantics/publishedVersion |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|