Optimizing SVM Model as Predicting Model for Sewer Pipes in the Two Main Cities in Colombia

Nathalie Hernández; Nicolas Caradot; Hauke Sonnenberg; Pascale Rouault; Andrés Torres

doi:10.1007/978-3-319-99867-1_159

Optimizing SVM Model as Predicting Model for Sewer Pipes in the Two Main Cities in Colombia

Nathalie Hernández, Nicolas Caradot, Hauke Sonnenberg, Pascale Rouault, Andrés Torres

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

As in most of the cities around the world, in the last 30 years Latin-American ones have focused on investing in building infrastructure to provide sewer and water services to the communities. However, these infrastructures are going aging day to day. The municipalities need to extend management activities by the development of support tools such as deterioration models to face the aging problem. In the literature of sewer asset management, SVM has been a useful tool to predict and forecast the structural condition of pipes. In this work, the use of differential evolution method as optimization tool was implemented to find the optimal hyper-parameters for SVM models. The SVM models were applied in the main cities of Colombia (Bogota and Medellin) given as a result that the optimized SVM model provides less than 5% of deviation in the prediction of structural conditions in both cities.

Original language	English
Title of host publication	New Trends in Urban Drainage Modelling - UDM 2018
Editors	Giorgio Mannina
Publisher	Springer Verlag
Pages	926-931
Number of pages	6
ISBN (Print)	9783319998664
DOIs	https://doi.org/10.1007/978-3-319-99867-1_159
State	Published - 2018
Event	11th International Conference on Urban Drainage Modelling, UDM 2018 - Palermo, Italy Duration: 23 Sep 2018 → 26 Sep 2018

Publication series

Name	Green Energy and Technology
ISSN (Print)	1865-3529
ISSN (Electronic)	1865-3537

Conference

Conference	11th International Conference on Urban Drainage Modelling, UDM 2018
Country/Territory	Italy
City	Palermo
Period	23/09/18 → 26/09/18

Keywords

Deviation analysis
Differential evolution method
Optimization
Sewer asset management
Support vector machines

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-319-99867-1_159

Cite this

@inproceedings{05267e888ed0428bbe0e46b98a1c4d14,

title = "Optimizing SVM Model as Predicting Model for Sewer Pipes in the Two Main Cities in Colombia",

abstract = "As in most of the cities around the world, in the last 30 years Latin-American ones have focused on investing in building infrastructure to provide sewer and water services to the communities. However, these infrastructures are going aging day to day. The municipalities need to extend management activities by the development of support tools such as deterioration models to face the aging problem. In the literature of sewer asset management, SVM has been a useful tool to predict and forecast the structural condition of pipes. In this work, the use of differential evolution method as optimization tool was implemented to find the optimal hyper-parameters for SVM models. The SVM models were applied in the main cities of Colombia (Bogota and Medellin) given as a result that the optimized SVM model provides less than 5% of deviation in the prediction of structural conditions in both cities.",

keywords = "Deviation analysis, Differential evolution method, Optimization, Sewer asset management, Support vector machines",

author = "Nathalie Hern{\'a}ndez and Nicolas Caradot and Hauke Sonnenberg and Pascale Rouault and Andr{\'e}s Torres",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 11th International Conference on Urban Drainage Modelling, UDM 2018 ; Conference date: 23-09-2018 Through 26-09-2018",

year = "2018",

doi = "10.1007/978-3-319-99867-1_159",

language = "English",

isbn = "9783319998664",

series = "Green Energy and Technology",

publisher = "Springer Verlag",

pages = "926--931",

editor = "Giorgio Mannina",

booktitle = "New Trends in Urban Drainage Modelling - UDM 2018",

address = "Germany",

}

Hernández, N, Caradot, N, Sonnenberg, H, Rouault, P & Torres, A 2018, Optimizing SVM Model as Predicting Model for Sewer Pipes in the Two Main Cities in Colombia. in G Mannina (ed.), New Trends in Urban Drainage Modelling - UDM 2018. Green Energy and Technology, Springer Verlag, pp. 926-931, 11th International Conference on Urban Drainage Modelling, UDM 2018, Palermo, Italy, 23/09/18. https://doi.org/10.1007/978-3-319-99867-1_159

Optimizing SVM Model as Predicting Model for Sewer Pipes in the Two Main Cities in Colombia. / Hernández, Nathalie; Caradot, Nicolas; Sonnenberg, Hauke et al.
New Trends in Urban Drainage Modelling - UDM 2018. ed. / Giorgio Mannina. Springer Verlag, 2018. p. 926-931 (Green Energy and Technology).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Optimizing SVM Model as Predicting Model for Sewer Pipes in the Two Main Cities in Colombia

AU - Hernández, Nathalie

AU - Caradot, Nicolas

AU - Sonnenberg, Hauke

AU - Rouault, Pascale

AU - Torres, Andrés

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2019.

PY - 2018

Y1 - 2018

N2 - As in most of the cities around the world, in the last 30 years Latin-American ones have focused on investing in building infrastructure to provide sewer and water services to the communities. However, these infrastructures are going aging day to day. The municipalities need to extend management activities by the development of support tools such as deterioration models to face the aging problem. In the literature of sewer asset management, SVM has been a useful tool to predict and forecast the structural condition of pipes. In this work, the use of differential evolution method as optimization tool was implemented to find the optimal hyper-parameters for SVM models. The SVM models were applied in the main cities of Colombia (Bogota and Medellin) given as a result that the optimized SVM model provides less than 5% of deviation in the prediction of structural conditions in both cities.

AB - As in most of the cities around the world, in the last 30 years Latin-American ones have focused on investing in building infrastructure to provide sewer and water services to the communities. However, these infrastructures are going aging day to day. The municipalities need to extend management activities by the development of support tools such as deterioration models to face the aging problem. In the literature of sewer asset management, SVM has been a useful tool to predict and forecast the structural condition of pipes. In this work, the use of differential evolution method as optimization tool was implemented to find the optimal hyper-parameters for SVM models. The SVM models were applied in the main cities of Colombia (Bogota and Medellin) given as a result that the optimized SVM model provides less than 5% of deviation in the prediction of structural conditions in both cities.

KW - Deviation analysis

KW - Differential evolution method

KW - Optimization

KW - Sewer asset management

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=85071521995&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-99867-1_159

DO - 10.1007/978-3-319-99867-1_159

M3 - Conference contribution

AN - SCOPUS:85071521995

SN - 9783319998664

T3 - Green Energy and Technology

SP - 926

EP - 931

BT - New Trends in Urban Drainage Modelling - UDM 2018

A2 - Mannina, Giorgio

PB - Springer Verlag

T2 - 11th International Conference on Urban Drainage Modelling, UDM 2018

Y2 - 23 September 2018 through 26 September 2018

ER -

Optimizing SVM Model as Predicting Model for Sewer Pipes in the Two Main Cities in Colombia

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this