Prediction of pipe failures in water supply networks using logistic regression and support vector classification

•Prediction of >85% of pipe failures using both algorithms, LR and SVC.•Excellent abilities to avoid false classifications (AUCs).•Importance of training set balance in binary classification problems. Companies in charge of water supply networks are making a huge effort to optimally plan the annu...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Reliability engineering & system safety Ročník 196; s. 106754
Hlavní autoři:	Robles-Velasco, Alicia, Cortés, Pablo, Muñuzuri, Jesús, Onieva, Luis
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Barking Elsevier Ltd 01.04.2020 Elsevier BV
Témata:	Classification Failure Logistic regression Networks Optimization Pipe failures Pipes Predictive algorithms Reliability engineering Statistical analysis Support vector classification Sustainability management Water shortages Water supply Water supply networks Water supply systems Logistic regression Support vector classification Pipe failures Predictive algorithms Water supply networks
ISSN:	0951-8320, 1879-0836
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!