An ensemble classifier to predict track geometry degradation

C'ardenas-Gallo, Ivan and Sarmiento, Carlos A. and Morales, Gilberto A. and Bolivar, Manuel A. and Akhavan Tabatabaei, Raha (2017) An ensemble classifier to predict track geometry degradation. Reliability Engineering and System Safety, 161 . pp. 53-60. ISSN 0951-8320 (Print) 1879-0836 (Online)

This is the latest version of this item.

[thumbnail of UTSO_Journal_Revision_V2.pdf] PDF
Restricted to Repository staff only

Download (638kB) | Request a copy


Railway operations are inherently complex and source of several problems. In particular, track geometry defects are one of the leading causes of train accidents in the United States. This paper presents a solution approach which entails the construction of an ensemble classifier to forecast the degradation of track geometry. Our classifier is constructed by solving the problem from three different perspectives: deterioration, regression and classification. We considered a different model from each perspective and our results show that using an ensemble method improves the predictive performance.
Item Type: Article
Uncontrolled Keywords: Railroad maintenance, Defects, Gamma process, Logistic regression, Support vector machines, Classication, Ensemble algorithms
Subjects: Q Science > QA Mathematics > QA273-280 Probabilities. Mathematical statistics
Divisions: Sabancı Business School
Sabancı Business School > Operations Management and Information Systems
Depositing User: Raha Akhavan
Date Deposited: 16 Mar 2017 16:02
Last Modified: 26 Apr 2022 09:41

Available Versions of this Item

Actions (login required)

View Item
View Item