Methodologies for assessing costs of rail transit systems based on small sample data

Abstract

China has developed plans to build 87 mass transit rail lines, totalling 2500 km, in 25 cities from 2009 to 2015. The life-cycle costs of the urban rail transit systems have become the focus of both the government and the private sector involved in these large-scale investments. However, the availability of quality data has posed a major challenge to such life-cycle cost analyses; in other words, for any methodology to be effective, it must have the capability of working with very limited amount of available data, or small sample data. In this article, two cost assessment methodologies, fuzzy cluster and support vector machine, are proposed to analyse the life-cycle cost of urban rail transit systems based on small sample data. A case study featuring Line 1 of the Shijiazhuang urban rail transit system was employed to demonstrate the validity of the proposed methodologies. The analysis results indicate that the two assessment methodologies are valid for the life-cycle cost assessment of urban rail transit systems when only small sample data are available.

Keywords:

• urban rail transit
• life-cycle cost
• fuzzy clustering
• support vector machine

Additional information

Funding

This research was funded by the National Natural Science Foundation of China [Grant No: 51008201], Natural Science Foundation of Hebei Province in China [Grant No: E2012210016 and E2014210152], Science Program of Hebei Province in China [Grant Nos: 13455408D and 13456236D], and the Scientific Research Foundation of Education Department of Hebei Province for Outstanding Young Teachers in University in China [Grant Nos. Y2012033 and ZD2014084]. This research is further sponsored by the Outstanding Young Talent Foundation of Hebei Province in China, Talent Program of Hebei Province in China [Grant No. A201400212] and the Outstanding Young Talent Foundation of Shijiazhuang Tiedao University in China.