Rule extraction for tram faults via data mining for safe transportation

Document Type

Journal Article

Publication Date


Subject Area

place - asia, place - europe, mode - tram/light rail, planning - safety/accidents


Rail system safety, Data-mining, Rule extraction, Fault prediction


The demand to travel by rail is ever increasing because it benefits passengers. Also it is important for railway administrators to carry passengers safely to their destinations. One of the parameters that cause unsafety transportation is faults in railway transportation. Undergoing safety procedures and developing safety systems require awareness of what is causing unsafe conditions. This can be obtained by learning from the past. Data mining is a tool to extract information from historical data. One of the most common fields of transportation to apply data mining is fault analysis. In the present study the data set of 4-year record of tram faults from a railway transportation company in Turkey was obtained to carry out rule extraction from the occurrence of faults that cause delays in tram services. For this purpose, we used a rough set tool Rosetta as well as Weka for rule extraction. As a result, we obtained meaningful and useful rules, and these rules were interpreted.


Permission to publish the abstract has been given by Elsevier, copyright remains with them.


Transportation Research Part A Home Page: