Random Forest-Based Covariate Shift in Addressing Non-Stationarity of Railway Track Data

The multi-modal transportation network in which the freight rail plays an essential role continues to enhance the United States’ contributions in the global market. For years, track geometry defects data are often gathered by visual inspections. However, automated track vehicles are now deployed for the same purpose to save time and cost. One of the limitations of an automated vehicle is the likelihood of non-stationarity of the gathered data due to external influence. The effect of non-stationarity may lead to the wrong representation of track conditions and thereby increases the possibility of false model output. This study applies the supervised Machine Learning (ML) methods to detect the non-stationarity of the geometry data. The methods include Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM). The authors vary the train-test and validation ratio in phases to ascertain each Machine Learning methods’ accuracy and adaptability to different distributions. In the first phase, the Random Forest and the Support Vector Machine show an accuracy of 97.1% while the Logistic Regression reveals 96% accuracy. In the second and third phases, the Random forest method gives a better result than other supervised learners with an accuracy of 97% and 97.1% respectively. Similarly, for validation, the Random Forest performs better than other classifiers with an accuracy of 98%. Conclusively, the developed models’ application indicates that the Random Forest is a more effective approach to detecting non-stationarity of track geometry data.

Language

• English

Project

• Status: Active
• Funding: $50000
• Contract Numbers:

  69A3551747132

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Project Managers:

  Zarembski, Allan

• Start Date: 20210901
• Expected Completion Date: 20230930
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Automatic data collection systems; Machine learning; Railroad tracks
• Subject Areas: Data and Information Technology; Maintenance and Preservation; Railroads;

Filing Info

• Accession Number: 01787404
• Record Type: Research project
• Source Agency: University Transportation Center on Improving Rail Transportation Infrastructure Sustainability and Durability
• Contract Numbers: 69A3551747132
• Files: UTC, RIP
• Created Date: Nov 6 2021 2:52PM