Abstract

In discussions of track geometry, track safety takes precedence over other requirements because its shortfall often leads to unrecoverable loss. Track geometry is unanimously positioned as the index for safety evaluation—corrective or predictive—to predict the rightful maintenance regime based on track conditions. A recent study has shown that track defect probability thresholds can best be explored using a hybrid index. Hence, a dimension reduction technique that combines both safety components and geometry quality is needed. It is observed that dimensional space representation of track parameters without prior covariate shift evaluation could affect the overall distribution as the underlying discrepancies could pose a problem for the accuracy of the prediction. In this study, the authors applied a covariate shift framework to track geometry parameters before applying the dimension reduction techniques. While both principal component analysis (PCA) and t-distributed stochastic neighbor embedding (TSNE) are viable techniques that express the probability distribution of parameters based on correlation in their embedded space and inclination to maximize the variance, shift distribution evaluation should be considered. In conclusion, we demonstrate that our framework can detect and evaluate a covariate shift likelihood in a high-dimensional track geometry defect problem.

References

1.
Bakhtiary
,
A.
,
Zakeri
,
J. A.
, and
Mohammadzadeh
,
S.
,
2021
, “
An Opportunistic Preventive Maintenance Policy for Tamping Scheduling of Railway Tracks
,”
Int. J. Rail Transp.
,
9
(
1
), pp.
1
22
.
2.
Zhu
,
T.
,
Xiao
,
S.
,
Lei
,
C.
,
Wang
,
X.
,
Zhang
,
J.
,
Yang
,
B.
,
Yang
,
G.
, and
Li
,
Y.
,
2020
, “
Rail Vehicle Crashworthiness Based on Collision Energy Management: An Overview
,”
Int. J. Rail Transp.
,
9
(
2
), pp.
101
131
.
3.
McAleer Law
,
2021
, “
Train Accident Statistics
,” 2020, https://www.mcaleerlaw.com/train-accident-statistics.html, Accessed February 10, 2021.
4.
Kang
,
Y.
,
Iranitalab
,
A.
, and
Khattak
,
A.
,
2019
, “
Modeling Railroad Trespassing Crash Frequency Using a Mixed-Effects Negative Binomial Model
,”
Int. J. Rail Transp.
,
7
(
3
), pp.
208
218
.
5.
FRA
,
2020
, “
Train Fatalities, Injuries, and Accidents by Type of Accident
,” National Transportation Statistics, https://www.bts.gov/content/train-fatalities-injuries-and-accidents-type-accidenta, Accessed February 8, 2021.
6.
Mazareanu
,
E.
,
2021
, “
United States—Rail Accidents and Incidents 2013–2019 Published by E. Mazareanu, Mar 27, 2020. This Statistic Represents the Number of Rail Accidents and Incidents in the United States From 2013 Through 2019. In 2019, the United States Registered 937 Rail
,” 2020, https://www.statista.com/statistics/204569/rail-accidents-in-the-us/.
7.
FRA.Gov
,
2020
, “Highway Rail Accidents,” https://catalog.data.gov/dataset/highway-rail-accidents, Accessed February 8, 2021.
8.
Ambros
,
J.
,
Perůtka
,
J.
,
Skládaný
,
P.
, and
Tučka
,
P.
,
2020
, “
Enhancing the Insight Into Czech Railway Level Crossings’ Safety Performance
,”
Int. J. Rail Transp.
,
8
(
1
), pp.
99
108
.
9.
Wu
,
S. C.
,
Xu
,
Z. W.
,
Liu
,
Y. X.
,
Kang
,
G. Z.
, and
Zhang
,
Z. X.
,
2018
, “
On the Residual Life Assessment of High-Speed Railway Axles Due to Induction Hardening
,”
Int. J. Rail Transp.
,
6
(
4
), pp.
218
232
.
10.
Lasisi
,
A.
,
Merheb
,
A.
,
Zarembski
,
A.
, and
Attoh-Okine
,
N.
,
2019
, “
Rail Track Quality and T-Stochastic Neighbor Embedding for Hybrid Track Index
,”
2019 IEEE International Conference on Big Data, Big Data 2019
,
Los Angeles, CA
, pp.
1470
1477
.
11.
Lidén
,
T.
,
2015
, “
Railway Infrastructure Maintenance—A Survey of Planning Problems and Conducted Research
,”
Transp. Res. Procedia
,
10
(
7
), pp.
574
583
.
12.
Lasisi
,
A.
, and
Attoh-Okine
,
N.
,
2019
, “
Machine Learning Ensembles and Rail Defects Prediction: Multilayer Stacking Methodology
,”
ASCE-ASME J. Risk Uncertain. Eng. Syst. Part A Civ. Eng.
,
5
(
4)
, p.
04019016
.
13.
Moreno-Torres
,
J. G.
,
Raeder
,
T.
,
Alaiz-Rodríguez
,
R.
,
Chawla
,
N. V.
, and
Herrera
,
F.
,
2012
, “
A Unifying View on Dataset Shift in Classification
,”
Pattern Recognit.
,
45
(
1
), pp.
521
530
.
14.
Sun
,
Y. Q.
,
2018
, “
Mitigating Train Derailments Due to Sharp Curve and Overspeed
,”
Front. Mech. Eng.
,
4
(
8
), pp.
1
12
.
15.
Offenbacher
,
S.
,
Neuhold
,
J.
,
Veit
,
P.
, and
Landgraf
,
M.
,
2020
, “
Analyzing Major Track Quality Indices and Introducing a Universally Applicable TQI
,”
Appl. Sci.
,
10
(
23
), pp.
1
17
.
16.
He
,
Q.
,
Li
,
H.
,
Bhattacharjya
,
D.
,
Parikh
,
D. P.
, and
Hampapur
,
A.
,
2015
, “
Track Geometry Defect Rectification Based on Track Deterioration Modelling and Derailment Risk Assessment
,”
J. Oper. Res. Soc.
,
66
(
3
), pp.
392
404
.
17.
Higgins
,
C.
, and
Liu
,
X.
,
2018
, “
Modeling of Track Geometry Degradation and Decisions on Safety and Maintenance: A Literature Review and Possible Future Research Directions
,”
Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit
,
232
(
5
), pp.
1385
1397
.
18.
Cárdenas-Gallo
,
I.
,
Sarmiento
,
C. A.
,
Morales
,
G. A.
,
Bolivar
,
M. A.
, and
Akhavan-Tabatabaei
,
R.
,
2017
, “
An Ensemble Classifier to Predict Track Geometry Degradation
,”
Reliab. Eng. System Safety
,
161
, pp.
53
60
.
19.
He
,
Q.
,
Li
,
H.
,
Bhattacharjya
,
D.
,
Parikh
,
D. P.
, and
Hampapur
,
A.
,
2015
, “
Track Geometry Defect Rectification Based on Track Deterioration Modelling and Derailment Risk Assessment
,”
J. Oper. Res. Soc.
,
66
(
3
), pp.
392
404
.
20.
Falamarzi
,
A.
,
Moridpour
,
S.
, and
Nazem
,
M.
,
2021
, “
A Time-Based Track Quality Index: Melbourne Tram Case Study
,”
Int. J. Rail Transp.
,
9
(
1
), pp.
23
38
.
21.
Wang
,
B. Z.
,
Barkan
,
C. P. L.
, and
Rapik Saat
,
M.
,
2020
, “
Quantitative Analysis of Changes in Freight Train Derailment Causes and Rates
,”
J. Transp. Eng. A: Syst.
,
146
(
11
), p.
04020127
.
22.
Lasisi
,
A.
, and
Attoh-Okine
,
N.
,
2018
, “
Principal Components Analysis and Track Quality Index: A Machine Learning Approach
,”
Transp. Res. Part C Emerg. Technol.
,
91
(
3
), pp.
230
248
.
23.
Hajizadeh
,
S.
,
Núñez
,
A.
, and
Tax
,
D. M. J.
,
2016
, “
Semi-Supervised Rail Defect Detection From Imbalanced Image Data
,”
IFAC-PapersOnLine
,
49
(
3
), pp.
78
83
.
24.
Balogun
,
I.
, and
Attoh-Okine
,
N.
,
2021
, “
Random Forest-Based Covariate Shift in Addressing Nonstationarity of Railway Track Data
,”
ASCE-ASME J. Risk Uncertain. Eng. Syst. Part A Civ. Eng.
,
7
(
3
), p.
04021028
.
25.
Polo
,
F. M.
, and
Vicente
,
R.
,
2020
, “
Covariate Shift Adaptation in High-Dimensional and Divergent Distributions
,” arXiv, 1.
26.
Sharma
,
S.
,
Cui
,
Y.
,
He
,
Q.
,
Mohammadi
,
R.
, and
Li
,
Z.
,
2018
, “
Data-Driven Optimization of Railway Maintenance for Track Geometry
,”
Transp. Res. Part C Emerg. Technol.
,
90
(
9
), pp.
34
58
.
27.
Reddi
,
S. J.
,
Poczos
,
B.
, and
Smola
,
A.
,
2015
, “
Doubly Robust Covariate Shift Correction
,”
AAAI Conference on Artificial Intelligence
,
Austin, TX
,
Jan. 25–30
, pp.
1
14
.
28.
Wang
,
S.
,
McCormick
,
T. H.
, and
Leek
,
J. T.
,
2020
, “
Methods for Correcting Inference Based on Outcomes Predicted by Machine Learning
,”
Proc. Natl. Acad. Sci.
,
117
(
48
), pp.
30266
30275
.
29.
Soleimanmeigouni
,
I.
,
Ahmadi
,
A.
, and
Kumar
,
U.
,
2018
, “
Track Geometry Degradation and Maintenance Modelling: A Review
,”
Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit
,
232
(
1
), pp.
73
102
.
30.
Dharani
,
G.
,
Nair
,
N. G.
,
Satpathy
,
P.
, and
Christopher
,
J.
,
2019
, “
Covariate Shift:
A
Review and Analysis on Classifiers
,”
2019 Global Conference for Advancement in Technology (GCAT) 2019
,
Bangalore, India
,
Oct. 18–20
, pp.
1
6
.
31.
Wang
,
F.
, and
Rudin
,
C.
,
2017
, “
Extreme Dimension Reduction for Handling Covariate Shift
,” arXiv.
32.
Joshi
,
Y.
,
2021
, “
Applications of Principal Component Analysis (PCA)
,” https://iq.opengenus.org/applications-of-pca/, Accessed January 13, 2021.
33.
Demšar
,
U.
,
Harris
,
P.
,
Brunsdon
,
C.
,
Fotheringham
,
A. S.
, and
McLoone
,
S.
,
2013
, “
Principal Component Analysis on Spatial Data: An Overview
,”
Ann. Assoc. Am. Geogr.
,
103
(
1
), pp.
106
128
.
34.
Alken
,
P.
,
Maute
,
A.
,
Richmond
,
A. D.
,
Vanhamäki
,
H.
, and
Egbert
,
G. D.
,
2017
, “
An Application of Principal Component Analysis to the Interpretation of Ionospheric Current Systems
,”
J. Geophys. Res.: Space Phys.
,
122
(
5
), pp.
5687
5708
.
35.
García-Alonso
,
C. R.
,
Pérez-Naranjo
,
L. M.
, and
Fernández-Caballero
,
J. C.
,
2014
, “
Multiobjective Evolutionary Algorithms to Identify Highly Autocorrelated Areas: The Case of Spatial Distribution in Financially Compromised Farms
,”
Ann. Oper. Res.
,
219
(
1
), pp.
187
202
.
You do not currently have access to this content.