Page 77 - Read Online

Page 170 Ji et al. Intell Robot 2021;1(2):151-75 https://dx.doi.org/10.20517/ir.2021.14

formed by randomly selecting images from each of the categories. All combinations, for example, “Normal
vs. Defect_1” or “Defect_2 vs. Defect_3”, were tested with 10 pairs and the mean, minimum, and maximum
values of test output distance were summarized for analysis. During the testing phase, the images were
chosen randomly. These images belonged to a different set of classes that were never shown to the network
during training. As described, all combinations of pairwise comparisons were tested with 10 different
sample image pairs. The mean Euclidean (L2) distance was computed as the similarity score.

Our experiment results show that, when two test images belong to the same class, their dissimilarity score is
smaller than those of images from two different classes. A threshold value can be chosen to determine
whether two images are from the same or different classes based on the test similarity scores. We also notice
that the threshold value has a decent margin to vary. From our experiments, 82.5% of test images actually
from the same class were predicted to be “from the same class”, while 80.8% of test images actually from
different classes were predicted to be “from different classes”. The binary classification accuracy was
calculated as 81.67% and F1-score as 81.82%. The accuracy level is acceptable to the current rail
maintenance operations with the potentials for further improvement.

Both cases can perform rail track condition monitoring and anomaly detection and classifications tasks with
deep learning methods with the same dataset. The case studies deal with them in different ways with
different deep learning models. Datasets generated from the maintenance operations are put into good use
with the deep learning models to improve the rail track maintenance operations. Training of Siamese
convolutional neural network was observed to take a shorter time than the classic convolutional neural
network approach. The existing hardware setup in the rail operations did not require significant
modification. The features extracted by the deep learning models performed better than the approaches of
selected man-made features.

6. CONCLUSIONS
This paper presents the importance and criticality of rail track condition monitoring to safe rail operations.
We give a brief overview of the historical development of deep learning and list common deep learning
models. Deep learning came into the rapid development phase after 2012; therefore, we review the deep
learning applications to rail track condition monitoring from 2013 to 2021. The applications are reviewed
according to the temporal evolutions, the regional adoptions, the data type, and the deep learning models.
We then discuss the potential challenges and research opportunities for applying deep learning to rail track
condition monitoring. Two application case studies are shared to illustrate the implementation of deep
learning methods in rail track condition monitoring.

DECLARATIONS
Acknowledgment
This research is part of the project supported by SMRT Corporation Ltd. The opinions, findings, and
conclusions or recommendations expressed in this publication are those of the author(s) and do not
necessarily reflect those of the company.

Authors’ contributions
Investigated the research area, reviewed and summarized the literature, wrote and edited the original draft:
Ji A
Managed the research activity planning and execution, contributed to the development of ideas according
to the research aims: Woo WL, Wong EWL