Call for Papers: Special Issue on “Deep Learning Based Mechanical and

Structural Health Monitoring”

Scope

Traditional damage detection approaches have two big branches that are physics model-based
approaches which rely on numerical models and data-driven approaches which requires damage sensitive
feature formulation. However, physics model-based methods were not reliable due to discrepancies
between actual dynamic behavior of system and that of numerical model, and the data-driven methods
have difficulties to extract or formulate reliable damage sensitive features to consider measurement
uncertainties. Recent development of artificial intelligence especially various deep learning algorithms
significantly affects to many engineering disciplines. One of the most affected areas is mechanical and
structural health monitoring (MSHM) due to their abilities to extract multi-level features to detect various
mechanical and structural damage within images or any data measured from various types of sensors.
However, this topic is still in the early and emerging stage with huge potential for future innovation.

Therefore, this Special Issue calls for original scientific and technical contributions about Deep Learning
Based Mechanical and Structural Health Monitoring. The topics of interests that include, but not limited
to the following:

• Computer vision-based defect/damage detection, segmentation

• Data augmentation or generation
• Data-driven based supervised and unsupervised damage detection
• Abnormal or anomaly detection
• Data recovering methods
• Non-destructive MSHM
• Unmanned aerial vehicles adopted approaches for MSHM
• Image reconstruction or digital twins for damage mapping or MSHM
• Internal damage detection or monitoring
• Automated MSHM system

Keywords

• Deep learning
• Damage detection
• Unmanned aerial vehicle
• Image reconstruction
• Digital twin
• Unsupervised training
• Convolutional neural network
• Recurrent neural network
 • Reinforced learning
• Computer vision
• 1-dimentional data

Submission guidelines

Please submit your paper to Manuscript Central as the Special Issue on “Deep Learning Based Mechanical
and Structural Health Monitoring”.

Submissions shall adhere to the journal Author Guidelines.

Important Dates

Submission Deadline: 31st Jan, 2023

Guest Editors

• Young-Jin Cha, University of Manitoba, Canada

• Sattar Dorafshan, University of North Dakota, U.S.

Biography of Guest Editor

Prof. Young-Jin Cha

Professor Young-Jin Cha received his Ph.D. (2008) from Texas A&M University in
the Department of Civil and Environmental Engineering. He served as a post-
doctoral associate at the Massachusetts Institute of Technology (MIT) until 2014.
He then joined the Department of Civil Engineering at the University of Manitoba
in 2014. His key scientific contribution is advanced deep learning-based
automated structural health monitoring (SHM) with autonomous unmanned
aerial vehicles (UAVs). He was reported as top 0.45% and 0.65% cited scientist
within Civil Engineering field and top 2% cited scientist in all areas for single year
impact in the world in 2020 and 2021 from the Mendeley metadata of citations
analyzed by Elsevier and coordinated by Stanford University. He has been reported more than serval
hundred times as the most read author, most read research items, and citations in the Civil Engineering
Dept. at U of M, with more than 99,000 readings since his account on www.researchgate.net was opened
(retrieved on June 20, 2022). He was named to 2005 Who’s Who in America, organized many symposiums
in the MIT and Caltech through Engineering Mechanics Institute Conferences with the topics of Deep
Learning and Autonomous UAVs for SHM. He is serving as an Associate Editor in Engineering Reports,
Wiley and International Conference on Patten Recognition, Editorial Board Members, and core peer-
reviewers in many top engineering journals associated with ASCE, Elsevier, IEEE, and Wiley. He is also
serving and was severed as Chairman, Co-Chairs and Technical/Organizing Committee members in many
internal conferences in his research discipline such as AI and SHM.

Dr. Sattar Dorafshan

 Dr. Sattar Dorafshan is an Assistant Professor of Civil Engineering at the University of
North Dakota. He is the director of Sustainable Infrastructure Research Initiative at the College of
Engineering and Mines, and he co-directs the Transportation Technology Research Initiative supported by
the North Dakota Department of Transportation. Dr. Dorafshan has been a pioneer in the application of
remote sensing (visual imagery, infrared thermography, hyperspectral imagery), and non-destructive
evaluation methods (impact echo and ground penetrating radar) for robust assessment of civil
infrastructure. He has developed advanced artificial intelligence models such as deep convolutional neural
networks for automated data analysis and defect detection in civil infrastructure. Dr. Dorafshan has
managed several internal and external grants/awards since joining the University of North Dakota in Jan
2020. He was a postdoctoral research fellow at the Federal Highway Administration’s Turner-Fairbank
Highway Research Center between 2019 and 2020. He graduated with B.S., M.S., and Ph.D. degree in Civil
Engineering from University of Tabriz, Isfahan University of Technology, and Utah State University,
respectively.