Quarterly Webinar Series


Assistive Intelligence (AI):
Intelligent Data Analytics Algorithms to Assist Human Experts

Presented: January 30, 2019, 11:00 AM Central Time
Speaker: Dr. Zhaozheng Yin, Missouri University of Science and Technology



Artificial Intelligence, particularly deep learning, has recently received increasing attention in many applications, such as image classification, speech recognition, and computer games. The success of deep learning algorithms requires big annotated datasets for training, gradient-based optimization algorithms, and powerful computational resources. In the case of civil infrastructure inspection, we can collect big data from different imaging sensors such as color, thermal, and hyperspectral cameras. Three issues encounter in this application. First, it is tedious and expensive to let human experts annotate the datasets to train deep learning algorithms. Second, the offline trained deep learning algorithms may not be able to adapt to new civil infrastructures. Third and lastly, the trained deep learning algorithm works like a black box on new data, without the domain knowledge from human experts. In this project, we investigate intelligent data analytics algorithms with human experts in the loop, called Assistive Intelligence (AI). Using the bridge inspection as a case study, we aim to find regions-of-interest (e.g., joints with damages) over long video sequences. The data analytics algorithm is initially trained from a small set of data. Given the dataset of a new bridge, bridge experts only need to annotate a few region-of-interest examples as the seed; our algorithm will retrieve corresponding examples in the rest of videos. Human experts can also return some incorrectly retrieved samples to the data analytics algorithm for further refinement. Thus, while the data analytics algorithm can assist human in an efficient way, bridge experts can leverage their domain knowledge in the adaptation of the computational tool in different scenarios.


Dr. Zhaozheng Yin received his PhD in Computer Science and Engineering from Penn State in 2009 and received his Master and Bachelor degrees at the University of Wisconsin-Madison and Tsinghua University.  He is specialized in Computer Vision, Image Processing and Machine Learning, with broad applications in structure health monitoring.  Dr. Yin has been a faculty member in Computer Science at Missouri S&T since September 2011. He is a recipient of CVPR Best Doctoral Spotlight Award (2009), MICCAI Young Scientist Award (2012, finalist in 2015 and 2010), NSF CAREER Award (2014), Department Outstanding Junior Faculty Research Award (2014) and Missouri S&T Faculty Research Award (2014, 2017), Best Paper Award of CVPR Workshop on Understanding Hands in Actions (2015). He is a Daniel St. Clair Faculty Fellow in the Computer Science department since 2015, and a Dean’s Scholar in the College of Engineering and Computing since 2016. 


Toward Autonomous Wall-climbing Robots for
Inspection of Concrete Bridges and Tunnels

Presented: September 19, 2018, 11:00 AM Central Time
Speaker: Dr. Jizhong Xiao, Professor, The City College of New York



In addition to visual inspection for surface flaws, inspectors are often required to detect subsurface defects (e.g., delamination and voids) using nondestructive evaluation (NDE) instruments, such as ground penetration radar (GPR) and impact sounding device, in order to determine the structural integrity of bridges and tunnels. In these cases, access to critical locations for reliable and safe inspections is a challenge.

Since 2002, Dr. Jizhong Xiao’s group has developed four generations of wall-climbing robots for NDE inspection of bridges and tunnels. These robots combine the advantages of aerodynamic attraction and suction to achieve a desirable balance of strong adhesion and high mobility. For example, Rise-Rover with two drive modules can carry up to 450 N payload, and GPR-Rover can carry a small GPR antenna for subsurface flaw detection and utility survey on concrete structures. These robots can reach difficult-to-access areas (e.g., the bottom side of bridge decks), take close-up pictures, record and transmit NDE data to a host computer for further analysis. They can potentially make bridge inspection faster, safer, and cheaper without affecting traffic flow on roadways.

This presentation will review the recent development of smart and autonomous wall-climbing robots to realize automated inspection of civil infrastructure with minimal human intervention.


Dr. Jizhong Xiao is a Professor in the Electrical Engineering Department at The City College of New York, the flagship campus of the City University of New York. Dr. Xiao's research interests include robotics and control, cyber-physical systems, non-destructive evaluation (NDE) of infrastructures, autonomous navigation and 3D simultaneous localization and mapping (SLAM), real-time and embedded computing, assistive technology, multi-agent systems and swarm robotics.


climbing robots for steel bridge inspection and evaluation

Presented: June 21, 2018, 12 p.m. Central Time
Speaker: Dr. Hung La, Assistant Professor, University of Nevada, Reno

View Webinar



Steel structures and steel bridges, constituting a major part in civil infrastructure, require adequate maintenance and health monitoring. In the U.S., more than 50,000 steel bridges are either deficient or functionally obsolete, which likely presents a growing threat to people's safety. The collapse of numerous bridges recorded over the past 16 years has shown significant impact on the safety of all travelers.

In this presentation, the design and implementation of two different climbing robots for steel structure inspection are reported. Based on the magnetic wheel design, the robot can climb on different steel surface structures (i.e., flat, cylinder, cube). The robots can be remotely controlled or programmed to move autonomously on steel structures. Current tests shows that the robots can carry up to 8 pounds of load while being able to adhere strongly on the steel surface. Climbing capability tests are done on bridges and on several steel structures with coated or unclean surfaces. Although the steel surface is curved and rusty, the robots can still adhere tightly.


Dr. Hung La is an Assistant Professor of Computer Science and Engineering at the University of Nevada, Reno, Director of the Advanced Robotics and Automation Laboratory, and principal investigator for the INSPIRE UTC. He works in the areas of robotics and control systems. His current interests are in bridge inspection robotic system developments, mobile sensor networks, and multi-robot systems. Dr. La is an associate editor of the IEEE Transactions on Human-Machine Systems. Dr. La has received the prestigious 2014 ASCE Charles Pankow Award for the development of Robotics Assisted Bridge Inspection Tool (RABIT).  He is the recipient of 3 Best Paper Awards and a Best Presentation Award at international conferences.

microwave materials characterization and imaging
for structural health monitoring

Presented: March 15, 2018
Speaker: Dr. Reza Zoughi, Schlumberger Endowed Professor, Missouri S&T

view webinar


The relatively small wavelengths and large bandwidths associated with microwave signals make them great candidates for inspection of construction materials and structures, and for materials characterization and imaging. Signals at these frequencies readily penetrate inside of dielectric materials and composites and interact with their materials characteristics and inner structures. Water molecule is dipolar and possesses a relatively large complex dielectric constant, which is also highly sensitive to the presence of ions that increase its electrical conductivity. Consequently, chemical and physical changes in construction materials affect their complex dielectric constant. This can be measured, and through analytical and empirical dielectric mixing formulae, correlated to those changes. Examples of applications would be, presence of delamination in a bridge deck and pavement, permeation of moisture behind retaining walls or corrosion of reinforcing steel bars which can be imaged with microwave techniques. One of the critical trade-off issues is between the microwave signal penetration into concrete vs. frequency of operation. Dielectric of concrete, particularly when moist, has a relatively high loss factor. As such, lower microwave frequencies are suitable to achieve reasonable penetration. Image resolution degrades as a function of decrease in operating frequency, therefore, a balance must be reached when using these techniques for imaging cement-based materials. In this webinar, issues related to concrete materials property evaluation and high-resolution imaging will be discussed, and examples will be provided.


Dr. Reza Zoughi
Schlumberger Endowed Professor
Electrical and Computer Engineering Department
Director, Applied Microwave Nondestructive Testing Laboratory (amntl)
Missouri University of Science and Technology (Missouri S&T)
Email: zoughir@mst.edu
URLs: http://amntl.mst.edu/people/zoughi/zoughi2/, http://amntl.mst.edu/  

Dr. Reza Zoughi is the Schlumberger Endowed Professor in the Electrical and Computer Engineering department at Missouri S&T.  Dr. Zoughi’s research activities are broad many of them are in the area of civil structure evaluation and imaging involving materials characterization of cement-based materials and structures, detection and evaluation of alkali silica reaction (ASR) and gel formation, and imaging of rebars for detecting corrosion.  He had his research team have developed high-resolution, portable 3D microwave camera suitable for a number of critical applications. Dr. Zoughi holds 18 patents in the field of microwave nondestructive testing and imaging.

Drone-Enabled Remote Sensing for Transportation Infrastructure Assessment

Presented:  December 13, 2017
Speaker: Colin Brooks, Michigan Technological University

view webinar


Unmanned aerial systems (UAS or “drones”) are a rapidly developing technology that can help meet the needs of transportation agencies for reliable, repeatable data that can save money and increase safety for the data collection process. By taking advantage of flexible platforms that can deploy a variety of sensors, transportation agencies and their information suppliers can help meet these data needs for operations, asset management, and other areas. Location-specific data on infrastructure condition and distresses can help with improved management of assets.

In this presentation, recent applied research led by a Michigan Technological University team is reviewed, with a focus on bridge condition assessment and corridor monitoring. Examples of 3D optical, thermal, and LiDAR data are shown and how analysis methods result in usable information to meet pressing data needs. Finding spalls and delaminations, characterizing cracking, inventory of roadway assets, and related applications will be shown. Achievable resolutions and accuracies will be reviewed and how these data are transformed into asset condition data.


Colin Brooks, MEM
Senior Research Scientist
Environmental, Transportation, and Decision Support Lab
Michigan Tech Research Institute (MTRI)
Michigan Technological University
Email: cnbrooks@mtu.edu
URL: www.mtri.org 

Mr. Brooks  has been leading transportation and environmental remote sensing application studies for MTRI in bridge condition assessment, unpaved road condition, mapping of invasive aquatic plants, freight flow monitoring, bridge scour, wetland assessment, unmanned aerial vehicle applications, slope stability assessment, bridge inspection tools, asset management, decision support systems, and rail network modeling. Projects have assessed environmental areas of concern and transportation infrastructure in Alaska, Michigan, Ohio, Alaska, Nebraska, Iowa, South Dakota, and elsewhere. He has led software development projects to help find new wetlands mitigation sites and to create tablet-based data entry systems for bridge inspections. He is currently completing a PhD with a focus on using drones to map and monitor Eurasian watermilfoil while also developing drone applications for road and bridge condition assessment.

Lab-on-Sensor for Structural Behavior Monitoring: Theory and Applications

DATE/TIME: September 28, 2017, 11:00 AM–12:00 PM Central Time (US and Canada)
PRESENTED BY: Genda Chen, Ph.D., P.E., F.ASCE, Missouri University of Science and Technology



There are over 600,000 bridges in the U.S. National Bridge Inventory (NBI). Nearly 50% of them rapidly approach their design life and deteriorate at an alarming rate, particularly under an increasing volume of overweight trucks. Visual inspection as the current practice in bridge management is labor intensive and subjective, resulting in inconsistent and less reliable element ratings. Lab-on-sensor technologies can provide supplemental mission-critical data to the visual inspection for both qualitative and quantitative evaluations of structural conditions, and thus critical decision-making of cost-effective strategies in bridge preservation.

In this presentation, the design and operation characteristics of highway bridges are first reviewed to establish the needs for structural behavior monitoring in order to align monitoring outcomes with daily practices in bridge preservation. The responses of steel-and concrete-grider bridges to earthquake/tsunami events and the deterioration of aging bridges are then introduced to demonstrate the types of structural limits to prevent through planned, monitored, and evaluated maintenances. Next, a lab-on-sensor design theory is presented and applied to detect and assess structural behaviors such as concrete cracking, foundation scour, and steel corrosion. For each mechanical or electrochemical behavior, the theory includes three steps: (1) Extension of the behavior from a structural element to its nearby deployed sensor with a special mechanism, (2) Calibration of the sensed parameter with the behavior of the sensor mechanism and (3) Behavior correlation of the sensor mechanism with the nearby structural element. For crack detection and assessment, coax cable sensors are designed, fabricated, calibrated and applied to an in-service low-volume bridge based on the propagation and change of electromagnetic waves in a coax cable. For foundation scour detection and assessment, smart rocks with embedded magnet(s) are designed, fabricated, calibrated and applied to an in-service high-volume bridge based on the change of magnetic fields around a smart rock deployed around a foundation. For steel corrosion detection and assessment, Fe-C coated long period fiber grating sensors are designed, fabricated, calibrated and applied to reinforced concrete specimens in laboratory based on the change in wavelength of the light transmitting through the gratings. Finally, the accuracy, resolution and measurement range of various sensors are discussed before this presentation is concluded.


Professor Genda Chen, Ph.D., P.E., F. ASCE, F. SEI
Professor and Robert W. Abbett Distinguished Chair in Civil Engineering
Director, System and Process Assessment Research Laboratory (SPAR Lab)
Director, INSPIRE University Transportation Center (INSPIRE UTC)
Associate Director, Mid-America Transportation Center (MATC)
Missouri University of Science and Technology (Missouri S&T)
Email: gchen@mst.edu, inspire-utc@mst.edu
http://web.mst.edu/~gchen/, http://inspire-utc.mst.edu

Dr. Chen received his Ph.D. degree from State University of New York at Buffalo in 1992 and joined Missouri S&T in 1996 after over three years of bridge design, inspection, and construction practices with Steinman Consulting Engineers (later merged to Parsons Transportation Group) in New York City. He was granted two patents and authored over 350 publications in structural health monitoring, structural control, interface mechanics and deterioration, bridge engineering, and multi-hazard effects. He received the 1998 National Science Foundation CAREER Award, the 2004 Academy of Civil Engineers Faculty Achievement Award, and the 2009, 2011, and 2013 Missouri S&T Faculty Research Awards. He is Chair of the 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure in 2019, Associate Editor of the Journal of Civil Structural Health Monitoring, Editorial Member of Advances in Structural Engineering, a council member of the International Society for Structural Health Monitoring of Intelligent Infrastructure, and an executive member of the U.S. Panel on Structural Control and Monitoring. He was a member of post-disaster reconnaissance teams after the 2005 Category III Atlantic Hurricane, the 2008 M7.9 China Earthquake, the 2010 M8.8 Chile Earthquake, and the 2011 M9.0 Great East Japan Earthquake. He was elected to ASCE Fellow in 2007 and Structural Engineering Institute (SEI) Fellow in 2013. In 2016, he was nominated and inducted into the Academy of Civil Engineers at Missouri S&T.