Dr. Zhiwu Xie, technology development librarian in the University Libraries and associate director of VTSIL will lead the grant entitled "Developing Library Cyberinfrastructure Strategy for Big Data Sharing and Reuse" from National Leadership Grant for Libraries from the Institute of Museum and Library Services (IMLS). Together with Tyler Walters, dean and professor, University Libraries; Edward Fox, professor of computer science in the College of Engineering; Pablo Tarazaga, assistant professor of mechanical engineering in the College of Engineering and Jiangping Chen, associate professor in the Department of Library and Information Sciences at the University of North Texas, will also help evaluate and review the project.
More on the Virginia Tech story can be seen here. The IMLS grant description/narrative can be read at the IMLS website here.
Dr. Xie with Dr. Tarazaga receive National Leadership Grant for Libraries from the Institute of Museum and Library Services
Dustin Bales successfully defended his master thesis entitled "Characteristic Classification of Walkers via Underfloor Accelerometer Gait Measurements through Machine Learning." His work has multiple applications in soft biometrics, specialized marketing and security and threat detection.
Great job Dustin!
Abstract: The ability to classify occupants in a building has far-reaching applications in security, monitoring human health, and managing energy resources effectively. In this work, gender and weight of walkers are classified via machine learning or pattern recognition techniques. Accelerometers mounted beneath the floor of Virginia Tech’s Goodwin Hall measured walkers’ gait. These acceleration measurements serve as the inputs to machine learning techniques allowing for classification. For this work, the gait of fifteen individual walkers was recorded via fourteen accelerometers as they, alone, walked down the instrumented hallway, in multiple trials. These machine learning algorithms produce an 88 % accurate model for gender classification. The machine learning algorithms included are Bagged Decision Trees, Boosted Decision Trees, Support Vector Machines (SVMs), and Neural Networks. Data reduction techniques achieve a higher gender classification accuracy of 93 % and classify weight with 64 % accuracy. The data reduction techniques are Discrete Empirical Interpolation Method (DEIM), Q-DEIM, and Projection Coefficients. A two- part methodology is proposed to implement the approach completed in this thesis work. The first step validates the algorithm design choices, i.e. using bagged or boosted decision trees for classification. The second step reduces the walking data measured to truncate accelerometers which do not aid in increasing characteristic classification.
Candidate Biography: Dustin conducts research at Virginia Tech as part of the Smart Infrastructure Laboratory. He is a member of GAiTE LLC which is working to transition the technology developed in the Smart Infrastructure Lab to consumer markets.
Bachelors of Science in Mechanical Engineering, 2014 University of Wyoming, Laramie, WY
Dr. Tarazaga visited the VTTI bridge which is the tallest bridge in Virginia for another possible instrumentation project. This would extend VTSIL's instrumentation capabilities to bridges with the potential to carry out work in several other domains. Stay tuned to see what happens and how this moves forward. Very exciting!
Mico Woolard, PhD student with Dr. Tarazaga, is working on localization algorithms in order to perform human tracking in Goodwin Hall. He has now leveraged some of his work in classification and signal processing to create a solid piano as a demonstration of the interactive capabilities that a smart building can achieve. This demo will also be going to the German Hannover Messe 2016 Expo where Dr. Tarazaga and Mico will talk about VTSIL.
Playing in one of the monitors at the entrance of Goodwin Hall is our VTSIL video showcasing some of our research and system. You don't have to come to the building to see it but we recommend it!
See youtube link below.
Name: B.F. Spencer, Jr. | Nathan M. and Anne M. Newmark Endowed Chair of Civil Engineering University of Illinois at Urbana-Champaign
Title: Monitoring of Civil Infrastructure: from Research to Engineering Practice
Date: Monday, September 21, 2015
Time: 1:30 pm- 2:30 pm
Location: 261 Durham Hall
Host: Dr. Matt Eatheron, Dr. Mahendra Singh and Dr. Pablo Tarazga
The ability to continuously monitor the integrity of civil infrastructure in real-time offers the opportunity to reduce maintenance and inspection costs, while providing for increased safety to the public. Furthermore, after natural disasters, it is imperative that emergency facilities and evacuation routes, including bridges and highways, be assessed for safety. Addressing all of these issues is the objective of structural health monitoring (SHM). Smart sensors densely distributed over structures can provide rich information for structural health monitoring using their sensing, computational, and wireless communication capabilities. Though smart sensor technology has seen substantial advances during recent years, implementation of smart sensors on full-scale structures has been limited; interdisciplinary efforts to address issues in sensors, networks, and application specific algorithms have only now begun to germinate. Following an overview of these issues, a new paradigm for structural health monitoring employing a network of smart sensors will be presented. Because of its ability to meet the demands of data intensive applications such as SHM, MEMSIC’s Imote2 is adopted for this research. Two full-scale deployments will be presented. The first is for the Jindo Bridge, a cable-stayed bridge in South Korea with a 344m main span. This project constitutes the world’s largest deployment of wireless sensors to monitor civil infrastructure. The second deployment is for campaign-monitoring of a railroad bridge south of Chicago. These results demonstrate the efficacy and maturity of wireless smart sensor technology. Finally, future directions are indicated.
Bio: B.F. Spencer, Jr. received his Ph.D. in theoretical and applied mechanics from the University of Illinois at Urbana-Champaign in 1985. He worked on the faculty at the University of Notre Dame for 17 years before returning to the University of Illinois at Urbana-Champaign, where he currently holds the Nathan M. and Anne M. Newmark Endowed Chair in Civil Engineering and is the Director of the Newmark Structural Engineering Laboratory. His research has been primarily in the areas of smart structures, stochastic fatigue, stochastic computational mechanics, and natural hazard mitigation. He is a Fellow of ASCE, a Foreign Member of the Polish of Sciences, the North American Editor in Chief of Smart Structures and Systems, and the past president of the Asia-Pacific Network of Centers for Research in Smart Structures Technology.
Extra links: Dr. Spencer's Lab- Smart Structure Technology Laboratory
Eric Schmidt, executive chairman of Google, visits VT to deliver the University Commencement address of 2015. While here he visited VTSIL and VAST.
We are very honored by his visit!
Dr. Mike Todd from UCSD will visit VTSIL and give the ME distinguished lecture on May 7th. His talk is entitled "A Bayesian Experimental Design Approach to Structural Health Monitoring With Specific Application to Ultrasonic Interrogation" and will be in Holden Hall at 3:30pm.
This presentation introduces a new approach for approaching structural health monitoring (SHM) applications. Starting from a general formulation of Bayes risk, we derive a global optimality criterion within a detection theory framework. The optimal design configuration is then established as the one that minimizes the total computed Bayes Risk (or loss) for the application. While the approach is suitable for many sensing/actuation SHM processes, we focus on the example of active sensing using guided ultrasonic waves by implementing an appropriate general statistical model of the wave propagation and feature extraction process. This example implements both pulse-echo and pitch-catch actuation schemes and takes into account line-of-site visibility and non-uniform damage probabilities over the monitored structure. The design space considers the optimal placement and selection of transducers. We provide a few actuator/sensor placement test problems (within the separate problems of detection and localization) and discuss the optimal solutions generated by the algorithm. Such a scheme allows for proper uncertainty quantification in the design and application process of SHM solutions.
Professor Michael Todd received his BS (1992), MS (1993), and PhD (1996) from Duke University in the Department of Mechanical Engineering and Materials Science. He was then an ASEE. postdoctoral fellow (1996), staff research engineer (1998), and Section Head (2000) at the Naval Research Laboratory in the Fiber Optic Smart Structures Section. He joined the Structural Engineering Department at the University of California San Diego in 2003, where he currently serves as Vice Chair. Among his numerous honors are the Alan Berman NRL Publication Award (1999), NRL Patent Award (2003,2004), UC San Diego Hellman Fellow (2004-2005), and the Structural Health Monitoring Person-of-the-Year Award (2005).
The one and only Gilbert Strang visits VTSIL and VAST.
Gil gave the inaugural talk to the Distinguished Lecture & Celebration of Virginia Tech's Computational Modeling and Data Analytics (CMDA) Degree.
For those of you that don't know who Dr. Strang is I recommend you visits his homepage, books and online courses.
Here is avery brief bio from the program : Gilbert Strang, Professor of Mathematics at MIT, is renowned for fundamental contributions to Finite element methods, wavelets, applied mathematics, and linear algebra. His articles, books, and videos have changed the way we think about these fields, and inspired countless scientists and engineers.
VT SIL NEWS
Sign up to our RSS Feed! Easy to do and you will be up to date on the latest VT SIL news.