Big Data Structural Health Monitoring

Identifying barely visible, critically important trends in large (gigabyte to terabyte size) structural data sets.

Funded by the National Science Foundation.

Solar Panel Diagnostics

Employing electrical spread-sprectrum reflectometry to quickly and easily identify faults in large-scale solar arrays.

Funded by the Department of Energy.

Data-Driven Acoustic Models

Merging digital twins with signal processing to improve data analysis capabilities in structural acoustics.

Funded by the Air Force Office of Scientific Research.

Audio Denoising and Dereverberation

Removing distortions from audio data to improve audio quality and intelligibility.

Funded by Harman International.

Join the Artificial Intelligence for Material Sensing Slack Group

We have recently started a multi-discplinary Slack workgroup on incorporating artificial intelligence and machine learning into material sensing and nondestructive evaluation. The group has monthly seminars. All are free to join us.

Join Here!

About the SmartData Lab

Data permeates every part of society. As a result, there have been many advances on how to effectively process this data. These advances make use of concepts from many disciplines, including linear algebra, representation theory, network theory, and machine learning. These methods provide technical disciplines with many benefits: quicker data processing, more effective information extraction, and better data fusion from multiple sources. These new ideas also form the framework for solving some the greatest technical grand challenges of today.

 The SmartData Lab uses these advances for creating new diagnostics systems, new data-driven acoustics models, and new time-series analysis algorithms. The new diagnostics systems process acoustic data to monitor the integrity of aircrafts, train rails, industrial systems, and other structures. The new data-driven acoustic models improve these processing by integrating digital twins model with our data analysis algorithms. The new time-series algorithms remove distortions from the data to draw statistically significant conclusions from it.

Meet the Lab!

Below are the current members of the UF SmartData Lab.

See Full List of Current and Former Members

Joel B. Harley

Lab Director

Research

Diagnostics, acoustics, and time-series analysis

Resources
ORCID
Google ScholarResearchGate

K. Supreet Alguri

PhD Researcher

Research

 Dictionary learning and compressive sensing for structural health monitoring

ReSources
WebsiteGoogle ScholarResearchGate

Alexander Douglass

PhD Researcher

Research

Compensation of environmental and operational effects for structural health monitoring

Soroosh Sabeti

PhD Researcher

Research

Prediction of isotropic and anisotropic wavefields from limited data

Yi Tang

PhD Researcher

Research

Adaptive prediction and control of sepsis and norepinephrine in clinical settings

Sungwon Kim

Postdoc Researcher

Research

Impact monitoring of carbon fiber composite panels

Daniel Alabi

PhD Researcher

Research

Ultrasonic characterization of thin films

Kang Yang

PhD Researcher

Research

Physical-Inspired learning with waves

Ishan Khurjekar

PhD Researcher

Research

 Deep neural networks for robust localization

Harsha Tetali

PhD Researcher

Research

Studying the intersection of machine learning and physics

Ayobami Edun

PhD Researcher

Research

Advanced data science for solar diagnositcs

Redi Tola

Undergraduate Researcher

Research

Solar panels diagnostics with spread sprectrum time-domain reflectometry

David Garcia

Undergraduate Researcher (currently at Toyota Reseach Institute)

Research

Solar panels diagnostics with spread sprectrum time-domain reflectometry

Featured Publications

Below are some of our recent and popular publications.

See Full Publication List

Sparse Recovery of the Multimodal and Dispersive Characteristics of Lamb Waves

Journal of the Acoustical Society of America


Official Link

Scale transform signal processing for optimal ultrasonic temperature compensation

IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control


Official Link

Data-driven matched field processing for Lamb wave structural health monitoring

Journal of the Acoustical Society of America


Official Link

Robust ultrasonic damage detection under complex environmental conditions using singular value decomposition

Ultrasonics


Official Link

Predictive guided wave models through sparse modal representations

Proceedings of the IEEE


Official Link

Statistical partial wavefield imaging using Lamb wave signals

Structural Health Monitoring


Official Link

Funding

Thank you to all of our sponsers below who have supported our research work and the students committed to it.

Join the SmartData Lab! Positions available.