“Hyperspectral Imaging and Machine Learning”

Location: LTS Auditorium, 8080 Greenmead Drive

Speaker:
Wojciech Czaja
Professor, Department of Mathematics

Abstract:
In this talk we provide an overview of some of the recent efforts dedicated to utilizing the advances arising in the context of big data and machine learning, for the purposes of improving the analysis of hyperspectral imagery.

Hyperspectral sensors enable the detection, identification and analysis of remotely sensed materials, which has significant implications in areas ranging from agriculture to homeland security. Machine learning provides algorithms with predictive capabilities. This, combined with an immense growth of the volume of available hyperspectral data, raises interesting scientific possibilities.

We shall present some of these that deal with efficient data representation, material classification, and data fusion.

Speaker Bio:
Wojciech Czaja is a professor of mathematics at the University of Maryland, College Park, a member of both the Norbert Wiener Center for Harmonic Analysis and Applications and the Center for Scientific Computation and Mathematical Modeling, and a Marie Curie Fellow.

His publications range from theoretical and applied mathematics to remote sensing, biomedical imaging, and computational biology.

Czaja is a co-author of the books “Integration and Modern Analysis” (Birkhauser, 2009) and a series “Excursions in Harmonic Analysis” (Birkhauser, 2013-2017).

His current research interests include applied harmonic analysis, machine learning, and data science.