CISE Seminar: Ananya Sen Gupta, University of Iowa
Date: Friday, September 15, 2023
Time: 3:00pm – 4:00pm
Location: 665 Commonwealth Avenue, CDS 1101
Ananya Sen Gupta
Associate Professor, Department of Electrical and Computer Engineering
University of Iowa
Interpreting Geometric Concepts into Sonar Feature Representations: Case Studies and Challenges
Sonar target recognition and shallow water communications are critically important for naval situational awareness and environmental sustainability. Testing popular machine learning techniques over underwater acoustic data is especially interesting as they provide the exciting opportunity to seek new scientific knowledge in a realm dominated by complex, dynamic, unpredictable, and often unknown factors. The underwater acoustic realm also challenges emerging feature engineering and knowledge discovery techniques due to the dominance of non-linear time-varying overlap across important multi-dimensional features. Such overlap leads to feature dictionaries that are difficult to track or quantify, e.g. the persistent target features may occupy a latent but changing subspace, or occluded against features from a structured background. In this talk, I will discuss these challenges commonly encountered in underwater acoustics using case studies from field experiments as well as physics-driven simulations in this domain to provide robust ground truths. I will provide practical examples from my research across several disciplines, discuss how to implement key geometric ideas into well-known AI frameworks, and explain how we can use the powerful combination of topology and braid theory to quantify what makes a machine-discovered feature informative.
Ananya Sen Gupta received their PhD from the University of Illinois at Urbana-Champaign in 2006, spent a significant part of their research career (2008-2012) at the Woods Hole Oceanographic Institution (WHOI), and is currently an Associate Professor in Electrical and Computer Engineering at the University of Iowa. Dr. Sen Gupta’s research interests lie in the nexus of signal processing, pattern recognition and knowledge discovery, with emphasis on AI-enabled remote sensing in high-noise, high-clutter and highly dynamic environments. They specialize in harnessing classic signals theory and geometric constructs with current state-of-the-art in machine cognition to extract scientifically relevant information from sensor measurements corrupted by structured background interference. Their research has found broad applications in underwater acoustic communications, sonar target recognition, space plasma studies in Earth’s Van Allen radiation belts and the Martian ionosphere, spacecraft magnetometer measurements, oil spill fingerprinting, air pollution and food contamination studies, and more recently in dance image/video processing. They have numerous peer-reviewed publications as well as a US patent documenting their research across the last two decades.
Dr. Sen Gupta has served as a guest editor for the IEEE Journal of Oceanic Engineering and currently serves as an Associate Editor for IEEE Access and PeerJ Computer Science journals. They are also currently co-chair of the Technical Committee for Data Analytics, Integration and Modeling for IEEE Ocean Engineering Society, a participating member of the Signal Processing technical committee at the Acoustical Society of America (ASA). Across the last decade, they have given invited talks, organized/chaired special sessions and participated as a reviewer across multiple ASA meetings and/or Oceans conferences. Dr. Sen Gupta has also contributed as a member of the Oceans and Arts committees in IEEE Planet Positive 2030 efforts towards harnessing technology towards environmental sustainability in the wake of climate change.
Faculty Host: Vivek Goyal
Student Host: Ahmad Ahmad