Enhancing wireless signal perception through combined processing and learning methods
Madani, Sohrab
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/127337
Description
Title
Enhancing wireless signal perception through combined processing and learning methods
Author(s)
Madani, Sohrab
Issue Date
2024-12-05
Director of Research (if dissertation) or Advisor (if thesis)
Al-Hassanieh, Haitham
Doctoral Committee Chair(s)
Patel, Sanjay J
Committee Member(s)
Gupta, Saurabh
Mitra, Sayan
Department of Study
Electrical & Computer Eng
Discipline
Electrical & Computer Engr
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Wireless sensing, Deep learning, Signal processing
Abstract
In recent years, wireless signals have transcended their traditional role in communication systems, emerging as a powerful medium for sensing and perception. These electromagnetic waves have demonstrated remarkable versatility, enabling applications ranging from coarse-grained autonomous vehicle perception to finegrained physiological monitoring of human vital signs. While the underlying sensing mechanisms vary across applications, they fundamentally leverage the same physical properties of radio frequency propagation, creating opportunities for unified theoretical frameworks and methodological approaches.
This dissertation introduces novel hybrid methodologies that bridge classical signal processing techniques with modern deep learning approaches. We build upon established wireless sensing foundations while introducing innovative processing pipelines that combine domain-specific signal transformations with adaptive neural architectures. Our framework extends beyond application-specific solutions, presenting a generalizable approach to wireless signal processing that maintains theoretical rigor while embracing the flexibility of data-driven methods.
Through extensive experimental validation, we demonstrate the efficacy of our proposed methods across multiple perception tasks. Specifically, we address critical challenges in autonomous vehicle sensing and indoor object localization and tracking. Our approach leverages domain knowledge of wireless propagation characteristics to inform the design of specialized learning architectures, resulting in significant performance improvements over traditional methods. The methodologies developed in this work not only advance the state-of-the-art in wireless sensing but also establish new paradigms for integrating physical understanding with learning-based approaches in signal processing systems.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
