Ph.D. Thesis

My doctoral research combined machine learning with robust signal processing in low signal-to-noise regimes.

PhD thesis visual

Thesis: Detection of underground installations in hostile environments.

During my PhD studies, I had the privilege of working on a project funded by the U.S. Army Research Office (ARO) and led by my adviser, Prof. Nathan Intrator, together with Nobel laureateNobel laureate Prof. Leon N. Cooper. The project combined machine-learning techniques with a bank of unmatched filters to estimate object distance from time-of-arrival in signal-to-noise-ratio regimes below the classical detection threshold. This approach enabled the use of low-power acoustic pulses to detect underground installations while remaining covert.

U.S. Army Research Office seal Project report (PDF)

Publications Based on the Thesis

  1. 2008 Journal

    A data fusion and multiple ping method for improving the resolution of low-power acoustic and seismic sensing

    A. Apartsin, N. Intrator

    J. Acoustical Society of America, 124(4)

  2. 2010 Conference

    SNR-dependent filtering for Time Of Arrival estimation in high noise

    A. Apartsin, L.N. Cooper, N. Intrator

    IEEE Workshop on Machine Learning for Signal Processing

  3. 2011 Conference

    Biosonar-inspired source localization in low SNR

    A. Apartsin, L.N. Cooper, N. Intrator

    Int. Conf. Bio-inspired Systems and Signal Processing

  4. 2012 Journal

    Semi-coherent time of arrival estimation using regression

    A. Apartsin, L.N. Cooper, N. Intrator

    J. Acoustical Society of America, 132(2)

  5. 2013 Journal

    Time-of-flight estimation in the presence of outliers. Part I: Single echo processing

    A. Apartsin, L.N. Cooper, N. Intrator

    IEEE Trans. Geoscience and Remote Sensing, 52(6)

  6. 2013 Journal

    Time-of-flight estimation in the presence of outliers. Part II: Multiple echo processing

    A. Apartsin, L.N. Cooper, N. Intrator

    IEEE Trans. Geoscience and Remote Sensing, 52(7)

  7. 2014 Journal

    Energy-Efficient Time-of-Flight Estimation in the Presence of Outliers: A Machine Learning Approach

    A. Apartsin, L.N. Cooper, N. Intrator

    IEEE J. Selected Topics in Applied Earth Observations, 7(4)

Award

  • 2011: The Don and Sara Maren Foundation award for outstanding achievements in Ph.D. studies.

Quick Links