Author ORCID Identifier
0009-0000-8097-171X
Document Type
Dissertation
Date of Award
5-31-2024
Degree Name
Doctor of Philosophy in Electrical Engineering - (Ph.D.)
Department
Electrical and Computer Engineering
First Advisor
Alexander Haimovich
Second Advisor
Ali Abdi
Third Advisor
Joerg Kliewer
Fourth Advisor
Eliza Zoi-Heleni Michalopoulou
Fifth Advisor
Alex R. Dytso
Abstract
In this work, machine learning theory is applied to the design of a radar detector in order to train a machine learning-based detector that is robust against Doppler shifts. The radar system is designed to work with data that would be otherwise intractable to conventional optimal detector design, such as transmitted noise waveforms and the effects of one-bit quantization at the receiver. The detection performance of the one-bit receiver is shown to match the performance of the derived square-law sign correlator detector. The resulting learning-based detector also introduces Doppler tolerance to the system, which allows for the successful detection of a waveform that has been Doppler shifted due to sufficiently high target velocity. This is achieved by selecting the training data to best represent all expected Doppler shifts as well as interference effects. For further performance gains, the training data can be adjusted based on a priori estimates of the true Doppler and noise covariance values. Additionally, the advantages to using one-bit data are highlighted, which includes the reduction of computational power and memory requirements, and it is proven that this learning-based detector can be trained to detect waveforms even through the harsh non-linear effects of one-bit quantization.
Recommended Citation
Wensell, Kyle Peter, "Machine learning-based design of doppler tolerant radar" (2024). Dissertations. 1761.
https://digitalcommons.njit.edu/dissertations/1761
Included in
Automotive Engineering Commons, Data Science Commons, Signal Processing Commons, Systems and Communications Commons
