Abstract
This paper investigates the detection of a weak transient broadband signal. We compare a polynomial subspace detection approach to a likelihood ratio test. While the later is statistically optimal, there may be reasons of computational efficiency and numerical robustness to combine such a likelihood ratio test with the subspace approach. We provide a review of these methods, highlight some of their similarities and differences, and demonstrate in simulations that in particular in the case of detecting very weak signals or signals in very dispersive environments, there may be a compelling argument for combining the two test methods.
Original language | English |
---|---|
Title of host publication | 32nd European Signal Processing Conference |
Subtitle of host publication | EUSIPCO 2024 |
Place of Publication | Piscataway, NJ |
Publisher | IEEE |
Pages | 1312-1316 |
Number of pages | 5 |
ISBN (Print) | 9789464593617 |
Publication status | Published - 30 Aug 2024 |
Event | 32nd European Signal Processing Conference - Lyon Convention Centre, Lyon, France Duration: 26 Aug 2024 → 30 Aug 2024 https://eusipcolyon.sciencesconf.org/ |
Conference
Conference | 32nd European Signal Processing Conference |
---|---|
Abbreviated title | EUSIPCO'24 |
Country/Territory | France |
City | Lyon |
Period | 26/08/24 → 30/08/24 |
Internet address |
Keywords
- likelihood ratio
- subspace approach
- signal