Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 23, Issue 5, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2016.2553042
Keywords
Active drift learning; cognitive radar; data-driven adaptive radar; incremental learning; nonstationary environment
Categories
Funding
- U.S. Missile Defense Agency (MDA) at the Oak Ridge National Laboratory [DE-AC05-00OR22725]
- Department of Energy
Ask authors/readers for more resources
Most existing radar algorithms are developed under the assumption that the environment (clutter) is stationary. However, in practice, the characteristics of the clutter can vary enormously depending on the radar-operational scenarios. If unaccounted for, these nonstationary variabilities may drastically hinder the radar performance. Therefore, to overcome such shortcomings, we develop a data-driven method for target detection in nonstationary environments. In this method, the radar dynamically detects changes in the environment and adapts to these changes by learning the new statistical characteristics of the environment and by intelligibly updating its statistical detection algorithm. Specifically, we employ drift detection algorithms to detect changes in the environment; incremental learning, particularly learning under concept drift algorithms, to learn the new statistical characteristics of the environment from the new radar data that become available in batches over a period of time. The newly learned environment characteristics are then integrated in the detection algorithm. We use Monte Carlo simulations to demonstrate that the developed method provides a significant improvement in the detection performance compared with detection techniques that are not aware of the environmental changes.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available