Bouzabia, Hamda, Kaddoum, Georges and Do, Tri Nhu.
2024.
« Deep learning-based interference detection, classification, and forecasting algorithm for ESM radar systems ».
IEEE Access, vol. 12.
pp. 148120-148142.
Compte des citations dans Scopus : 1.
Preview |
PDF
Kaddoum-G-2024-29776.pdf - Published Version Use licence: Creative Commons CC BY-NC-ND. Download (2MB) | Preview |
Abstract
In this study, aiming to address the challenges posed by interference from communication systems and jammers, we investigate the application of deep learning (DL) in electronic support measures (ESM) radar systems. Our primary objective is to detect, classify, and forecast interference that can disrupt detection of low probability of intercept (LPI) and low probability of detection (LPD) signals. The proposed algorithm uses a time-frequency distribution (TFD) and received interference strength (RIS) to detect and predict interference. To ensure high precision,we develop a new DL-based outlier detection (OD) technique that is based on the relationship between true positive rate (TPR) and latent space. More specifically, the OD technique applies a new dual-threshold mechanism to the TFD representation for interference detection. We also introduce a DL-enabled classifier designed using the OD architecture to identify the source of interference. Finally, we forecast the RIS by proposing a newDL autoregressive (AR) model through a sliding window designed using the classifier’s output. By integrating OD in classifier design and using its output for forecasting, our approach achieves superior accuracy as compared to independent models. Simulation results demonstrate that the proposed algorithm outperforms others, particularly in lowsignal-to-interference plus noise ratio (SINR) conditions. Specifically, in terms of interference detection, our algorithm achieves 0.9978 TPR, 0.9415 recall, and 0.0004 false positive ratio (FPR). With regard to classification, it records 0.9784 precision and 0.7847 recall. In forecasting, it achieves a 0.2100 mean average error (MAE), thus significantly enhancingESMradar awareness. The TFD feature also proves to be more accurate than in-phase and quadrature features. These strengths, coupled with an optimal balance of cost and accuracy, make our framework robust and resistant to interference.
| Item Type: | Peer reviewed article published in a journal |
|---|---|
| Professor: | Professor Kaddoum, Georges |
| Affiliation: | Génie électrique |
| Date Deposited: | 05 Nov 2024 19:47 |
| Last Modified: | 08 Nov 2024 15:20 |
| URI: | https://espace2.etsmtl.ca/id/eprint/29776 |
Actions (login required)
 |
View Item |