A Deep Learning based Signal Dimension Estimator with Single Snapshot Signal in Phased Array Radar Application

TL;DR

This paper introduces a deep learning-based method for estimating signal dimension in phased array radar using only a single snapshot, outperforming traditional techniques in detection and resolution.

Contribution

The proposed DLSDE employs a 2D-CNN to automatically extract features for signal dimension estimation from a single snapshot, unlike existing methods requiring multiple data snapshots.

Findings

DLSDE improves detection SNR by over 15dB.

DLSDE enhances resolution by more than 1 degree.

The method outperforms traditional eigen-decomposition and information criterion approaches.

Abstract

Signal dimension, defined here as the number of copies with different delays or angular shifts, is a prerequisite for many high-resolution delay estimation and direction-finding algorithms in sensing and communication systems. Thus, correctly estimating signal dimension itself becomes crucial. In this paper, we present a deep learning-based signal dimension estimator (DLSDE) with single-snapshot observation in the example application of phased array radar. Unlike traditional model-based and existing deep learning-based signal dimension estimators relying on eigen-decomposition and information criterion, to which multiple data snapshots would be needed, the proposed DLSDE uses two-dimensional convolutional neural network (2D-CNN) to automatically develop features corresponding to the dimension of the received signal. Our study shows that DLSDE significantly outperforms traditional methods in terms of the successful detection rate and resolution. In a phased array radar with 32 antenna elements, DLSDE improves detection Signal to Noise Ratio (SNR) by >15dB and resolution by >1{\deg}. This makes the proposed method suitable for distinguishing multiple signals that are spatially correlated or have small angular separation. More importantly, our solution operates with a single snapshot signal, which is incompatible with other existing deep learning-based methods.