Emergent Mind

Practical Radar Sensing Using Two Stage Neural Network for Denoising OTFS Signals

(2310.00897)
Published Oct 2, 2023 in cs.IT and math.IT

Abstract

Noise contamination affects the performance of orthogonal time frequency space (OTFS) signals in real-world environments, making radar sensing challenging. Our objective is to derive the range and velocity from the delay-Doppler (DD) domain for radar sensing by using OTFS signaling. This work introduces a two-stage approach to tackle this issue. In the first stage, we use a convolutional neural network (CNN) model to classify the noise levels as moderate or severe. Subsequently, if the noise level is severe, the OTFS samples are denoised using a generative adversarial network (GAN). The proposed approach achieves notable levels of accuracy in the classification of noisy signals and mean absolute error (MAE) for the entire system even in low signal-to-noise ratio (SNR) scenarios.

We're not able to analyze this paper right now due to high demand.

Please check back later (sorry!).

Generate a summary of this paper on our Pro plan:

We ran into a problem analyzing this paper.

Newsletter

Get summaries of trending comp sci papers delivered straight to your inbox:

Unsubscribe anytime.