Wideband Signal Localization with Spectral Segmentation

TL;DR

This paper introduces a neural network approach for wideband signal localization that jointly detects and estimates signal parameters, outperforming traditional energy detection methods in recall by 8 dB.

Contribution

It defines the signal localization task, proposes new metrics, and provides a dataset and training framework for neural networks to improve spectrum sensing accuracy.

Findings

Neural network approach achieves 8 dB higher recall than energy detection.

Introduces a new dataset for training signal localization models.

Provides baseline metrics and evaluation framework for the task.

Abstract

Signal localization is a spectrum sensing problem that jointly detects the presence of a signal and estimates a center frequency and bandwidth. This is a step beyond most spectrum sensing work which estimates "present" or "not present" detections for either a single channel or fixed sized channels. We define the signal localization task, present the metrics of precision and recall, and establish baselines for traditional energy detection on this task. We introduce a new dataset that is useful for training neural networks to perform this task and show a training framework to train signal detectors to achieve the task and present precision and recall curves over SNR. This neural network based approach shows an 8 dB improvement in recall over the traditional energy detection approach with minor improvements in precision.