A Wideband Signal Recognition Dataset

TL;DR

This paper introduces a comprehensive dataset and training framework for wideband signal recognition, advancing spectrum sensing by enabling detection, localization, and classification of signals using machine learning.

Contribution

It presents a new dataset and training methodology for neural networks to perform wideband signal recognition, extending beyond traditional detection tasks.

Findings

Dataset facilitates training of neural networks for wideband recognition

Training framework improves recognition accuracy

Supports detection, localization, and classification tasks

Abstract

Signal recognition is a spectrum sensing problem that jointly requires detection, localization in time and frequency, and classification. This is a step beyond most spectrum sensing work which involves signal detection to estimate "present" or "not present" detections for either a single channel or fixed sized channels or classification which assumes a signal is present. We define the signal recognition task, present the metrics of precision and recall to the RF domain, and review recent machine-learning based approaches to this problem. We introduce a new dataset that is useful for training neural networks to perform these tasks and show a training framework to train wideband signal recognizers.