A Wideband Signal Recognition Dataset
| Autor: | Timothy J. O'Shea, Nathan West, Tamoghna Roy |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Signal Processing (eess.SP)
Artificial neural network Computer science business.industry Pattern recognition Signal Domain (software engineering) Task (computing) FOS: Electrical engineering electronic engineering information engineering Segmentation Detection theory Artificial intelligence Electrical Engineering and Systems Science - Signal Processing Precision and recall business Communication channel |
| Zdroj: | SPAWC |
| DOI: | 10.48550/arxiv.2110.00518 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|