Rozproszone Wykrywanie Zaj\k{e}to\'sci Widma Oparte na Uczeniu Federacyjnym

TL;DR

This paper introduces a federated learning approach for spectrum occupancy detection that enables sensors to detect signals like DVB-T without needing access to labeled training data, demonstrated through hardware experiments.

Contribution

The paper proposes a novel distributed federated learning method for spectrum detection, addressing data access limitations in sensors without labeled data.

Findings

FL effectively detects DVB-T signals in hardware experiments

Federated approach reduces need for labeled training data

Improves spectrum sensing in distributed sensor networks

Abstract

Spectrum occupancy detection is a key enabler for dynamic spectrum access, where machine learning algorithms are successfully utilized for detection improvement. However, the main challenge is limited access to labeled data about users transmission presence needed in supervised learning models. We present a distributed federated learning approach that addresses this challenge for sensors without access to learning data. The paper discusses the results of the conducted hardware experiment, where FL has been applied for DVB-T signal detection.