Project Description

This research project focuses on the development of an automatic classification system for radio transmissions based on software defined radio (SDR) and machine learning.

The ability to quickly and accurately identify primary users and other participants is essential, especially for cognitive radio (CR) applications in which several participants use a radio band autonomously. Precise classification enables CR participants to make optimum use of their radio band without interfering with the transmissions of others.

In addition, an automatic classification system is also important for monitoring compliance with the frequency plan. In view of the large number of signals, manual identification and classification is not practicable for economic reasons. Such a system can support the Federal Network Agency (BNetzA) or organisations such as the Intruder Monitoring of the German Amateur Radio Club (DARC) in identifying band intruders.