Artificial Intelligence for Automatic Classification of Unintentional Electromagnetic Interference in Air Traffic Control Communications

Abstract

The rapidly increase of wireless systems in safety- and security applications calls for more automatic monitoring of electromagnetic interference in the vicinity of critical applications. For efficiency reasons, such automatic monitoring techniques need to be complemented with methods for automatic analyses and classification of the collected interference data. In this paper, we show the possibility of using artificial intelligence (AI) in the form of machine learning (ML) to automatically identify and classify interference signals out of the total measured electromagnetic environment. We exemplify how a k-nearest neighbors (k-NN) algorithm could be used to automatically identify and classify different kinds of interference signals from intended transmitters in air-traffic control communications. The results are also an example of the potential of using AI-methods in Electromagnetic Compatibility (EMC) applications.