Interference identification based on long term spectrum monitoring and cluster analysis
Ilia G. Iliev, Boncho Gueorguiev Bonev, Kliment N. Angelov, Peter Zhelev Petkov, Vladimir K. Poulkov · 2016
In this paper we propose an approach for interference recognition and frequency channel identification based on the analysis of the large amount of data obtained from long term spectrum monitoring. We illustrate the approach with an example of the detection of a specific type of interference in the uplink of a 3G network caused by the effect “ducting”. Further, using Hjorth parameters for the creation of a set of robust feature descriptor, we show how the dimensionality of the space of the primary parameter data could be reduced and apply it to cluster analysis for interference and channel identification.