Among the most important applications of Deep Learning to engineering are those in wireless communication (WC). WC concerns the processing, communication, and transfer of data performed between two or more devices that are not connected by an electrical conductor.
Considering the constantly increasing volume of devices being deployed, the wireless ecosystem is getting saturated. This poses new challenges to WC, since frequency band allocation needs to move from static to dynamic, in order to try to optimize spectrum occupancy.
There have been several recent works in the literature which use Deep Learning to predict radio frequency spectrum occupancy. In this poster presentation, we will concentrate on the analysis of Deep Learning algorithms for spectrum occupancy prediction in interfering wireless systems, using simulated data.
Future work will address the problem of spectrum occupancy with real-time data from the metropolitan Fort Wayne area.

This is a work done by:
L. Le, J. Asher, N. Hinniger, T. Kelly, P. Klopfenstein, M. Masters, S. Owusu, R. Ruble, W.K. Sellers, A. Yano;
Mentor: Prof. A.M. Selvitella, Co-Mentors: Prof. T. Cooklev and Prof. P. Dragnev

Loading...

Taking too long?

Reload document

| Open in new tab