ML aided context feature extraction for cognitive radio
Computer Networks: The International Journal of Computer and Telecommunications Networking
| Hi-index | 0.00 |
Cognitive radio is a new paradigm for wireless communications offering a solution to conciliate the current spectrum demand growth and underutilization without changes to the existing legacy wireless systems. Secondary users should be able to identify spatial and temporal spectrum holes not occupied by primary users and use them opportunistically, without generating interference to primary receivers. For that purpose, having knowledge of the primary network is required to ensure an appropriate secondary user operation. In this context, and assuming there is no cooperation between primary and secondary networks, this paper proposes a new framework, based on image processing techniques, aimed at combining a number of sensed samples at different geographical positions collected by secondary sensors, in order to estimate the positions of the different primary transmitters. The results can be used to discover frequencies that can be used by a secondary network without disturbing primary receivers. Our results, performed in a realistic scenario, show the efficacy of the proposed framework in estimating transmitter positions.