New approaches in clustering methodsfor communication systems

With the development of wireless technology in today's communication systems, it has brought the problem of spectrum scarcity. The reason for this problem can be shown as the use of spectrum only by licensed users. The use of the available spectrum by certain users prevents the efficient and effective use of a scarce resource. At this stage, the concept of cognitive radio, which allows the opportunistic use of the spectrum, emerges. Cognitive radio is a technology that can intelligently detect an empty spectrum and allocate the spectrum to secondary users without interfering with licensed users. In this study, eigenvalue-based spectrum detection was preferred as the spectrum detection method. The eigenvalue-based spectrum detection method is widely used because there is no need for prior knowledge about the signal and noise to be detected. The covariance matrix obtained by this method was compared to the ratio of the maximum eigenvalue and the minimum eigenvalue with a threshold and the presence of the signal was investigated. Cognitive radio users were divided into groups using k-means, which is a clustering method. The aim here is to accelerate the spectrum perception of cognitive radio users grouped with k-means.