Title: Cooperative spectrum sensing based on locally linear embedding and Adaboost in dynamic fading channel

Authors: Yanhui Wang; Dongliang Bian; Jun Pan

Addresses: Department of Computer Information Engineering, Baoding Vocational and Technical College, Hebei, Baoding, 071051,China ' Department of Computer Information Engineering, Baoding Vocational and Technical College, Hebei, Baoding, 071051,China ' Department of Computer Information Engineering, Baoding Vocational and Technical College, Hebei, Baoding, 071051,China

Abstract: In mountainous areas and dense forests, the performance of spectrum sensing is largely degraded due to factors such as shadow fading and noise uncertainty, which results in serious consequences of wasting spectrum resources. To overcome these problems, a novel cooperative spectrum sensing method based on local linear embedding (LLE) and Adaboost is proposed. This method addresses the characteristics of dynamically fading channels and does not rely on any a priori information. Firstly, cognitive radio (CR) users with excellent performance are selected to participate in spectrum sensing, while later important information components of nonlinear data in the received signal are obtained through LLE, and finally the excellent classification performance of Adaboost is used to achieve accurate sensing of the main user signal. Comparative experiments are conducted in a low SNR environment; the proposed algorithm can effectively obtain the received signal feature information and accurately achieve spectrum sensing.

Keywords: cooperative spectrum sensing; CR user selection; local linear embedding; LLE; Adaboost.

DOI: 10.1504/IJMIC.2024.135537

International Journal of Modelling, Identification and Control, 2024 Vol.44 No.1, pp.41 - 48

Received: 30 Jun 2022
Received in revised form: 01 Sep 2022
Accepted: 20 Sep 2022
Published online: 18 Dec 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article