You can view the full text of this article for free using the link below.

Title: Analysis of unsupervised primary-secondary user recognition using DTW and DFW in cognitive radio networks

Authors: Stephen G. Miller; Paul M. Kump

Addresses: ArrowSlate, White Plains, NY, 10603, USA ' ArrowSlate, White Plains, NY, 10603, USA; SUNY Maritime College, Bronx, NY, 10465, USA

Abstract: Primary user (PU) and secondary users (SU) identification is critical to tiered spectrum sharing algorithms in cognitive radio (CR) networks. This paper focuses on a methodology to improve PU and SU identification using unsupervised classical learning methods. An experimental approach is studied using dynamic time warping (DTW) and dynamic frequency warping (DFW), which is DTW applied to the frequency domain. Principal component analysis (PCA) is used as a lightweight autoencoder. This work's focus is to minimise the need for extensive training data and class labelling for efficient cognitive node deployment. A variety of different modulations are explored including quadrature amplitude modulation (QAM), phase shift keying (PSK), pulse amplitude modulation (PAM), frequency shift keying (FSK), amplitude modulation (AM), and frequency modulation (FM).

Keywords: cognitive radio; DTW; dynamic time warping; DFW; dynamic frequency warping; machine learning; primary-secondary user detection.

DOI: 10.1504/IJMNDI.2023.133244

International Journal of Mobile Network Design and Innovation, 2023 Vol.10 No.4, pp.233 - 239

Received: 23 May 2023
Accepted: 09 Jun 2023

Published online: 03 Sep 2023 *

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