Statistical Feature-Based SVM Wideband Sensing

Poor accuracy at low SNR makes fast autonomous wideband sensing in real-time difficult for cognitive radios. Support Vector Machines (SVM) can be an alternative in learning this sensing environment. But online training with conventional Eigen features has high complexity. This letter develops and va...

Full description

Saved in:
Bibliographic Details
Published in:IEEE communications letters 2020-03, Vol.24 (3), p.581-584
Main Authors: Varma, Ashwini Kumar, Mitra, Debjani
Format: Article
Language:English
Subjects:
Broadband
Cognitive radio
Correlation
Detection
eigen feature
Feature extraction
Learning
low SNR
Sensors
Signal to noise ratio
Support vector machines
SVM
Training
Wideband
wideband sensing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Poor accuracy at low SNR makes fast autonomous wideband sensing in real-time difficult for cognitive radios. Support Vector Machines (SVM) can be an alternative in learning this sensing environment. But online training with conventional Eigen features has high complexity. This letter develops and validates on real-world data an efficient quick learning SVM-based blind sensing model using two new simple statistical features that can accurately detect signals at low SNR. Named as Smoothed Correlation of Reversed Spectrum Segments (SCRSS) and Variance of Multi-Scale Moving Averages (VMMA), they can speed up sensing to almost five times that of Eigen learning. With reduced computational cost, they appear to be promising in next-generation intelligent cognitive radio networks.
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2019.2959355