Analysis of Spectrum Occupancy Using Machine Learning Algorithms

TL;DR

This paper compares various machine learning algorithms for spectrum occupancy analysis, identifying SVM as the most effective, and introduces an improved SVM method using the fire fly algorithm for better performance.

Contribution

The paper provides a comprehensive comparison of supervised and unsupervised ML techniques for spectrum analysis and proposes a novel SVM-FFA hybrid algorithm that outperforms existing methods.

Findings

SVM achieves the highest classification accuracy among tested algorithms.

The hybrid SVM-FFA algorithm outperforms standard classifiers in accuracy.

Numerical results support the effectiveness of the proposed hybrid approach.

Abstract

In this paper, we analyze the spectrum occupancy using different machine learning techniques. Both supervised techniques (naive Bayesian classifier (NBC), decision trees (DT), support vector machine (SVM), linear regression (LR)) and unsupervised algorithm (hidden markov model (HMM)) are studied to find the best technique with the highest classification accuracy (CA). A detailed comparison of the supervised and unsupervised algorithms in terms of the computational time and classification accuracy is performed. The classified occupancy status is further utilized to evaluate the probability of secondary user outage for the future time slots, which can be used by system designers to define spectrum allocation and spectrum sharing policies. Numerical results show that SVM is the best algorithm among all the supervised and unsupervised classifiers. Based on this, we proposed a new SVM algorithm by combining it with fire fly algorithm (FFA), which is shown to outperform all other algorithms.