Skip to main navigation Skip to search Skip to main content

A relevance vector machine based probability prediction method of channel available time

  • Zhenyu Xu
  • , Dezhi Li
  • , Shuo Shi*
  • , Zhenbang Wang
  • , Jin Yao Jiang
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • State Grid Harbin Electric Power Supply Company
  • People’s Liberation Army

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The uncertainty of spectrum resources will seriously affect the prediction results of cognitive radio, and then affect the communication channel allocation and spectrum access. Therefore, it is very important to judge, analyze and estimate the state change of the spectrum resources. This paper introduces the RVM (Relevance Vector Machine) theory and put forward the probability interval prediction method of channel state duration. Based on the traditional machine learning, RVM is integrated with the Bayesian inference framework, and it can give the estimate value of the prediction error and give the prediction interval, which can cover the real value well.

Original languageEnglish
Title of host publicationCommunications, Signal Processing, and Systems - Proceedings of the 2017 International Conference on Communications, Signal Processing, and Systems
EditorsQilian Liang, Min Jia, Jiasong Mu, Wei Wang, Xuhong Feng, Baoju Zhang
PublisherSpringer Verlag
Pages1650-1658
Number of pages9
ISBN (Print)9789811065705
DOIs
StatePublished - 2019
Event6th International Conference on Communications, Signal Processing, and Systems, CSPS 2017 - Harbin, China
Duration: 14 Jul 201716 Jul 2017

Publication series

NameLecture Notes in Electrical Engineering
Volume463
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference6th International Conference on Communications, Signal Processing, and Systems, CSPS 2017
Country/TerritoryChina
CityHarbin
Period14/07/1716/07/17

Fingerprint

Dive into the research topics of 'A relevance vector machine based probability prediction method of channel available time'. Together they form a unique fingerprint.

Cite this