Skip to main navigation Skip to search Skip to main content

Active learning for kNN based on bagging features

  • Shi Shuo*
  • , Liu Yuhai
  • , Huang Yuehua
  • , Zhu Shihua
  • , Liu Yong
  • *Corresponding author for this work
  • Ocean University of China
  • Nokia
  • Yuxi Hongta Tobacco Group Co., Ltd.
  • Qingdao University

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

Abstract

Ensemble methods that train multiple learners and then combine their predictions have been shown to be very effective in supervised learning. But bagging is not work very well in some case, such as k-Nearest Neighbor (kNN). At the same time, Query Learning Strategies using Bagging [1] is also not work very well. From features view, we introduce bagging features active learning (ALBF) for kNN and apply this method to ML-kNN. Experiments in UCI data set show that prediction accuracy could be significantly improved by ALBF.

Original languageEnglish
Title of host publicationProceedings - 4th International Conference on Natural Computation, ICNC 2008
Pages61-64
Number of pages4
DOIs
StatePublished - 2008
Externally publishedYes
Event4th International Conference on Natural Computation, ICNC 2008 - Jinan, China
Duration: 18 Oct 200820 Oct 2008

Publication series

NameProceedings - 4th International Conference on Natural Computation, ICNC 2008
Volume7

Conference

Conference4th International Conference on Natural Computation, ICNC 2008
Country/TerritoryChina
CityJinan
Period18/10/0820/10/08

Fingerprint

Dive into the research topics of 'Active learning for kNN based on bagging features'. Together they form a unique fingerprint.

Cite this