Design for fast adaboost with feature selection

Xiao Long Liang, Wei Hua Li, Xin Lin

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

1 Scopus citations

Abstract

Since the original Adaboost algorithm is very time-consuming in training, we have designed an improved Adaboost, which adds a process of feature selection to the original Adaboost algorithm. After each round of training, we retain the features whose error rate to classify the samples are relatively low and remove the features with high error rate. In this way the time for the next training is reduced, and the whole algorithm is accelerated.

Original languageEnglish
Title of host publicationManufacturing Science and Technology (ICMST2013)
Pages566-569
Number of pages4
DOIs
StatePublished - 2013
Event4th International Conference on Manufacturing Science and Technology, ICMST 2013 - Dubai, United Arab Emirates
Duration: 3 Aug 20134 Aug 2013

Publication series

NameAdvanced Materials Research
Volume816-817
ISSN (Print)1022-6680

Conference

Conference4th International Conference on Manufacturing Science and Technology, ICMST 2013
Country/TerritoryUnited Arab Emirates
CityDubai
Period3/08/134/08/13

Keywords

  • Adaboost
  • Feature selection
  • Machine learning

Fingerprint

Dive into the research topics of 'Design for fast adaboost with feature selection'. Together they form a unique fingerprint.

Cite this