A new weighted classifier combination method with two-step evidential discounting operations

Xuxia Zhang, Jingfei Duan, Zuowei Zhang, Zhun Ga Liu

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

1 Scopus citations

Abstract

In target recognition, multi-source fusion, such as multiple radar fusion has to be considered to achieve accurate identification. In classification fusion problem, the classifiers are often considered with different weights. DS rule is used for optimizing the classifier weights. The evidence discounting operation with classifier weights can improve the classifier reliability. However, the classification results of different patterns by a common classifier may also have different reliability. Thus, evidence distance and conflict are used to determine the pattern weights. Some real data sets are used to test the proposed method, and results show that the proposed method can efficiently improve the classification accuracy.

Original languageEnglish
Title of host publication2019 International Applied Computational Electromagnetics Society Symposium-China, ACES 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9780996007894
DOIs
StatePublished - Aug 2019
Event2019 International Applied Computational Electromagnetics Society Symposium-China, ACES 2019 - Nanjing, China
Duration: 8 Aug 201911 Aug 2019

Publication series

Name2019 International Applied Computational Electromagnetics Society Symposium-China, ACES 2019

Conference

Conference2019 International Applied Computational Electromagnetics Society Symposium-China, ACES 2019
Country/TerritoryChina
CityNanjing
Period8/08/1911/08/19

Keywords

  • Classifier fusion
  • Conflicting measure
  • Evidence theory
  • Pattern weight

Fingerprint

Dive into the research topics of 'A new weighted classifier combination method with two-step evidential discounting operations'. Together they form a unique fingerprint.

Cite this