Skip to main navigation Skip to search Skip to main content

Citation-kNN algorithm based on locally-weighting

  • School of Computer Science and Technology, Harbin Institute of Technology

Research output: Contribution to journalArticlepeer-review

Abstract

The Citation-kNN algorithm improves traditional kNN algorithm and can be applied to solve multiinstance learning issue. But its 0-1 decision strategy has some limitations. To overcome this issue, the locally-weighted Citation-kNN algorithm is presented in this paper. Considering distribution of the samples, the distance-based weighted method and the scatter-based weighted method are proposed. And their combinations are discussed. The method is applied to the standard database MUSK and the breast ultrasound image database. The results confirm that the method has higher accuracy comparing with that by using Citation-kNN algorithm.

Original languageEnglish
Pages (from-to)627-632
Number of pages6
JournalDianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology
Volume35
Issue number3
DOIs
StatePublished - Mar 2013
Externally publishedYes

Keywords

  • Citation-kNN
  • Distribution of samples
  • Image recognition
  • Locally weighted
  • Multi-Instance Learning (MIL)

Fingerprint

Dive into the research topics of 'Citation-kNN algorithm based on locally-weighting'. Together they form a unique fingerprint.

Cite this