Earticle

초록

영어

Similarity search is one of the most studied research fields in data mining. Given a query data point Q, how to find its closest neighbors efficiently and effectively has always been a challenging research topic. In this paper, we discuss continuous research on data analysis based on our previous work on similarity search problems, and present an approach to improving the scalability of the PanKNN algorithm [13]. This proposed approach can assist to improve the performance of existing data analysis technologies, such as data mining approaches in Bioinformatics.

목차

Abstract
 1. Introduction
 2. Related work
 3. Solving similarity problems
 4. A Scalable Approach to Finding the Nearest Neighbors
  4.1. Segment Mergence
  4.2. Example 1
  4.3. Example 2
  4.4. Example 3
  4.5. Finding nearest neighbors with scalability
  4.6. Time and space analysis
 5. Experiments
  5.1. Experiments on high-dimensional data sets
  5.2. Experiments of PanKNN-scalable vs. PanKNN
 6. Conclusion
 References

키워드

저자

• Yong Shi [ Department of Computer Science and Information Systems Kennesaw State University ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Bio-Science and Bio-Technology

• 간기

  격월간

• pISSN

  2233-7849

• 수록기간

  2009~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605