Comparative study of distance functions for nearest neighbors

Walters-Williams, Janett and Li, Yan (2010) Comparative study of distance functions for nearest neighbors. In: Advanced techniques in computing sciences and software engineering. Springer Science+Business Media, Dordrecht, Netherlands, pp. 79-84. ISBN 978-90-481-3659-9


Many learning algorithms rely on distance metrics to receive their input data. Research has shown that these metrics can improve the performance of these algorithms. Over the years an often popular function is the Euclidean function. In this paper, we investigate a number of different metrics proposed by different communities, including Mahalanobis, Euclidean, Kullback-Leibler and Hamming distance. Overall, the best-performing method is the Mahalanobis distance metric.

Statistics for USQ ePrint 19996
Statistics for this ePrint Item
Item Type: Book Chapter (Commonwealth Reporting Category B)
Refereed: Yes
Item Status: Live Archive
Additional Information: Chapter 14. Permanent restrcited access to published version due to publisher copyright policy. Advanced Techniques in Computing Sciences and Software Engineering includes selected papers form the conference proceedings of the International Conference on Systems, Computing Sciences and Software Engineering (SCSS 2008) which was part of the International Joint Conferences on Computer, Information and Systems Sciences and Engineering (CISSE 2008).
Faculty / Department / School: Historic - Faculty of Sciences - Department of Maths and Computing
Date Deposited: 09 Nov 2011 06:43
Last Modified: 20 Oct 2014 04:48
Uncontrolled Keywords: Kullback-Leibler distance, Euclidean distance, Mahalanobis distance, Manhattan distance, Hamming distance, Minkowski distance, nearest neighbor
Fields of Research : 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
09 Engineering > 0906 Electrical and Electronic Engineering > 090609 Signal Processing
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970110 Expanding Knowledge in Technology
Identification Number or DOI: 10.1007/978-90-481-3660-5_14

Actions (login required)

View Item Archive Repository Staff Only