• About SAF
• Join
• Renew
• Login
• Profile
• Contact Us
• SAF Store

• Certification
• Convention
• Education
• Career Center
• Publications
• Working Groups
• Online Communities
• Event Calendar

Authors: Finley, Andrew O.¹; McRoberts, Ronald E.¹; Ek, Alan R.¹

Source: Forest Science, Volume 52, Number 2, April 2006 , pp. 130-135(6)

Abstract:

This article explores the utility of an efficient nearest neighbor (NN) search algorithm for applications in multisource kNN forest attribute imputation. The search algorithm reduces the number of distance calculations between a given target vector and each reference vector, thereby decreasing the time needed to discover the NN subset. Results of five trials show gains in NN search efficiency ranging from 75 to 98% for k = 1. The search algorithm can be easily incorporated into routines that optimize feature subsets or weights, values of k, distance decomposition coefficients, and mapping.

Keywords: k-nearest neighbor; mapping; remote sensing; multisource

Document Type: Research article

Affiliations: 1: Andrew O. Finley, Department of Forest Resources, University of Minnesota, 115 Green Hall, 1530 Cleveland Ave. North, St. Paul, MN 55108—Phone: (612) 624-1714; Ronald E. McRoberts, Forest Inventory and Analysis, North Central Research Station, USDA Forest Service, 1992 Folwell Ave., St. Paul, MN 55108. Alan R. Ek, Department of Forest Resources, University of Minnesota, 115 Green Hall, 1530 Cleveland Ave. North, St. Paul, MN 55108, Email: afinley@gis.umn.edu.