The K-Maximum Subarray algorithm as an alternative clustering analysis for the spatial weed aggregation pattern
Type of content
Conference Contributions - Other
UC permalink
Publisher's DOI/URI
Thesis discipline
Degree name
Publisher
University of Canterbury. Computer Science and Software Engineering
University of Canterbury. Geography
University of Canterbury. Mathematics and Statistics
University of Canterbury. Geography
University of Canterbury. Mathematics and Statistics
Journal Title
Journal ISSN
Volume Title
Language
Date
2008
Authors
Fukuda, K.
Brown, J.A.
Williams, P.
Kean, J.
Abstract
Weed invasions can alter the nature of the environment, the surrounding ecosystem and human activities, and it will cost us to manage and control them. This study introduces the K-Maximum Subarray Algorithm to investigate the spatial distribution patterns of hawthorn, grown over 100 years in Porters Pass. The K-Maximum subarray algorithm (K-MSA) investigates its maximum clustering patterns by identifying K-number of maximum growth patches. Further, the observed and simulated maximum weed growth patchiness were investigated for randomness of the aggregation pattern. Results demonstrated how the weed distribution pattern has changed over four decades, with samples in 1966, 1976, 1986 and 2008.
Description
Citation
Fukuda, K., Brown, J.A., Williams, P., Kean, J. (2008) The K-Maximum Subarray algorithm as an alternative clustering analysis for the spatial weed aggregation pattern. Hamilton, New Zealand: 59th Annual Conference of the New Zealand Statistics Association, 1-2 Sep 2008.