DSpace
 

Researchspace >
General science, engineering & technology >
General science, engineering & technology >
General science, engineering & technology >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10204/6399

Title: Combining binary classifiers to improve tree species discrimination at leaf level
Authors: Dastile, X
Jäger, G
Debba, P
Cho, M
Keywords: Error Correcting Output Codes
ECOC
Neural Networks
K-nearest Neighbour
Hyperspectral Data
Binary Classifiers
Issue Date: Nov-2012
Citation: Dastile, X, Jäger, G, Debba, P and Cho, M. Combining binary classifiers to improve tree species discrimination at leaf level. Conference Proceedings of the 54th Annual Conference of the South African Statistical Association, Port Elizabeth, 5-9 November 2012
Series/Report no.: Workflow;9886
Abstract: This paper focuses on the discrimination of seven different savannah tree species at leaf level using hyperspectral data. The data is small in size, high-dimensional and shows large within-species variability combined with small between species variability which makes discrimination between the tree species (hereafter referred to as classes) challenging. We focus on two classification methods: K-nearest neighbour and feed-forward neural networks for the discrimination of the classes. For both methods, direct 7-class prediction results in high misclassification rates. We therefore construct binary classifiers for all possible binary classification problems and combine them using Error Correcting Output Codes (ECOC) to form a 7-class predictor. ECOC with 1-nearest neighbour binary classifiers result in no improvement compared to a 1-nearest neighbour 7-class predictor whereas ECOC with neural networks binary classifiers improve accuracy by 10% compared to neural networks 7-class predictor, and error rates become acceptable.
Description: Conference Proceedings of the 54th Annual Conference of the South African Statistical Association, Port Elizabeth, 5-9 November 2012
URI: http://www.sasa2012.co.za/
http://hdl.handle.net/10204/6399
Appears in Collections:Sensor science and technology
Logistics and quantitative methods
Advanced mathematical modelling and simulation
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Debba1_2012.pdf376.32 kBAdobe PDFView/Open
View Statistics

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback