A hierarchical classification approach based on the K nearest neighbour algorithm is proposed for effective discrimination of bamboo species. The use of generalised least squares weighting pre-processing proved essential to achieve optimum discriminant accuracy and allowed near infrared spectra of both leaves and stem to be merged and used together. This work can have significant implications for the conservation of Giant Pandas.
LiG.Y.HuangA.M.WangG.QinD.C. and JiangZ.H., “Rapid determination of Klason lignin content in bamboo by NIR”, Guang pu xue yu guang pu fen xi= Guang pu, 27.10, 1977–1980 (2007).
3.
PingZ.HaifenYQianHe Q.Y. and XiaowenL., “Rapid assessment of bamboo quality for giant pandas using near infrared reflectance spectroscopy”, Modern Scientific Instruments3, 22 (2007).
4.
WiedowerE.HansenR.BissellH.OuelletteR.KoubaA.StuthJ.RudeB. and TollesonD., “Use of near infrared spectroscopy to discriminate between and predict the nutrient composition of different species and parts of bamboo: Application for studying giant panda foraging ecology”, J. Near Infrared Spectrosc.17, 265 (2009). doi: https://dx-doi-org.web.bisu.edu.cn/10.1255/jnirs.848
WiseB.M.GallagherN.B.BroR.ShaverJ.M.WindigW. and KochR.S., PLS Toolbox for use with MATLAB. Eigenvector Research, Washington, DC, USA (2006).
7.
WiseB.M.MartensH.BroR. and HøyM., Calibration Transfer by Generalized Least Squares. Available at http://www.eigenvector.com/Docs/ (accessed August 2015).
DotlichM.KattnerR.M.RoginskiR. and ShaverJ.M., “Enhanced classification of placebo and active formulations via hierarchical modelling,”Amer. Pharmaceut. Rev.16, 7 (2013).
