SIMCA 法判别分析木材生物腐朽的研究 - ICBR

2 7 , 4
Vol1 27 ,No1 4 ,pp6862690
2 0 0 7 4 Spectroscopy and Spectral Analysis April , 2007
SIMCA
1 , 1 ,2 3 , 1 , 2
11 , 100091
21 , 100102
, , ,
, , SIMCA
, , SIMCA
, SIMCA ,
PCA SIMCA ,
100 % , 8215 %100 % ; ( ) ,
100 % , 85 %100 % ; SIMCA 100 % ,
,
; SIMCA ; PCA ; ; ;
: O65713 ; S78213 : A : 100020593 (2007) 0420686205
,
, ,
, [1 , 2 ]
, 52
[3 ] ,
,
,
(
) ,
,
[4 , 5 ] ,
,
, ( N IR) SIMCA ( soft independent
modeling of class analog)
[629 ] ,
, , ,
,
[10 ] , N IR
, N IR
, SIMCA
1
111
, ,
, ,
()
140 ,
20 , 60 60
112
ASD ()
Field Spec g 350
: 2006204221 , : 2006208206
: 948 (2006245 ,200324227) (20052M201)
: , 1976 , e2mail : zyang @caf1ac1cn 3

4
687
2 500 nm , ,
DC ,
30 ,
2 cm ,
30
, ASD
,
5002 500 nm SIMCA
113 SIMCA
,
, ,
,
PCA2 SIM2
CA PL S ( PL S , discriminant analysis) ,
SIMCA PL S Unscrambler g
SIMCA
, SIMCA
PCA ,
PCA ,
, ,
,
, , 1 Sam2
ples Gi Gj , Gi
SIMCA ( mahalanobis dis2
tance , MD)
PCA ,
PCA , SIMCA
PCA , 2
4
Fig12 PCA model of the non2decay samples in SIMCA
Fig13 PCA model of the white2rot samples in SIMCA
Fig11 The principle of distance2discrimination analysis
2
211 SIMCA
SIMCA , : (1)
PCA ,
PCA ; (2) PCA
, SIMCA ,
,
, , ,
2/ 3 SIMCA , 1/ 3
Fig14 PCA model of the brown2rot samples in SIMCA
2 , 3 4 Scores ,
,
, ,
; Influence PCA

688
27
, (Leverage) ( Residual)
,
(Outlier)
,
, ,
,
, , 24 ,
,
,
,
212 SIMCA
SIMCA ,
, ,
, Unscrambler g SIMCA
SIMCA
, 57 SIMCA
, ,
, ;
(Sample leverage) ,
, ,
;
= 0105
,
0105) , SIMCA ,
(1715 %) ,
,
SIMCA PCA ,
PCA
,
Fig1 6 The discrimination results of white2decay
samples of training set by SIMCA
Fig17 The discrimination results of brown2decay
samples of training set by SIMCA
Table 1 The discriminant results of wood biological
decay of test set by SIMCA
Training set
( n = 93)
Non2decay
/ %
White2rot
decay/ %
Brown2rot
decay/ %
Fig1 5 The discrimination results of non2decay
samples of training set by SIMCA
N ,W , and B stands for non2decay , white2rot
and brown2rot decay samples , respectively
57 , 7 7
(= 01 05) ,
, 7
,
1 SIMCA
, , SIMCA
, SIMCA
100 % , 8215 % 100 % (=
Disciminant probability
(= 0105)
213 SIMCA
100 8215 100
, 47 810
SIMCA ,
, 8 9 10 SIMCA
(= 0105)
810 , 10 3
(
) , 2
SIMCA , ,
SIMCA , SIMCA

4
689
100 % ,
85 %100 %(= 0105) , SIMCA
, ,
15 %SIMCA
, ,
,
3
SIMCA
Fig1 10 The discrimination results of brown2decay
samples in tset set by SIMCA
Table 2 The discrimination results of wood biological
decay of test set by SIMCA
Test set
( n = 47)
Disciminant probability
(= 0105)
Non2decay
/ %
White2rot
decay/ %
Brown2rot
decay/ %
100 85 100
Fig1 8 The discrimination results of non2decay
samples in tset set by SIMCA
Fig1 9 The discrimination results of white2decay
samples in tset set by SIMCA
SIMCA
,
100 % 8215 %100 % ; (
) , 100 % , 85 %
100 %
, SIMCA
100 % , , ,
,
PCA
,
:
Chung2Yun Hse Dale ,

690
27
[ 1 ] Winandy J E , Morrell J J . Wood and Fiber Science , 1993 , 25 (3) : 278.
[ 2 ] Curling S F , Clausen C A , Winandy J E. Forest Product Journal , 2002 , 52 (7/ 8) : 34.
[ 3 ] Lee H L , Chen G C , Rowell R M. Holzforschung , 2004 , 58 : 311.
[ 4 ] Backa S , Brolin A , Nilsson T. Holzforschung , 2001 , 55 (3) : 225.
[ 5 ] M ller U , Bammer R , Teischinger A. Holzforschung , 2002 , 56 (5) : 529.
[ 6 ] WAN G L I , ZHUO Lin , HE Ying , et al ( , , , ) . Spectroscopy and Spectral Analysis() , 2004 ,
24 (12) : 1537.
[ 7 ] L I Qing2bo , YAN G Li2min , L IN G Xiao2feng , et al (, , , ) . Spectroscopy and Spectral Analysis(
) , 2004 , 24 (4) : 414.
[ 8 ] YAN G Zhong , J IAN G Ze2hui , FEI Ben2hua , et al ( , , , ) . Scientia Silvae Sinicae () , 2005 , 41 (4) : 177.
[ 9 ] J IAN G Ze2hui , FEI Ben2hua , YAN G Zhong (, , ) . Spectroscopy and Spectral Analysis() , 2007 ,
27 (3) : 435.
[ 10 ] YAN G Zhong , J IAN G Ze2hui , FEI Ben2hua ( , , ) . Scientia Silvae Sinicae () , 2006 , 42 (3) : 99.
Discrimination of Wood Biological Decay by Soft Independent Modeling of
Class Analogy ( SIMCA) Pattern Recognition Based on Principal
Component Analysis
YAN G Zhong 1 , J IAN G Ze2hui 1 ,2 3 , FEI Ben2hua 1 , Q IN Dao2chun 2
1. Research Institute of Wood Industry , Chinese Academy of Forestry , Beijing 100091 , China
2. International Center for Bamboo and Rattan , Beijing 100102 , China
Abstract Wood , as a biomass materials , tends to be attacked by microorganisms , and its structure could be rapidly destroyed by
biological decay. Therefore , it s significant to rapidly and accurately detect or identify biological decay in wood. Recently , exten2
sive research has demonstrated that near infrared spectroscopy (N IR) and soft independent modeling of class analogy (SIMCA)
can be used to discriminate or detect a wide variety of food , medicine and agricultural products. The use of N IR coupled with
principal component analysis ( PCA) and SIMCA pattern recognition to detect wood biological decay was investigated in the pres2
ent paper. The results showed that N IR spectroscopy coupled with SIMCA pattern recognition could be used to rapidly detect the
biological decay in wood. The discrimination accuracy by the SIMCA model based on the training set for the non2decay , white2rot
and brown2rot decay samples were 100 % , 8215 % and 100 % , respectively ; and that for the samples for the test set were 100 % ,
85 % and 100 % , respectively. However , some white2rot decay samples were mis2discriminated as brown2rot decay , for which
the main reasons might be that the training set does not have enough typical samples , and there s a slight difference between
white2rot and brown2rot decay during the early stage of decay.
Keywords Near infrared spectroscopy (N IR) ; Soft independent modeling of class analogy (SIMCA) ; Principal component anal2
ysis ( PCA) ; Wood ; Biological decay ; Discrimination
(Received Apr. 21 , 2006 ; accepted Aug. 6 , 2006)
3 Corresponding author