Identification of Blueberry Beverage Using Vis/NIR Spectroscopy

Abstract

Four kinds of blueberry beverage from different varieties, a total of 140 samples were acquired and analyzed by applying of spectrum technology. Using Savitzky-Golay spectral smoothing and multiplicative scatter correction (MSC) on the sample data pretreatment, four varieties of blueberry beverage were cluster analyzed by using principal component analysis method (PCA),a three-dimensional score view was achieved by the first 3 principal components of all samples (PC1, PC2 and PC3), which shows an obvious classification effect on the blueberry beverage. The first three principal components of the load diagram analysis, the characteristic bands related with the blueberry beverage varieties were 420-430nm, 490-500nm, 570-580nm and 1350-1365nm. According to the cumulative contribution rate (99.20%) of the first 6 principal components, the first 6 principal components was choosed as the input of multilayer perceptron (MLP) neural network, 100 samples in all the blueberry beverage samples were selected as a training set, and the remaining 40 samples were used as the prediction set. Training set were trained and prediction set were predicted by applying the multilayer perceptron neural network, and the correct rate of prediction were 100%.Research shows, using principal component analysis combined with multilayer perceptron neural network to identify the varieties of blueberry beverage is feasible.

Full text

* Corresponding author: wgfsara@126.com
Identification of Blueberry Beverage Using Vis/NIR Spectroscopy
Dongze Li, Guifang Wu*, Hai Ma, Zhao Liu, Guiquan Liu, and Junhua Hou
College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot, China
Abstract. Four kinds of blueberry beverage from different varieties, a total of 140 samples were acquired
and analyzed by applying of spectrum technology. Using Savitzky-Golay spectral smoothing and
multiplicative scatter correction (MSC) on the sample data pretreatment, four varieties of blueberry
beverage were cluster analyzed by using principal component analysis method (PCA),a three-dimensional
score view was achieved by the first 3 principal components of all samples (PC1, PC2 and PC3), which
shows an obvious classification effect on the blueberry beverage. The first three principal components of the
load diagram analysis, the characteristic bands related with the blueberry beverage varieties were 420-
430nm, 490-500nm, 570-580nm and 1350-1365nm. According to the cumulative contribution rate (99.20%)
of the first 6 principal components, the first 6 principal components was choosed as the input of multilayer
perceptron (MLP) neural network, 100 samples in all the blueberry beverage samples were selected as a
training set, and the remaining 40 samples were used as the prediction set. Training set were trained and
prediction set were predicted by applying the multilayer perceptron neural network, and the correct rate of
prediction were 100%.Research shows, using principal component analysis combined with multilayer
perceptron neural network to identify the varieties of blueberry beverage is feasible.
Key words: Blueberry beverage, Vis/NIR spectroscopy, PCA, MLP neural network
1 Introduction
Blueberry, also known as bilberry, is called the King of
Berries because of their special texture, sweet-tart taste,
and a nutrious abundance in VC[1-2].The earliest
cultivation of blueberries took place in North America,
but that happened less than a hundred years ago[3]. In
China, the cultivation area of blueberries is mainly in
Greater Khingan Mountains, Lesser Khingan Mountains,
which are in northeast of China, and Shandong Peninsula.
In Zhejiang, Hubei and Sichuan Basin and other areas
also have a small amount of cultivation. With an
abundance in vitamin, Superoxide Dismutase (SOD),
arbutin and flavonoids compounds, blueberries are
antioxidant food. It not only works in erythropsine
synthesis, vision improvement, immune enhancement
and cardiac strengthen[4], but also helpful in medical
efforts against aging, ulceration, inflammation and
cardiovascular diseases[5].Wild blueberries contain many
great substances such as folic acid and ursolic acid that
are good for hypertension treatment, and anthocyanin
that is capable of preventing and curing inflammation[6-7].
Blueberries are also natural anti-cancer fruit because of
the existence of many active constituents that inhibit the
activity of cancer cell growth and even accelerate their
apoptosis[8]. For Healthy adults, a moderate drinking of
blueberry beverage everyday could not only reduce the
memory of the recession, but also can improve the
body's ability to resist oxidative stress, while reducing
the loss of lymphocyte DNA[9].
Blueberry beverage is mainly made from blueberries,
which gains much popularity among people. However,
blueberry beverage in market is various and the
identifications of blueberry beverage varieties are also
complex and diverse[10]. To better develop blueberry
beverage, it’s vital and necessary to find a fast and
effective way among these complex and diverse
identifications
Visible/near infrared spectroscopy is a spectroscopic
method that bases on different results of the absorption
of electromagnetic waves against different substances,
which is typically applied in the field of chemistry,
medical, agriculture and detection of agricultural
products[11-12]. And if NIR Spectroscopy is applied in the
identification of blueberry beverage, there will be many
advantages such as fast speed, high efficiency, no
damage, high stability and accuracy[13-14].
Principal Component Analysis (PCA), can
effectively find the most important elements and
structure among a large number of data. It can also
remove the noise and redundancy to deal with the
original complex data for dimension reduction
processing so that the simple structure inside the
complex data can be extracted. That is, without affecting
the main spectral information, many original variables
can be replaced with few variables. As one of neural
network[15-16]. Multilayer Perceptron (MLP) neural
network, which is widely used in pattern recognition
MATEC Web of Conferences 139, 00050 (2017) DOI: 10.1051/matecconf/201713900050
ICMITE 2017
© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution
License 4.0 (http://creativecommons.org/licenses/by/4.0/).

with good distribution ability, can solve the complex
classification problem of pattern distribution[17-18].
In this study visible/ near infrared spectroscopy
(NIRS) and principal Component Analysis (PCA) with
Multilayer Perceptron (MLP), as a new way for
blueberry beverage identification, are used to analyze
different kinds of blueberry beverage.
2 Materials and Methods Network
2.1 Instrument and Equipment
American ASD (Analytical Spectral Device) company
Quality Spec spectrometer, its probe field of view angle
is 25 degrees, the resolution is 3.5nm, spectral range of
350 ~ 1830nm, which sampling interval are 1.4nm @
350 ~ 1000nm, 2nm @ 1000 ~ 1830nm, spectral
resolution are 3nm @ 700nm, 10nm @ 1400nm.
Analysis software is ASD View Spec Pro 6.0,
Unscrambler 9.7, SPSS19.0.
2.2 Sample Source and Spectral Scan
A total of 35 blueberry beverages of four varieties of
Genhe blueberry juice, Ye Laoda, Ye Shanpo and Wild
blueberry were collected randomly, samples were
collected before the blueberry beverages were shaken
well and 140 samples were prepared. The spectral
scanning adopts transmission method with an optical
path of 2 mm, each sample was scanned 30 times and
three spectral curves were preserved, the average
spectrum of the three spectral curves was used as the
final transmission spectrum.
2.3 Preprocessing of spectral data
In order to reduce or eliminate the effects of noise,
baseline drift and sample nonuniformity during spectral
scanning, the original spectrum needs to be
mathematically transformed to improve the accuracy and
stability of the estimation model.
2.3.1 Smooth method
Savitzky-Golay convolution smoothing is an
improvement on moving smoothing by multiplying the
measured value by the smoothing factor to reduce the
effect of smoothing on useful information and then
fitting of the least squares method. The concrete formula
is:
,
1
w
ks k k i i
iw
x x xh
H



 

(1)
In formula (1),
i
h
represent the smoothing factor,
H
represent the normalization factor.
2.3.2 Multiplicative scatter correction
When calculating the multiplicative scatter correction
(MSC) for the acquired spectrum, the average spectrum
is used instead of the "ideal" spectrum to the least
squares method fit of each spectrum and the average
spectrum so that the average spectrum can as much as
possible becomes as linear relationship. The concrete
formula is:
2.3.2.1 Calculate the average (ideal) spectrum of
the sample
1
n
i
i
X
Xn



(2)
2.3.2.2 Perform linear regression and the
regression coefficients
i
a
and regression constants
i
b
were obtained by least squares method
ii i
X aX b 
(3)
2.3.2.3 Correct each spectrum
,
ii
iM
i
Xb
Xa


(4)
In formula(2)(3)(4),
i
X
represent the sample
spectrum,
n
represent the number of samples,
X
represent the average spectrum,
i
a
represent the
regression coefficients,
i
b
represent the regression
constants,
,iM
X
represent the corrected spectrum.
2.3.3 Preprocessed spectra
In the Unscrambler 9.7 software, Savitzky-Golay
smoothing is used, the smoothing point is 9, and the
multiple scattering correction (MSC) is used to
preprocess the sample. The processing effect is the best.
In order to remove the noise effects of the first and the
end of the spectral curve, use the spectrum of the band
400 ~ 1800 nm[19-21]. The spectral curves of the four
blueberry beverages were obtained after pretreatment.
As shown in Fig. 1, the spectral lines of one sample were
arbitrarily selected in each blueberry beverage
sample.Taking the abscissa as the wavelength of the
spectrum and the ordinate as the absorbance of each
sample.
MATEC Web of Conferences 139, 00050 (2017) DOI: 10.1051/matecconf/201713900050
ICMITE 2017
2

400 600 800 1000 1200 1400 1600 1800
0.25
0.50
0.75
1.00
1.25
1.50
1.75
2.00
2.25
Absorbance/log(1/R)
Wavelength/nm
Genhe Blueberry Juice
Ye Laoda
Ye Shanpo
Wild Blueberry
Fig. 1. Spectral curve four varieties of blueberry beverage.
2.4 Principal component analysis
A total of 140 samples were cluster analyzed by using
principal component analysis method of four blueberry
beverages, blueberry juice, Ye Laoda, Ye Shanpo and
Wild blueberry. As shown in Fig.2, in which the X, Y
and Z axes respectively represent the scores of the first
principal component (PC1), the second principal
component (PC2) and the third principal component
(PC3).The four kinds of blueberry beverages in Fig.2
were divided into four categories, indicating that PC1,
PC2 and PC3 have very good clustering effect on four
kinds of blueberry beverages also can qualitatively
characterize the characteristics of the four blueberry
beverages. But the edge sample distinction of Genhe
blueberry juice, Ye Laoda and Ye Shanpo are not
obvious.In order to improve the prediction accuracy,
using principal component analysis combined with
multilayer perceptron neural network to establish
detection and analysis model of four kinds of blueberry
beverage.
-4 -3 -2 -1 0123
-1
0
1
2
-6
-4
-2
0
2
4
Genhe Blueberry Juice
Ye Laoda
Ye Shanpo
Wild Blueberry
PC3
PC2
PC1
Fig. 2. Blueberry beverage principal component cluster
diagram.
3 Test Results and Analysis
3.1 Characteristic bands selected
According to the principal component 1, 2, 3 in the
entire wavelength range of the load value shown in Fig.
3.Taking abscissa as the wavelength of 400 ~ 1800nm,
the ordinate as the load of different principal components
in each wavelength variable values. The correlation
between the principal component and the absorbance of
the blueberry beverage at each wavelength. From Figure
3 can be obtained that range in 420 ~ 430nm, 490 ~
500nm, 570 ~ 580nm and 1350 ~ 1365nm have
maximum correlation with principal component. The
main component 4-20 has maximum correlation with the
absorbance of these four blueberry beverage’s bands.
Therefore, the four wavelength bands were selected as
the characteristic bands of near infrared spectrum of the
blueberry beverage over the entire wavelength range.
400 600 800 1000 1200 1400 1600 1800
-0.06
-0.04
-0.02
0.00
0.02
0.04
0.06
0.08
0.10
X-Loading
Wavelength/nm
PC1
PC2
PC3
Fig. 3. The load of the principal component values.
3.2 Principal component analysis results
The cumulative contribution rate of the first six principal
components has reached 99.204% by the principal
component analysis method. As shown in Table 1,the
spectral data of 140 samples were replaced by the first
six principal components. All the samples were analyzed
by the first six principal components.
Table 1. The cumulative contribution rate of the principal
component.
3.3 Identification of blueberry beverage based
on multilayer perceptron neural network
Principal
Component
PC1 PC2 PC3 PC4 PC5 PC6
Cumulative
Contribution
Rate
53.65
%
91.16
%
95.67
%
97.83
%
98.64
%
99.20
%
MATEC Web of Conferences 139, 00050 (2017) DOI: 10.1051/matecconf/201713900050
ICMITE 2017
3

The first six principal components obtained by principal
component analysis are used as inputs to the multilayer
perceptron (MLP) neural network. The three-layer
network structure is chosen as the best training structure,
and its structure is 6 nodes, the hidden layer is 5 nodes
and the output layer is 4 nodes, with hyperbolic tangent
as the activation function of the hidden layer, softmax as
the activation function of the output layer. A total of 100
blueberry beverage samples were used as training set for
training. The remaining 40 blueberry beverage samples
were used as test set. The results show that, as shown in
Table 2 ("1" is Genhe blueberry juice, "2" is Ye Laoda,
"3" is Ye Shanpo, "4" is Wild blueberry) accuracy of
four kinds of blueberry beverage classification has
reached 100%.
Table 2. Blueberry beverage classification prediction accuracy.
Blueberry
Beverage
Varieties
1 2 3 4 Accuracy
Rate
1 10 0 0 0 100%
2
0
10
0
0
100%
3
0
0
10
0
100%
4
0
0
0
10
100%
4 Conclusion
Based on the combination of principal component
analysis and multilayer perceptron(MLP) neural network,
the model of blueberry beverage brand identification was
established, and the accuracy of classification prediction
was 100%.This fully illustrates the use of near infrared
spectroscopy technology can quickly and accurately
identify blueberry beverage varieties. This method of
principal component analysis combined with multilayer
perceptron (MLP) neural network is use the principal
component as the input of multilayer perceptron(MLP)
neural network, which can reduce the calculation of
neural network, accelerate the training of the sample and
eliminate the spectral signal interference, greatly
improving the accuracy of the forecast. At the same time,
the characteristic bands of the blueberry beverage brand
are 420 ~ 430nm, 490 ~ 500nm, 570 ~ 580nm and 1350
~ 1365nm., which are closely related to the beverage
brands of Blueberry. Therefore, it is feasible to use the
principal component analysis and the multi-layer
perceptron neural network to identify the varieties of
blueberry beverages. It also opens up a good prospect for
the future development of blueberry beverage testing
equipments.
Acknowledgment
This work was supported by National Natural Science
Foundation of China (6126511); Higher School Doctoral
Discipline Special Research Fund (20111515120004);
Inner Mongolia Natural Science Foundation of China
(2102MS0915); Inner Mongolia Agricultural University
doctoral research start fund (BJ09-18).
References
1. A. Han Zhang. Wild blueberry health care value.
Heilongjiang STI. 13, 87 (2013)
2. K. Kim Mina, Han Sub Kwak. Influence of
functional information on consumer liking and
consumer perception for blueberry functional
beverages. IJFST. 50, 70-76 (2013)
3. Shiow Y. Wang, Hangjun Chen, J CAMP MARY,
et al. Genotype and heavy season influence
blueberry antioxidant capacity and other quality
attributes. IJFST. 47, 1540- 1549 (2012)
4. J. Barba Francisco, J. Esteve Maria, Frigola Ana.
Physicochemica and nutritional characteristics of
blueberry juice after high pressure processing. FRI.
50, 545-549 (2013)
5. Ying Wang, Shu Wang, Chunguang Ren, etc.
Blueberry wine fermentation process and quality of
the relationship between the study. Guizhou Science.
31, 75-78 (2013)
6. Pengxiang Han, Bei Zhang, Xuqiao Feng, etc.
Blueberry nutrition and health functions and its
development and utilization. FIT. 36, 370-375,379
(2015)
7. Yangcheng Song, Yujuan Chen, Hao Li, etc.
Blueberries in the rapid detection of anthocyanins.
Food Science. 31, 334-336 (2010)
8. Lihua Pan, Jianfei Wang, Xinggan Ye, etc.
Blueberry anthocyanin extraction process and its
immunomodulatory activity. Food Science. 35, 81-
86 (2014)
9. Haiyan Gao, Long Xu, Hangjun Chen, etc.
Blueberry postharvest quality control and anti-
oxidation research progress. Chinese JFS. 6, 1-8
(2013)
10. Haige Li, Yanjun Wu, Yange Yang, etc. Advances
in technology research to identify the authenticity of
berry juice. Food Science. 37, 243-250 (2016)
11. Guifang Wu, Hai Ma, Xin Pan. Identification of
varieties of natural textile fiber based on vis / NIR
infrared spectroscopy. IAEAC.Institute of Electrical
and Electronics Engineers Inc, 585-589 (2015)
12. R. BEGHI, V. GIOVENZANA, A.SPINARDI, etc.
Derivation of a blueberry ripeness index with a view
to a low-cost, handheld optical sensing device for
supporting harvest decisions. Transaction of the
ASABE. 56, 1551 -1559 (2013)
13. Guifang Wu, Wei Jiang, Chunguang Wang, etc.
Quality inspection of tomato shelf life based on TPA
and Vis / NIR. MFST. 31, 290-294 (2015)
14. Guifang Wu, Chunguang Wang. Investigating the
effects of simulated transport vibration on tomato
tissue damage based on Vis / NIR spectroscopy.
PBT. 98, 41-47 (2014)
15. Shirong Ai, Ruimei Wu, Yan Wu. Study on the
Identification of Tea Beverage by Near Infrared
Spectroscopy Based on BP Neural Network. Anhui
JAS. 14, 7658-7659, 7662 (2010)
MATEC Web of Conferences 139, 00050 (2017) DOI: 10.1051/matecconf/201713900050
ICMITE 2017
4

16. Daniel Cozzolino, Wies Cynkar, Nevil Shah, etc.
Varietal differentiation of grape juice based on the
analysis of near- and mid-infrared spectral data.
Analyticical Methods. 5, 381- 387 (2012)
17. Royston Goodacre, David Hammond, B. Kell
Douglas. Quantitative analysis of the adulteration of
orange juice with sucrose using pyrolysis mass
spectrometry and chemometrics. JAAP. 40-41, 135-
158 (1997)
18. I. Suarez Gracirla, A.Ortiz Oscar, M. Aballay Pablo,
etc. Adaptive neural model predictive control for the
grape juice concentration process. // International
Conference on Industrial Technology. Universidad
Tecnica Federico Santa Maria. Institute of Electrical
and Electronics Engineers Inc. 57-62 (2010)
19. Guifang Wu, Yixiang Jiang, Yanyan Wang, etc.
Identification of dry red wine varieties based on
independent principal component and BP neural
network. SSA. 29, 1268-1271 (2009)
20. Jianhu Wu, Juntao Lei, Qi Yang. Identification of
Dry Date by Using Visible / Near Infrared
Spectroscopy. JFSQI. 7, 1870-1875 (2016)
21. Yulu Wang, Hui Guo, Changjie Han. Study on
identification method of different mutton based on
visible / near infrared spectroscopy. FST. 40, 298-
302 (2015)
MATEC Web of Conferences 139, 00050 (2017) DOI: 10.1051/matecconf/201713900050
ICMITE 2017
5