Abstract

Visible and near-infrared (Vis∕NIR) reflectance spectroscopy has been investigated for its ability to nondestructively detect acidity in bayberry juice. What we believe to be a new, better mathematic model is put forward, which we have named principal component analysis–stepwise regression analysis–backpropagation neural network (PCA-SRA-BPNN), to build a correlation between the spectral reflectivity data and the acidity of bayberry juice. In this model, the optimum network parameters, such as the number of input nodes, hidden nodes, learning rate, and momentum, are chosen by the value of root-mean-square (rms) error. The results show that its prediction statistical parameters are correlation coefficient (r) of 0.9451 and root-mean-square error of prediction (RMSEP) of 0.1168. Partial least-squares (PLS) regression is also established to compare with this model. Before doing this, the influences of various spectral pretreatments (standard normal variate, multiplicative scatter correction, S. Golay first derivative, and wavelet package transform) are compared. The PLS approach with wavelet package transform preprocessing spectra is found to provide the best results, and its prediction statistical parameters are correlation coefficient (r) of 0.9061 and RMSEP of 0.1564. Hence, these two models are both desirable to analyze the data from Vis∕NIR spectroscopy and to solve the problem of the acidity prediction of bayberry juice. This supplies basal research to ultimately realize the online measurements of the juice's internal quality through this Vis∕NIR spectroscopy technique.

© 2007 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. G. Downey and J. Boussion, "Authentication of coffee bean variety by near infrared reflectance spectroscopy of dried extract," J. Sci. Food Agric. 71, 41-49 (1996).
    [CrossRef]
  2. I. Wesley, "The application of near infrared spectroscopy to the identification of fruit pulps," Fruit Process. 6, 263-266 (1996).
  3. T. M. Baye, T. C. Pearson, and A. M. Settles, "Development of a calibration to predict maize seed composition using single kernel near infrared spectroscopy," J. Cereal Sci. 43, 236-243 (2006).
    [CrossRef]
  4. T. Naes and T. Isaksson, "Locally weighted regression and scatter correction for near-infrared reflectance data," Anal. Chem. 62, 664-673 (1990).
    [CrossRef]
  5. H. Holst, "Comparison of different calibration methods suited for calibration problems with many variables," Appl. Spectrosc. 46, 1780-1784 (1992).
    [CrossRef]
  6. Y. He, S. J. Feng, X. F. Deng, and X. L. Li, "Study on lossless discrimination of varieties of yogurt using the visible/NIR-spectroscopy," Food Res. Int. 39, 645-650 (2006).
    [CrossRef]
  7. Y. He, X. L. Li, and Y. N. Shao, "Quantitative analysis of the varieties of apple using near infrared spectroscopy by principle component analysis and BP model," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3809, pp. 1053-1056.
  8. Y. He, Y. Zhang, and L. G. Xiang, "Study of application model on BP neural network optimized by fuzzy clustering," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3789, pp. 712-720.
  9. A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
    [CrossRef]
  10. X. L. Chu, H. F. Yuan, and W. Z. Lu, "Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique," Prog. Chem. 16, 528-542 (2004).
  11. P. Chalus, Y. Roggo, S. Walter, and M. Ulmschneider, "Near-infrared determination of active substance content in intact low-dosage tablets," Talanta 66, 1294-1302 (2005).
    [CrossRef]
  12. Y. C. Liang and Z. S. Yi, The Handbook of Analytical Chemistry: Chemistry Metrology (Chemical Industry Press, 2001).
  13. J. Chen, Y. Shi, and S. Shi, "Noise analysis of digital ultrasonic nondestructive evaluation system," Int. J. Pressure Vessels Piping 76, 619-631 (1999).
    [CrossRef]
  14. M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
    [CrossRef]

2006 (2)

Y. He, S. J. Feng, X. F. Deng, and X. L. Li, "Study on lossless discrimination of varieties of yogurt using the visible/NIR-spectroscopy," Food Res. Int. 39, 645-650 (2006).
[CrossRef]

T. M. Baye, T. C. Pearson, and A. M. Settles, "Development of a calibration to predict maize seed composition using single kernel near infrared spectroscopy," J. Cereal Sci. 43, 236-243 (2006).
[CrossRef]

2005 (4)

Y. He, X. L. Li, and Y. N. Shao, "Quantitative analysis of the varieties of apple using near infrared spectroscopy by principle component analysis and BP model," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3809, pp. 1053-1056.

Y. He, Y. Zhang, and L. G. Xiang, "Study of application model on BP neural network optimized by fuzzy clustering," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3789, pp. 712-720.

P. Chalus, Y. Roggo, S. Walter, and M. Ulmschneider, "Near-infrared determination of active substance content in intact low-dosage tablets," Talanta 66, 1294-1302 (2005).
[CrossRef]

M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
[CrossRef]

2004 (1)

X. L. Chu, H. F. Yuan, and W. Z. Lu, "Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique," Prog. Chem. 16, 528-542 (2004).

2001 (1)

Y. C. Liang and Z. S. Yi, The Handbook of Analytical Chemistry: Chemistry Metrology (Chemical Industry Press, 2001).

1999 (2)

J. Chen, Y. Shi, and S. Shi, "Noise analysis of digital ultrasonic nondestructive evaluation system," Int. J. Pressure Vessels Piping 76, 619-631 (1999).
[CrossRef]

A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
[CrossRef]

1996 (2)

G. Downey and J. Boussion, "Authentication of coffee bean variety by near infrared reflectance spectroscopy of dried extract," J. Sci. Food Agric. 71, 41-49 (1996).
[CrossRef]

I. Wesley, "The application of near infrared spectroscopy to the identification of fruit pulps," Fruit Process. 6, 263-266 (1996).

1992 (1)

1990 (1)

T. Naes and T. Isaksson, "Locally weighted regression and scatter correction for near-infrared reflectance data," Anal. Chem. 62, 664-673 (1990).
[CrossRef]

Baye, T. M.

T. M. Baye, T. C. Pearson, and A. M. Settles, "Development of a calibration to predict maize seed composition using single kernel near infrared spectroscopy," J. Cereal Sci. 43, 236-243 (2006).
[CrossRef]

Boussion, J.

G. Downey and J. Boussion, "Authentication of coffee bean variety by near infrared reflectance spectroscopy of dried extract," J. Sci. Food Agric. 71, 41-49 (1996).
[CrossRef]

Candolfi, A.

A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
[CrossRef]

Chalus, P.

P. Chalus, Y. Roggo, S. Walter, and M. Ulmschneider, "Near-infrared determination of active substance content in intact low-dosage tablets," Talanta 66, 1294-1302 (2005).
[CrossRef]

Chen, J.

J. Chen, Y. Shi, and S. Shi, "Noise analysis of digital ultrasonic nondestructive evaluation system," Int. J. Pressure Vessels Piping 76, 619-631 (1999).
[CrossRef]

Chu, X. L.

X. L. Chu, H. F. Yuan, and W. Z. Lu, "Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique," Prog. Chem. 16, 528-542 (2004).

Deng, X. F.

Y. He, S. J. Feng, X. F. Deng, and X. L. Li, "Study on lossless discrimination of varieties of yogurt using the visible/NIR-spectroscopy," Food Res. Int. 39, 645-650 (2006).
[CrossRef]

Downey, G.

G. Downey and J. Boussion, "Authentication of coffee bean variety by near infrared reflectance spectroscopy of dried extract," J. Sci. Food Agric. 71, 41-49 (1996).
[CrossRef]

Feng, S. J.

Y. He, S. J. Feng, X. F. Deng, and X. L. Li, "Study on lossless discrimination of varieties of yogurt using the visible/NIR-spectroscopy," Food Res. Int. 39, 645-650 (2006).
[CrossRef]

Hailey, P. A.

A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
[CrossRef]

He, Y.

Y. He, S. J. Feng, X. F. Deng, and X. L. Li, "Study on lossless discrimination of varieties of yogurt using the visible/NIR-spectroscopy," Food Res. Int. 39, 645-650 (2006).
[CrossRef]

Y. He, Y. Zhang, and L. G. Xiang, "Study of application model on BP neural network optimized by fuzzy clustering," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3789, pp. 712-720.

Y. He, X. L. Li, and Y. N. Shao, "Quantitative analysis of the varieties of apple using near infrared spectroscopy by principle component analysis and BP model," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3809, pp. 1053-1056.

Hirota, K.

M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
[CrossRef]

Holst, H.

Isaksson, T.

T. Naes and T. Isaksson, "Locally weighted regression and scatter correction for near-infrared reflectance data," Anal. Chem. 62, 664-673 (1990).
[CrossRef]

Jouan-Rimbaud, D.

A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
[CrossRef]

Kawamoto, K.

M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
[CrossRef]

Kusumoputro, B.

M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
[CrossRef]

Li, X. L.

Y. He, S. J. Feng, X. F. Deng, and X. L. Li, "Study on lossless discrimination of varieties of yogurt using the visible/NIR-spectroscopy," Food Res. Int. 39, 645-650 (2006).
[CrossRef]

Y. He, X. L. Li, and Y. N. Shao, "Quantitative analysis of the varieties of apple using near infrared spectroscopy by principle component analysis and BP model," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3809, pp. 1053-1056.

Liang, Y. C.

Y. C. Liang and Z. S. Yi, The Handbook of Analytical Chemistry: Chemistry Metrology (Chemical Industry Press, 2001).

Lu, W. Z.

X. L. Chu, H. F. Yuan, and W. Z. Lu, "Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique," Prog. Chem. 16, 528-542 (2004).

Maesschalck, R. D.

A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
[CrossRef]

Massart, D. L.

A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
[CrossRef]

Naes, T.

T. Naes and T. Isaksson, "Locally weighted regression and scatter correction for near-infrared reflectance data," Anal. Chem. 62, 664-673 (1990).
[CrossRef]

Novuhara, H.

M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
[CrossRef]

Pearson, T. C.

T. M. Baye, T. C. Pearson, and A. M. Settles, "Development of a calibration to predict maize seed composition using single kernel near infrared spectroscopy," J. Cereal Sci. 43, 236-243 (2006).
[CrossRef]

Roggo, Y.

P. Chalus, Y. Roggo, S. Walter, and M. Ulmschneider, "Near-infrared determination of active substance content in intact low-dosage tablets," Talanta 66, 1294-1302 (2005).
[CrossRef]

Settles, A. M.

T. M. Baye, T. C. Pearson, and A. M. Settles, "Development of a calibration to predict maize seed composition using single kernel near infrared spectroscopy," J. Cereal Sci. 43, 236-243 (2006).
[CrossRef]

Shao, Y. N.

Y. He, X. L. Li, and Y. N. Shao, "Quantitative analysis of the varieties of apple using near infrared spectroscopy by principle component analysis and BP model," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3809, pp. 1053-1056.

Shi, S.

J. Chen, Y. Shi, and S. Shi, "Noise analysis of digital ultrasonic nondestructive evaluation system," Int. J. Pressure Vessels Piping 76, 619-631 (1999).
[CrossRef]

Shi, Y.

J. Chen, Y. Shi, and S. Shi, "Noise analysis of digital ultrasonic nondestructive evaluation system," Int. J. Pressure Vessels Piping 76, 619-631 (1999).
[CrossRef]

Ulmschneider, M.

P. Chalus, Y. Roggo, S. Walter, and M. Ulmschneider, "Near-infrared determination of active substance content in intact low-dosage tablets," Talanta 66, 1294-1302 (2005).
[CrossRef]

Walter, S.

P. Chalus, Y. Roggo, S. Walter, and M. Ulmschneider, "Near-infrared determination of active substance content in intact low-dosage tablets," Talanta 66, 1294-1302 (2005).
[CrossRef]

Wesley, I.

I. Wesley, "The application of near infrared spectroscopy to the identification of fruit pulps," Fruit Process. 6, 263-266 (1996).

Widyanto, M. R.

M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
[CrossRef]

Xiang, L. G.

Y. He, Y. Zhang, and L. G. Xiang, "Study of application model on BP neural network optimized by fuzzy clustering," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3789, pp. 712-720.

Yi, Z. S.

Y. C. Liang and Z. S. Yi, The Handbook of Analytical Chemistry: Chemistry Metrology (Chemical Industry Press, 2001).

Yuan, H. F.

X. L. Chu, H. F. Yuan, and W. Z. Lu, "Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique," Prog. Chem. 16, 528-542 (2004).

Zhang, Y.

Y. He, Y. Zhang, and L. G. Xiang, "Study of application model on BP neural network optimized by fuzzy clustering," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3789, pp. 712-720.

Anal. Chem. (1)

T. Naes and T. Isaksson, "Locally weighted regression and scatter correction for near-infrared reflectance data," Anal. Chem. 62, 664-673 (1990).
[CrossRef]

Appl. Soft Comput. (1)

M. R. Widyanto, H. Novuhara, K. Kawamoto, K. Hirota, and B. Kusumoputro, "Improving recognition and generalization capability of back-propagation NN using a self organized network inspired by immune algorithm (SONIA)," Appl. Soft Comput. 6, 72-84 (2005).
[CrossRef]

Appl. Spectrosc. (1)

Food Res. Int. (1)

Y. He, S. J. Feng, X. F. Deng, and X. L. Li, "Study on lossless discrimination of varieties of yogurt using the visible/NIR-spectroscopy," Food Res. Int. 39, 645-650 (2006).
[CrossRef]

Fruit Process. (1)

I. Wesley, "The application of near infrared spectroscopy to the identification of fruit pulps," Fruit Process. 6, 263-266 (1996).

Int. J. Pressure Vessels Piping (1)

J. Chen, Y. Shi, and S. Shi, "Noise analysis of digital ultrasonic nondestructive evaluation system," Int. J. Pressure Vessels Piping 76, 619-631 (1999).
[CrossRef]

J. Cereal Sci. (1)

T. M. Baye, T. C. Pearson, and A. M. Settles, "Development of a calibration to predict maize seed composition using single kernel near infrared spectroscopy," J. Cereal Sci. 43, 236-243 (2006).
[CrossRef]

J. Pharm. Biomed. Anal. (1)

A. Candolfi, R. D. Maesschalck, D. Jouan-Rimbaud, P. A. Hailey, and D. L. Massart, "The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra," J. Pharm. Biomed. Anal. 21, 115-132 (1999).
[CrossRef]

J. Sci. Food Agric. (1)

G. Downey and J. Boussion, "Authentication of coffee bean variety by near infrared reflectance spectroscopy of dried extract," J. Sci. Food Agric. 71, 41-49 (1996).
[CrossRef]

Prog. Chem. (1)

X. L. Chu, H. F. Yuan, and W. Z. Lu, "Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique," Prog. Chem. 16, 528-542 (2004).

Talanta (1)

P. Chalus, Y. Roggo, S. Walter, and M. Ulmschneider, "Near-infrared determination of active substance content in intact low-dosage tablets," Talanta 66, 1294-1302 (2005).
[CrossRef]

Other (3)

Y. C. Liang and Z. S. Yi, The Handbook of Analytical Chemistry: Chemistry Metrology (Chemical Industry Press, 2001).

Y. He, X. L. Li, and Y. N. Shao, "Quantitative analysis of the varieties of apple using near infrared spectroscopy by principle component analysis and BP model," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3809, pp. 1053-1056.

Y. He, Y. Zhang, and L. G. Xiang, "Study of application model on BP neural network optimized by fuzzy clustering," in Lecture Notes in Artificial Intelligence (Springer-Verlag, 2005), Vol. 3789, pp. 712-720.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (4)

Fig. 1
Fig. 1

(Color online) Collection system of bayberry juice.

Fig. 2
Fig. 2

Neural network topology of BPNN.

Fig. 3
Fig. 3

(Color online) Prediction results of 60 unknown bayberry juices by using the PCA-SRA-BPNN mode.

Fig. 4
Fig. 4

(Color online) Prediction results of 60 unknown bayberry juices by using the PLS model.

Tables (3)

Tables Icon

Table 1 pH Range for Each Brand of the Bayberry Juice

Tables Icon

Table 2 Calibration and Validation Results of PLS for Analyzing Acidity of Bayberry Juice

Tables Icon

Table 3 Prediction Statistics Using PCA-SRA-BPNN–Stepwise Regression Neural Network and PLS for Acidity of Bayberry Juice

Equations (3)

Equations on this page are rendered with MathJax. Learn more.

X = T P 1 + E ,
rms = 1 n i = 1 n ( y ^ i y i ) 2 ,
PRESS = i ( y ^ i y i ) 2 ,

Metrics