Sliding Window-based DCT Features for Tea Quality Prediction Using Electronic Tongue

ABSTRACT

The electronic tongue (ET) system is a multi-electrode system where each electrode generates a specific electronic response in presence of different chemical substances in the sample. The efficiency of an ET system mostly depends on the discriminating power of the electronic signature generated by the electrode array. In this work, a sliding window approach is used to extract discrete cosine transform (DCT) coefficients from the ET response and the corresponding energy for different position of window are used as the features of the ET response. The efficacy of the proposed method is verified on three types of ET data sets to predict four different quality of black tea using two kernel classifiers, namely support vector machine (SVM) and vector valued regularized kernel function approximation (VVRKFA).

References

1. Ivarsson, P., Holmin, S., Hojer, N. E., Krantz- Rulcker, C., and Winquist, F. 2001. Discrimination of tea by means of a voltammetric electronic tongue and different applied waveforms. Sensor Actuat. B-Chem., 76, 1-3, 449--454. DOI=10.1016/S0925-4005(01)005834.
2. Valsov, Y., Legin, A., Rudnitskya, A., and Bychkov, E. 1996. Cross-sensitivity of chalcogenide glass sensors in solutions of heavy metal ions. Sensor Actuat. B-Chem., 34, 1-3, 456--461.
3. Ivarsson, P., Krantz-Rulcker, C., Winquist, F., and Lundstrom, I. 2005. A voltammetric electronic tongue. Chem. Sens., 30, 1, i258-i259.
4. Scampicchio, M., Benedetti, S., Brunetti, B., and Mannino, S. 2006. Amperometric electronic tongue for the evaluation of the tea astringency. Electroanal., 18, 17, 1643--1648.
5. Legin, A., Rudnitskaya, A., Valsov, Y., Natale, D., Mazzone, C., and D'Amico, A. 1999. Application of electronic tongue for quantitative analysis of mineral water and wine. Electroanalysis, 11, 10-11, 814--820.
6. Lowton, B., A., and Pethig, R. 1993. Determining the fat content of milk and cream using AC conductivity measurements. Meas. Sci. Technol., 4, 1, 38--41.
7. Scozzari, A., Acito, N., and Corsini, G. 2007 A novel method based on voltammetry for the qualitative analysis of water. IEEE Trans. Instrum. Meas., 56, 6, 2688--2697.
8. Ciosek, P., Brzozka, Z., and Wroblewski, W. 2006. Electronic tongue for flow-through analysis of beverages. Sensor Actuat. B-Chem., 118, 1-2, 454--460.
9. Ivarsson, P., Krantz-Rulcker, C., Winquist, F., and Lundstrom, I. 2005. A voltammetric electronic tongue. Chem. Sens, 30, 1, i258-i259.
10. Haddad, R., Carmel, and L., and Harel, D. 2007. A feature extraction algorithm for multi-peak Signals in electronic noses. Sensor Actuat. B-Chem., 120, 2, 462--472.
11. Ding, H., Ge, H., and Liu, J. 2005. High performance of gas identification by wavelet transform-based fast feature extraction from temperature modulated semiconductor gas sensors. Sensor Actuat. B-Chem, 107, 2, 749--755.
12. Scozarri, A., Acito, N., and Corsini, G. 2007. A novel method based on voltammetry for the qualitative analysis of water. IEEE Trans. Instrum. Meas., 56, 6, 2688--2697.
13. Valle, S., Li, w., and Qin, S. J. 2012. Selection of the number of principal components: the variance of the reconstruction error criterion with a comparison to other methods. Ind. Eng. Chem. Res, 38, 11, 4389--4401.
14. Saha, P., Ghorai, S., Tudu, B., Bandyopadhyay, R., and Bhattacharyya, N. 2014. A novel method of black tea quality prediction using electronic tongue Signals. IEEE Trans. Instrum. Meas, 63, 10, 2472--2479, DOI=10.1109/TIM.2014.2310615.
15. Signes, M. T., Garcia, J. M., and Mora, H. 2009. Improvement of the discrete cosine transform calculation by means of a recursive method. Mathematical and Computer Modelling, 50, 5-6, 750--764.
16. Karwal, V., Sherlock, B. G., and Kakad, Y. P. 2013 Independently updating the DCT and DST for shifting windowed data. Journal of the Franklin Institute, 350, 6, 1345--1357.
17. Vapnik, V. N. 1998. The Nature of Statistical Learning Theory, John Willy & Sons, Inc., New York.
18. Burges, C. J. C. 1998. A tutorial on support vector machines for pattern recognition. Data Min. and Knowl. Disc., 2, 2, 121--167.
19. Hsu, C. -W., and Lin, C. -J. 2002. A comparison of methods for multi-class support vector machines. IEEE Trans. N. Nets., 13, 2, 415--425.
20. Saha, P., Ghorai, S., Tudu, B. Bandyopadhyay, R., and Bhattacharyya, N. 2012. Multi-class support vector machine for quality estimation of black tea using electronic nose. In Proceedings of the ICST-2012, Kolkata, India. 571--576.
21. Ghorai, S., Mukherjee, A., and Dutta, P. K. 2010. Discriminant analysis for fast multiclass data classification through regularized kernel function approximation. IEEE Trans. N. Nets, 21, 6, 1020--1029.
22. Ghorai, S., Mukherjee, A., and Dutta, P. K. 2012. Advances in Proximal Kernel Classifiers, LAP LAMBERT Academic Publishing, Germany.
23. Ghorai, S., Mukherjee, A., Gangadaran, M., and Dutta, P. K. 2013. Automatic Defect Detection on Hot Rolled Flat Steel Products. IEEE Trans. Instrum. Meas, 62, 3 (2013), 612--621.
24. Palit, M., Tudu, B., Dutta, P. K., Dutta, A., Jana, A., Roy, J. K., Bhattacharyya, N., Bandyopadhyay, R., and Chatterjee, A. 2010. Classification of black tea taste and correlation with tea taster's mark using voltammetric electronic tongue. IEEE Trans. Instrum. Meas, 59, 8, 2230--2239.
25. Rao, K. R., Yip, P., and Britanak, V. 2007. Discrete Cosine Transform: Algorithms, Advantages, Applications, Academic Press, Inc., Orlando, Flo., USA.
26. Chang, C. C., and Lin, C. J. 2001. LIBSVM: A library for support vector machines, Tech. Report, DOI=http://www.csie.ntu.edu.tw/~cjlin/libsvm.
27. Mitchell, T. M. 1997. Machine Learning, The McGRaw Hill Companies, Inc., Singapore, Ch. 5, 148.

Index Terms

• Computing methodologies

  • Machine learning