CFP last date
20 December 2024
Reseach Article

Indian Tea Discriminator: SVM Approach

Published on April 2016 by Princee Gupta, Rajesh K. Shukla
International Conference on ICT for Healthcare
Foundation of Computer Science USA
ICTHC2015 - Number 1
April 2016
Authors: Princee Gupta, Rajesh K. Shukla
8a0e570b-0279-4368-9ca4-bd977f94437d

Princee Gupta, Rajesh K. Shukla . Indian Tea Discriminator: SVM Approach. International Conference on ICT for Healthcare. ICTHC2015, 1 (April 2016), 20-24.

@article{
author = { Princee Gupta, Rajesh K. Shukla },
title = { Indian Tea Discriminator: SVM Approach },
journal = { International Conference on ICT for Healthcare },
issue_date = { April 2016 },
volume = { ICTHC2015 },
number = { 1 },
month = { April },
year = { 2016 },
issn = 0975-8887,
pages = { 20-24 },
numpages = 5,
url = { /proceedings/icthc2015/number1/24655-8253/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference on ICT for Healthcare
%A Princee Gupta
%A Rajesh K. Shukla
%T Indian Tea Discriminator: SVM Approach
%J International Conference on ICT for Healthcare
%@ 0975-8887
%V ICTHC2015
%N 1
%P 20-24
%D 2016
%I International Journal of Computer Applications
Abstract

Artificial Organoleptic Systems are being used today for a variety of detection tasks from quality control of food products to medical diagnosis. The optimization of sample preparation, signal processing, feature extraction, classifier are as important as choice of sensors within the array in enhancing the performance of the organoleptic system. It is difficult to determine if all features considered are necessary for the classifier while classifying megavariate data. The presence of irrelevant features increases the dimensionality of the search space, which can potentially deluge the accuracy of the Pattern Recognition (PARC) techniques. Hence, a systematic method is required to reduce the number of features in order to optimize the performance of PARC. Tea in present time is the most popular beverages having huge global marketing. It is a very complex chemical compound graded by various testers' score, which led to many human errors and may vary from person to person. This problem can be solved by using an instrument called "Electronic Tongue (i-tongue)" that gives fast, reliable and repeatable results. This system analyses liquid including an array of non-specific chemical sensors with partial specificity for different component in liquid samples and appropriate pattern recognition capable of recognizing the qualitative and quantitative composition of sample and complex solutions. In this project we use "Principal Component Analysis (PCA)" to reduce the dimension of features and "Support Vector Machine (SVM)" to classify different tea samples including an array of non-specific chemical sensors.

References
  1. Andrey Legin, Alisa Rudnitskaya, David Clapham, Boris Seleznev, Kevin Lord and Yuri Vlasov "Electronic tongue for pharmaceutical analytics — quantification of tastes and masking effects" J. Bioanalytical Chemistry, 2004, V. 380, pp. 36-45.
  2. P. Devijver and J. Kittler, Pattern Recognition: A Statistical Approach, Prentice Hall, 1982.
  3. Bishop C M. Neural Networks for Pattern Recognition. Oxford University Press. 1995.
  4. A. Riul, H. C. de Sousa, R. R. Malmegrim, D. S. dos Santos, A. C. P. L. F. Carvalho, F. J. Fonseca, O. N. Oliveira, L. H. C. Mattoso, Wine classification by taste sensors made from ultra-thin films and using neural networks, Sensors and Actuators B: Chemical 98 (2004) 77–82.
  5. B. Tudu, A. Jana, A. Metla, D. Ghosh, N. Bhattacharyya, R. Bandyopadhyay, Elec- tronic nose for black tea quality evaluation by an incremental RBF network, Sensors and Actuators B: Chemical 138 (2009) 90–95.
  6. N. Bhattacharyya, R. Bandyopadhyay, M. Bhuyan, A. Ghosh, R. K. Mudi, Correlation of multi-sensor array data with "Tasters" panel evaluation for objective assessment of black tea flavour, in: Int. Proc. ISOEN-2005, Barcelona, Spain, April 13–15, 2005.
  7. Yu. Vlasov, A. Legin, A. Rudnitskaya, C. DiNatale, A. D'Amico,Nonspecific sensor arrays ("electronic tongue") for chemical analysis of liquids (IUPAC Technical Report), Pure and Applied Chemistry 77 (2005) 1965–1983.
  8. K. Toko, Electronic sensing of tastes, Electroanalysis 10 (1998) 657–669.
  9. E. Phaisangittisagul, H. T. Nagle, Sensor Selection for Machine Olfaction Based on Transient Feature Extraction, Instrumentation and Measurement, IEEE Transactions on, 57 (2008) 369-378.
  10. Cheng Tan, Lijun Xu, Zhang Cao," On-Line Fuel Identification Using Optical Sensing and Support Vector Machines Technique", I2MTC 2009 - International Instrumentation and Measurement Technology Conference Singapore, 5-7 May 2009, 2009 IEEE.
  11. Xiao-Dong Wang, Hao-Ran Zhang, Chang-Jiang Zhang," Signals Recognition Of Electronic Nose Based On Support Vector Machines", Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, 18-21 August 2005, 2005 IEEE.
  12. Lihong Zheng and Xiangjian He," Classification Techniques in Pattern Recognition", Proceedings ISBN 80-903100-8-7 WSCG'2005, January 31-February 4, 2005.
  13. Spector, A. Z. 1989. Achieving application requirements. In Distributed Systems, S. Mullender.
  14. Chih-Chung Chang and Chih-Jen Lin. LIBSVM -- A library for Support Vector Machines. From: http://www. csie. ntu. edu. tw/~cjlin/libsvm/index. html [Online].
Index Terms

Computer Science
Information Sciences

Keywords

Pca Svm Parc Electronic Tongue I-tongue Hyperplane Pattern Recognition.