Vol. 145, No. 10, September 2012, pp. 65-76

Abstract: An electronic tongue based on voltammetry (VE-tongue) was developed and its application towards discriminating the Indian wines based on their non volatile chemical profiles is reported in this paper. Eight types of Indian wine were analyzed and classified using the E-tongue by principal component analysis (PCA) and Artificial neural networks (ANN) respectively. A new statistical features based data reduction methodology of voltammetric response signals for classification of Indian wines has been proposed which has reduced the original data size by 99.02 %. An ANN based classifier was trained with the reduced features from the original data for classification of Indian wines. A classification success rate of 97.5 % was achieved for all the eight brands of Indian wines. The results show that the VE-tongue can discriminate Indian wines into natural and useful groupings and may become an important tool for standardization of wine quality.

Keywords: Indian wine, Electronic tongue, Feature extraction, Principal component analysis (PCA), Artificial neural networks (ANN)

Buy this article online (it will be send to you in the pdf format by e-mail) or subscribe Sensors & Transducers journal

(12 issues per year plus special issues; 40 % discount for payment IFSA Members):

Download <here> the Library Journal Recommendation Form

Read more about Chemical Sensors

1999 - 2012 Copyright ©, International Frequency Sensor Association (IFSA). All Rights Reserved.

Home - News - Links - Archives - Tools - Voltage-to-Frequency Converters - Standardization - Patents - Marketplace - Projects - Wish List - e-Shop - Sensor Jobs - Membership - Videos - Publishing - Site Map - Subscribe - Search

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Submit Press Release - Submit White Paper - Testimonies - Twitter - Facebook - LinkedIn