This paper describes the use of voltammetric electronic tongue and pattern recognition techniques used as a biomimetic system for classifying eight varieties of Indian juices. The responses from the voltammetric electronic tongue were recorded for all the samples of eight varieties of juices. In order to classify the juices into different classes, different pattern recognition techniques were used. The data being large as is the case with voltammetric signals is analyzed using Principal Component Analysis to transform the data into a low dimensional feature vector space involving Principal components thereby realizing dimensionality reduction of the responses followed by the selection of relevant principal components. Later, these relevant principal components are used as inputs to a distance based classifier for classifying the juices and the classification accuracy attained is 100%. The results demonstrate the feasibility of voltammetric electronic tongue combined with pattern recognition techniques for discriminating and classifying the juice samples.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.