Electronic nose for black tea quality evaluation using kernel based clustering approach

Black Tea is conventionally tested by human sensory panel called “Tea Tasters”, who assign quality scores to different tea samples. This paper proposed a method of separation using the device named as electronic noise. The various tea samples have been analyzed using the popular method of separation, like PCA and LDA. For better separation among different scores of tea samples, the kernel based PCA as well as kernel based LDA methods have been considered in this case as the clustering algorithm. The method exhibits a better performance than those of traditional methods. Also the separation index has been evaluated and shows its efficacy