Evaluation of Density Based Odor Classification by General Type-2 Fuzzy Set Induced Pattern Classifier

Abstract

In recent days, density based Odor classification using EEG is a promising issue. As our environment becomes polluted with various gases, it is necessary to know that which gas is present in the atmosphere and in what density. Our work in this paper gives an elementary approach to solve this problem. We have utilized liquid stimuli with three different concentration levels as Low (25% aroma and 75% water), medium (50% aroma and 50% water) and High (75% aroma and 25% water). General type-2 Fuzzy Classifier is used to classify the three different density stimuli. An accuracy of 86% is obtained in this experiment. Thus, we can illustrate that different density stimuli can be separable with EEG signals. The accuracy level can be further increased with other improved classifiers.