Odor classification plays an important role in understanding
the brain computation of object recognition 1, 2. Animals can use chemical
signals to understand ecological information from the environment. Those
chemical signals frequently change in different concentration to convey
different messages. Here, in this paper, we try to recognize different odorous
stimulus across different concentration level. This experiment can be used as a
preliminary tool for diseases diagnosis in medical technology 4. This
approach can also be utilized in coal mines to observe the changes in odor
sensing of coal mine workers during gas exposure 3. Depending on
psychological dimensions of human odor, perception is a vital issue in olfactory
research. There has been extensive research in various disciplines for
characterized odorant quality and description using pattern recognition
technique 5. Amongst all these studies, our work adds a new direction in the
field of olfactory classification.
In literature 6, a recurrent neural network
model is designed to classify different aromatic stimuli and discriminate them
using EEG analysis. The effects of each factor of human odor perceptual
qualities are discussed in 7. Article 8 reveals that the odor quality
varies with the concentration of the odorant stimulus. An electronic nose is
developed to classify odor and classify using neural network in 9-10.
In the process of human smell perception, all the
aromatic stimuli are sensed by the receptors which are located in the olfactory
epithelium 6. Odor molecules are then transferred through several hundred
receptors for perceiving a particular olfactory stimulus. According to the
various concentration of aromatic stimulus, different kinds of EEG signals are
generated from different brain regions. Olfactory perception is highly
associated with four parts of brain region namely prefrontal, frontal,
temporal, and parietal.
In this paper, we try to design an odor
classification depending on their molecular concentration. Here, we use
different types of smell stimuli like perfume, Dettol, Acetic Acid and Alcohol.
Then the subjects are asked to perceive these smell stimuli in low, medium and
high dilution according to different concentration levels. For classification
of odor perception we use here General Type-2 Fuzzy Set (GT2FS) Induced
Classifier 11. This proposed system is smart enough to classify the mixture
of different concentration level of different liquid aroma.
The paper is divided into six sections. In
Section II, we provide the basic overview of the proposed system. In Section
III, we illustrate the details of classifier design. Experimental details are
given in Section IV. Classifier performance analysis is undertaken in Section
V. Conclusions are listed in Section VI.