Among major sensory modalities, the physical stimulus attributes to perception mapping is more or less well defined in vision and audition, but not in olfaction. Although, the molecular concentration to perceived odor intensity mapping has been established, there is no known general systematic relationship of molecular properties onto the olfactory percept. In other words, it has been a challenge to predict the smell of a novel molecule by its physicochemical structure, or the physicochemical structure of a novel smell. My work aims at discovering inherent statistical structure in large chemical and perceptual databases available online in order to derive principles for predicting odor perception from the chemical structure of odorants. It will test the explanatory possibilities of this novel perspective, and will contribute new sources and fresh approaches to the fields of modern data analysis and olfaction science. I also work in using social network models for optimization of artificial organoleptic systems(electronic tongue and nose). I am also actively involved in developing human interaction based evolutionary algorithms.