Title :
Neuro-based olfactory model for estimation of sensory characteristic of mice
Author :
Soh, Zu ; Tusji, Toshio ; Takiguchi, Noboru ; Tsuji, Toshio
Author_Institution :
Grad. Sch. of Eng., Hiroshima Univ., Higashi-Hiroshima
Abstract :
Recently, the demand for odor processing apparatuses is increasing in the fragrance and food industries. In this paper, we propose a neural network model of the olfactory system as basis for biomimetic e-nose. The model has two distinctive features. First, it converts the properties of odorant molecule to the neural activity pattern of living mice. Second, the olfactory ldquoAttentionrdquo mechanism is introduced. The simulation results show that the model can predict the odor coding manner on the glomeruli by appropriately adjusting the parameters. Further, the tendency in accuracy rate of odor discrimination is consistent with that of living mice.
Keywords :
biomimetics; chemioception; electronic noses; food processing industry; neural nets; biomimetic e-nose; food industry; living mice; neural activity pattern; neural network model; neuro-based olfactory model; odor processing apparatus; sensory characteristic; Biomimetics; Data engineering; Food industry; Humans; Mice; Neurons; Olfactory; Pattern recognition; Predictive models; Service robots; Attention; Glomeruli activity pattern; Neural Network Model; Olfactory System;
Conference_Titel :
Robotics and Biomimetics, 2008. ROBIO 2008. IEEE International Conference on
Conference_Location :
Bangkok
Print_ISBN :
978-1-4244-2678-2
Electronic_ISBN :
978-1-4244-2679-9
DOI :
10.1109/ROBIO.2009.4913042
