SELF-ORGANIZING SENSORY MAPS IN ODOR CLASSIFICATION MIMICKING

A system for artificial olfaction is introduced, which is composed of a sensor array for gas sensing and a self-organising artificial neural network. A detailed reformulation of the most effective Self-Organisi ng sensory Map (SOM)-based algorithms for odour classification and oth er applications is provided. An opto-electronic micromachined implemen tation of the neural network is introduced, which employs a novel hybr id mechanism for activating neural groups, avoiding fabricated cloning templates hardware.