Optimized probabilistic neural networks in recognizing fragrance mixtures using higher number of sensors

Abstract

The electronic odor discrimination system have developed. The developed system showed high recognition probability to discriminate various single odors to its high generality properties; however, the system had a limitation in recognizing the fragrances mixture. In order to improve the performance of the proposed system, development of the sensor and other neural network are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from 4 quartz resonator-basic resonance frequencies 10 MHz with new 16 quartz resonator-basic resonance frequencies 20 MHz, but also by replacing the pattern classifier from back propagation (BP) neural network with variance of back propagation, probabilistic neural network (PNN) and optimized-PNN. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing fragrance mixtures. The using of new sensing system and employing various neural networks have produced higher capability to recognize the fragrance mixtures compared to the earlier mentioned system