Artificial Odor Discrimination System Using MultipleQuartz Resonator Sensor and FNLVQ-MSA NeuralNetwork for Recognizing Concentration of Odor

摘要

An electronic odor discrimination system had been developed. The developed systemshowed high recognition probability to discriminate various single odors to its high generalityproperties, however the system had a limitation in recognizing the fragrances mixture. In order toimprove the performance of the proposed system, development of the sensor and other neural networkare being sought. This paper explains the improvement of the capability of that system. In thisexperiment, the improvement is conducted not only by replacing the last hardware system from 4quartz resonator-basic resonance frequencies 10 MHz with new 16 quartz resonator-basic resonancefrequencies 20 MHz, but also by replacing the pattern classifier from Back Propagation (BP) neuralnetwork with Variance of Back Propagation, Probabilistic Neural Network (PNN) and Fuzzy-NeuroLearning Vector Quantization. Matrix similarity analysis (MSA) is then proposed to increase theaccuracy of the FNLVQ, become FNLVQ-MSA neural system in determining the best exemplarvector, for speeding up its convergence. The purpose of the recent study is to construct a newartificial odor discrimination system for recognizing the concentration of fragrance. The using of newsensing system and FNLVQ-MSA has produced higher capability to recognize the concentration offragrance compared to the earlier mentioned system.