Artificial odor discrimination system using multiple quartz-resonator sensor and neural network for recognizing fragrance mixtures

Abstract

Human sensory test is often used for obtaining the sensory quantities of odors; however, the fluctuation of results due to the expert's condition can cause discrepancies among panelist. Artificial odor discrimination system is constructed to overcome the limitation of the already existing sensory test systems. Authors have developed an electronic odor discrimination system by using 4 quartz-resonator sensitive membranes as the sensors and had fundamental resonance frequencies 10 MHz. In recognizing and classifying the output pattern, the system used back propagation (BP) neural network as the pattern recognizer. This system can recognize the limited odor mixtures. The capability of the system can be amended by improving the hardware and changing the software of pattern classifier. This paper proposes a new sensing system using 16 multiple quartz resonator sensors array and basic resonance frequencies 20 MHz. Also modify various neural network called probabilistic neural network (PNN) and fuzzy-neuro learning vector quantization (FLVQ) as the automated pattern recognition system. The purpose of the recent study is to construct an artificial odor discrimination system for recognizing the fragrance mixtures. It is found out that the using of new sensing system as in PNN and FLVQ produces higher capability compare to the conventional sensing system with back propagation (BP) neural network.