Artificial odor discrimination system using multiple quartz resonator sensors and various neural networks for recognizing fragrance mixtures

Abstract

An electronic odor discrimination system had been developed by using four quartz resonator-sensitive membranes basic-resonance frequencies at 10 MHz as a sensor and analyzed the measurement data through a back propagation (BP) as the pattern recognition system. 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. This system also had other disadvantages, such as classifying the unknown category of odor as the known category of odor. In order to improve the performance of the proposed system, development of the sensor and other neural networks (NNs) 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 four quartz resonator-basic resonance frequencies at 10 MHz with new 16 quartz resonator-basic resonance frequencies at 20 MHz, but also by replacing the pattern classifier from BP NNs with the variance of BP, probabilistic NNs, and fuzzy-neuro learning vector quantization (FNLVQ). Matrix similarity analysis (MSA) is then proposed to increase the accuracy of the FNLVQ, to become FNLVQ-MSA neural systems in determining the best exemplar vector, for speeding up its convergence. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing the fragrance mixtures, in addition to recognizing the unknown fragrance mixtures. The use of new sensing systems and FNLVQ-MSA has produced higher capability, compared to the previously mentioned system.Index Terms-Fuzzy-neuro learning vector quantization (FNLVQ), matrix similarity analysis (MSA), multiple quartz-resonator sensors, neural networks (NNs), odor discrimination system.

PSO Algorithm for Single and Multiple Odor Sources Localization Problems: Progress and Challenge

“…Vin is a velocity vector for the i-th (i = 1,2,3,) particle on the n-th iteration (n = 1,2,3). χ is a constriction factor which has a value of less than one, c 1 Velocity calculation with Eq. 1 determines the robot's position for the next step.…”

Untitled

“…Outlier klasifikasi adalah data yang muncul pada saat uji coba di mana data tersebut bukan merupakan anggota bagian dari kelas train. Algoritma ini merupakan pengembangan dari Fuzzy Learning Vector Quantization [18][19][20] Dalam penelitian ini peneliti mengunakan data aritmia dari MIT-BIH [23]. Tata penulisan dalam paper ini terbagi sebagai berikut, Bab II berisi tentang pra pemrosesan data EKG.…”

Machine Learning: How It Can Help Nanocomputing

“…Examples of this are use of artificial neural networks to classify vapor measurements from thin films of nanoparticles, 35 salmonella detection by an artificial neural network coupled with an electronic sensor array, 36 pattern recognition by CMOL (CMOS/nanowire/MOLecular hybrids 37 ), odor discrimination using quartz resonator sensors, and neural networks for recognizing fragrance mixtures. 38 Similarly, machine learning techniques can be used in processing of nanosensor data for human analysis, such as the use of principal component analysis on gas and vapor data in a 2006 paper by Lu et al 39 In some of the above mentioned cases the sensors include nanotechnology, but in all these cases the computation is done by conventional electronics. An attractive future direction is to perform also the processing of the sensory information in nanoscale; such nanoscale computation can not be realized at present.…”