Design of Experiments for optimizing and selectivity study of mems sensor array based electronic nose for hazardous gases measurement

Purpose – The purpose of the paper is to propose a new optimization algorithm to realize a synchronous optimization of sensor array and classifier, to improve the performance of E-nose in the detection of wound infection. When an electronic nose (E-nose) is used to detect the wound infection, sensor array’s optimization and parameters’ setting of classifier have a strong impact on the classification accuracy. Design/methodology/approach – An enhanced quantum-behaved particle swarm optimization based on genetic algorithm, genetic quantum-behaved particle swarm optimization (G-QPSO), is proposed to realize a synchronous optimization of sensor array and classifier. The importance-factor (I-F) method is used to weight the sensors of E-nose by its degree of importance in classification. Both radical basis function network and support vector machine are used for classification. Findings – The classification accuracy of E-nose is the highest when the weighting coefficients of the I-F method and classifier’s parameters are optimized by G-QPSO. All results make it clear that the proposed method is an ideal optimization method of E-nose in the detection of wound infection. Research limitations/implications – To make the proposed optimization method more effective, the key point of further research is to enhance the classifier of E-nose. Practical implications – In this paper, E-nose is used to distinguish the class of wound infection; meanwhile, G-QPSO is used to realize a synchronous optimization of sensor array and classifier of E-nose. These are all important for E-nose to realize its clinical application in wound monitoring. Originality/value – The innovative concept improves the performance of E-nose in wound monitoring and paves the way for the clinical detection of E-nose.

Download Full-text

Study on Sensor Array Optimization of Medical Electronic Nose for Wound Infection Detection

IEEE Transactions on Circuits & Systems II Express Briefs ◽

10.1109/tcsii.2021.3112597 ◽

2021 ◽

pp. 1-1

Author(s):

Junhui Qian ◽

Mengchen Lu ◽

Fengchun Tian ◽

Ran Liu

Keyword(s):

Wound Infection ◽

Electronic Nose ◽

Sensor Array ◽

Infection Detection ◽

Medical Electronic ◽

Array Optimization

Download Full-text

Nano Sensor Using One Dimensional Porous Indium Oxide and Pattern Recognition Method of Its Electronic Information

Journal of Nanoelectronics and Optoelectronics ◽

10.1166/jno.2021.2955 ◽

2021 ◽

Vol 16 (2) ◽

pp. 255-263

Author(s):

Qinghong Wu ◽

Wanying Zhang

Keyword(s):

Pattern Recognition ◽

Indium Oxide ◽

Electronic Nose ◽

Sensor Array ◽

Dimensional Space ◽

Ordinary Least Squares ◽

Acquisition Time ◽

Pattern Recognition Method ◽

Recognition Method ◽

Linear Discriminant

Due to its high sensitivity, low price and fast response speed, gas sensors based on metal oxide nanomate-rials have attracted many researchers to modify and explore the materials. First, pure indium oxide (In2O3) nanotubes (NTs)/porous NTs (PNTs) and Ho doped In2O3 NTs/PNTs are prepared by electrospinning and calcination. Then, based on the prepared nanomaterials, the 6-channel sensor array is obtained and used in the electronic nose sensing system for wine product identification. The system obtains the frequency signals of different liquor products by means of 6-channel sensor array, analyzes the extracted electronic signal characteristic information by means of ordinary least squares, and introduces the pattern recognition method of moving average and linear discriminant to identify liquor products. In the experiment, compared with pure In2O3 NTs sensor, pure In2O3 PNTs sensor has higher sensitivity to 100 ppm ethanol gas, and the sensitivity is further improved after mixing Ho. Among them, 6 mol% Ho + In2O3 PNTs have the highest sensitivity and the shortest response time; based on the electronic nose system composed of prepared nanomaterial sensor array, frequency signals of different Wu Liang Ye wines are collected. With the extension of acquisition time, the corresponding frequency first decreases and then becomes stable; the extracted liquor characteristic signal is projected into two-dimensional space and three-dimensional space. The results show that the pattern recognition system based on this method can extract the characteristic signals of liquor products and distinguish them.

Download Full-text