Drift Compensation for Electronic Nose Based on Sample Distribution Weighting Cross Domain Extreme Learning Machine

被引：2
|
作者：
Yan J. [1 ,2 ]
Chen F. [3 ]
Yi R. [3 ]
Wang Z. [3 ]
机构：
[1] National & Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology (Chonging), Chongqing
[2] College of Artificial Intelligence, Southwest University, Chongqing
[3] College of Electronic and Information Engineering, Southwest University, Chongqing
来源：
Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science) | 2020年 / 48卷 / 12期
基金：
中国国家自然科学基金;
关键词：
Drift compensation; Electronic nose; Extreme learning machine; Sample distribution weighting; Subspace learning;
D O I：
10.12141/j.issn.1000-565X.200316
中图分类号：
学科分类号：
摘要：
To solve the problem of low classification accuracy of electronic nose (E-nose) caused by sensor drift in various applications, a sample distribution weighting cross domain extreme learning machine model was proposed. Considering the different contributions of a single sample to the global distribution discrepancy measure, it uses the maximum mean discrepancy based on the sample distribution weighting as a measure of the sample distribution discrepancy between domains. The data of source domain and target domain were projected onto a high-dimensional extreme learning machine feature space. Then a suitable projection direction was found, by which the data was projected onto a common subspace. Thus the source domain and target domain data in the subspace had a similar distribution. Matlab was used to simulate this algorithm, and the effects of different number of hidden layer nodes on the recognition rate of the algorithm were compared so as to verify the feasibility of the algorithm. The results show that the model proposed in this paper can significantly reduce the distribution discrepancies between the two domains, and can meet the distribution requirements of traditional classification algorithms for training and test data, thus to improve the classification accuracy of E-nose. © 2020, Editorial Department, Journal of South China University of Technology. All right reserved.
引用
收藏
页码：105 / 113
页数：8
相关论文
共 31 条
  • [1] CHILO J, PELEGRI-SEBASTIA J, CUPANE M, Et al., E-nose application to food industry production, IEEE Instrumentation and Measurement Magazine, 19, 1, pp. 27-33, (2016)
  • [2] DESHMUKH S, BANDYOPADHYAY R, BHATTACHARYYA N, Et al., Application of electronic nose for industrial odors and gaseous emissions measurement and monitoring-An overview, Talanta, 144, pp. 329-340, (2015)
  • [3] GIANNOUKOS S, AGAPIOU A, TAYLOR S., Advances in chemical sensing technologies for VOCs in breath for security/threat assessment, illicit drug detection, and human trafficking activity, Journal of Breath Research, 12, 2, (2018)
  • [4] FITZGERALD J E, BUI E T H, SIMON N M, Et al., Artificial nose technology: status and prospects in diagnostics, Trends in Biotechnology, 35, 1, pp. 33-42, (2017)
  • [5] FLAMMINI A, MARIOLI D, TARONI A., A low-cost interface to high-value resistive sensors varying over a wide range, IEEE Transactions on Instrumentation and Measurement, 53, 4, pp. 1052-1056, (2004)
  • [6] FERNANDEZ L, MARCO S, GUTIERREZ-GALVEZ A., Robustness to sensor damage of a highly redundant gas sensor array, Sensors and Actuators B-Chemical, 218, 31, pp. 296-302, (2015)
  • [7] DUTTA R, HINES E L, GARDNER J W, Et al., Tea quality prediction using a tin oxide-based electronic nose: an artificial intelligence approach, Sensors and Actuators B: Chemical, 94, 2, pp. 228-237, (2003)
  • [8] SIYANG S, WONGCHOOSUK C, KERDCHAROEN T., Diabetes diagnosis by direct measurement from urine odor using electronic nose, Proceedings of the 5th Biomedical Engineering International Conference, pp. 1-4, (2012)
  • [9] YOLANDA G M, .CONCEPCION M, JOSE L P P, Et al., Electronic nose based on metal oxide semiconductor sensors and pattern recognition techniques: characterization of vegetable oils, Analytica Chimica Acta, 449, 1, pp. 69-80, (2001)
  • [10] YAN J, TIAN F C, SHEN Y, Et al., Feature extraction from sensor data for detection of wound pathogen based on electronic nose, Sensors and Materials, 24, 2, pp. 57-73, (2012)
1234