Comparison of machine learning algorithms for concentration detection and prediction of formaldehyde based on electronic nose
Authors:
- 21 March 2016
- journal article
- research article
- Published by Emerald Publishing in Sensor Review
- Vol. 36 (2) , 207-216
Abstract
Purpose: Sensor arrays and pattern recognition-based electronic nose (E-nose) is a typical detection and recognition instrument for indoor air quality (IAQ). The E-nose is able to monitor several pollutants in the air by mimicking the human olfactory system. Formaldehyde concentration prediction is one of the major functionalities of the E-nose, and three typical machine learning (ML) algorithms are most frequently used, including back propagation (BP) neural network, radial basis function (RBF) neural network and support vector regression (SVR). Design/methodology/approach: This paper comparatively evaluates and analyzes those three ML algorithms under controllable environment, which is built on a marketable sensor arrays E-nose platform. Variable temperature (T), relative humidity (RH) and pollutant concentrations (C) conditions were measured during experiments to support the investigation. Findings: Regression models have been built using the above-mentioned three typical algorithms, and in-depth analysis demonstrates that the model of the BP neural network results in a better prediction performance than others. Originality/value: Finally, the empirical results prove that ML algorithms, combined with low-cost sensors, can make high-precision contaminant concentration detection indoor.Keywords
This publication has 27 references indexed in Scilit:
- A comparison of different chemometrics approaches for the robust classification of electronic nose dataAnalytical and Bioanalytical Chemistry, 2014
- Gas chromatography–mass spectroscopy optimization by computer simulation, application to the analysis of 93 volatile organic compounds in workplace ambient airAnalytica Chimica Acta, 2014
- Improving estimates of air pollution exposure through ubiquitous sensing technologiesEnvironmental Pollution, 2013
- Preoxidation for Colorimetric Sensor Array Detection of VOCsJournal of the American Chemical Society, 2011
- Peak assignment in multi-capillary column–ion mobility spectrometry using comparative studies with gas chromatography–mass spectrometry for VOC analysisAnalytical and Bioanalytical Chemistry, 2009
- Electronic Nose: Current Status and Future TrendsChemical Reviews, 2008
- A pattern recognition method for electronic noses based on an olfactory neural networkSensors and Actuators B: Chemical, 2007
- Development of a preconcentration unit for a SAW sensor micro array and its use for indoor air quality monitoringSensors and Actuators B: Chemical, 2003
- Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithmIEEE Transactions on Neural Networks, 1998
- A brief history of electronic nosesSensors and Actuators B: Chemical, 1994