Abstract
We propose a data refinement and channel selection method for vapor classification in a portable e-nose system. For the robust e-nose system in a real environment, we propose to reduce the noise in the data measured by sensor arrays and distinguish the important part in the data by the use of feature feedback. Experimental results on different volatile organic compounds data show that the proposed data refinement method gives good clustering for different classes and improves the classification performance. Also, we design a new sensor array that consists only of the useful channels. For this purpose, each channel is evaluated by measuring its discriminative power based on the feature mask used in the data refinement. Through the experimental results, we show that the new sensor array improves both the classification rates and the efficiency in computation and data storage.
Highlights
An electronic nose (e-nose) is an instrument that is designed to detect and discriminate vapors using an array of sensors [1,2,3,4,5,6]
We proposed a new data refinement and channel selection method for vapor classification in the portable e-nose system
The data measured by a portable e-nose system is likely to be corrupted by noise, which interferes with feature extraction for classification
Summary
An electronic nose (e-nose) is an instrument that is designed to detect and discriminate vapors using an array of sensors [1,2,3,4,5,6]. In an early electronic nose, calorimetric sensors were used to perform measurements on vapors, and the measurements were usually expressed in arrays of colors, i.e., in the form of colored images [7] Such an e-nose system, which was used only in a laboratory environment, utilized complicated analytic procedures including the use of precise equipment such as gas chromatography (GC) system or a mass spectrometer (MS) combined with sophisticated machine intelligence. Some feature extraction or selection methods can be used effectively to classify vapors for the portable e-nose system. In [13], the hierarchical classification method that combines Fisher discriminant analysis and modified Sammon mapping was proposed Some vector machines such as the support vector machine or relevance vector machine were used to classify vapors [14,15]. We propose a new data refinement and channel selection method for vapor classification.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
