Selective Detection of Target Volatile Organic Compounds in Contaminated Air Using Sensor Array with Machine Learning: Aging Notes and Mold Smells in Simulated Automobile Interior Contaminant Gases
| Autor: | Woosuck Shin, Takafumi Akamatsu, Yutaro Koyama, Akihiro Tsuruta, Toshio Itoh, Kazuhisa Uchiyama, Yoshitake Masuda |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
age-related body odor
semiconductive-type gas sensor 02 engineering and technology lcsh:Chemical technology Interference (wave propagation) Machine learning computer.software_genre medicine.disease_cause 01 natural sciences Biochemistry Article Analytical Chemistry chemistry.chemical_compound principal-component analysis (PCA) Sensor array Mold 0202 electrical engineering electronic engineering information engineering medicine linear discriminant analysis (LDA) indoor-air contamination lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation business.industry 010401 analytical chemistry 020206 networking & telecommunications fungi odor Atomic and Molecular Physics and Optics 0104 chemical sciences Random forest machine learning Odor chemistry Feature (computer vision) Environmental science Contaminated air Artificial intelligence Butyl acetate business computer |
| Zdroj: | Sensors (Basel, Switzerland) Sensors, Vol 20, Iss 2687, p 2687 (2020) Sensors Volume 20 Issue 9 |
| ISSN: | 1424-8220 |
| Popis: | We investigated the selective detection of target volatile organic compounds (VOCs) which are age-related body odors (namely, 2-nonenal, pelargonic acid, and diacetyl) and a fungal odor (namely, acetic acid) in the presence of interference VOCs from car interiors (namely, n-decane, and butyl acetate). We used eight semiconductive gas sensors as a sensor array analyzing their signals using machine learning principal-component analysis (PCA), and linear-discriminant analysis (LDA) as dimensionality-reduction methods k-nearest-neighbor (kNN) classification to evaluate the accuracy of target-gas determination and random forest and ReliefF feature selections to choose appropriate sensors from our sensor array. PCA and LDA scores from the sensor responses to each target gas with contaminant gases were generally within the area of each target gas hence discrimination between each target gas was nearly achieved. Random forest and ReliefF efficiently reduced the required number of sensors, and kNN verified the quality of target-gas discrimination by each sensor set |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|