« Previous AbstractA new matrix assisted ionization method for the analysis of volatile and nonvolatile compounds by atmospheric probe mass spectrometry    Next AbstractEfficacy of aggregation pheromone in trapping red palm weevil (Rhynchophorus ferrugineus Olivier) and rhinoceros beetle (Oryctes rhinoceros Linn.) from infested coconut palms »

Anal Methods

Title:		Machine learning and signal processing assisted differential mobility spectrometry (DMS) data analysis for chemical identification
Author(s):		Chakraborty P; Rajapakse MY; McCartney MM; Kenyon NJ; Davis CE;
Address:		"Department of Mechanical and Aerospace Engineering, University of California Davis, Davis, CA, USA. cedavis@ucdavis.edu. UC Davis Lung Center, One Shields Avenue, Davis, CA, USA. VA Northern California Health Care System, 10535 Hospital Way, Mather, CA, USA. Department of Internal Medicine, University of California Davis, Davis, CA, USA"
Journal Title:		Anal Methods
Year:		2022
Volume:		20220901
Issue:		34
Page Number:		3315 - 3322
DOI:		10.1039/d2ay00723a
ISSN/ISBN:		1759-9679 (Electronic) 1759-9660 (Print) 1759-9660 (Linking)
Abstract:		"Differential mobility spectrometry (DMS)-based detectors are being widely studied to detect chemical warfare agents, explosives, chemicals, drugs and analyze volatile organic compounds (VOCs). The dispersion plots from DMS devices are complex to effectively analyze through visual inspection. In the current work, we adopted machine learning to differentiate pure chemicals and identify chemicals in a mixture. In particular, we observed the convolutional neural network algorithm exhibits excellent accuracy in differentiating chemicals in their pure forms while also identifying chemicals in a mixture. In addition, we propose and validate the magnitude-squared coherence (msc) between the DMS data of known chemical composition and that of an unknown sample can be sufficient to inspect the chemical composition of the unknown sample. We have shown that the msc-based chemical identification requires the least amount of experimental data as opposed to the machine learning approach"
Keywords:		*Data Analysis Ion Mobility Spectrometry Machine Learning Spectrum Analysis/methods *Volatile Organic Compounds/analysis;
Notes:		"MedlineChakraborty, Pranay Rajapakse, Maneeshin Y McCartney, Mitchell M Kenyon, Nicholas J Davis, Cristina E eng I01 BX004965/BX/BLRD VA/ U18 TR003795/TR/NCATS NIH HHS/ UG3 OD023365/OD/NIH HHS/ U01 TR004083/TR/NCATS NIH HHS/ UL1 TR001860/TR/NCATS NIH HHS/ P30 ES023513/ES/NIEHS NIH HHS/ Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S. England 2022/08/16 Anal Methods. 2022 Sep 1; 14(34):3315-3322. doi: 10.1039/d2ay00723a"