Articles | Volume 12, issue 6
https://doi.org/10.5194/amt-12-3435-2019
https://doi.org/10.5194/amt-12-3435-2019
Research article
 | 
28 Jun 2019
Research article |  | 28 Jun 2019

Automatic pollen recognition with the Rapid-E particle counter: the first-level procedure, experience and next steps

Ingrida Šaulienė, Laura Šukienė, Gintautas Daunys, Gediminas Valiulis, Lukas Vaitkevičius, Predrag Matavulj, Sanja Brdar, Marko Panic, Branko Sikoparija, Bernard Clot, Benoît Crouzy, and Mikhail Sofiev

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by I. Sauliene on behalf of the Authors (15 Apr 2019)  Author's response   Manuscript 
ED: Referee Nomination & Report Request started (17 Apr 2019) by Vassilis Amiridis
RR by Anonymous Referee #4 (09 May 2019)
RR by Anonymous Referee #1 (22 May 2019)
ED: Publish as is (30 May 2019) by Vassilis Amiridis
AR by I. Sauliene on behalf of the Authors (07 Jun 2019)  Manuscript 
Download
Short summary
The goal is to evaluate the capabilities of the new Rapid-E monitor and to construct a first-level pollen recognition algorithm. The output data were treated with ANN aiming at classification of the injected pollen. Algorithms based on scattering and fluorescence data alone fall short of acceptable quality. The combinations of these exceeded 80 % accuracy for 5 out of 11 pollen species. Constructing multistep algorithms with sequential discrimination of pollen can be a possible way forward.