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

Viewed

Total article views: 4,234 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
2,702 1,393 139 4,234 305 155 147
  • HTML: 2,702
  • PDF: 1,393
  • XML: 139
  • Total: 4,234
  • Supplement: 305
  • BibTeX: 155
  • EndNote: 147
Views and downloads (calculated since 21 Jan 2019)
Cumulative views and downloads (calculated since 21 Jan 2019)

Viewed (geographical distribution)

Total article views: 4,234 (including HTML, PDF, and XML) Thereof 4,019 with geography defined and 215 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 27 Mar 2024
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.