Testing the Raman parameters of pollen spectra in automatic identification

• Type: Article in International Scientific Journal
• Date: 2021

Authors

Pereira, SG (Author) Other; Guedes, A (Author) FCUP; Abreu, I (Author) FCUP; Ribeiro, H (Author) FCUP

Journal

Title: Aerobiologia

Vol. 37

Pages: 15-28

ISSN: 0393-5965

Publisher: Springer Nature

Indexing

ISI Web of Knowledge - 3 Citations

Scopus - 3 Citations

Other information

Authenticus ID: P-00S-Z81

DOI: 10.1007/s10453-020-09669-1

Abstract (EN): Pollen identification and quantification are used in many fields of application and research has been conducted to attain accurate automatic pollen recognition aiming to reduce the laborious work and subjectivity in human identification. The aim of our study was to evaluate the capacity of Raman parameters of pollen spectra, calculated for only 7 common band intervals in a limited spectral range, to be used as future technique in pollen automatic identification. There were analyzed 15 different pollen species considered to induce allergic reactions. Raman spectra were acquired at an excitation wavelength of 785 nm in a spectral region from 1000 to 1800 cm(-1), preprocessed and deconvoluted to determine the Raman parameters: wavenumber, full width at half maximum of the band and integrated intensity. Seven common band intervals of all Raman spectra, in the fingerprint areas 1000-1010, 1300-1460 and 1500-1700 cm(-1), were chosen for the classification of the pollen species using SVM (support vector machine). Our results showed that the classification accuracy of all pollen species was 100% in the training step, while in the testing step 14 out of the 15 pollen species were correctly assigned (93.3%), including the discrimination between 5 Poaceae species and between Betula pendula and Corylus avellana. It was also observed that all Raman parameters are important in the classification as well as all wavenumber areas considered. So, our study indicates that the Raman parameters of pollen spectra can be a promising methodology for automatic pollen recognition.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 14