Alternaria spore exposure in Bavaria, Germany, measured using artificial intelligence algorithms in a network of BAA500 automatic pollen monitors.
Allergy
Alternaria
Automatic monitors
Classification
Convolutional neural networks
Fungal spores
Time series
U-net
Journal
The Science of the total environment
ISSN: 1879-1026
Titre abrégé: Sci Total Environ
Pays: Netherlands
ID NLM: 0330500
Informations de publication
Date de publication:
25 Feb 2023
25 Feb 2023
Historique:
received:
08
09
2022
revised:
09
11
2022
accepted:
10
11
2022
pubmed:
21
11
2022
medline:
17
1
2023
entrez:
20
11
2022
Statut:
ppublish
Résumé
Although Alternaria spores are well-known allergenic fungal spores, automatic bioaerosol recognition systems have not been trained to recognize these particles until now. Here we report the development of a new algorithm able to classify Alternaria spores with BAA500 automatic bioaerosol monitors. The best validation score was obtained when the model was trained on both data from the original dataset and artificially generated images, with a validation unweighted mean Intersection over Union (IoU), also called Jaccard Index, of 0.95. Data augmentation techniques were applied to the training set. While some particles were not recognized (false negatives), false positives were few. The results correlated well with manual counts (mean of four Hirst-type traps), with R
Identifiants
pubmed: 36403848
pii: S0048-9697(22)07280-1
doi: 10.1016/j.scitotenv.2022.160180
pii:
doi:
Substances chimiques
Allergens
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
160180Informations de copyright
Copyright © 2022 Elsevier B.V. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of competing interest The authors report no conflict of interest. Tom Stemmler is currently working at Helmut Hund Gmbh., however this had no effect on the results presented as the investigations were carried out in compliance with good scientific practices.