Automated Spore Measurements Using Microscopy, Image Analysis, and Peak Recognition of Near-Monodisperse Aerosols

Wagner, Jeff; Macher, Janet M.

doi:10.1080/02786826.2012.674232

Cited by 27 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both standard (500-1000x) and high magnification (1000-5000x) were used to identify specific particle shapes and other characteristics. Fourteen to twentytwo images of randomly selected positions on the aerosol deposit were obtained for each filter, followed by image analysis using ImageJ software (Schneider et al, 2012;Wagner and Macher, 2012). Bioaerosols were identified based on their size, shape, and texture, and classified by category before being manually counted.…”

Section: Microscopic Analysis Of Fungal Spores Pollen Grains and Plmentioning

confidence: 99%

Characterization of Ambient PM10 Bioaerosols in a California Agricultural Town

Chow

Yang

Wang

et al. 2015

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

Ambient bioaerosols in PM 10 samples were measured at three sites in Corcoran, an agricultural town in the southern San Joaquin Valley (SJV) of California, during fall of 2000 corresponding to the cotton harvest season. Elevated bioaerosol concentrations were measured near grain elevators (GRA site) and a cotton handling facility (BAI site) as compared to levels in a residential community (COP site), ~2 km northeast of these sources. Average endotoxin levels (13 ± 17 EU/m 3 ) at the grain elevator site were three to eight times higher than averages at the nearby cotton-handling and residential sites. The highest level (47.6 EU/m 3 ) at the grain elevator site was about half of the exposure limit of 90 EU/m 3 set by the Dutch Expert Committee on Occupational Safety. Particle counts of fungal spore (66,333 particles/m 3 ) and pollen grain (2,600 particles/m 3 ) concentrations were more than double those reported in the literature. Average fungal biomarker concentrations of 170 and 131 ng/m 3 for arabitol and mannitol, respectively, were 1-2 orders of magnitude higher than those from nonagricultural areas. The low correlation (r < 0.11) of three fungal markers (i.e., (1→3)-β-D-glucan, arabitol, and mannitol) with fungi counts is consistent with findings by others and indicates that these are insufficient as surrogates to represent fungal exposure. Agricultural activities contributed measureable amounts to PM 10 mass and organic carbon (OC), dominated by fungal spores (i.e., 5.4-5.8% PM 10 mass and 11.5-14.7% OC). The sum of fungal spores, pollen grains, and plant detritus accounted for an average of 11-15% PM 10 and 24-33% OC mass. Bioaerosols can be important contributors to PM 10 mass in farming communities similar to Corcoran, especially during intense agricultural activities.

show abstract

Section: Microscopic Analysis Of Fungal Spores Pollen Grains and Plmentioning

confidence: 99%

Characterization of Ambient PM10 Bioaerosols in a California Agricultural Town

Chow

Yang

Wang

et al. 2015

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

show abstract

“…Oteros et al24 automatically observed pollen by comparing the microscopic images of pollen samples collected from collection devices with 58 criteria based on an image library. Other research on automatic detection has been carried out by Kawashima et al .,25 O'Connor et al .,26 and Wagner and Macher 27…”

Section: Discussionmentioning

confidence: 99%

Deep Neural Network-Based Concentration Model for Oak Pollen Allergy Warning in South Korea

Seo

Kim

Cho

et al. 2020

Allergy Asthma Immunol Res

View full text Add to dashboard Cite

PurposeOak is the dominant tree species in Korea. Oak pollen has the highest sensitivity rate among all allergenic tree species in Korea. A deep neural network (DNN)-based estimation model was developed to determine the concentration of oak pollen and overcome the shortcomings of conventional regression models.MethodsThe DNN model proposed in this study utilized weather factors as the input and provided pollen concentrations as the output. Weather and pollen concentration data were used from 2007 to 2016 obtained from the Korea Meteorological Administration pollen observation network. Because it is difficult to prevent over-fitting and underestimation by using a DNN model alone, we developed a bootstrap aggregating-type ensemble model. Each of the 30 ensemble members was trained with random sampling at a fixed rate according to the pollen risk grade. To verify the effectiveness of the proposed model, we compared its performance with those of models of regression and support vector regression (SVR) under the same conditions, with respect to the prediction of pollen concentrations, risk levels, and season length.ResultsThe mean absolute percentage error in the estimated pollen concentrations was 11.18%, 10.37%, and 5.04% for the regression, SVR and DNN models, respectively. The start of the pollen season was estimated to be 20, 22, and 6 days earlier than that predicted by the regression, SVR and DNN models, respectively. Similarly, the end of the pollen season was estimated to be 33, 20, and 9 days later that predicted by the regression, SVR and DNN models, respectively.ConclusionsOverall, the DNN model performed better than the other models. However, the prediction of peak pollen concentrations needs improvement. Improved observation quality with optimization of the DNN model will resolve this issue.

show abstract

“…Furthermore, the count accuracy is affected by colour inhomogeneity of the image, and problems such as vignetting could mislead the entire analysis. In conclusion, the approaches based on image processing methods typically provide rapid solutions for counting cells [69]. Nevertheless, there is still no general image-based method capable of accurately counting both live and dead cells, of all possible cell typologies (i.e., cells with different size and different morphologies of dead cells), in a typical situation where the images present debris and colour inhomogeneity.…”

Section: Cell Counting Approachesmentioning

confidence: 98%